Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,58 +1,32 @@
 {
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
   "architectures": [
-    "MBartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
   "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "do_blenderbot_90_layernorm": false,
-  "dropout": 0.1,
-  "early_stopping": null,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "extra_pos_embeddings": 2,
-  "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "no_repeat_ngram_size": null,
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": null,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "scale_embedding": false,
-  "static_position_embeddings": false,
-  "tokenizer_class": "BarthezTokenizer",
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
-  "use_cache": false,
-  "vocab_size": 50594
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 110208
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2139aa0df60063c5f2a89b26029f1e46a73d98ca4786df7e9f5e8f8aa2ce3fd8
-size 558937304
+oid sha256:030be25143ccd1d78f909c41318fb2ecc301e9c81c4835b77323d13e3a68f361
+size 1470068592

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b1742741bbc7df44be28b94d10d9ab05ad1cce2d8e70ac745824b916791397
+size 2996811

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd54aa42eef0dd482320f74af4126bc2997a856ba65d8619476c5b9c42dc0d7e
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9380964b4b2206fff8b4f1535e87c70866b61a1d77c927a05f1aaa0e184890d1
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6218a7bb0fe5f214de8ffed80e034797b70aa538fcf9b5e6aedd7d40c0317f31
+size 1465

special_tokens_map.json

@@ -1,18 +1,106 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
@@ -20,13 +108,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
@@ -34,13 +115,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

trainer_state.json

@@ -1,142 +1,364 @@
 {
-  "best_global_step": 5570,
-  "best_metric": 0.7717538371980056,
-  "best_model_checkpoint": "./checkpoints/checkpoint-5570",
-  "epoch": 0.9998653923812088,
-  "eval_steps": 1114,
-  "global_step": 5571,
+  "best_global_step": 16280,
+  "best_metric": 0.05104936846864332,
+  "best_model_checkpoint": "checkpoints/checkpoint-16280",
+  "epoch": 1.9992631708215645,
+  "eval_steps": 1628,
+  "global_step": 16280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0897384125274824,
-      "grad_norm": 0.10910310596227646,
-      "learning_rate": 4.901672070547205e-05,
-      "loss": 2.0607,
+      "epoch": 0.06140243153628884,
+      "grad_norm": 0.31788545846939087,
+      "learning_rate": 4.99487482593161e-05,
+      "loss": 0.639,
       "step": 500
     },
     {
-      "epoch": 0.1794768250549648,
-      "grad_norm": 0.11283092200756073,
-      "learning_rate": 4.6136704554635066e-05,
-      "loss": 0.1219,
+      "epoch": 0.12280486307257768,
+      "grad_norm": 0.21716584265232086,
+      "learning_rate": 4.9794381003990576e-05,
+      "loss": 0.3961,
       "step": 1000
     },
     {
-      "epoch": 0.19993718311123077,
-      "eval_cer": 0.7744026050691318,
-      "eval_loss": 0.06905069202184677,
-      "eval_runtime": 2200.6581,
-      "eval_samples_per_second": 80.463,
-      "eval_steps_per_second": 0.21,
-      "step": 1114
-    },
-    {
-      "epoch": 0.26921523758244714,
-      "grad_norm": 0.07702942937612534,
-      "learning_rate": 4.9413107833705604e-05,
-      "loss": 0.0709,
+      "epoch": 0.1842072946088665,
+      "grad_norm": 0.32310155034065247,
+      "learning_rate": 4.9537535426562465e-05,
