Upload folder using huggingface_hub
Browse files- config.json +34 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +753 -0
- tokenizer.json +0 -0
- tokenizer_config.json +959 -0
- trainer_state.json +2780 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/codet5p-220m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 3072,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dense_act_fn": "relu",
|
| 13 |
+
"device_map": "auto",
|
| 14 |
+
"dropout_rate": 0.1,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"feed_forward_proj": "relu",
|
| 17 |
+
"initializer_factor": 1.0,
|
| 18 |
+
"is_encoder_decoder": true,
|
| 19 |
+
"is_gated_act": false,
|
| 20 |
+
"layer_norm_epsilon": 1e-06,
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"n_positions": 512,
|
| 23 |
+
"num_decoder_layers": 12,
|
| 24 |
+
"num_heads": 12,
|
| 25 |
+
"num_layers": 12,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"relative_attention_max_distance": 128,
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.38.2",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32100
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 0,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.38.2",
|
| 8 |
+
"use_cache": false
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be9d15935068c9e1c1bbf639b8d926fa3ddc169e21c701f0f232d1211007a9ef
|
| 3 |
+
size 891558696
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea4e9db6603d9237f15556c79dfa8010d5ebd5e09900be89ee5f8be19ebd96c7
|
| 3 |
+
size 447691160
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a31d7f648f6de0e22201444447661f9868e75ea6c8fcfdddaf19b8d926606c13
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e765c138857d0512f08fccf3f80d6b56577aa6ed602bf5213da46cd1932b86bc
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,753 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<extra_id_99>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<extra_id_98>",
|
| 12 |
+
"lstrip": true,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<extra_id_97>",
|
| 19 |
+
"lstrip": true,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<extra_id_96>",
|
| 26 |
+
"lstrip": true,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<extra_id_95>",
|
| 33 |
+
"lstrip": true,
|
| 34 |
+
"normalized": true,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "<extra_id_94>",
|
| 40 |
+
"lstrip": true,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "<extra_id_93>",
|
| 47 |
+
"lstrip": true,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "<extra_id_92>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<extra_id_91>",
|
| 61 |
+
"lstrip": true,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "<extra_id_90>",
|
| 68 |
+
"lstrip": true,
|
| 69 |
+
"normalized": true,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<extra_id_89>",
|
| 75 |
+
"lstrip": true,
|
| 76 |
+
"normalized": true,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "<extra_id_88>",
|
| 82 |
+
"lstrip": true,
|
| 83 |
+
"normalized": true,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"content": "<extra_id_87>",
|
| 89 |
+
"lstrip": true,
|
| 90 |
+
"normalized": true,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"content": "<extra_id_86>",
|
| 96 |
+
"lstrip": true,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"content": "<extra_id_85>",
|
| 103 |
+
"lstrip": true,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"content": "<extra_id_84>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"content": "<extra_id_83>",
|
| 117 |
+
"lstrip": true,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "<extra_id_82>",
|
| 124 |
+
"lstrip": true,
|
| 125 |
+
"normalized": true,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"content": "<extra_id_81>",
|
| 131 |
+
"lstrip": true,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"content": "<extra_id_80>",
|
| 138 |
+
"lstrip": true,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"content": "<extra_id_79>",
|
| 145 |
+
"lstrip": true,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"content": "<extra_id_78>",
|
| 152 |
+
"lstrip": true,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "<extra_id_77>",
|
| 159 |
+
"lstrip": true,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"content": "<extra_id_76>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"content": "<extra_id_75>",
|
| 173 |
+
"lstrip": true,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"content": "<extra_id_74>",
|
| 180 |
+
"lstrip": true,
|
| 181 |
+
"normalized": true,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"content": "<extra_id_73>",
|
| 187 |
+
"lstrip": true,
|
| 188 |
+
"normalized": true,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"single_word": false
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"content": "<extra_id_72>",
|
| 194 |
+
"lstrip": true,
|
| 195 |
+
"normalized": true,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"single_word": false
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"content": "<extra_id_71>",
|
| 201 |
+
"lstrip": true,
|
| 202 |
+
"normalized": true,
|
| 203 |
+
"rstrip": false,
|
| 204 |
+
"single_word": false
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"content": "<extra_id_70>",
|
| 208 |
+
"lstrip": true,
|
| 209 |
+
"normalized": true,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"content": "<extra_id_69>",
|
| 215 |
+
"lstrip": true,
|
| 216 |
+
"normalized": true,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"content": "<extra_id_68>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"content": "<extra_id_67>",
|
| 229 |
+
"lstrip": true,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"content": "<extra_id_66>",
|
| 236 |
+
"lstrip": true,
|
| 237 |
+
"normalized": true,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"single_word": false
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"content": "<extra_id_65>",
|
| 243 |
+
"lstrip": true,
|
| 244 |
+
"normalized": true,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"single_word": false
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"content": "<extra_id_64>",
|
| 250 |
+
"lstrip": true,
|
| 251 |
+
"normalized": true,
|
| 252 |
+
"rstrip": false,
|
| 253 |
+
"single_word": false
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"content": "<extra_id_63>",
|
| 257 |
+
"lstrip": true,
|
| 258 |
+
"normalized": true,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"single_word": false
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"content": "<extra_id_62>",
|
| 264 |
+
"lstrip": true,
|
| 265 |
+
"normalized": true,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"content": "<extra_id_61>",
|
| 271 |
+
"lstrip": true,
|
| 272 |
+
"normalized": true,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"content": "<extra_id_60>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"content": "<extra_id_59>",
|
| 285 |
+
"lstrip": true,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"content": "<extra_id_58>",
|
| 292 |
+
"lstrip": true,
|
| 293 |
+
"normalized": true,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"single_word": false
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"content": "<extra_id_57>",
|
| 299 |
+
"lstrip": true,
|
| 300 |
+
"normalized": true,
|
| 301 |
+
"rstrip": false,
|
| 302 |
+
"single_word": false
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"content": "<extra_id_56>",
|
| 306 |
+
"lstrip": true,
|
| 307 |
+
"normalized": true,
|
| 308 |
+
"rstrip": false,
|
| 309 |
+
"single_word": false
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"content": "<extra_id_55>",
|
| 313 |
+
"lstrip": true,
|
| 314 |
+
"normalized": true,
|
| 315 |
+
"rstrip": false,
|
| 316 |
+
"single_word": false
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"content": "<extra_id_54>",
|
| 320 |
+
"lstrip": true,
|
| 321 |
+
"normalized": true,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"content": "<extra_id_53>",
|
| 327 |
+
"lstrip": true,
|
| 328 |
+
"normalized": true,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"content": "<extra_id_52>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": true,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"content": "<extra_id_51>",
|
| 341 |
+
"lstrip": true,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"content": "<extra_id_50>",
|
| 348 |
+
"lstrip": true,
|
| 349 |
+
"normalized": true,
|
| 350 |
+
"rstrip": false,
|
| 351 |
+
"single_word": false
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"content": "<extra_id_49>",
|
| 355 |
+
"lstrip": true,
|
| 356 |
+
"normalized": true,
|
| 357 |
+
"rstrip": false,
|
| 358 |
+
"single_word": false
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"content": "<extra_id_48>",
|
| 362 |
+
"lstrip": true,
|
| 363 |
+
"normalized": true,
|
| 364 |
+
"rstrip": false,
|
| 365 |
+
"single_word": false
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"content": "<extra_id_47>",
|
| 369 |
+
"lstrip": true,
|
| 370 |
+
"normalized": true,
|
| 371 |
+
"rstrip": false,
|
| 372 |
+
"single_word": false
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"content": "<extra_id_46>",
|
| 376 |
+
"lstrip": true,
|
| 377 |
+
"normalized": true,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"content": "<extra_id_45>",
|
| 383 |
+
"lstrip": true,
|
| 384 |
+
"normalized": true,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"content": "<extra_id_44>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": true,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"content": "<extra_id_43>",
|
| 397 |
+
"lstrip": true,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"content": "<extra_id_42>",
|
| 404 |
+
"lstrip": true,
|
| 405 |
+
"normalized": true,
|
| 406 |
+
"rstrip": false,
|
| 407 |
+
"single_word": false
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"content": "<extra_id_41>",
|
| 411 |
+
"lstrip": true,
|
| 412 |
+
"normalized": true,
|
| 413 |
+
"rstrip": false,
|
| 414 |
+
"single_word": false
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"content": "<extra_id_40>",
|
| 418 |
+
"lstrip": true,
|
| 419 |
+
"normalized": true,
|
| 420 |
+
"rstrip": false,
|
| 421 |
+
"single_word": false
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"content": "<extra_id_39>",
|
| 425 |
+
"lstrip": true,
|
| 426 |
+
"normalized": true,
|
| 427 |
+
"rstrip": false,
|
| 428 |
+
"single_word": false
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"content": "<extra_id_38>",
|
| 432 |
+
"lstrip": true,
|
| 433 |
+
"normalized": true,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"content": "<extra_id_37>",
|
| 439 |
+
"lstrip": true,
|
| 440 |
+
"normalized": true,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"content": "<extra_id_36>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": true,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"content": "<extra_id_35>",
|
| 453 |
+
"lstrip": true,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"content": "<extra_id_34>",
|
| 460 |
+
"lstrip": true,
|
| 461 |
+
"normalized": true,
|
| 462 |
+
"rstrip": false,
|
| 463 |
+
"single_word": false
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"content": "<extra_id_33>",
|
| 467 |
+
"lstrip": true,
|
| 468 |
+
"normalized": true,
|
| 469 |
+
"rstrip": false,
|
| 470 |
+
"single_word": false
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"content": "<extra_id_32>",
|
| 474 |
+
"lstrip": true,
|
| 475 |
+
"normalized": true,
|
| 476 |
+
"rstrip": false,
|
| 477 |
+
"single_word": false
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"content": "<extra_id_31>",
|
| 481 |
+
"lstrip": true,
|
| 482 |
+
"normalized": true,
|
| 483 |
+
"rstrip": false,
|
| 484 |
+
"single_word": false
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"content": "<extra_id_30>",
|
| 488 |
+
"lstrip": true,
|
| 489 |
+
"normalized": true,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"content": "<extra_id_29>",
|
| 495 |
+
"lstrip": true,
|
| 496 |
+
"normalized": true,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"content": "<extra_id_28>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": true,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"content": "<extra_id_27>",
|
| 509 |
+
"lstrip": true,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"content": "<extra_id_26>",
|
| 516 |
+
"lstrip": true,
|
| 517 |
+
"normalized": true,
|
| 518 |
+
"rstrip": false,
|
| 519 |
+
"single_word": false
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"content": "<extra_id_25>",
|
| 523 |
+
"lstrip": true,
|
| 524 |
+
"normalized": true,
|
| 525 |
+
"rstrip": false,
|
| 526 |
+
"single_word": false
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"content": "<extra_id_24>",
|
| 530 |
+
"lstrip": true,
|
| 531 |
+
"normalized": true,
|
| 532 |
+
"rstrip": false,
|
| 533 |
+
"single_word": false
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"content": "<extra_id_23>",
|
| 537 |
+
"lstrip": true,
|
| 538 |
+
"normalized": true,
|
| 539 |
+
"rstrip": false,
|
| 540 |
+
"single_word": false
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"content": "<extra_id_22>",
|
| 544 |
+
"lstrip": true,
|
| 545 |
+
"normalized": true,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"content": "<extra_id_21>",
|
| 551 |
+
"lstrip": true,
|
| 552 |
+
"normalized": true,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"content": "<extra_id_20>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": true,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"content": "<extra_id_19>",
|
| 565 |
+
"lstrip": true,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"content": "<extra_id_18>",
|
| 572 |
+
"lstrip": true,
|
| 573 |
+
"normalized": true,
|
| 574 |
+
"rstrip": false,
|
| 575 |
+
"single_word": false
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"content": "<extra_id_17>",
|
| 579 |
+
"lstrip": true,
|
| 580 |
+
"normalized": true,
|
| 581 |
+
"rstrip": false,
|
| 582 |
+
"single_word": false
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"content": "<extra_id_16>",
|
| 586 |
+
"lstrip": true,
|
| 587 |
+
"normalized": true,
|
| 588 |
+
"rstrip": false,
|
| 589 |
+
"single_word": false
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"content": "<extra_id_15>",
|
| 593 |
+
"lstrip": true,
|
| 594 |
+
"normalized": true,
|
| 595 |
+
"rstrip": false,
|
| 596 |
+
"single_word": false
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"content": "<extra_id_14>",
|
| 600 |
+
"lstrip": true,
|
| 601 |
+
"normalized": true,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"content": "<extra_id_13>",
|
| 607 |
+
"lstrip": true,
|
| 608 |
+
"normalized": true,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"content": "<extra_id_12>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": true,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"content": "<extra_id_11>",
|
| 621 |
+
"lstrip": true,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"content": "<extra_id_10>",
|
| 628 |
+
"lstrip": true,
|
| 629 |
+
"normalized": true,
|
| 630 |
+
"rstrip": false,
|
| 631 |
+
"single_word": false
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"content": "<extra_id_9>",
|
| 635 |
+
"lstrip": true,
|
| 636 |
+
"normalized": true,
|
| 637 |
+
"rstrip": false,
|
| 638 |
+
"single_word": false
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"content": "<extra_id_8>",
|
| 642 |
+
"lstrip": true,
|
| 643 |
+
"normalized": true,
|
| 644 |
+
"rstrip": false,
|
| 645 |
+
"single_word": false
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"content": "<extra_id_7>",
|
| 649 |
+
"lstrip": true,
|
| 650 |
+
"normalized": true,
|
| 651 |
+
"rstrip": false,
|
| 652 |
+
"single_word": false
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"content": "<extra_id_6>",
|
| 656 |
+
"lstrip": true,
|
| 657 |
+
"normalized": true,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"content": "<extra_id_5>",
|
| 663 |
+
"lstrip": true,
|
| 664 |
+
"normalized": true,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"content": "<extra_id_4>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": true,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"content": "<extra_id_3>",
|
| 677 |
+
"lstrip": true,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"content": "<extra_id_2>",
|
| 684 |
+
"lstrip": true,
|
| 685 |
+
"normalized": true,
|
| 686 |
+
"rstrip": false,
|
| 687 |
+
"single_word": false
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"content": "<extra_id_1>",
|
| 691 |
+
"lstrip": true,
|
| 692 |
+
"normalized": true,
|
| 693 |
+
"rstrip": false,
|
| 694 |
+
"single_word": false
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"content": "<extra_id_0>",
|
| 698 |
+
"lstrip": true,
|
| 699 |
+
"normalized": true,
|
| 700 |
+
"rstrip": false,
|
| 701 |
+
"single_word": false
|
| 702 |
+
}
|
| 703 |
+
],
|
| 704 |
+
"bos_token": {
|
| 705 |
+
"content": "<s>",
|
| 706 |
+
"lstrip": false,
|
| 707 |
+
"normalized": true,
|
| 708 |
+
"rstrip": false,
|
| 709 |
+
"single_word": false
|
| 710 |
+
},
|
| 711 |
+
"cls_token": {
|
| 712 |
+
"content": "<s>",
|
| 713 |
+
"lstrip": false,
|
| 714 |
+
"normalized": true,
|
| 715 |
+
"rstrip": false,
|
| 716 |
+
"single_word": false
|
| 717 |
+
},
|
| 718 |
+
"eos_token": {
|
| 719 |
+
"content": "</s>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": true,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false
|
| 724 |
+
},
|
| 725 |
+
"mask_token": {
|
| 726 |
+
"content": "<mask>",
|
| 727 |
+
"lstrip": true,
|
| 728 |
+
"normalized": true,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false
|
| 731 |
+
},
|
| 732 |
+
"pad_token": {
|
| 733 |
+
"content": "<pad>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": true,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false
|
| 738 |
+
},
|
| 739 |
+
"sep_token": {
|
| 740 |
+
"content": "</s>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false
|
| 745 |
+
},
|
| 746 |
+
"unk_token": {
|
| 747 |
+
"content": "<unk>",
|
| 748 |
+
"lstrip": false,
|
| 749 |
+
"normalized": true,
|
| 750 |
+
"rstrip": false,
|
| 751 |
+
"single_word": false
|
| 752 |
+
}
|
| 753 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32000": {
|
| 45 |
+
"content": "<extra_id_99>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32001": {
|
| 53 |
+
"content": "<extra_id_98>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32002": {
|
| 61 |
+
"content": "<extra_id_97>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32003": {
|
| 69 |
+
"content": "<extra_id_96>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32004": {
|
| 77 |
+
"content": "<extra_id_95>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32005": {
|
| 85 |
+
"content": "<extra_id_94>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32006": {
|
| 93 |
+
"content": "<extra_id_93>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32007": {
|
| 101 |
+
"content": "<extra_id_92>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32008": {
|
| 109 |
+
"content": "<extra_id_91>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32009": {
|
| 117 |
+
"content": "<extra_id_90>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32010": {
|
| 125 |
+
"content": "<extra_id_89>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32011": {
|
| 133 |
+
"content": "<extra_id_88>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32012": {
|
| 141 |
+
"content": "<extra_id_87>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32013": {
|
| 149 |
+
"content": "<extra_id_86>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32014": {
|
| 157 |
+
"content": "<extra_id_85>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32015": {
|
| 165 |
+
"content": "<extra_id_84>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32016": {
|
| 173 |
+
"content": "<extra_id_83>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32017": {
|
| 181 |
+
"content": "<extra_id_82>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32018": {
|
| 189 |
+
"content": "<extra_id_81>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32019": {
|
| 197 |
+
"content": "<extra_id_80>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32020": {
|
| 205 |
+
"content": "<extra_id_79>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32021": {
|
| 213 |
+
"content": "<extra_id_78>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32022": {
|
| 221 |
+
"content": "<extra_id_77>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32023": {
|
| 229 |
+
"content": "<extra_id_76>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32024": {
|
| 237 |
+
"content": "<extra_id_75>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32025": {
|
| 245 |
+
"content": "<extra_id_74>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32026": {
|
| 253 |
+
"content": "<extra_id_73>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32027": {
|
| 261 |
+
"content": "<extra_id_72>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32028": {
|
| 269 |
+
"content": "<extra_id_71>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32029": {
|
| 277 |
+
"content": "<extra_id_70>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32030": {
|
| 285 |
+
"content": "<extra_id_69>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32031": {
|
| 293 |
+
"content": "<extra_id_68>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32032": {
|
| 301 |
+
"content": "<extra_id_67>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32033": {
|
| 309 |
+
"content": "<extra_id_66>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32034": {
|
| 317 |
+
"content": "<extra_id_65>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": true,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32035": {
|
| 325 |
+
"content": "<extra_id_64>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": true,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32036": {
|
| 333 |
+
"content": "<extra_id_63>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": true,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32037": {
|
| 341 |
+
"content": "<extra_id_62>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": true,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32038": {
|
| 349 |
+
"content": "<extra_id_61>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": true,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32039": {
|
| 357 |
+
"content": "<extra_id_60>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": true,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32040": {
|
| 365 |
+
"content": "<extra_id_59>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": true,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32041": {
|
| 373 |
+
"content": "<extra_id_58>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": true,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32042": {
|
| 381 |
+
"content": "<extra_id_57>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": true,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32043": {
|
| 389 |
+
"content": "<extra_id_56>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": true,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32044": {
|
| 397 |
+
"content": "<extra_id_55>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": true,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32045": {
|
| 405 |
+
"content": "<extra_id_54>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": true,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32046": {
|
| 413 |
+
"content": "<extra_id_53>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": true,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32047": {
|
| 421 |
+
"content": "<extra_id_52>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": true,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32048": {
|
| 429 |
+
"content": "<extra_id_51>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": true,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32049": {
|
| 437 |
+
"content": "<extra_id_50>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": true,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32050": {
|
| 445 |
+
"content": "<extra_id_49>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": true,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32051": {
|
| 453 |
+
"content": "<extra_id_48>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": true,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32052": {
|
| 461 |
+
"content": "<extra_id_47>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": true,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32053": {
|
| 469 |
+
"content": "<extra_id_46>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": true,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32054": {
|
| 477 |
+
"content": "<extra_id_45>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": true,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32055": {
|
| 485 |
+
"content": "<extra_id_44>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": true,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32056": {
|
| 493 |
+
"content": "<extra_id_43>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": true,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32057": {
|
| 501 |
+
"content": "<extra_id_42>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": true,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32058": {
|
| 509 |
+
"content": "<extra_id_41>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": true,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32059": {
|
| 517 |
+
"content": "<extra_id_40>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": true,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32060": {
|
| 525 |
+
"content": "<extra_id_39>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": true,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32061": {
|
| 533 |
+
"content": "<extra_id_38>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": true,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32062": {
|
| 541 |
+
"content": "<extra_id_37>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": true,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32063": {
|
| 549 |
+
"content": "<extra_id_36>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": true,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32064": {
|
| 557 |
+
"content": "<extra_id_35>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": true,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32065": {
|
| 565 |
+
"content": "<extra_id_34>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": true,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32066": {
|
| 573 |
+
"content": "<extra_id_33>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": true,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32067": {
|
| 581 |
+
"content": "<extra_id_32>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": true,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32068": {
|
| 589 |
+
"content": "<extra_id_31>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": true,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32069": {
|
| 597 |
+
"content": "<extra_id_30>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": true,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32070": {
|
| 605 |
+
"content": "<extra_id_29>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": true,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32071": {
|
| 613 |
+
"content": "<extra_id_28>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": true,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32072": {
|
| 621 |
+
"content": "<extra_id_27>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": true,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32073": {
|
| 629 |
+
"content": "<extra_id_26>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": true,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32074": {
|
| 637 |
+
"content": "<extra_id_25>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": true,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32075": {
|
| 645 |
+
"content": "<extra_id_24>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": true,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32076": {
|
| 653 |
+
"content": "<extra_id_23>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": true,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32077": {
|
| 661 |
+
"content": "<extra_id_22>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": true,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32078": {
|
| 669 |
+
"content": "<extra_id_21>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": true,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32079": {
|
| 677 |
+
"content": "<extra_id_20>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": true,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32080": {
|
| 685 |
+
"content": "<extra_id_19>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": true,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32081": {
|
| 693 |
+
"content": "<extra_id_18>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": true,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32082": {
|
| 701 |
+
"content": "<extra_id_17>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": true,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32083": {
|
| 709 |
+
"content": "<extra_id_16>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": true,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32084": {
|
| 717 |
+
"content": "<extra_id_15>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": true,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32085": {
|
| 725 |
+
"content": "<extra_id_14>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": true,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32086": {
|
| 733 |
+
"content": "<extra_id_13>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": true,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32087": {
|
| 741 |
+
"content": "<extra_id_12>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": true,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32088": {
|
| 749 |
+