+      "loss": 0.3303,
       "step": 1500
     },
     {
-      "epoch": 0.3589536501099296,
-      "grad_norm": 0.048379454761743546,
-      "learning_rate": 4.695072154439477e-05,
-      "loss": 0.0526,
-      "step": 2000
+      "epoch": 0.19992631708215644,
+      "eval_avg": 0.07433640047160056,
+      "eval_cer": 0.048444434926464684,
+      "eval_der": 0.054747223027151605,
+      "eval_loss": 0.2203781008720398,
+      "eval_runtime": 1149.449,
+      "eval_samples_per_second": 45.035,
+      "eval_steps_per_second": 0.352,
+      "eval_wer": 0.1198175434611854,
+      "step": 1628
     },
     {
-      "epoch": 0.39987436622246153,
-      "eval_cer": 0.7726060406484112,
-      "eval_loss": 0.03332927078008652,
-      "eval_runtime": 436.8886,
-      "eval_samples_per_second": 405.3,
-      "eval_steps_per_second": 1.057,
-      "step": 2228
+      "epoch": 0.24560972614515536,
+      "grad_norm": 0.1829567700624466,
+      "learning_rate": 4.997155120906588e-05,
+      "loss": 0.287,
+      "step": 2000
     },
     {
-      "epoch": 0.44869206263741196,
-      "grad_norm": 0.04356146231293678,
-      "learning_rate": 4.970863550514242e-05,
-      "loss": 0.0398,
+      "epoch": 0.3070121576814442,
+      "grad_norm": 0.1720687448978424,
+      "learning_rate": 4.984333190353011e-05,
+      "loss": 0.2682,
       "step": 2500
     },
     {
-      "epoch": 0.5384304751648943,
-      "grad_norm": 0.03718848526477814,
-      "learning_rate": 4.767405209364289e-05,
-      "loss": 0.0348,
+      "epoch": 0.368414589217733,
+      "grad_norm": 0.19322410225868225,
+      "learning_rate": 4.961243195561407e-05,
+      "loss": 0.2506,
       "step": 3000
     },
     {
-      "epoch": 0.5998115493336923,
-      "eval_cer": 0.7720533296293449,
-      "eval_loss": 0.022723019123077393,
-      "eval_runtime": 439.0491,
-      "eval_samples_per_second": 403.306,
-      "eval_steps_per_second": 1.052,
-      "step": 3342
+      "epoch": 0.3998526341643129,
+      "eval_avg": 0.061321180853411116,
+      "eval_cer": 0.04388846969480041,
+      "eval_der": 0.03895160822949064,
+      "eval_loss": 0.18064290285110474,
+      "eval_runtime": 1155.5329,
+      "eval_samples_per_second": 44.798,
+      "eval_steps_per_second": 0.35,
+      "eval_wer": 0.10112346463594228,
+      "step": 3256
     },
     {
-      "epoch": 0.6281688876923768,
-      "grad_norm": 0.03279432654380798,
-      "learning_rate": 4.384876624004233e-05,
-      "loss": 0.03,
+      "epoch": 0.42981702075402184,
+      "grad_norm": 0.16168585419654846,
+      "learning_rate": 4.998779393767303e-05,
+      "loss": 0.2339,
       "step": 3500
     },
     {
-      "epoch": 0.7179073002198592,
-      "grad_norm": 0.032072387635707855,
-      "learning_rate": 3.8534883130104934e-05,
-      "loss": 0.027,
+      "epoch": 0.4912194522903107,
+      "grad_norm": 0.12988826632499695,
+      "learning_rate": 4.988596305882391e-05,
+      "loss": 0.2271,
       "step": 4000
     },
     {
-      "epoch": 0.7997487324449231,
-      "eval_cer": 0.7718523934618883,
-      "eval_loss": 0.01841309294104576,
-      "eval_runtime": 436.0956,
-      "eval_samples_per_second": 406.037,
-      "eval_steps_per_second": 1.059,
-      "step": 4456
+      "epoch": 0.5526218838265995,
+      "grad_norm": 0.11692152917385101,
+      "learning_rate": 4.9681275337621505e-05,
+      "loss": 0.2181,
+      "step": 4500
     },
     {
-      "epoch": 0.8076457127473415,
-      "grad_norm": 0.0274814460426569,
-      "learning_rate": 3.2152071176988856e-05,