"content": "<extra_id_11>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": true,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32089": {
|
| 757 |
+
"content": "<extra_id_10>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": true,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32090": {
|
| 765 |
+
"content": "<extra_id_9>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": true,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32091": {
|
| 773 |
+
"content": "<extra_id_8>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": true,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32092": {
|
| 781 |
+
"content": "<extra_id_7>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": true,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32093": {
|
| 789 |
+
"content": "<extra_id_6>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": true,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32094": {
|
| 797 |
+
"content": "<extra_id_5>",
|
| 798 |
+
"lstrip": true,
|
| 799 |
+
"normalized": true,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32095": {
|
| 805 |
+
"content": "<extra_id_4>",
|
| 806 |
+
"lstrip": true,
|
| 807 |
+
"normalized": true,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32096": {
|
| 813 |
+
"content": "<extra_id_3>",
|
| 814 |
+
"lstrip": true,
|
| 815 |
+
"normalized": true,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32097": {
|
| 821 |
+
"content": "<extra_id_2>",
|
| 822 |
+
"lstrip": true,
|
| 823 |
+
"normalized": true,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"32098": {
|
| 829 |
+
"content": "<extra_id_1>",
|
| 830 |
+
"lstrip": true,
|
| 831 |
+
"normalized": true,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"32099": {
|
| 837 |
+
"content": "<extra_id_0>",
|
| 838 |
+
"lstrip": true,
|
| 839 |
+
"normalized": true,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
}
|
| 844 |
+
},
|
| 845 |
+
"additional_special_tokens": [
|
| 846 |
+
"<extra_id_99>",
|
| 847 |
+
"<extra_id_98>",
|
| 848 |
+
"<extra_id_97>",
|
| 849 |
+
"<extra_id_96>",
|
| 850 |
+
"<extra_id_95>",
|
| 851 |
+
"<extra_id_94>",
|
| 852 |
+
"<extra_id_93>",
|
| 853 |
+
"<extra_id_92>",
|
| 854 |
+
"<extra_id_91>",
|
| 855 |
+
"<extra_id_90>",
|
| 856 |
+
"<extra_id_89>",
|
| 857 |
+
"<extra_id_88>",
|
| 858 |
+
"<extra_id_87>",
|
| 859 |
+
"<extra_id_86>",
|
| 860 |
+
"<extra_id_85>",
|
| 861 |
+
"<extra_id_84>",
|
| 862 |
+
"<extra_id_83>",
|
| 863 |
+
"<extra_id_82>",
|
| 864 |
+
"<extra_id_81>",
|
| 865 |
+
"<extra_id_80>",
|
| 866 |
+
"<extra_id_79>",
|
| 867 |
+
"<extra_id_78>",
|
| 868 |
+
"<extra_id_77>",
|
| 869 |
+
"<extra_id_76>",
|
| 870 |
+
"<extra_id_75>",
|
| 871 |
+
"<extra_id_74>",
|
| 872 |
+
"<extra_id_73>",
|
| 873 |
+
"<extra_id_72>",
|
| 874 |
+
"<extra_id_71>",
|
| 875 |
+
"<extra_id_70>",
|
| 876 |
+
"<extra_id_69>",
|
| 877 |
+
"<extra_id_68>",
|
| 878 |
+
"<extra_id_67>",
|
| 879 |
+
"<extra_id_66>",
|
| 880 |
+
"<extra_id_65>",
|
| 881 |
+
"<extra_id_64>",
|
| 882 |
+
"<extra_id_63>",
|
| 883 |
+
"<extra_id_62>",
|
| 884 |
+
"<extra_id_61>",
|
| 885 |
+
"<extra_id_60>",
|
| 886 |
+
"<extra_id_59>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_57>",
|
| 889 |
+
"<extra_id_56>",
|
| 890 |
+
"<extra_id_55>",
|
| 891 |
+
"<extra_id_54>",
|
| 892 |
+
"<extra_id_53>",
|
| 893 |
+
"<extra_id_52>",
|
| 894 |
+
"<extra_id_51>",
|
| 895 |
+
"<extra_id_50>",
|
| 896 |
+
"<extra_id_49>",
|
| 897 |
+
"<extra_id_48>",
|
| 898 |
+
"<extra_id_47>",
|
| 899 |
+
"<extra_id_46>",
|
| 900 |
+
"<extra_id_45>",
|
| 901 |
+
"<extra_id_44>",
|
| 902 |
+
"<extra_id_43>",
|
| 903 |
+
"<extra_id_42>",
|
| 904 |
+
"<extra_id_41>",
|
| 905 |
+
"<extra_id_40>",
|
| 906 |
+
"<extra_id_39>",
|
| 907 |
+
"<extra_id_38>",
|
| 908 |
+
"<extra_id_37>",
|
| 909 |
+
"<extra_id_36>",
|
| 910 |
+
"<extra_id_35>",
|
| 911 |
+
"<extra_id_34>",
|
| 912 |
+
"<extra_id_33>",
|
| 913 |
+
"<extra_id_32>",
|
| 914 |
+
"<extra_id_31>",
|
| 915 |
+
"<extra_id_30>",
|
| 916 |
+
"<extra_id_29>",
|
| 917 |
+
"<extra_id_28>",
|
| 918 |
+
"<extra_id_27>",
|
| 919 |
+
"<extra_id_26>",
|
| 920 |
+
"<extra_id_25>",
|
| 921 |
+
"<extra_id_24>",
|
| 922 |
+
"<extra_id_23>",
|
| 923 |
+
"<extra_id_22>",
|
| 924 |
+
"<extra_id_21>",
|
| 925 |
+
"<extra_id_20>",
|
| 926 |
+
"<extra_id_19>",
|
| 927 |
+
"<extra_id_18>",
|
| 928 |
+
"<extra_id_17>",
|
| 929 |
+
"<extra_id_16>",
|
| 930 |
+
"<extra_id_15>",
|
| 931 |
+
"<extra_id_14>",
|
| 932 |
+
"<extra_id_13>",
|
| 933 |
+
"<extra_id_12>",
|
| 934 |
+
"<extra_id_11>",
|
| 935 |
+
"<extra_id_10>",
|
| 936 |
+
"<extra_id_9>",
|
| 937 |
+
"<extra_id_8>",
|
| 938 |
+
"<extra_id_7>",
|
| 939 |
+
"<extra_id_6>",
|
| 940 |
+
"<extra_id_5>",
|
| 941 |
+
"<extra_id_4>",
|
| 942 |
+
"<extra_id_3>",
|
| 943 |
+
"<extra_id_2>",
|
| 944 |
+
"<extra_id_1>",
|
| 945 |
+
"<extra_id_0>"
|
| 946 |
+
],
|
| 947 |
+
"bos_token": "<s>",
|
| 948 |
+
"clean_up_tokenization_spaces": true,
|
| 949 |
+
"cls_token": "<s>",
|
| 950 |
+
"eos_token": "</s>",
|
| 951 |
+
"errors": "replace",
|
| 952 |
+
"mask_token": "<mask>",
|
| 953 |
+
"model_max_length": 512,
|
| 954 |
+
"pad_token": "<pad>",
|
| 955 |
+
"sep_token": "</s>",
|
| 956 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 957 |
+
"trim_offsets": true,
|
| 958 |
+
"unk_token": "<unk>"
|
| 959 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2780 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.1402364451691804,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 31500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.8877573609352112,
|
| 14 |
+
"learning_rate": 9.98641119717353e-06,
|
| 15 |
+
"loss": 2.7747,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.891560435295105,
|
| 21 |
+
"learning_rate": 9.97282239434706e-06,
|
| 22 |
+
"loss": 2.3805,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02,
|
| 27 |
+
"grad_norm": 1.140250563621521,
|
| 28 |
+
"learning_rate": 9.959233591520588e-06,
|
| 29 |
+
"loss": 2.2018,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03,
|
| 34 |
+
"grad_norm": 1.5957276821136475,
|
| 35 |
+
"learning_rate": 9.945644788694116e-06,
|
| 36 |
+
"loss": 2.1426,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03,
|
| 41 |
+
"grad_norm": 1.0516589879989624,
|
| 42 |
+
"learning_rate": 9.932055985867646e-06,
|
| 43 |
+
"loss": 2.0379,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"eval_codebleu": 0.02236215080832533,
|
| 49 |
+
"eval_dataflow_match_score": 0.020328127538115238,
|
| 50 |
+
"eval_loss": 2.005807876586914,
|
| 51 |
+
"eval_ngram_match_score": 7.828601095920155e-05,
|
| 52 |
+
"eval_runtime": 211.5866,
|
| 53 |
+
"eval_samples_per_second": 12.019,
|
| 54 |
+
"eval_steps_per_second": 1.503,
|
| 55 |
+
"eval_syntax_match_score": 0.06800422172156935,
|
| 56 |
+
"eval_weighted_ngram_match_score": 0.0010379679626575443,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"grad_norm": 1.4408249855041504,
|
| 62 |
+
"learning_rate": 9.918467183041175e-06,
|
| 63 |
+
"loss": 2.1005,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.05,
|
| 68 |
+
"grad_norm": 1.042541742324829,
|
| 69 |
+
"learning_rate": 9.904878380214705e-06,
|
| 70 |
+
"loss": 2.0475,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05,
|
| 75 |
+
"grad_norm": 0.9206609129905701,
|
| 76 |
+
"learning_rate": 9.891289577388233e-06,
|
| 77 |
+
"loss": 2.0145,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.06,
|
| 82 |
+
"grad_norm": 1.2876330614089966,
|
| 83 |
+
"learning_rate": 9.87770077456176e-06,
|
| 84 |
+
"loss": 1.9729,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.07,
|
| 89 |
+
"grad_norm": 1.5496817827224731,
|
| 90 |
+
"learning_rate": 9.86411197173529e-06,
|
| 91 |
+
"loss": 1.9755,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.07,
|
| 96 |
+
"eval_codebleu": 0.026625421991617458,
|
| 97 |
+
"eval_dataflow_match_score": 0.017334601907502377,
|
| 98 |
+
"eval_loss": 1.8824141025543213,
|
| 99 |
+
"eval_ngram_match_score": 0.0001360979918249884,
|
| 100 |
+
"eval_runtime": 210.1093,
|
| 101 |
+
"eval_samples_per_second": 12.103,
|
| 102 |
+
"eval_steps_per_second": 1.513,
|
| 103 |
+
"eval_syntax_match_score": 0.085743571008139,
|
| 104 |
+
"eval_weighted_ngram_match_score": 0.0032874170590034683,
|
| 105 |
+
"step": 1000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.07,
|
| 109 |
+
"grad_norm": 1.479344129562378,
|
| 110 |
+
"learning_rate": 9.85052316890882e-06,
|
| 111 |
+
"loss": 1.9526,
|
| 112 |
+
"step": 1100
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.08,
|
| 116 |
+
"grad_norm": 1.1165575981140137,
|
| 117 |
+
"learning_rate": 9.83693436608235e-06,
|
| 118 |
+
"loss": 1.9212,
|
| 119 |
+
"step": 1200
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.09,
|
| 123 |
+
"grad_norm": 1.871772289276123,
|
| 124 |
+
"learning_rate": 9.823345563255877e-06,
|
| 125 |
+
"loss": 1.8674,
|
| 126 |
+
"step": 1300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.1,
|
| 130 |
+
"grad_norm": 1.1310107707977295,
|
| 131 |
+
"learning_rate": 9.809756760429407e-06,
|
| 132 |
+
"loss": 1.9083,
|
| 133 |
+
"step": 1400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.1,
|
| 137 |
+
"grad_norm": 1.2779932022094727,
|
| 138 |
+
"learning_rate": 9.796167957602935e-06,
|
| 139 |
+
"loss": 1.8672,
|
| 140 |
+
"step": 1500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.1,
|
| 144 |
+
"eval_codebleu": 0.03411263800674984,
|
| 145 |
+
"eval_dataflow_match_score": 0.035922307567354324,
|
| 146 |
+
"eval_loss": 1.8209562301635742,
|
| 147 |
+
"eval_ngram_match_score": 0.00019790870128407514,
|
| 148 |
+
"eval_runtime": 209.7736,
|
| 149 |
+
"eval_samples_per_second": 12.123,
|
| 150 |
+
"eval_steps_per_second": 1.516,
|
| 151 |
+
"eval_syntax_match_score": 0.09630802330065559,
|
| 152 |
+
"eval_weighted_ngram_match_score": 0.004022312457705368,
|
| 153 |
+
"step": 1500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.11,
|
| 157 |
+
"grad_norm": 1.2445776462554932,
|
| 158 |
+
"learning_rate": 9.782579154776465e-06,
|
| 159 |
+
"loss": 1.8163,
|
| 160 |
+
"step": 1600
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.12,
|
| 164 |
+
"grad_norm": 1.673412561416626,
|
| 165 |
+
"learning_rate": 9.768990351949994e-06,
|
| 166 |
+
"loss": 1.8664,
|
| 167 |
+
"step": 1700
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.12,
|
| 171 |
+
"grad_norm": 1.3831863403320312,
|
| 172 |
+
"learning_rate": 9.755401549123524e-06,
|
| 173 |
+
"loss": 1.8336,
|
| 174 |
+
"step": 1800
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.13,
|
| 178 |
+
"grad_norm": 1.5055395364761353,
|
| 179 |
+
"learning_rate": 9.741812746297052e-06,
|
| 180 |
+
"loss": 1.879,
|
| 181 |
+
"step": 1900
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.14,
|
| 185 |
+
"grad_norm": 1.3736721277236938,
|
| 186 |
+
"learning_rate": 9.72822394347058e-06,
|
| 187 |
+
"loss": 1.8522,
|
| 188 |
+
"step": 2000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.14,
|
| 192 |
+
"eval_codebleu": 0.04137599574546961,
|
| 193 |
+
"eval_dataflow_match_score": 0.06186619636599912,
|
| 194 |
+
"eval_loss": 1.7707544565200806,
|
| 195 |
+
"eval_ngram_match_score": 0.00026554637185762897,
|
| 196 |
+
"eval_runtime": 210.486,
|
| 197 |
+
"eval_samples_per_second": 12.082,
|
| 198 |
+
"eval_steps_per_second": 1.511,
|
| 199 |
+
"eval_syntax_match_score": 0.09913941829547991,
|
| 200 |
+
"eval_weighted_ngram_match_score": 0.00423282194854177,
|
| 201 |
+
"step": 2000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.14,
|
| 205 |
+
"grad_norm": 1.5695489645004272,
|
| 206 |
+
"learning_rate": 9.71463514064411e-06,
|
| 207 |
+
"loss": 1.7906,
|
| 208 |
+
"step": 2100
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.15,
|
| 212 |
+
"grad_norm": 1.4151173830032349,
|
| 213 |
+
"learning_rate": 9.701046337817639e-06,
|
| 214 |
+
"loss": 1.8182,
|
| 215 |
+
"step": 2200
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.16,
|
| 219 |
+
"grad_norm": 1.7115099430084229,
|
| 220 |
+
"learning_rate": 9.687457534991169e-06,
|
| 221 |
+
"loss": 1.8232,
|
| 222 |
+
"step": 2300
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.16,
|
| 226 |
+
"grad_norm": 1.1658021211624146,
|
| 227 |
+
"learning_rate": 9.673868732164697e-06,
|
| 228 |
+
"loss": 1.7381,
|
| 229 |
+
"step": 2400
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.17,
|
| 233 |
+
"grad_norm": 1.5483379364013672,
|
| 234 |
+
"learning_rate": 9.660279929338226e-06,
|
| 235 |
+
"loss": 1.7707,
|
| 236 |
+
"step": 2500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.17,
|
| 240 |
+
"eval_codebleu": 0.041373696094825684,
|
| 241 |
+
"eval_dataflow_match_score": 0.06151811199034646,
|
| 242 |
+
"eval_loss": 1.7324126958847046,
|
| 243 |
+
"eval_ngram_match_score": 0.00031767245966084565,
|
| 244 |
+
"eval_runtime": 210.1473,
|
| 245 |
+
"eval_samples_per_second": 12.101,
|
| 246 |
+
"eval_steps_per_second": 1.513,
|
| 247 |
+
"eval_syntax_match_score": 0.09862185146846902,
|
| 248 |
+
"eval_weighted_ngram_match_score": 0.0050371484608264,
|
| 249 |
+
"step": 2500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.18,
|
| 253 |
+
"grad_norm": 1.138310194015503,
|
| 254 |
+
"learning_rate": 9.646691126511754e-06,
|
| 255 |
+
"loss": 1.702,
|
| 256 |
+
"step": 2600
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.18,
|
| 260 |
+
"grad_norm": 1.5409811735153198,
|
| 261 |
+
"learning_rate": 9.633102323685284e-06,
|
| 262 |
+
"loss": 1.7403,
|
| 263 |
+
"step": 2700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.19,
|
| 267 |
+
"grad_norm": 1.2863227128982544,
|
| 268 |
+
"learning_rate": 9.619513520858813e-06,
|
| 269 |
+
"loss": 1.7514,
|
| 270 |
+
"step": 2800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.2,
|
| 274 |
+
"grad_norm": 1.523219347000122,
|
| 275 |
+
"learning_rate": 9.605924718032343e-06,
|
| 276 |
+
"loss": 1.7735,
|
| 277 |
+
"step": 2900
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.2,
|
| 281 |
+
"grad_norm": 1.6315879821777344,
|
| 282 |
+
"learning_rate": 9.592335915205871e-06,
|
| 283 |
+
"loss": 1.7289,
|
| 284 |
+
"step": 3000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.2,
|
| 288 |
+
"eval_codebleu": 0.03736357788677419,
|
| 289 |
+
"eval_dataflow_match_score": 0.04515814633467152,
|
| 290 |
+
"eval_loss": 1.6959866285324097,
|
| 291 |
+
"eval_ngram_match_score": 0.00026766267346779954,
|
| 292 |
+
"eval_runtime": 209.9032,
|
| 293 |
+
"eval_samples_per_second": 12.115,
|
| 294 |
+
"eval_steps_per_second": 1.515,
|
| 295 |
+
"eval_syntax_match_score": 0.09879437374413931,
|
| 296 |
+
"eval_weighted_ngram_match_score": 0.0052341287948181195,
|
| 297 |
+
"step": 3000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.21,
|
| 301 |
+
"grad_norm": 1.5990880727767944,
|
| 302 |
+
"learning_rate": 9.5787471123794e-06,
|
| 303 |
+
"loss": 1.7275,
|
| 304 |
+
"step": 3100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.22,
|
| 308 |
+
"grad_norm": 1.787031650543213,
|
| 309 |
+
"learning_rate": 9.565158309552928e-06,
|
| 310 |
+
"loss": 1.7112,
|
| 311 |
+
"step": 3200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.22,
|
| 315 |
+
"grad_norm": 1.6794238090515137,
|
| 316 |
+
"learning_rate": 9.551569506726458e-06,
|
| 317 |
+
"loss": 1.683,
|
| 318 |
+
"step": 3300
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.23,
|
| 322 |
+
"grad_norm": 2.1808717250823975,
|
| 323 |
+
"learning_rate": 9.537980703899988e-06,
|
| 324 |
+
"loss": 1.8087,
|
| 325 |
+
"step": 3400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.24,
|
| 329 |
+
"grad_norm": 1.737121343612671,
|
| 330 |
+
"learning_rate": 9.524391901073516e-06,
|
| 331 |
+
"loss": 1.7739,
|
| 332 |
+
"step": 3500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.24,
|
| 336 |
+
"eval_codebleu": 0.03697189900391692,
|
| 337 |
+
"eval_dataflow_match_score": 0.03780196319587868,
|
| 338 |
+
"eval_loss": 1.668063998222351,
|
| 339 |
+
"eval_ngram_match_score": 0.0003274646611745997,
|
| 340 |
+
"eval_runtime": 208.872,
|
| 341 |
+
"eval_samples_per_second": 12.175,
|
| 342 |
+
"eval_steps_per_second": 1.522,
|
| 343 |
+
"eval_syntax_match_score": 0.1035438105096511,
|
| 344 |
+
"eval_weighted_ngram_match_score": 0.006214357648963285,
|
| 345 |
+
"step": 3500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24,
|
| 349 |
+
"grad_norm": 1.6818939447402954,
|
| 350 |
+
"learning_rate": 9.510803098247045e-06,
|
| 351 |
+
"loss": 1.7366,
|
| 352 |
+
"step": 3600
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.25,
|
| 356 |
+
"grad_norm": 1.4390071630477905,
|
| 357 |
+
"learning_rate": 9.497214295420573e-06,
|
| 358 |
+
"loss": 1.6693,
|
| 359 |
+
"step": 3700
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.26,
|
| 363 |
+
"grad_norm": 1.443108081817627,
|
| 364 |
+
"learning_rate": 9.483625492594103e-06,
|
| 365 |
+
"loss": 1.6856,
|
| 366 |
+
"step": 3800
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.26,
|
| 370 |
+
"grad_norm": 1.6540530920028687,
|
| 371 |
+
"learning_rate": 9.470036689767632e-06,
|
| 372 |
+
"loss": 1.6965,
|
| 373 |
+
"step": 3900
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.27,
|
| 377 |
+
"grad_norm": 1.178989291191101,
|
| 378 |
+
"learning_rate": 9.456447886941162e-06,
|
| 379 |
+
"loss": 1.6797,
|
| 380 |
+
"step": 4000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.27,
|
| 384 |
+
"eval_codebleu": 0.033575238882649495,
|
| 385 |
+
"eval_dataflow_match_score": 0.025967094423688303,
|
| 386 |
+
"eval_loss": 1.6396487951278687,
|
| 387 |
+
"eval_ngram_match_score": 0.00023558729997467283,
|
| 388 |
+
"eval_runtime": 209.0765,
|
| 389 |
+
"eval_samples_per_second": 12.163,
|
| 390 |
+
"eval_steps_per_second": 1.521,
|
| 391 |
+
"eval_syntax_match_score": 0.1018591812295764,
|
| 392 |
+
"eval_weighted_ngram_match_score": 0.006239092577358598,
|
| 393 |
+
"step": 4000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.28,
|
| 397 |
+
"grad_norm": 1.888967752456665,
|
| 398 |
+
"learning_rate": 9.44285908411469e-06,
|
| 399 |
+
"loss": 1.6815,
|
| 400 |
+
"step": 4100
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.29,
|
| 404 |
+
"grad_norm": 1.4612641334533691,
|
| 405 |
+
"learning_rate": 9.42927028128822e-06,
|
| 406 |
+
"loss": 1.6089,
|
| 407 |
+
"step": 4200
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.29,
|
| 411 |
+
"grad_norm": 1.5609626770019531,
|
| 412 |
+
"learning_rate": 9.415681478461748e-06,
|
| 413 |
+
"loss": 1.6824,
|
| 414 |
+
"step": 4300
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.3,
|
| 418 |
+
"grad_norm": 1.38056218624115,
|
| 419 |
+
"learning_rate": 9.402092675635277e-06,
|
| 420 |
+
"loss": 1.679,
|
| 421 |
+
"step": 4400
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.31,
|
| 425 |
+
"grad_norm": 1.928477168083191,
|
| 426 |
+
"learning_rate": 9.388503872808807e-06,
|
| 427 |
+
"loss": 1.6737,
|
| 428 |
+
"step": 4500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.31,
|
| 432 |
+
"eval_codebleu": 0.03436485059379589,
|
| 433 |
+
"eval_dataflow_match_score": 0.025433365047687558,
|
| 434 |
+
"eval_loss": 1.619603157043457,
|
| 435 |
+
"eval_ngram_match_score": 0.00025042578946432695,
|
| 436 |
+
"eval_runtime": 210.4293,
|
| 437 |
+
"eval_samples_per_second": 12.085,
|
| 438 |
+
"eval_steps_per_second": 1.511,
|
| 439 |
+
"eval_syntax_match_score": 0.10487324686922811,
|
| 440 |
+
"eval_weighted_ngram_match_score": 0.006902364668803559,
|
| 441 |
+
"step": 4500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.31,
|
| 445 |
+
"grad_norm": 1.467225432395935,
|
| 446 |
+
"learning_rate": 9.374915069982335e-06,
|
| 447 |
+
"loss": 1.642,
|
| 448 |
+
"step": 4600
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.32,
|
| 452 |
+
"grad_norm": 1.4231284856796265,
|
| 453 |
+
"learning_rate": 9.361326267155864e-06,
|
| 454 |
+
"loss": 1.6238,
|
| 455 |
+
"step": 4700
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.33,
|
| 459 |
+
"grad_norm": 1.61458158493042,
|
| 460 |
+
"learning_rate": 9.347737464329394e-06,
|
| 461 |
+
"loss": 1.6226,
|
| 462 |
+
"step": 4800
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.33,
|
| 466 |
+
"grad_norm": 1.8465476036071777,
|
| 467 |
+
"learning_rate": 9.334148661502922e-06,
|
| 468 |
+
"loss": 1.6427,
|
| 469 |
+
"step": 4900
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.34,
|
| 473 |
+
"grad_norm": 2.1492788791656494,
|
| 474 |
+
"learning_rate": 9.320559858676452e-06,
|
| 475 |
+
"loss": 1.6783,
|
| 476 |
+
"step": 5000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.34,
|
| 480 |
+
"eval_codebleu": 0.03197730480981573,
|
| 481 |
+
"eval_dataflow_match_score": 0.018842967535330563,
|
| 482 |
+
"eval_loss": 1.596398115158081,
|
| 483 |
+
"eval_ngram_match_score": 0.00021050334214284166,
|
| 484 |
+
"eval_runtime": 209.9696,
|
| 485 |
+
"eval_samples_per_second": 12.111,
|
| 486 |
+
"eval_steps_per_second": 1.515,
|
| 487 |
+
"eval_syntax_match_score": 0.10182873612210518,
|
| 488 |
+
"eval_weighted_ngram_match_score": 0.0070270122396843505,
|
| 489 |
+
"step": 5000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.35,
|
| 493 |
+
"grad_norm": 1.5661336183547974,
|
| 494 |
+
"learning_rate": 9.306971055849981e-06,
|
| 495 |
+
"loss": 1.6227,
|
| 496 |
+
"step": 5100
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.35,
|
| 500 |
+
"grad_norm": 1.5441151857376099,
|
| 501 |
+
"learning_rate": 9.293382253023509e-06,
|
| 502 |
+
"loss": 1.6525,
|
| 503 |
+
"step": 5200
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.36,
|
| 507 |
+
"grad_norm": 1.507628083229065,
|
| 508 |
+
"learning_rate": 9.279793450197039e-06,
|
| 509 |
+
"loss": 1.649,
|
| 510 |
+
"step": 5300
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.37,
|
| 514 |
+
"grad_norm": 1.5360280275344849,
|
| 515 |
+
"learning_rate": 9.266204647370567e-06,
|
| 516 |
+
"loss": 1.6738,
|
| 517 |
+
"step": 5400
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.37,
|
| 521 |
+
"grad_norm": 1.6375775337219238,
|
| 522 |
+
"learning_rate": 9.252615844544096e-06,
|
| 523 |
+
"loss": 1.5854,
|
| 524 |
+
"step": 5500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.37,
|
| 528 |
+
"eval_loss": 1.5711854696273804,
|
| 529 |
+
"eval_runtime": 70.8487,
|
| 530 |
+
"eval_samples_per_second": 35.893,
|
| 531 |
+
"eval_steps_per_second": 4.488,
|
| 532 |
+
"step": 5500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.38,
|
| 536 |
+
"grad_norm": 1.5210243463516235,
|
| 537 |
+
"learning_rate": 9.239027041717626e-06,
|
| 538 |
+
"loss": 1.621,
|
| 539 |
+
"step": 5600
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.39,
|
| 543 |
+
"grad_norm": 1.2972959280014038,
|
| 544 |
+
"learning_rate": 9.225438238891154e-06,
|
| 545 |
+
"loss": 1.6124,
|
| 546 |
+
"step": 5700
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.39,
|
| 550 |
+
"grad_norm": 1.902424693107605,
|
| 551 |
+
"learning_rate": 9.211849436064683e-06,
|
| 552 |
+
"loss": 1.6012,
|
| 553 |
+
"step": 5800
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.4,
|
| 557 |
+
"grad_norm": 1.865466594696045,
|
| 558 |
+
"learning_rate": 9.198260633238213e-06,
|
| 559 |
+
"loss": 1.5745,
|
| 560 |
+
"step": 5900
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.41,
|
| 564 |
+
"grad_norm": 1.6546335220336914,
|
| 565 |
+
"learning_rate": 9.184671830411741e-06,
|
| 566 |
+
"loss": 1.5874,
|
| 567 |
+
"step": 6000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.41,
|
| 571 |
+
"eval_loss": 1.553696870803833,
|
| 572 |
+
"eval_runtime": 70.799,
|
| 573 |
+
"eval_samples_per_second": 35.919,
|
| 574 |
+
"eval_steps_per_second": 4.492,
|
| 575 |
+
"step": 6000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.41,
|
| 579 |
+
"grad_norm": 1.7478700876235962,
|
| 580 |
+
"learning_rate": 9.17108302758527e-06,
|
| 581 |
+
"loss": 1.5666,
|
| 582 |
+
"step": 6100
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.42,
|
| 586 |
+
"grad_norm": 1.5560758113861084,
|
| 587 |
+
"learning_rate": 9.1574942247588e-06,
|
| 588 |
+
"loss": 1.5382,
|
| 589 |
+
"step": 6200
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.43,
|
| 593 |
+
"grad_norm": 1.4764758348464966,
|
| 594 |
+
"learning_rate": 9.143905421932328e-06,
|
| 595 |
+
"loss": 1.5408,
|
| 596 |
+
"step": 6300
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.43,
|
| 600 |
+
"grad_norm": 1.6634376049041748,
|
| 601 |
+
"learning_rate": 9.130316619105858e-06,
|
| 602 |
+
"loss": 1.5688,
|
| 603 |
+
"step": 6400
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.44,
|
| 607 |
+
"grad_norm": 1.673550009727478,
|
| 608 |
+
"learning_rate": 9.116727816279387e-06,
|
| 609 |
+
"loss": 1.5445,
|
| 610 |
+
"step": 6500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.44,
|
| 614 |
+
"eval_loss": 1.5321872234344482,
|
| 615 |
+
"eval_runtime": 70.8079,
|
| 616 |
+
"eval_samples_per_second": 35.914,
|
| 617 |
+
"eval_steps_per_second": 4.491,
|
| 618 |
+
"step": 6500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.45,
|
| 622 |
+
"grad_norm": 1.572766900062561,
|
| 623 |
+
"learning_rate": 9.103139013452915e-06,
|
| 624 |
+
"loss": 1.5596,
|
| 625 |
+
"step": 6600
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.46,
|
| 629 |
+
"grad_norm": 1.4650744199752808,
|
| 630 |
+
"learning_rate": 9.089550210626445e-06,
|
| 631 |
+
"loss": 1.5327,
|
| 632 |
+
"step": 6700
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.46,
|
| 636 |
+
"grad_norm": 1.8133198022842407,
|
| 637 |
+
"learning_rate": 9.075961407799973e-06,
|
| 638 |
+
"loss": 1.5789,
|
| 639 |
+
"step": 6800
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.47,
|
| 643 |
+
"grad_norm": 1.6164945363998413,
|
| 644 |
+
"learning_rate": 9.062372604973503e-06,
|
| 645 |
+
"loss": 1.4918,
|
| 646 |
+
"step": 6900
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.48,
|
| 650 |
+
"grad_norm": 1.7517341375350952,
|
| 651 |
+
"learning_rate": 9.048783802147032e-06,
|
| 652 |
+
"loss": 1.4947,
|
| 653 |
+
"step": 7000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.48,
|
| 657 |
+
"eval_loss": 1.5142408609390259,
|
| 658 |
+
"eval_runtime": 70.7829,
|
| 659 |
+
"eval_samples_per_second": 35.927,
|
| 660 |
+
"eval_steps_per_second": 4.493,
|
| 661 |
+
"step": 7000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.48,
|
| 665 |
+
"grad_norm": 2.3255422115325928,
|
| 666 |
+
"learning_rate": 9.03519499932056e-06,
|
| 667 |
+
"loss": 1.5434,
|
| 668 |
+
"step": 7100
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.49,
|
| 672 |
+
"grad_norm": 2.118253469467163,
|
| 673 |
+
"learning_rate": 9.02160619649409e-06,
|
| 674 |
+
"loss": 1.5191,
|
| 675 |
+
"step": 7200
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5,
|
| 679 |
+
"grad_norm": 1.5948559045791626,
|
| 680 |
+
"learning_rate": 9.008017393667618e-06,
|
| 681 |
+
"loss": 1.5437,
|
| 682 |
+
"step": 7300
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5,
|
| 686 |
+
"grad_norm": 1.4735013246536255,
|
| 687 |
+
"learning_rate": 8.994428590841147e-06,
|
| 688 |
+
"loss": 1.5217,
|
| 689 |
+
"step": 7400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.51,
|
| 693 |
+
"grad_norm": 1.5940884351730347,
|
| 694 |
+
"learning_rate": 8.980839788014677e-06,
|
| 695 |
+
"loss": 1.5113,
|
| 696 |
+
"step": 7500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.51,
|
| 700 |
+
"eval_loss": 1.4991660118103027,
|
| 701 |
+
"eval_runtime": 70.7857,
|
| 702 |
+
"eval_samples_per_second": 35.925,
|
| 703 |
+
"eval_steps_per_second": 4.492,
|
| 704 |
+
"step": 7500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.52,
|
| 708 |
+
"grad_norm": 1.7738714218139648,
|
| 709 |
+
"learning_rate": 8.967250985188207e-06,
|
| 710 |
+
"loss": 1.5253,
|
| 711 |
+
"step": 7600
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.52,
|
| 715 |
+
"grad_norm": 1.8445935249328613,
|
| 716 |
+
"learning_rate": 8.953662182361734e-06,
|
| 717 |
+
"loss": 1.5359,
|
| 718 |
+
"step": 7700
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.53,
|
| 722 |
+
"grad_norm": 1.5108485221862793,
|
| 723 |
+
"learning_rate": 8.940073379535264e-06,
|
| 724 |
+
"loss": 1.5228,
|
| 725 |
+
"step": 7800
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.54,
|
| 729 |
+
"grad_norm": 1.7147557735443115,
|
| 730 |
+
"learning_rate": 8.926484576708792e-06,
|
| 731 |
+
"loss": 1.5228,
|
| 732 |
+
"step": 7900
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.54,
|
| 736 |
+
"grad_norm": 1.5899161100387573,
|
| 737 |
+
"learning_rate": 8.912895773882322e-06,
|
| 738 |
+
"loss": 1.4889,
|
| 739 |
+
"step": 8000
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.54,
|
| 743 |
+
"eval_loss": 1.4857795238494873,
|
| 744 |
+
"eval_runtime": 70.8945,
|
| 745 |
+
"eval_samples_per_second": 35.87,
|
| 746 |
+
"eval_steps_per_second": 4.486,
|
| 747 |
+
"step": 8000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.55,
|
| 751 |
+
"grad_norm": 1.6886754035949707,
|
| 752 |
+
"learning_rate": 8.899306971055851e-06,
|
| 753 |
+
"loss": 1.4898,
|
| 754 |
+
"step": 8100
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.56,
|
| 758 |
+
"grad_norm": 1.5048600435256958,
|
| 759 |
+
"learning_rate": 8.885718168229381e-06,
|
| 760 |
+
"loss": 1.5239,
|
| 761 |
+
"step": 8200
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.56,
|
| 765 |
+
"grad_norm": 1.8773216009140015,
|
| 766 |
+
"learning_rate": 8.872129365402909e-06,
|
| 767 |
+
"loss": 1.4889,
|
| 768 |
+
"step": 8300
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.57,
|
| 772 |
+
"grad_norm": 1.7063783407211304,
|
| 773 |
+
"learning_rate": 8.858540562576437e-06,
|
| 774 |
+
"loss": 1.4472,
|
| 775 |
+
"step": 8400
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.58,
|
| 779 |
+
"grad_norm": 1.5942984819412231,
|
| 780 |
+
"learning_rate": 8.844951759749966e-06,
|
| 781 |
+
"loss": 1.4998,
|
| 782 |
+
"step": 8500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.58,
|
| 786 |
+
"eval_loss": 1.4711333513259888,
|
| 787 |
+
"eval_runtime": 70.9176,
|
| 788 |
+
"eval_samples_per_second": 35.858,
|
| 789 |
+
"eval_steps_per_second": 4.484,
|
| 790 |
+
"step": 8500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.58,
|
| 794 |
+
"grad_norm": 1.818272352218628,
|
| 795 |
+
"learning_rate": 8.831362956923496e-06,
|
| 796 |
+
"loss": 1.5504,
|
| 797 |
+
"step": 8600
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.59,
|
| 801 |
+
"grad_norm": 1.8230923414230347,
|
| 802 |
+
"learning_rate": 8.817774154097026e-06,
|
| 803 |
+
"loss": 1.5182,
|
| 804 |
+
"step": 8700