-      "loss": 0.0248,
-      "step": 4500
+      "epoch": 0.5997789512464694,
+      "eval_avg": 0.06223662921729023,
+      "eval_cer": 0.03700322837976026,
+      "eval_der": 0.055956727518601486,
+      "eval_loss": 0.19135934114456177,
+      "eval_runtime": 1153.4306,
+      "eval_samples_per_second": 44.879,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.09374993175350896,
+      "step": 4884
     },
     {
-      "epoch": 0.8973841252748239,
-      "grad_norm": 0.025461740791797638,
-      "learning_rate": 2.520441835335607e-05,
-      "loss": 0.0232,
+      "epoch": 0.6140243153628884,
+      "grad_norm": 0.12457627058029175,
+      "learning_rate": 4.9374576774384186e-05,
+      "loss": 0.2112,
       "step": 5000
     },
     {
-      "epoch": 0.9871225378023063,
-      "grad_norm": 0.026277432218194008,
-      "learning_rate": 1.8240621417367316e-05,
-      "loss": 0.0222,
+      "epoch": 0.6754267468991773,
+      "grad_norm": 0.13500584661960602,
+      "learning_rate": 4.8967134993181585e-05,
+      "loss": 0.2042,
       "step": 5500
     },
     {
-      "epoch": 0.9996859155561538,
-      "eval_cer": 0.7717538371980056,
-      "eval_loss": 0.016575267538428307,
-      "eval_runtime": 437.5161,
-      "eval_samples_per_second": 404.719,
-      "eval_steps_per_second": 1.056,
-      "step": 5570
+      "epoch": 0.736829178435466,
+      "grad_norm": 0.14300259947776794,
+      "learning_rate": 4.846063400258344e-05,
+      "loss": 0.1994,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7982316099717549,
+      "grad_norm": 0.15229490399360657,
+      "learning_rate": 4.785716723543856e-05,
+      "loss": 0.1941,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7997052683286258,
+      "eval_avg": 0.05848093903880644,
+      "eval_cer": 0.034985685323039174,
+      "eval_der": 0.05257239447503411,
+      "eval_loss": 0.17743617296218872,
+      "eval_runtime": 1154.8064,
+      "eval_samples_per_second": 44.826,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.08788473731834603,
+      "step": 6512
+    },
+    {
+      "epoch": 0.8596340415080437,
+      "grad_norm": 0.10620284080505371,
+      "learning_rate": 4.9950986655011213e-05,
+      "loss": 0.1892,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9210364730443326,
+      "grad_norm": 0.10538509488105774,
+      "learning_rate": 4.9798882653846754e-05,
+      "loss": 0.1843,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9824389045806214,
+      "grad_norm": 0.11998545378446579,
+      "learning_rate": 4.954428172468978e-05,
+      "loss": 0.1814,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9996315854107822,
+      "eval_avg": 0.05574338139826937,
+      "eval_cer": 0.0337392713322537,
+      "eval_der": 0.05011513570945588,
+      "eval_loss": 0.16507230699062347,
+      "eval_runtime": 1158.6086,
+      "eval_samples_per_second": 44.679,
+      "eval_steps_per_second": 0.35,
+      "eval_wer": 0.08337573715309854,
+      "step": 8140
+    },
+    {
+      "epoch": 1.0438413361169103,
+      "grad_norm": 0.12560783326625824,
+      "learning_rate": 4.9189048589485774e-05,
+      "loss": 0.1764,
+      "step": 8500
+    },
+    {
+      "epoch": 1.105243767653199,
+      "grad_norm": 0.10523095726966858,
+      "learning_rate": 4.8733228183318665e-05,
+      "loss": 0.1735,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1666461991894879,
+      "grad_norm": 0.11041487008333206,
+      "learning_rate": 4.817931533427457e-05,
+      "loss": 0.1715,
+      "step": 9500