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.6,
|
| 808 |
+
"grad_norm": 1.8054814338684082,
|
| 809 |
+
"learning_rate": 8.804185351270554e-06,
|
| 810 |
+
"loss": 1.5136,
|
| 811 |
+
"step": 8800
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.6,
|
| 815 |
+
"grad_norm": 1.7768468856811523,
|
| 816 |
+
"learning_rate": 8.790596548444083e-06,
|
| 817 |
+
"loss": 1.4643,
|
| 818 |
+
"step": 8900
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.61,
|
| 822 |
+
"grad_norm": 1.9298087358474731,
|
| 823 |
+
"learning_rate": 8.777007745617611e-06,
|
| 824 |
+
"loss": 1.4449,
|
| 825 |
+
"step": 9000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.61,
|
| 829 |
+
"eval_loss": 1.4553042650222778,
|
| 830 |
+
"eval_runtime": 71.0741,
|
| 831 |
+
"eval_samples_per_second": 35.78,
|
| 832 |
+
"eval_steps_per_second": 4.474,
|
| 833 |
+
"step": 9000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.62,
|
| 837 |
+
"grad_norm": 1.979022741317749,
|
| 838 |
+
"learning_rate": 8.76341894279114e-06,
|
| 839 |
+
"loss": 1.5057,
|
| 840 |
+
"step": 9100
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.63,
|
| 844 |
+
"grad_norm": 1.6144100427627563,
|
| 845 |
+
"learning_rate": 8.74983013996467e-06,
|
| 846 |
+
"loss": 1.4893,
|
| 847 |
+
"step": 9200
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.63,
|
| 851 |
+
"grad_norm": 1.7385257482528687,
|
| 852 |
+
"learning_rate": 8.7362413371382e-06,
|
| 853 |
+
"loss": 1.4427,
|
| 854 |
+
"step": 9300
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.64,
|
| 858 |
+
"grad_norm": 2.218280792236328,
|
| 859 |
+
"learning_rate": 8.722652534311728e-06,
|
| 860 |
+
"loss": 1.445,
|
| 861 |
+
"step": 9400
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.65,
|
| 865 |
+
"grad_norm": 1.760903000831604,
|
| 866 |
+
"learning_rate": 8.709063731485256e-06,
|
| 867 |
+
"loss": 1.4364,
|
| 868 |
+
"step": 9500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.65,
|
| 872 |
+
"eval_loss": 1.4402815103530884,
|
| 873 |
+
"eval_runtime": 70.7715,
|
| 874 |
+
"eval_samples_per_second": 35.933,
|
| 875 |
+
"eval_steps_per_second": 4.493,
|
| 876 |
+
"step": 9500
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.65,
|
| 880 |
+
"grad_norm": 1.4513877630233765,
|
| 881 |
+
"learning_rate": 8.695474928658785e-06,
|
| 882 |
+
"loss": 1.437,
|
| 883 |
+
"step": 9600
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.66,
|
| 887 |
+
"grad_norm": 1.703837513923645,
|
| 888 |
+
"learning_rate": 8.681886125832315e-06,
|
| 889 |
+
"loss": 1.4565,
|
| 890 |
+
"step": 9700
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.67,
|
| 894 |
+
"grad_norm": 2.192049980163574,
|
| 895 |
+
"learning_rate": 8.668297323005845e-06,
|
| 896 |
+
"loss": 1.4654,
|
| 897 |
+
"step": 9800
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.67,
|
| 901 |
+
"grad_norm": 2.012014150619507,
|
| 902 |
+
"learning_rate": 8.654708520179373e-06,
|
| 903 |
+
"loss": 1.4975,
|
| 904 |
+
"step": 9900
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.68,
|
| 908 |
+
"grad_norm": 2.117527484893799,
|
| 909 |
+
"learning_rate": 8.641119717352902e-06,
|
| 910 |
+
"loss": 1.4446,
|
| 911 |
+
"step": 10000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.68,
|
| 915 |
+
"eval_loss": 1.4303960800170898,
|
| 916 |
+
"eval_runtime": 70.9752,
|
| 917 |
+
"eval_samples_per_second": 35.829,
|
| 918 |
+
"eval_steps_per_second": 4.48,
|
| 919 |
+
"step": 10000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"grad_norm": 2.3108479976654053,
|
| 924 |
+
"learning_rate": 8.62753091452643e-06,
|
| 925 |
+
"loss": 1.4801,
|
| 926 |
+
"step": 10100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.69,
|
| 930 |
+
"grad_norm": 1.4589275121688843,
|
| 931 |
+
"learning_rate": 8.61394211169996e-06,
|
| 932 |
+
"loss": 1.4579,
|
| 933 |
+
"step": 10200
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7,
|
| 937 |
+
"grad_norm": 1.7688006162643433,
|
| 938 |
+
"learning_rate": 8.60035330887349e-06,
|
| 939 |
+
"loss": 1.471,
|
| 940 |
+
"step": 10300
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.71,
|
| 944 |
+
"grad_norm": 1.6766855716705322,
|
| 945 |
+
"learning_rate": 8.586764506047019e-06,
|
| 946 |
+
"loss": 1.4532,
|
| 947 |
+
"step": 10400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.71,
|
| 951 |
+
"grad_norm": 2.0386102199554443,
|
| 952 |
+
"learning_rate": 8.573175703220547e-06,
|
| 953 |
+
"loss": 1.3998,
|
| 954 |
+
"step": 10500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.71,
|
| 958 |
+
"eval_loss": 1.4204617738723755,
|
| 959 |
+
"eval_runtime": 70.7476,
|
| 960 |
+
"eval_samples_per_second": 35.945,
|
| 961 |
+
"eval_steps_per_second": 4.495,
|
| 962 |
+
"step": 10500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.72,
|
| 966 |
+
"grad_norm": 1.9797570705413818,
|
| 967 |
+
"learning_rate": 8.559586900394075e-06,
|
| 968 |
+
"loss": 1.3922,
|
| 969 |
+
"step": 10600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.73,
|
| 973 |
+
"grad_norm": 1.7562373876571655,
|
| 974 |
+
"learning_rate": 8.545998097567605e-06,
|
| 975 |
+
"loss": 1.4378,
|
| 976 |
+
"step": 10700
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.73,
|
| 980 |
+
"grad_norm": 1.6127831935882568,
|
| 981 |
+
"learning_rate": 8.532409294741134e-06,
|
| 982 |
+
"loss": 1.4483,
|
| 983 |
+
"step": 10800
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.74,
|
| 987 |
+
"grad_norm": 1.6120541095733643,
|
| 988 |
+
"learning_rate": 8.518820491914664e-06,
|
| 989 |
+
"loss": 1.3961,
|
| 990 |
+
"step": 10900
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.75,
|
| 994 |
+
"grad_norm": 1.5521306991577148,
|
| 995 |
+
"learning_rate": 8.505231689088192e-06,
|
| 996 |
+
"loss": 1.4101,
|
| 997 |
+
"step": 11000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.75,
|
| 1001 |
+
"eval_loss": 1.4052175283432007,
|
| 1002 |
+
"eval_runtime": 70.9316,
|
| 1003 |
+
"eval_samples_per_second": 35.851,
|
| 1004 |
+
"eval_steps_per_second": 4.483,
|
| 1005 |
+
"step": 11000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.75,
|
| 1009 |
+
"grad_norm": 2.4100379943847656,
|
| 1010 |
+
"learning_rate": 8.491642886261721e-06,
|
| 1011 |
+
"loss": 1.4224,
|
| 1012 |
+
"step": 11100
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.76,
|
| 1016 |
+
"grad_norm": 1.7542225122451782,
|
| 1017 |
+
"learning_rate": 8.47805408343525e-06,
|
| 1018 |
+
"loss": 1.4238,
|
| 1019 |
+
"step": 11200
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.77,
|
| 1023 |
+
"grad_norm": 2.3809213638305664,
|
| 1024 |
+
"learning_rate": 8.464465280608779e-06,
|
| 1025 |
+
"loss": 1.3968,
|
| 1026 |
+
"step": 11300
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.77,
|
| 1030 |
+
"grad_norm": 1.490343451499939,
|
| 1031 |
+
"learning_rate": 8.450876477782309e-06,
|
| 1032 |
+
"loss": 1.4512,
|
| 1033 |
+
"step": 11400
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.78,
|
| 1037 |
+
"grad_norm": 1.663609504699707,
|
| 1038 |
+
"learning_rate": 8.437287674955838e-06,
|
| 1039 |
+
"loss": 1.4772,
|
| 1040 |
+
"step": 11500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.78,
|
| 1044 |
+
"eval_loss": 1.3936774730682373,
|
| 1045 |
+
"eval_runtime": 70.914,
|
| 1046 |
+
"eval_samples_per_second": 35.86,
|
| 1047 |
+
"eval_steps_per_second": 4.484,
|
| 1048 |
+
"step": 11500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.79,
|
| 1052 |
+
"grad_norm": 1.5684208869934082,
|
| 1053 |
+
"learning_rate": 8.423698872129366e-06,
|
| 1054 |
+
"loss": 1.4276,
|
| 1055 |
+
"step": 11600
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.79,
|
| 1059 |
+
"grad_norm": 1.6131608486175537,
|
| 1060 |
+
"learning_rate": 8.410110069302894e-06,
|
| 1061 |
+
"loss": 1.4067,
|
| 1062 |
+
"step": 11700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.8,
|
| 1066 |
+
"grad_norm": 2.017564058303833,
|
| 1067 |
+
"learning_rate": 8.396521266476424e-06,
|
| 1068 |
+
"loss": 1.4028,
|
| 1069 |
+
"step": 11800
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.81,
|
| 1073 |
+
"grad_norm": 2.383514165878296,
|
| 1074 |
+
"learning_rate": 8.382932463649953e-06,
|
| 1075 |
+
"loss": 1.4028,
|
| 1076 |
+
"step": 11900
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.82,
|
| 1080 |
+
"grad_norm": 2.202026605606079,
|
| 1081 |
+
"learning_rate": 8.369343660823483e-06,
|
| 1082 |
+
"loss": 1.3671,
|
| 1083 |
+
"step": 12000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.82,
|
| 1087 |
+
"eval_loss": 1.3839792013168335,
|
| 1088 |
+
"eval_runtime": 70.7236,
|
| 1089 |
+
"eval_samples_per_second": 35.957,
|
| 1090 |
+
"eval_steps_per_second": 4.496,
|
| 1091 |
+
"step": 12000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.82,
|
| 1095 |
+
"grad_norm": 1.499125361442566,
|
| 1096 |
+
"learning_rate": 8.355754857997011e-06,
|
| 1097 |
+
"loss": 1.4193,
|
| 1098 |
+
"step": 12100
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.83,
|
| 1102 |
+
"grad_norm": 1.3109521865844727,
|
| 1103 |
+
"learning_rate": 8.34216605517054e-06,
|
| 1104 |
+
"loss": 1.3969,
|
| 1105 |
+
"step": 12200
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.84,
|
| 1109 |
+
"grad_norm": 2.689412832260132,
|
| 1110 |
+
"learning_rate": 8.328577252344068e-06,
|
| 1111 |
+
"loss": 1.4141,
|
| 1112 |
+
"step": 12300
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.84,
|
| 1116 |
+
"grad_norm": 1.6615593433380127,
|
| 1117 |
+
"learning_rate": 8.314988449517598e-06,
|
| 1118 |
+
"loss": 1.3512,
|
| 1119 |
+
"step": 12400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.85,
|
| 1123 |
+
"grad_norm": 1.994040846824646,
|
| 1124 |
+
"learning_rate": 8.301399646691128e-06,
|
| 1125 |
+
"loss": 1.4268,
|
| 1126 |
+
"step": 12500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.85,
|
| 1130 |
+
"eval_loss": 1.3757482767105103,
|
| 1131 |
+
"eval_runtime": 70.9944,
|
| 1132 |
+
"eval_samples_per_second": 35.82,
|
| 1133 |
+
"eval_steps_per_second": 4.479,
|
| 1134 |
+
"step": 12500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.86,
|
| 1138 |
+
"grad_norm": 2.2422096729278564,
|
| 1139 |
+
"learning_rate": 8.287810843864657e-06,
|
| 1140 |
+
"loss": 1.3549,
|
| 1141 |
+
"step": 12600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.86,
|
| 1145 |
+
"grad_norm": 1.4407843351364136,
|
| 1146 |
+
"learning_rate": 8.274222041038185e-06,
|
| 1147 |
+
"loss": 1.3934,
|
| 1148 |
+
"step": 12700
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.87,
|
| 1152 |
+
"grad_norm": 3.7289652824401855,
|
| 1153 |
+
"learning_rate": 8.260633238211713e-06,
|
| 1154 |
+
"loss": 1.3916,
|
| 1155 |
+
"step": 12800
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.88,
|
| 1159 |
+
"grad_norm": 1.819023847579956,
|
| 1160 |
+
"learning_rate": 8.247044435385243e-06,
|
| 1161 |
+
"loss": 1.3878,
|
| 1162 |
+
"step": 12900
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.88,
|
| 1166 |
+
"grad_norm": 1.6075499057769775,
|
| 1167 |
+
"learning_rate": 8.233455632558772e-06,
|
| 1168 |
+
"loss": 1.3469,
|
| 1169 |
+
"step": 13000
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.88,
|
| 1173 |
+
"eval_loss": 1.365922212600708,
|
| 1174 |
+
"eval_runtime": 71.0057,
|
| 1175 |
+
"eval_samples_per_second": 35.814,
|
| 1176 |
+
"eval_steps_per_second": 4.479,
|
| 1177 |
+
"step": 13000
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.89,
|
| 1181 |
+
"grad_norm": 1.9204126596450806,
|
| 1182 |
+
"learning_rate": 8.219866829732302e-06,
|
| 1183 |
+
"loss": 1.3456,
|
| 1184 |
+
"step": 13100
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.9,
|
| 1188 |
+
"grad_norm": 2.0110292434692383,
|
| 1189 |
+
"learning_rate": 8.20627802690583e-06,
|
| 1190 |
+
"loss": 1.3921,
|
| 1191 |
+
"step": 13200
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.9,
|
| 1195 |
+
"grad_norm": 1.4502629041671753,
|
| 1196 |
+
"learning_rate": 8.192689224079358e-06,
|
| 1197 |
+
"loss": 1.383,
|
| 1198 |
+
"step": 13300
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.91,
|
| 1202 |
+
"grad_norm": 2.5011653900146484,
|
| 1203 |
+
"learning_rate": 8.179100421252888e-06,
|
| 1204 |
+
"loss": 1.3413,
|
| 1205 |
+
"step": 13400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.92,
|
| 1209 |
+
"grad_norm": 1.4338220357894897,
|
| 1210 |
+
"learning_rate": 8.165511618426417e-06,
|
| 1211 |
+
"loss": 1.3531,
|
| 1212 |
+
"step": 13500
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 0.92,
|
| 1216 |
+
"eval_loss": 1.3567384481430054,
|
| 1217 |
+
"eval_runtime": 70.8084,
|
| 1218 |
+
"eval_samples_per_second": 35.914,
|
| 1219 |
+
"eval_steps_per_second": 4.491,
|
| 1220 |
+
"step": 13500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.92,
|
| 1224 |
+
"grad_norm": 1.8867733478546143,
|
| 1225 |
+
"learning_rate": 8.151922815599947e-06,
|
| 1226 |
+
"loss": 1.4115,
|
| 1227 |
+
"step": 13600
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"grad_norm": 1.897558331489563,
|
| 1232 |
+
"learning_rate": 8.138334012773476e-06,
|
| 1233 |
+
"loss": 1.3473,
|
| 1234 |
+
"step": 13700
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.94,
|
| 1238 |
+
"grad_norm": 2.6677191257476807,
|
| 1239 |
+
"learning_rate": 8.124745209947004e-06,
|
| 1240 |
+
"loss": 1.3982,
|
| 1241 |
+
"step": 13800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"grad_norm": 1.6690632104873657,
|
| 1246 |
+
"learning_rate": 8.111156407120532e-06,
|
| 1247 |
+
"loss": 1.3371,
|
| 1248 |
+
"step": 13900
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.95,
|
| 1252 |
+
"grad_norm": 1.668286919593811,
|
| 1253 |
+
"learning_rate": 8.097567604294062e-06,
|
| 1254 |
+
"loss": 1.3463,
|
| 1255 |
+
"step": 14000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"eval_loss": 1.3470206260681152,
|
| 1260 |
+
"eval_runtime": 70.8694,
|
| 1261 |
+
"eval_samples_per_second": 35.883,
|
| 1262 |
+
"eval_steps_per_second": 4.487,
|
| 1263 |
+
"step": 14000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.96,
|
| 1267 |
+
"grad_norm": 1.3303313255310059,
|
| 1268 |
+
"learning_rate": 8.083978801467592e-06,
|
| 1269 |
+
"loss": 1.3283,
|
| 1270 |
+
"step": 14100
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.96,
|
| 1274 |
+
"grad_norm": 1.8314011096954346,
|
| 1275 |
+
"learning_rate": 8.070389998641121e-06,
|
| 1276 |
+
"loss": 1.3382,
|
| 1277 |
+
"step": 14200
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.97,
|
| 1281 |
+
"grad_norm": 1.6911287307739258,
|
| 1282 |
+
"learning_rate": 8.056801195814649e-06,
|
| 1283 |
+
"loss": 1.3249,
|
| 1284 |
+
"step": 14300
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.98,
|
| 1288 |
+
"grad_norm": 2.0255990028381348,
|
| 1289 |
+
"learning_rate": 8.043212392988179e-06,
|
| 1290 |
+
"loss": 1.4345,
|
| 1291 |
+
"step": 14400
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.99,
|
| 1295 |
+
"grad_norm": 1.6872771978378296,
|
| 1296 |
+
"learning_rate": 8.029623590161707e-06,
|
| 1297 |
+
"loss": 1.3662,
|
| 1298 |
+
"step": 14500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.99,
|
| 1302 |
+
"eval_loss": 1.3394687175750732,
|
| 1303 |
+
"eval_runtime": 70.8165,
|
| 1304 |
+
"eval_samples_per_second": 35.91,
|
| 1305 |
+
"eval_steps_per_second": 4.49,
|
| 1306 |
+
"step": 14500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.99,
|
| 1310 |
+
"grad_norm": 1.2456538677215576,
|
| 1311 |
+
"learning_rate": 8.016034787335236e-06,
|
| 1312 |
+
"loss": 1.3152,
|
| 1313 |
+
"step": 14600
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.0,
|
| 1317 |
+
"grad_norm": 1.9343585968017578,
|
| 1318 |
+
"learning_rate": 8.002445984508766e-06,
|
| 1319 |
+
"loss": 1.3179,
|
| 1320 |
+
"step": 14700
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.01,
|
| 1324 |
+
"grad_norm": 1.6026442050933838,
|
| 1325 |
+
"learning_rate": 7.988857181682294e-06,
|
| 1326 |
+
"loss": 1.3445,
|
| 1327 |
+
"step": 14800
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.01,
|
| 1331 |
+
"grad_norm": 1.8159044981002808,
|
| 1332 |
+
"learning_rate": 7.975268378855823e-06,
|
| 1333 |
+
"loss": 1.3259,
|
| 1334 |
+
"step": 14900
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.02,
|
| 1338 |
+
"grad_norm": 1.6430504322052002,
|
| 1339 |
+
"learning_rate": 7.961679576029351e-06,
|
| 1340 |
+
"loss": 1.337,
|
| 1341 |
+
"step": 15000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.02,
|
| 1345 |
+
"eval_loss": 1.3323568105697632,
|
| 1346 |
+
"eval_runtime": 70.9018,
|
| 1347 |
+
"eval_samples_per_second": 35.867,
|
| 1348 |
+
"eval_steps_per_second": 4.485,
|
| 1349 |
+
"step": 15000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.03,
|
| 1353 |
+
"grad_norm": 2.036970853805542,
|
| 1354 |
+
"learning_rate": 7.948090773202881e-06,
|
| 1355 |
+
"loss": 1.3217,
|
| 1356 |
+
"step": 15100
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.03,
|
| 1360 |
+
"grad_norm": 1.6756584644317627,
|
| 1361 |
+
"learning_rate": 7.93450197037641e-06,
|
| 1362 |
+
"loss": 1.3008,
|
| 1363 |
+
"step": 15200
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.04,
|
| 1367 |
+
"grad_norm": 1.5923326015472412,
|
| 1368 |
+
"learning_rate": 7.92091316754994e-06,
|
| 1369 |
+
"loss": 1.3347,
|
| 1370 |
+
"step": 15300
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.05,
|
| 1374 |
+
"grad_norm": 1.809383749961853,
|
| 1375 |
+
"learning_rate": 7.907460252751734e-06,
|
| 1376 |
+
"loss": 1.3192,
|
| 1377 |
+
"step": 15400
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.05,
|
| 1381 |
+
"grad_norm": 2.035680055618286,
|
| 1382 |
+
"learning_rate": 7.893871449925262e-06,
|
| 1383 |
+
"loss": 1.3627,
|
| 1384 |
+
"step": 15500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.05,
|
| 1388 |
+
"eval_loss": 1.3219527006149292,
|
| 1389 |
+
"eval_runtime": 70.9632,
|
| 1390 |
+
"eval_samples_per_second": 35.835,
|
| 1391 |
+
"eval_steps_per_second": 4.481,
|
| 1392 |
+
"step": 15500
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.06,
|
| 1396 |
+
"grad_norm": 1.7485100030899048,
|
| 1397 |
+
"learning_rate": 7.880282647098791e-06,
|
| 1398 |
+
"loss": 1.3015,
|
| 1399 |
+
"step": 15600
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.07,
|
| 1403 |
+
"grad_norm": 2.0771241188049316,
|
| 1404 |
+
"learning_rate": 7.86669384427232e-06,
|
| 1405 |
+
"loss": 1.3261,
|
| 1406 |
+
"step": 15700
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.07,
|
| 1410 |
+
"grad_norm": 1.8625783920288086,
|
| 1411 |
+
"learning_rate": 7.853105041445849e-06,
|
| 1412 |
+
"loss": 1.3308,
|
| 1413 |
+
"step": 15800
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.08,
|
| 1417 |
+
"grad_norm": 1.8347725868225098,
|
| 1418 |
+
"learning_rate": 7.839516238619378e-06,
|
| 1419 |
+
"loss": 1.3637,
|
| 1420 |
+
"step": 15900
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.09,
|
| 1424 |
+
"grad_norm": 1.9449338912963867,
|
| 1425 |
+
"learning_rate": 7.825927435792908e-06,
|
| 1426 |
+
"loss": 1.2906,
|
| 1427 |
+
"step": 16000
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.09,
|
| 1431 |
+
"eval_loss": 1.3169829845428467,
|
| 1432 |
+
"eval_runtime": 70.9704,
|
| 1433 |
+
"eval_samples_per_second": 35.832,
|
| 1434 |
+
"eval_steps_per_second": 4.481,
|
| 1435 |
+
"step": 16000
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.09,
|
| 1439 |
+
"grad_norm": 1.6746830940246582,
|
| 1440 |
+
"learning_rate": 7.812338632966436e-06,
|
| 1441 |
+
"loss": 1.3326,
|
| 1442 |
+
"step": 16100
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.1,
|
| 1446 |
+
"grad_norm": 1.5581905841827393,
|
| 1447 |
+
"learning_rate": 7.798749830139966e-06,
|
| 1448 |
+
"loss": 1.2964,
|
| 1449 |
+
"step": 16200
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.11,
|
| 1453 |
+
"grad_norm": 2.1636734008789062,
|
| 1454 |
+
"learning_rate": 7.785161027313495e-06,
|
| 1455 |
+
"loss": 1.2867,
|
| 1456 |
+
"step": 16300
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.11,
|
| 1460 |
+
"grad_norm": 1.760335922241211,
|
| 1461 |
+
"learning_rate": 7.771572224487023e-06,
|
| 1462 |
+
"loss": 1.3017,
|
| 1463 |
+
"step": 16400
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.12,
|
| 1467 |
+
"grad_norm": 1.9209500551223755,
|
| 1468 |
+
"learning_rate": 7.757983421660553e-06,
|
| 1469 |
+
"loss": 1.331,
|
| 1470 |
+
"step": 16500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.12,
|
| 1474 |
+
"eval_loss": 1.3085339069366455,
|
| 1475 |
+
"eval_runtime": 70.9762,
|
| 1476 |
+
"eval_samples_per_second": 35.829,
|
| 1477 |
+
"eval_steps_per_second": 4.48,
|
| 1478 |
+
"step": 16500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.13,
|
| 1482 |
+
"grad_norm": 1.8936728239059448,
|
| 1483 |
+
"learning_rate": 7.74439461883408e-06,
|
| 1484 |
+
"loss": 1.3494,
|
| 1485 |
+
"step": 16600
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.13,
|
| 1489 |
+
"grad_norm": 1.6603670120239258,
|
| 1490 |
+
"learning_rate": 7.73080581600761e-06,
|
| 1491 |
+
"loss": 1.3443,
|
| 1492 |
+
"step": 16700
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.14,
|
| 1496 |
+
"grad_norm": 1.9962695837020874,
|
| 1497 |
+
"learning_rate": 7.71721701318114e-06,
|
| 1498 |
+
"loss": 1.3016,
|
| 1499 |
+
"step": 16800
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.15,
|
| 1503 |
+
"grad_norm": 1.7902451753616333,
|
| 1504 |
+
"learning_rate": 7.70362821035467e-06,
|
| 1505 |
+
"loss": 1.3107,
|
| 1506 |
+
"step": 16900
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.16,
|
| 1510 |
+
"grad_norm": 1.7962889671325684,
|
| 1511 |
+
"learning_rate": 7.690039407528197e-06,
|
| 1512 |
+
"loss": 1.3082,
|
| 1513 |
+
"step": 17000
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.16,
|
| 1517 |
+
"eval_loss": 1.3007583618164062,
|
| 1518 |
+
"eval_runtime": 70.8534,
|
| 1519 |
+
"eval_samples_per_second": 35.891,
|
| 1520 |
+
"eval_steps_per_second": 4.488,
|
| 1521 |
+
"step": 17000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.16,
|
| 1525 |
+
"grad_norm": 1.8448220491409302,
|
| 1526 |
+
"learning_rate": 7.676450604701725e-06,
|
| 1527 |
+
"loss": 1.3148,
|
| 1528 |
+
"step": 17100
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.17,
|
| 1532 |
+
"grad_norm": 2.124708652496338,
|
| 1533 |
+
"learning_rate": 7.662861801875255e-06,
|
| 1534 |
+
"loss": 1.3348,
|
| 1535 |
+
"step": 17200
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.18,
|
| 1539 |
+
"grad_norm": 1.5953021049499512,
|
| 1540 |
+
"learning_rate": 7.649272999048785e-06,
|
| 1541 |
+
"loss": 1.2575,
|
| 1542 |
+
"step": 17300
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.18,
|
| 1546 |
+
"grad_norm": 1.7431753873825073,
|
| 1547 |
+
"learning_rate": 7.635684196222314e-06,
|
| 1548 |
+
"loss": 1.3239,
|
| 1549 |
+
"step": 17400
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.19,
|
| 1553 |
+
"grad_norm": 2.0628209114074707,
|
| 1554 |
+
"learning_rate": 7.622095393395842e-06,
|
| 1555 |
+
"loss": 1.2904,
|
| 1556 |
+
"step": 17500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.19,
|
| 1560 |
+
"eval_loss": 1.2971383333206177,
|
| 1561 |
+
"eval_runtime": 70.8465,
|
| 1562 |
+
"eval_samples_per_second": 35.894,
|
| 1563 |
+
"eval_steps_per_second": 4.489,
|
| 1564 |
+
"step": 17500
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.2,
|
| 1568 |
+
"grad_norm": 2.154141902923584,
|
| 1569 |
+
"learning_rate": 7.608506590569371e-06,
|
| 1570 |
+
"loss": 1.2824,
|
| 1571 |
+
"step": 17600
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.2,
|
| 1575 |
+
"grad_norm": 1.7325314283370972,
|
| 1576 |
+
"learning_rate": 7.595053675771166e-06,
|
| 1577 |
+
"loss": 1.2587,
|
| 1578 |
+
"step": 17700
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.21,
|
| 1582 |
+
"grad_norm": 1.7533044815063477,
|
| 1583 |
+
"learning_rate": 7.581464872944694e-06,
|
| 1584 |
+
"loss": 1.2697,
|
| 1585 |
+
"step": 17800
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.22,
|
| 1589 |
+
"grad_norm": 1.642408847808838,
|
| 1590 |
+
"learning_rate": 7.567876070118223e-06,
|
| 1591 |
+
"loss": 1.2587,
|
| 1592 |
+
"step": 17900
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.22,
|
| 1596 |
+
"grad_norm": 2.0030946731567383,
|
| 1597 |
+
"learning_rate": 7.554287267291752e-06,
|
| 1598 |
+
"loss": 1.2825,
|
| 1599 |
+
"step": 18000
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.22,
|
| 1603 |
+
"eval_loss": 1.2882283926010132,
|
| 1604 |
+
"eval_runtime": 70.9711,
|
| 1605 |
+
"eval_samples_per_second": 35.831,
|
| 1606 |
+
"eval_steps_per_second": 4.481,
|
| 1607 |
+
"step": 18000
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.23,
|
| 1611 |
+
"grad_norm": 1.828447699546814,
|
| 1612 |
+
"learning_rate": 7.540698464465281e-06,
|
| 1613 |
+
"loss": 1.2162,
|
| 1614 |
+
"step": 18100
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.24,
|
| 1618 |
+
"grad_norm": 1.9078677892684937,
|
| 1619 |
+
"learning_rate": 7.527109661638811e-06,
|
| 1620 |
+
"loss": 1.2618,
|
| 1621 |
+
"step": 18200
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.24,
|
| 1625 |
+
"grad_norm": 1.7438205480575562,
|
| 1626 |
+
"learning_rate": 7.513520858812339e-06,
|
| 1627 |
+
"loss": 1.2972,
|
| 1628 |
+
"step": 18300
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.25,
|
| 1632 |
+
"grad_norm": 1.5308886766433716,
|
| 1633 |
+
"learning_rate": 7.499932055985868e-06,
|
| 1634 |
+
"loss": 1.2635,
|
| 1635 |
+
"step": 18400
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.26,
|
| 1639 |
+
"grad_norm": 1.7570804357528687,
|
| 1640 |
+
"learning_rate": 7.486343253159397e-06,
|
| 1641 |
+
"loss": 1.3104,
|
| 1642 |
+
"step": 18500
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.26,
|
| 1646 |
+
"eval_loss": 1.2821784019470215,
|
| 1647 |
+
"eval_runtime": 70.9616,
|
| 1648 |
+
"eval_samples_per_second": 35.836,
|
| 1649 |
+
"eval_steps_per_second": 4.481,
|
| 1650 |
+
"step": 18500
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.26,
|
| 1654 |
+
"grad_norm": 1.820691466331482,
|
| 1655 |
+
"learning_rate": 7.472754450332927e-06,
|
| 1656 |
+
"loss": 1.2978,
|
| 1657 |
+
"step": 18600
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.27,
|
| 1661 |
+
"grad_norm": 2.0996739864349365,
|
| 1662 |
+
"learning_rate": 7.4591656475064555e-06,
|
| 1663 |
+
"loss": 1.2925,
|
| 1664 |
+
"step": 18700
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.28,
|
| 1668 |
+
"grad_norm": 1.6602342128753662,
|
| 1669 |
+
"learning_rate": 7.445576844679985e-06,
|
| 1670 |
+
"loss": 1.243,
|
| 1671 |
+
"step": 18800
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.28,
|
| 1675 |
+
"grad_norm": 2.034649133682251,
|
| 1676 |
+
"learning_rate": 7.431988041853513e-06,
|
| 1677 |
+
"loss": 1.2775,
|
| 1678 |
+
"step": 18900
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.29,
|
| 1682 |
+
"grad_norm": 1.898582100868225,
|
| 1683 |
+
"learning_rate": 7.418399239027042e-06,
|
| 1684 |
+
"loss": 1.2786,
|
| 1685 |
+
"step": 19000
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.29,
|
| 1689 |
+
"eval_loss": 1.2745426893234253,
|
| 1690 |
+
"eval_runtime": 70.9759,
|
| 1691 |
+
"eval_samples_per_second": 35.829,
|
| 1692 |
+
"eval_steps_per_second": 4.48,
|
| 1693 |
+
"step": 19000
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.3,
|
| 1697 |
+
"grad_norm": 1.4128785133361816,
|
| 1698 |
+
"learning_rate": 7.4048104362005715e-06,
|
| 1699 |
+
"loss": 1.2656,
|
| 1700 |
+
"step": 19100
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.3,
|
| 1704 |
+
"grad_norm": 2.2971534729003906,
|
| 1705 |
+
"learning_rate": 7.3912216333741e-06,
|
| 1706 |
+
"loss": 1.2426,
|
| 1707 |
+
"step": 19200
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.31,
|
| 1711 |
+
"grad_norm": 1.783996820449829,
|
| 1712 |
+
"learning_rate": 7.37763283054763e-06,
|
| 1713 |
+
"loss": 1.272,
|
| 1714 |
+
"step": 19300
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.32,
|
| 1718 |
+
"grad_norm": 1.8958848714828491,
|
| 1719 |
+
"learning_rate": 7.364044027721159e-06,
|
| 1720 |
+
"loss": 1.2168,
|
| 1721 |
+
"step": 19400
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.32,
|
| 1725 |
+
"grad_norm": 2.1363043785095215,
|
| 1726 |
+
"learning_rate": 7.350455224894687e-06,
|
| 1727 |
+
"loss": 1.2734,
|
| 1728 |
+
"step": 19500
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 1.32,
|
| 1732 |
+
"eval_loss": 1.2699941396713257,
|
| 1733 |
+
"eval_runtime": 71.0334,
|
| 1734 |
+
"eval_samples_per_second": 35.8,
|
| 1735 |
+
"eval_steps_per_second": 4.477,
|
| 1736 |
+
"step": 19500
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.33,
|
| 1740 |
+
"grad_norm": 2.642695903778076,
|
| 1741 |
+
"learning_rate": 7.336866422068216e-06,
|
| 1742 |
+
"loss": 1.3135,
|
| 1743 |
+
"step": 19600
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.34,
|
| 1747 |
+
"grad_norm": 1.8240422010421753,
|
| 1748 |
+
"learning_rate": 7.323277619241746e-06,
|
| 1749 |
+
"loss": 1.2924,
|
| 1750 |
+
"step": 19700
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.35,
|
| 1754 |
+
"grad_norm": 1.8623692989349365,
|
| 1755 |
+
"learning_rate": 7.309688816415275e-06,
|
| 1756 |
+
"loss": 1.2907,
|
| 1757 |
+
"step": 19800
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.35,
|
| 1761 |
+
"grad_norm": 2.2778708934783936,
|
| 1762 |
+
"learning_rate": 7.296100013588804e-06,
|
| 1763 |
+
"loss": 1.2727,
|
| 1764 |
+
"step": 19900
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.36,
|
| 1768 |
+
"grad_norm": 1.8957061767578125,
|
| 1769 |
+
"learning_rate": 7.282511210762332e-06,
|
| 1770 |
+
"loss": 1.2656,
|
| 1771 |
+
"step": 20000
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.36,
|
| 1775 |
+
"eval_loss": 1.2644336223602295,
|
| 1776 |
+
"eval_runtime": 70.9373,
|
| 1777 |
+
"eval_samples_per_second": 35.849,
|
| 1778 |
+
"eval_steps_per_second": 4.483,
|
| 1779 |
+
"step": 20000
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.37,
|
| 1783 |
+
"grad_norm": 1.7855497598648071,
|
| 1784 |
+
"learning_rate": 7.268922407935861e-06,
|
| 1785 |
+
"loss": 1.2158,
|
| 1786 |
+
"step": 20100
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.37,
|
| 1790 |
+
"grad_norm": 1.8924943208694458,
|
| 1791 |
+
"learning_rate": 7.2553336051093905e-06,
|
| 1792 |
+
"loss": 1.2753,
|
| 1793 |
+
"step": 20200
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.38,
|
| 1797 |
+
"grad_norm": 2.0177762508392334,
|
| 1798 |
+
"learning_rate": 7.241880690311184e-06,
|
| 1799 |
+
"loss": 1.2406,
|
| 1800 |
+
"step": 20300
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 1.39,
|
| 1804 |
+
"grad_norm": 2.4161458015441895,
|
| 1805 |
+
"learning_rate": 7.228291887484713e-06,
|
| 1806 |
+
"loss": 1.2453,
|
| 1807 |
+
"step": 20400
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.39,
|
| 1811 |
+
"grad_norm": 1.7210235595703125,
|
| 1812 |
+
"learning_rate": 7.214703084658242e-06,
|
| 1813 |
+
"loss": 1.2107,
|
| 1814 |
+
"step": 20500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.39,
|
| 1818 |
+
"eval_loss": 1.258453607559204,
|
| 1819 |
+
"eval_runtime": 71.0477,
|
| 1820 |
+
"eval_samples_per_second": 35.793,
|
| 1821 |
+
"eval_steps_per_second": 4.476,
|
| 1822 |
+
"step": 20500
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.4,
|
| 1826 |
+
"grad_norm": 1.5457173585891724,
|
| 1827 |
+
"learning_rate": 7.201114281831771e-06,
|
| 1828 |
+
"loss": 1.2377,
|
| 1829 |
+
"step": 20600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.41,
|
| 1833 |
+
"grad_norm": 2.403831720352173,
|
| 1834 |
+
"learning_rate": 7.187525479005301e-06,
|
| 1835 |
+
"loss": 1.238,
|
| 1836 |
+
"step": 20700
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.41,
|
| 1840 |
+
"grad_norm": 2.01042103767395,
|
| 1841 |
+
"learning_rate": 7.173936676178829e-06,
|
| 1842 |
+
"loss": 1.2528,
|
| 1843 |
+
"step": 20800
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.42,
|
| 1847 |
+
"grad_norm": 2.197006940841675,
|
| 1848 |
+
"learning_rate": 7.160347873352358e-06,
|
| 1849 |
+
"loss": 1.2395,
|
| 1850 |
+
"step": 20900
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.43,
|
| 1854 |
+
"grad_norm": 2.503634214401245,
|
| 1855 |
+
"learning_rate": 7.146759070525887e-06,
|
| 1856 |
+
"loss": 1.2822,
|
| 1857 |
+
"step": 21000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.43,
|
| 1861 |
+
"eval_loss": 1.2508896589279175,
|
| 1862 |
+
"eval_runtime": 71.0512,
|
| 1863 |
+
"eval_samples_per_second": 35.791,
|
| 1864 |
+
"eval_steps_per_second": 4.476,
|
| 1865 |
+
"step": 21000
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.43,
|
| 1869 |
+
"grad_norm": 1.4275486469268799,
|
| 1870 |
+
"learning_rate": 7.133170267699417e-06,
|
| 1871 |
+
"loss": 1.2337,
|
| 1872 |
+
"step": 21100
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.44,
|
| 1876 |
+
"grad_norm": 2.1461949348449707,
|
| 1877 |
+
"learning_rate": 7.11971735290121e-06,
|
| 1878 |
+
"loss": 1.2576,
|
| 1879 |
+
"step": 21200
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.45,
|
| 1883 |
+
"grad_norm": 1.705665111541748,
|
| 1884 |
+
"learning_rate": 7.106128550074739e-06,
|
| 1885 |
+
"loss": 1.2311,
|
| 1886 |
+
"step": 21300
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.45,
|
| 1890 |
+
"grad_norm": 2.058223247528076,
|
| 1891 |
+
"learning_rate": 7.0925397472482685e-06,
|
| 1892 |
+
"loss": 1.2619,
|
| 1893 |
+
"step": 21400
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.46,
|
| 1897 |
+
"grad_norm": 1.4659618139266968,
|
| 1898 |
+
"learning_rate": 7.078950944421797e-06,
|
| 1899 |
+
"loss": 1.2188,
|
| 1900 |
+
"step": 21500
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.46,
|
| 1904 |
+
"eval_loss": 1.2478315830230713,
|
| 1905 |
+
"eval_runtime": 70.8088,
|
| 1906 |
+
"eval_samples_per_second": 35.914,
|
| 1907 |
+
"eval_steps_per_second": 4.491,
|
| 1908 |
+
"step": 21500
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.47,
|
| 1912 |
+
"grad_norm": 1.7102398872375488,
|
| 1913 |
+
"learning_rate": 7.065362141595325e-06,
|
| 1914 |
+
"loss": 1.2553,
|
| 1915 |
+
"step": 21600
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.47,
|
| 1919 |
+
"grad_norm": 2.445326089859009,
|
| 1920 |
+
"learning_rate": 7.051773338768855e-06,
|
| 1921 |
+
"loss": 1.2687,
|
| 1922 |
+
"step": 21700
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.48,
|
| 1926 |
+
"grad_norm": 2.055088758468628,
|
| 1927 |
+
"learning_rate": 7.038184535942384e-06,
|
| 1928 |
+
"loss": 1.254,
|
| 1929 |
+
"step": 21800
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.49,
|
| 1933 |
+
"grad_norm": 2.5781538486480713,
|
| 1934 |
+
"learning_rate": 7.024595733115913e-06,
|
| 1935 |
+
"loss": 1.2319,
|
| 1936 |
+
"step": 21900
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.49,
|
| 1940 |
+
"grad_norm": 1.9507685899734497,
|
| 1941 |
+
"learning_rate": 7.011006930289442e-06,
|
| 1942 |
+
"loss": 1.2185,
|
| 1943 |
+
"step": 22000
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 1.49,
|
| 1947 |
+
"eval_loss": 1.245086908340454,
|
| 1948 |
+
"eval_runtime": 71.042,
|
| 1949 |
+
"eval_samples_per_second": 35.796,
|
| 1950 |
+
"eval_steps_per_second": 4.476,
|
| 1951 |
+
"step": 22000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 1.5,
|
| 1955 |
+
"grad_norm": 2.347245216369629,
|
| 1956 |
+
"learning_rate": 6.997418127462972e-06,
|
| 1957 |
+
"loss": 1.2024,
|
| 1958 |
+
"step": 22100
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.51,
|
| 1962 |
+
"grad_norm": 1.6178568601608276,
|
| 1963 |
+
"learning_rate": 6.9838293246364995e-06,
|
| 1964 |
+
"loss": 1.2379,
|
| 1965 |
+
"step": 22200
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.52,
|
| 1969 |
+
"grad_norm": 1.7551498413085938,
|
| 1970 |
+
"learning_rate": 6.970240521810029e-06,
|
| 1971 |
+
"loss": 1.2344,
|
| 1972 |
+
"step": 22300
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 1.52,
|
| 1976 |
+
"grad_norm": 1.9250737428665161,
|
| 1977 |
+
"learning_rate": 6.956651718983558e-06,
|
| 1978 |
+
"loss": 1.2942,
|
| 1979 |
+
"step": 22400
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.53,
|
| 1983 |
+
"grad_norm": 1.640271782875061,
|
| 1984 |
+
"learning_rate": 6.9430629161570876e-06,
|
| 1985 |
+
"loss": 1.2441,
|
| 1986 |
+
"step": 22500
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.53,
|
| 1990 |
+
"eval_loss": 1.2352341413497925,
|
| 1991 |
+
"eval_runtime": 70.9437,
|
| 1992 |
+
"eval_samples_per_second": 35.845,
|
| 1993 |
+
"eval_steps_per_second": 4.482,
|
| 1994 |
+
"step": 22500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.54,
|
| 1998 |
+
"grad_norm": 2.083061456680298,
|
| 1999 |
+
"learning_rate": 6.929474113330616e-06,
|
| 2000 |
+
"loss": 1.1819,
|
| 2001 |
+
"step": 22600
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.54,
|
| 2005 |
+
"grad_norm": 1.8274168968200684,
|
| 2006 |
+
"learning_rate": 6.915885310504146e-06,
|
| 2007 |
+
"loss": 1.2243,
|
| 2008 |
+
"step": 22700
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 1.55,
|
| 2012 |
+
"grad_norm": 1.7711529731750488,
|
| 2013 |
+
"learning_rate": 6.902296507677674e-06,
|
| 2014 |
+
"loss": 1.2318,
|
| 2015 |
+
"step": 22800
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 1.56,
|
| 2019 |
+
"grad_norm": 2.0537028312683105,
|
| 2020 |
+
"learning_rate": 6.888707704851203e-06,
|
| 2021 |
+
"loss": 1.1958,
|
| 2022 |
+
"step": 22900
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 1.56,
|
| 2026 |
+
"grad_norm": 1.8466728925704956,
|
| 2027 |
+
"learning_rate": 6.875118902024732e-06,
|
| 2028 |
+
"loss": 1.2564,
|
| 2029 |
+
"step": 23000
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 1.56,
|
| 2033 |
+
"eval_loss": 1.2326687574386597,
|
| 2034 |
+
"eval_runtime": 70.9545,
|
| 2035 |
+
"eval_samples_per_second": 35.84,
|
| 2036 |
+
"eval_steps_per_second": 4.482,
|
| 2037 |
+
"step": 23000
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.57,
|
| 2041 |
+
"grad_norm": 1.6301406621932983,
|
| 2042 |
+
"learning_rate": 6.861530099198261e-06,
|
| 2043 |
+
"loss": 1.1904,
|
| 2044 |
+
"step": 23100
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.58,
|
| 2048 |
+
"grad_norm": 2.1303887367248535,
|
| 2049 |
+
"learning_rate": 6.847941296371791e-06,
|
| 2050 |
+
"loss": 1.2,
|
| 2051 |
+
"step": 23200
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.58,
|
| 2055 |
+
"grad_norm": 2.042210340499878,
|
| 2056 |
+
"learning_rate": 6.834352493545319e-06,
|
| 2057 |
+
"loss": 1.2432,
|
| 2058 |
+
"step": 23300
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.59,
|
| 2062 |
+
"grad_norm": 1.8403574228286743,
|
| 2063 |
+
"learning_rate": 6.820763690718848e-06,
|
| 2064 |
+
"loss": 1.2195,
|
| 2065 |
+
"step": 23400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.6,
|
| 2069 |
+
"grad_norm": 1.8628817796707153,
|
| 2070 |
+
"learning_rate": 6.807174887892377e-06,
|
| 2071 |
+
"loss": 1.2032,
|
| 2072 |
+
"step": 23500
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 1.6,
|
| 2076 |
+
"eval_loss": 1.2271267175674438,
|
| 2077 |
+
"eval_runtime": 70.9472,
|
| 2078 |
+
"eval_samples_per_second": 35.844,
|
| 2079 |
+
"eval_steps_per_second": 4.482,
|
| 2080 |
+
"step": 23500
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.6,
|
| 2084 |
+
"grad_norm": 2.2309892177581787,
|
| 2085 |
+
"learning_rate": 6.793586085065907e-06,
|
| 2086 |
+
"loss": 1.1931,
|
| 2087 |
+
"step": 23600
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.61,
|
| 2091 |
+
"grad_norm": 1.4337612390518188,
|
| 2092 |
+
"learning_rate": 6.7799972822394354e-06,
|
| 2093 |
+
"loss": 1.2401,
|
| 2094 |
+
"step": 23700
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.62,
|
| 2098 |
+
"grad_norm": 1.7968145608901978,
|
| 2099 |
+
"learning_rate": 6.766408479412965e-06,
|
| 2100 |
+
"loss": 1.233,
|
| 2101 |
+
"step": 23800
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.62,
|
| 2105 |
+
"grad_norm": 1.7918980121612549,
|
| 2106 |
+
"learning_rate": 6.7529555646147584e-06,
|
| 2107 |
+
"loss": 1.1874,
|
| 2108 |
+
"step": 23900
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.63,
|
| 2112 |
+
"grad_norm": 1.9370090961456299,
|
| 2113 |
+
"learning_rate": 6.739366761788287e-06,
|
| 2114 |
+
"loss": 1.2031,
|
| 2115 |
+
"step": 24000
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.63,
|
| 2119 |
+
"eval_loss": 1.2228479385375977,
|
| 2120 |
+
"eval_runtime": 70.9391,
|
| 2121 |
+
"eval_samples_per_second": 35.848,
|
| 2122 |
+
"eval_steps_per_second": 4.483,
|
| 2123 |
+
"step": 24000
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.64,
|
| 2127 |
+
"grad_norm": 2.238128900527954,
|
| 2128 |
+
"learning_rate": 6.725777958961815e-06,
|
| 2129 |
+
"loss": 1.2207,
|
| 2130 |
+
"step": 24100
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.64,
|
| 2134 |
+
"grad_norm": 1.9183790683746338,
|
| 2135 |
+
"learning_rate": 6.712189156135345e-06,
|
| 2136 |
+
"loss": 1.2263,
|
| 2137 |
+
"step": 24200
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.65,
|
| 2141 |
+
"grad_norm": 2.407428026199341,
|
| 2142 |
+
"learning_rate": 6.6986003533088736e-06,
|
| 2143 |
+
"loss": 1.2424,
|
| 2144 |
+
"step": 24300
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.66,
|
| 2148 |
+
"grad_norm": 1.837365746498108,
|
| 2149 |
+
"learning_rate": 6.685011550482403e-06,
|
| 2150 |
+
"loss": 1.1832,
|
| 2151 |
+
"step": 24400
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.66,
|
| 2155 |
+
"grad_norm": 1.9926724433898926,
|
| 2156 |
+
"learning_rate": 6.671422747655932e-06,
|
| 2157 |
+
"loss": 1.2088,
|
| 2158 |
+
"step": 24500
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.66,
|
| 2162 |
+
"eval_loss": 1.2178888320922852,
|
| 2163 |
+
"eval_runtime": 71.0012,
|
| 2164 |
+
"eval_samples_per_second": 35.816,
|
| 2165 |
+
"eval_steps_per_second": 4.479,
|
| 2166 |
+
"step": 24500
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.67,
|
| 2170 |
+
"grad_norm": 1.6491261720657349,
|
| 2171 |
+
"learning_rate": 6.657833944829462e-06,
|
| 2172 |
+
"loss": 1.2103,
|
| 2173 |
+
"step": 24600
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.68,
|
| 2177 |
+
"grad_norm": 1.825826644897461,
|
| 2178 |
+
"learning_rate": 6.6442451420029895e-06,
|
| 2179 |
+
"loss": 1.1911,
|
| 2180 |
+
"step": 24700
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.69,
|
| 2184 |
+
"grad_norm": 1.788091778755188,
|
| 2185 |
+
"learning_rate": 6.630656339176519e-06,
|
| 2186 |
+
"loss": 1.2246,
|
| 2187 |
+
"step": 24800
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.69,
|
| 2191 |
+
"grad_norm": 1.8941233158111572,
|
| 2192 |
+
"learning_rate": 6.617067536350048e-06,
|
| 2193 |
+
"loss": 1.197,
|
| 2194 |
+
"step": 24900
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.7,
|
| 2198 |
+
"grad_norm": 2.360272169113159,
|
| 2199 |
+
"learning_rate": 6.6034787335235775e-06,
|
| 2200 |
+
"loss": 1.1925,
|
| 2201 |
+
"step": 25000
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.7,
|
| 2205 |
+
"eval_loss": 1.2120610475540161,
|
| 2206 |
+
"eval_runtime": 70.9625,
|
| 2207 |
+
"eval_samples_per_second": 35.836,
|
| 2208 |
+
"eval_steps_per_second": 4.481,
|
| 2209 |
+
"step": 25000
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.71,
|
| 2213 |
+
"grad_norm": 2.0026679039001465,
|
| 2214 |
+
"learning_rate": 6.589889930697106e-06,
|
| 2215 |
+
"loss": 1.2063,
|
| 2216 |
+
"step": 25100
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 1.71,
|
| 2220 |
+
"grad_norm": 1.9979290962219238,
|
| 2221 |
+
"learning_rate": 6.576301127870636e-06,
|
| 2222 |
+
"loss": 1.1784,
|
| 2223 |
+
"step": 25200
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.72,
|
| 2227 |
+
"grad_norm": 1.682900071144104,
|
| 2228 |
+
"learning_rate": 6.562712325044164e-06,
|
| 2229 |
+
"loss": 1.1587,
|
| 2230 |
+
"step": 25300
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.73,
|
| 2234 |
+
"grad_norm": 2.0586678981781006,
|
| 2235 |
+
"learning_rate": 6.549123522217693e-06,
|
| 2236 |
+
"loss": 1.2031,
|
| 2237 |
+
"step": 25400
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.73,
|
| 2241 |
+
"grad_norm": 2.5424463748931885,
|
| 2242 |
+
"learning_rate": 6.535534719391222e-06,
|
| 2243 |
+
"loss": 1.2061,
|
| 2244 |
+
"step": 25500
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.73,
|
| 2248 |
+
"eval_loss": 1.209425449371338,
|
| 2249 |
+
"eval_runtime": 70.8814,
|
| 2250 |
+
"eval_samples_per_second": 35.877,
|
| 2251 |
+
"eval_steps_per_second": 4.486,
|
| 2252 |
+
"step": 25500
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 1.74,
|
| 2256 |
+
"grad_norm": 2.0070347785949707,
|
| 2257 |
+
"learning_rate": 6.521945916564751e-06,
|
| 2258 |
+
"loss": 1.2175,
|
| 2259 |
+
"step": 25600
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.75,
|
| 2263 |
+
"grad_norm": 1.7913732528686523,
|
| 2264 |
+
"learning_rate": 6.508357113738281e-06,
|
| 2265 |
+
"loss": 1.2005,
|
| 2266 |
+
"step": 25700
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.75,
|
| 2270 |
+
"grad_norm": 1.552306890487671,
|
| 2271 |
+
"learning_rate": 6.494768310911809e-06,
|
| 2272 |
+
"loss": 1.2011,
|
| 2273 |
+
"step": 25800
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 1.76,
|
| 2277 |
+
"grad_norm": 3.1545894145965576,
|
| 2278 |
+
"learning_rate": 6.481179508085338e-06,
|
| 2279 |
+
"loss": 1.17,
|
| 2280 |
+
"step": 25900
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 1.77,
|
| 2284 |
+
"grad_norm": 1.7653687000274658,
|
| 2285 |
+
"learning_rate": 6.467590705258867e-06,
|
| 2286 |
+
"loss": 1.1984,
|
| 2287 |
+
"step": 26000
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 1.77,
|
| 2291 |
+
"eval_loss": 1.2038514614105225,
|
| 2292 |
+
"eval_runtime": 70.8478,
|
| 2293 |
+
"eval_samples_per_second": 35.894,
|
| 2294 |
+
"eval_steps_per_second": 4.488,
|
| 2295 |
+
"step": 26000
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 1.77,
|
| 2299 |
+
"grad_norm": 1.9187010526657104,
|
| 2300 |
+
"learning_rate": 6.454001902432397e-06,
|
| 2301 |
+
"loss": 1.2051,
|
| 2302 |
+
"step": 26100
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 1.78,
|
| 2306 |
+
"grad_norm": 1.6188615560531616,
|
| 2307 |
+
"learning_rate": 6.440413099605925e-06,
|
| 2308 |
+
"loss": 1.1712,
|
| 2309 |
+
"step": 26200
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 1.79,
|
| 2313 |
+
"grad_norm": 1.9360331296920776,
|
| 2314 |
+
"learning_rate": 6.426824296779455e-06,
|
| 2315 |
+
"loss": 1.1531,
|
| 2316 |
+
"step": 26300
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 1.79,
|
| 2320 |
+
"grad_norm": 2.710357189178467,
|
| 2321 |
+
"learning_rate": 6.413235493952983e-06,
|
| 2322 |
+
"loss": 1.1707,
|
| 2323 |
+
"step": 26400
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 1.8,
|
| 2327 |
+
"grad_norm": 2.3331565856933594,
|
| 2328 |
+
"learning_rate": 6.399646691126512e-06,
|
| 2329 |
+
"loss": 1.1929,
|
| 2330 |
+
"step": 26500
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 1.8,
|
| 2334 |
+
"eval_loss": 1.2011253833770752,
|
| 2335 |
+
"eval_runtime": 70.8706,
|
| 2336 |
+
"eval_samples_per_second": 35.882,
|
| 2337 |
+
"eval_steps_per_second": 4.487,
|
| 2338 |
+
"step": 26500
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.81,
|
| 2342 |
+
"grad_norm": 2.030912399291992,
|
| 2343 |
+
"learning_rate": 6.386057888300041e-06,
|
| 2344 |
+
"loss": 1.1986,
|
| 2345 |
+
"step": 26600
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 1.81,
|
| 2349 |
+
"grad_norm": 2.1584174633026123,
|
| 2350 |
+
"learning_rate": 6.37246908547357e-06,
|
| 2351 |
+
"loss": 1.2564,
|
| 2352 |
+
"step": 26700
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 1.82,
|
| 2356 |
+
"grad_norm": 2.3068361282348633,
|
| 2357 |
+
"learning_rate": 6.3588802826471e-06,
|
| 2358 |
+
"loss": 1.1933,
|
| 2359 |
+
"step": 26800
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 1.83,
|
| 2363 |
+
"grad_norm": 1.5643947124481201,
|
| 2364 |
+
"learning_rate": 6.3452914798206285e-06,
|
| 2365 |
+
"loss": 1.1691,
|
| 2366 |
+
"step": 26900
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 1.83,
|
| 2370 |
+
"grad_norm": 2.531083822250366,
|
| 2371 |
+
"learning_rate": 6.331702676994157e-06,
|
| 2372 |
+
"loss": 1.1387,
|
| 2373 |
+
"step": 27000
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 1.83,
|
| 2377 |
+
"eval_loss": 1.1969281435012817,
|
| 2378 |
+
"eval_runtime": 70.8053,
|
| 2379 |
+
"eval_samples_per_second": 35.915,
|
| 2380 |
+
"eval_steps_per_second": 4.491,
|
| 2381 |
+
"step": 27000
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 1.84,
|
| 2385 |
+
"grad_norm": 1.800430417060852,
|
| 2386 |
+
"learning_rate": 6.318113874167686e-06,
|
| 2387 |
+
"loss": 1.1646,
|
| 2388 |
+
"step": 27100
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 1.85,
|
| 2392 |
+
"grad_norm": 1.8300161361694336,
|
| 2393 |
+
"learning_rate": 6.304525071341216e-06,
|
| 2394 |
+
"loss": 1.2104,
|
| 2395 |
+
"step": 27200
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 1.85,
|
| 2399 |
+
"grad_norm": 1.7128742933273315,
|
| 2400 |
+
"learning_rate": 6.2909362685147445e-06,
|
| 2401 |
+
"loss": 1.1932,
|
| 2402 |
+
"step": 27300
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.86,
|
| 2406 |
+
"grad_norm": 1.9414857625961304,
|
| 2407 |
+
"learning_rate": 6.277347465688274e-06,
|
| 2408 |
+
"loss": 1.1818,
|
| 2409 |
+
"step": 27400
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.87,
|
| 2413 |
+
"grad_norm": 1.9951707124710083,
|
| 2414 |
+
"learning_rate": 6.263758662861802e-06,
|
| 2415 |
+
"loss": 1.2024,
|
| 2416 |
+
"step": 27500
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 1.87,
|
| 2420 |
+
"eval_loss": 1.1932079792022705,
|
| 2421 |
+
"eval_runtime": 70.8009,
|
| 2422 |
+
"eval_samples_per_second": 35.918,
|
| 2423 |
+
"eval_steps_per_second": 4.491,
|
| 2424 |
+
"step": 27500
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.88,
|
| 2428 |
+
"grad_norm": 1.9903321266174316,
|
| 2429 |
+
"learning_rate": 6.250169860035331e-06,
|
| 2430 |
+
"loss": 1.1824,
|
| 2431 |
+
"step": 27600
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.88,
|
| 2435 |
+
"grad_norm": 2.8851983547210693,
|
| 2436 |
+
"learning_rate": 6.2365810572088605e-06,
|
| 2437 |
+
"loss": 1.1851,
|
| 2438 |
+
"step": 27700
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.89,
|
| 2442 |
+
"grad_norm": 2.0669078826904297,
|
| 2443 |
+
"learning_rate": 6.222992254382389e-06,
|
| 2444 |
+
"loss": 1.1646,
|
| 2445 |
+
"step": 27800
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.9,
|
| 2449 |
+
"grad_norm": 1.9089607000350952,
|
| 2450 |
+
"learning_rate": 6.209403451555919e-06,
|
| 2451 |
+
"loss": 1.1776,
|
| 2452 |
+
"step": 27900
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.9,
|
| 2456 |
+
"grad_norm": 2.2551538944244385,
|
| 2457 |
+
"learning_rate": 6.195814648729448e-06,
|
| 2458 |
+
"loss": 1.1909,
|
| 2459 |
+
"step": 28000
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.9,
|
| 2463 |
+
"eval_loss": 1.1877614259719849,
|
| 2464 |
+
"eval_runtime": 70.8691,
|
| 2465 |
+
"eval_samples_per_second": 35.883,
|
| 2466 |
+
"eval_steps_per_second": 4.487,
|
| 2467 |
+
"step": 28000
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.91,
|
| 2471 |
+
"grad_norm": 1.5612294673919678,
|
| 2472 |
+
"learning_rate": 6.182225845902976e-06,
|
| 2473 |
+
"loss": 1.1559,
|
| 2474 |
+
"step": 28100
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.92,
|
| 2478 |
+
"grad_norm": 2.8218579292297363,
|
| 2479 |
+
"learning_rate": 6.168637043076505e-06,
|
| 2480 |
+
"loss": 1.1652,
|
| 2481 |
+
"step": 28200
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.92,
|
| 2485 |
+
"grad_norm": 1.9702138900756836,
|
| 2486 |
+
"learning_rate": 6.155048240250035e-06,
|
| 2487 |
+
"loss": 1.1917,
|
| 2488 |
+
"step": 28300
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.93,
|
| 2492 |
+
"grad_norm": 2.3673105239868164,
|
| 2493 |
+
"learning_rate": 6.141459437423564e-06,
|
| 2494 |
+
"loss": 1.1336,
|
| 2495 |
+
"step": 28400
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.94,
|
| 2499 |
+
"grad_norm": 1.8467798233032227,
|
| 2500 |
+
"learning_rate": 6.127870634597093e-06,
|
| 2501 |
+
"loss": 1.1786,
|
| 2502 |
+
"step": 28500
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.94,
|
| 2506 |
+
"eval_loss": 1.1837141513824463,
|
| 2507 |
+
"eval_runtime": 70.7666,
|
| 2508 |
+
"eval_samples_per_second": 35.935,
|
| 2509 |
+
"eval_steps_per_second": 4.494,
|
| 2510 |
+
"step": 28500
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 1.94,
|
| 2514 |
+
"grad_norm": 1.830837368965149,
|
| 2515 |
+
"learning_rate": 6.114281831770621e-06,
|
| 2516 |
+
"loss": 1.1908,
|
| 2517 |
+
"step": 28600
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 1.95,
|
| 2521 |
+
"grad_norm": 1.7194899320602417,
|
| 2522 |
+
"learning_rate": 6.10069302894415e-06,
|
| 2523 |
+
"loss": 1.1541,
|
| 2524 |
+
"step": 28700
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 1.96,
|
| 2528 |
+
"grad_norm": 1.798368215560913,
|
| 2529 |
+
"learning_rate": 6.0871042261176796e-06,
|
| 2530 |
+
"loss": 1.1487,
|
| 2531 |
+
"step": 28800
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 1.96,
|
| 2535 |
+
"grad_norm": 1.9699339866638184,
|
| 2536 |
+
"learning_rate": 6.073515423291208e-06,
|
| 2537 |
+
"loss": 1.166,
|
| 2538 |
+
"step": 28900
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 1.97,
|
| 2542 |
+
"grad_norm": 2.1379947662353516,
|
| 2543 |
+
"learning_rate": 6.059926620464738e-06,
|
| 2544 |
+
"loss": 1.1724,
|
| 2545 |
+
"step": 29000
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 1.97,
|
| 2549 |
+
"eval_loss": 1.181123971939087,
|
| 2550 |
+
"eval_runtime": 92.5562,
|
| 2551 |
+
"eval_samples_per_second": 27.475,
|
| 2552 |
+
"eval_steps_per_second": 3.436,
|
| 2553 |
+
"step": 29000
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 1.98,
|
| 2557 |
+
"grad_norm": 2.405134439468384,
|
| 2558 |
+
"learning_rate": 6.046337817638267e-06,
|
| 2559 |
+
"loss": 1.1651,
|
| 2560 |
+
"step": 29100
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 1.98,
|
| 2564 |
+
"grad_norm": 1.8744902610778809,
|
| 2565 |
+
"learning_rate": 6.032749014811795e-06,
|
| 2566 |
+
"loss": 1.201,
|
| 2567 |
+
"step": 29200
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 1.99,
|
| 2571 |
+
"grad_norm": 3.014401435852051,
|
| 2572 |
+
"learning_rate": 6.019160211985324e-06,
|
| 2573 |
+
"loss": 1.1783,
|
| 2574 |
+
"step": 29300
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 2.0,
|
| 2578 |
+
"grad_norm": 2.104191780090332,
|
| 2579 |
+
"learning_rate": 6.005571409158854e-06,
|
| 2580 |
+
"loss": 1.1479,
|
| 2581 |
+
"step": 29400
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 2.0,
|
| 2585 |
+
"grad_norm": 1.9670746326446533,
|
| 2586 |
+
"learning_rate": 5.991982606332383e-06,
|
| 2587 |
+
"loss": 1.1372,
|
| 2588 |
+
"step": 29500
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 2.0,
|
| 2592 |
+
"eval_loss": 1.176620602607727,
|
| 2593 |
+
"eval_runtime": 92.464,
|
| 2594 |
+
"eval_samples_per_second": 27.503,
|
| 2595 |
+
"eval_steps_per_second": 3.439,
|
| 2596 |
+
"step": 29500
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 2.01,
|
| 2600 |
+
"grad_norm": 2.3720388412475586,
|
| 2601 |
+
"learning_rate": 5.978393803505912e-06,
|
| 2602 |
+
"loss": 1.1476,
|
| 2603 |
+
"step": 29600
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 2.02,
|
| 2607 |
+
"grad_norm": 2.047060251235962,
|
| 2608 |
+
"learning_rate": 5.964805000679441e-06,
|
| 2609 |
+
"loss": 1.1303,
|
| 2610 |
+
"step": 29700
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 2.02,
|
| 2614 |
+
"grad_norm": 1.9792667627334595,
|
| 2615 |
+
"learning_rate": 5.951216197852969e-06,
|
| 2616 |
+
"loss": 1.1462,
|
| 2617 |
+
"step": 29800
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 2.03,
|
| 2621 |
+
"grad_norm": 2.241187572479248,
|
| 2622 |
+
"learning_rate": 5.937627395026499e-06,
|
| 2623 |
+
"loss": 1.1031,
|
| 2624 |
+
"step": 29900
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 2.04,
|
| 2628 |
+
"grad_norm": 2.0233969688415527,
|
| 2629 |
+
"learning_rate": 5.9240385922000274e-06,
|
| 2630 |
+
"loss": 1.1396,
|
| 2631 |
+
"step": 30000
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 2.04,
|
| 2635 |
+
"eval_loss": 1.1728562116622925,
|
| 2636 |
+
"eval_runtime": 92.5707,
|
| 2637 |
+
"eval_samples_per_second": 27.471,
|
| 2638 |
+
"eval_steps_per_second": 3.435,
|
| 2639 |
+
"step": 30000
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 2.05,
|
| 2643 |
+
"grad_norm": 2.0683882236480713,
|
| 2644 |
+
"learning_rate": 5.910449789373557e-06,
|
| 2645 |
+
"loss": 1.1431,
|
| 2646 |
+
"step": 30100
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 2.05,
|
| 2650 |
+
"grad_norm": 1.9208968877792358,
|
| 2651 |
+
"learning_rate": 5.896860986547086e-06,
|
| 2652 |
+
"loss": 1.1391,
|
| 2653 |
+
"step": 30200
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 2.06,
|
| 2657 |
+
"grad_norm": 1.6621592044830322,
|
| 2658 |
+
"learning_rate": 5.883272183720614e-06,
|
| 2659 |
+
"loss": 1.1361,
|
| 2660 |
+
"step": 30300
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 2.07,
|
| 2664 |
+
"grad_norm": 1.9728045463562012,
|
| 2665 |
+
"learning_rate": 5.869683380894143e-06,
|
| 2666 |
+
"loss": 1.1606,
|
| 2667 |
+
"step": 30400
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 2.07,
|
| 2671 |
+
"grad_norm": 2.3189892768859863,
|
| 2672 |
+
"learning_rate": 5.856094578067672e-06,
|
| 2673 |
+
"loss": 1.1565,
|
| 2674 |
+
"step": 30500
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 2.07,
|
| 2678 |
+
"eval_loss": 1.1692627668380737,
|
| 2679 |
+
"eval_runtime": 92.5367,
|
| 2680 |
+
"eval_samples_per_second": 27.481,
|
| 2681 |
+
"eval_steps_per_second": 3.436,
|
| 2682 |
+
"step": 30500
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 2.08,
|
| 2686 |
+
"grad_norm": 1.936689853668213,
|
| 2687 |
+
"learning_rate": 5.842505775241202e-06,
|
| 2688 |
+
"loss": 1.1294,
|
| 2689 |
+
"step": 30600
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 2.09,
|
| 2693 |
+
"grad_norm": 1.4617129564285278,
|
| 2694 |
+
"learning_rate": 5.8289169724147306e-06,
|
| 2695 |
+
"loss": 1.1591,
|
| 2696 |
+
"step": 30700
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 2.09,
|
| 2700 |
+
"grad_norm": 1.5474071502685547,
|
| 2701 |
+
"learning_rate": 5.81532816958826e-06,
|
| 2702 |
+
"loss": 1.1377,
|
| 2703 |
+
"step": 30800
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 2.1,
|
| 2707 |
+
"grad_norm": 1.7175779342651367,
|
| 2708 |
+
"learning_rate": 5.801739366761788e-06,
|
| 2709 |
+
"loss": 1.1532,
|
| 2710 |
+
"step": 30900
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 2.11,
|
| 2714 |
+
"grad_norm": 1.8924795389175415,
|
| 2715 |
+
"learning_rate": 5.788150563935318e-06,
|
| 2716 |
+
"loss": 1.1002,
|
| 2717 |
+
"step": 31000
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 2.11,
|
| 2721 |
+
"eval_loss": 1.1667861938476562,
|
| 2722 |
+
"eval_runtime": 92.475,
|
| 2723 |
+
"eval_samples_per_second": 27.499,
|
| 2724 |
+
"eval_steps_per_second": 3.439,
|
| 2725 |
+
"step": 31000
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.11,
|
| 2729 |
+
"grad_norm": 2.3616528511047363,
|
| 2730 |
+
"learning_rate": 5.7745617611088465e-06,
|
| 2731 |
+
"loss": 1.1616,
|
| 2732 |
+
"step": 31100
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.12,
|
| 2736 |
+
"grad_norm": 1.7967276573181152,
|
| 2737 |
+
"learning_rate": 5.760972958282376e-06,
|
| 2738 |
+
"loss": 1.1817,
|
| 2739 |
+
"step": 31200
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.13,
|
| 2743 |
+
"grad_norm": 2.9053776264190674,
|
| 2744 |
+
"learning_rate": 5.747384155455905e-06,
|
| 2745 |
+
"loss": 1.1611,
|
| 2746 |
+
"step": 31300
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.13,
|
| 2750 |
+
"grad_norm": 2.2042810916900635,
|
| 2751 |
+
"learning_rate": 5.7337953526294346e-06,
|
| 2752 |
+
"loss": 1.1394,
|
| 2753 |
+
"step": 31400
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.14,
|
| 2757 |
+
"grad_norm": 1.8876034021377563,
|
| 2758 |
+
"learning_rate": 5.7202065498029625e-06,
|
| 2759 |
+
"loss": 1.1171,
|
| 2760 |
+
"step": 31500
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.14,
|
| 2764 |
+
"eval_loss": 1.1626156568527222,
|
| 2765 |
+
"eval_runtime": 92.4663,
|
| 2766 |
+
"eval_samples_per_second": 27.502,
|
| 2767 |
+
"eval_steps_per_second": 3.439,
|
| 2768 |
+
"step": 31500
|
| 2769 |
+
}
|
| 2770 |
+
],
|
| 2771 |
+
"logging_steps": 100,
|
| 2772 |
+
"max_steps": 73590,
|
| 2773 |
+
"num_input_tokens_seen": 0,
|
| 2774 |
+
"num_train_epochs": 5,
|
| 2775 |
+
"save_steps": 500,
|
| 2776 |
+
"total_flos": 1.55848975386624e+17,
|
| 2777 |
+
"train_batch_size": 8,
|
| 2778 |
+
"trial_name": null,
|
| 2779 |
+
"trial_params": null
|
| 2780 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98498687363a9e67d3d945942685e0ff1f43befa20a4ec5f62ad97f31e3e5d02
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|