+    },
+    {
+      "epoch": 1.1995579024929388,
+      "eval_avg": 0.0544335846636687,
+      "eval_cer": 0.03342891994782228,
+      "eval_der": 0.048513281174538105,
+      "eval_loss": 0.1576041877269745,
+      "eval_runtime": 1159.9625,
+      "eval_samples_per_second": 44.626,
+      "eval_steps_per_second": 0.349,
+      "eval_wer": 0.08135855286864571,
+      "step": 9768
+    },
+    {
+      "epoch": 1.2280486307257767,
+      "grad_norm": 0.1073341891169548,
+      "learning_rate": 4.998896962187747e-05,
+      "loss": 0.1674,
+      "step": 10000
+    },
+    {
+      "epoch": 1.2894510622620656,
+      "grad_norm": 0.11093363165855408,
+      "learning_rate": 4.988961418344719e-05,
+      "loss": 0.167,
+      "step": 10500
+    },
+    {
+      "epoch": 1.3508534937983545,
+      "grad_norm": 0.09265608340501785,
+      "learning_rate": 4.968738681210237e-05,
+      "loss": 0.165,
+      "step": 11000
+    },
+    {
+      "epoch": 1.3994842195750952,
+      "eval_avg": 0.05450751736133735,
+      "eval_cer": 0.03384634860456726,
+      "eval_der": 0.04814585144402502,
+      "eval_loss": 0.15283821523189545,
+      "eval_runtime": 1150.9092,
+      "eval_samples_per_second": 44.977,
+      "eval_steps_per_second": 0.352,
+      "eval_wer": 0.08153035203541975,
+      "step": 11396
+    },
+    {
+      "epoch": 1.4122559253346432,
+      "grad_norm": 0.10535308718681335,
+      "learning_rate": 4.999780685937908e-05,
+      "loss": 0.1617,
+      "step": 11500
+    },
+    {
+      "epoch": 1.473658356870932,
+      "grad_norm": 0.09392343461513519,
+      "learning_rate": 4.992486965915939e-05,
+      "loss": 0.161,
+      "step": 12000
+    },
+    {
+      "epoch": 1.535060788407221,
+      "grad_norm": 0.0898473933339119,
+      "learning_rate": 4.974891481067152e-05,
+      "loss": 0.1593,
+      "step": 12500
+    },
+    {
+      "epoch": 1.5964632199435098,
+      "grad_norm": 0.10352090746164322,
+      "learning_rate": 4.94706695576259e-05,
+      "loss": 0.1581,
+      "step": 13000
+    },
+    {
+      "epoch": 1.5994105366572517,
+      "eval_avg": 0.052648695144827624,
+      "eval_cer": 0.03269155476372104,
+      "eval_der": 0.04647078141601352,
+      "eval_loss": 0.1520785242319107,
+      "eval_runtime": 1154.3982,
+      "eval_samples_per_second": 44.842,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.07878374925474832,
+      "step": 13024
+    },
+    {
+      "epoch": 1.6578656514797987,
+      "grad_norm": 0.08162818104028702,
+      "learning_rate": 4.995337159613658e-05,
+      "loss": 0.1563,
+      "step": 13500
+    },
+    {
+      "epoch": 1.7192680830160874,
+      "grad_norm": 0.10093415528535843,
+      "learning_rate": 4.9803736946497604e-05,
+      "loss": 0.1549,
+      "step": 14000
+    },
+    {
+      "epoch": 1.7806705145523762,
+      "grad_norm": 0.0779104083776474,
+      "learning_rate": 4.9551585305458784e-05,
+      "loss": 0.1531,
+      "step": 14500
+    },
+    {
+      "epoch": 1.799336853739408,
+      "eval_avg": 0.05215597602151043,
+      "eval_cer": 0.032804504015484064,
+      "eval_der": 0.046157249106538095,
+      "eval_loss": 0.1437014639377594,
+      "eval_runtime": 1158.5459,
+      "eval_samples_per_second": 44.681,
+      "eval_steps_per_second": 0.35,
+      "eval_wer": 0.07750617494250915,
+      "step": 14652
+    },
+    {
+      "epoch": 1.8420729460886651,
+      "grad_norm": 0.09926008433103561,
+      "learning_rate": 4.919795884774044e-05,
+      "loss": 0.1519,
+      "step": 15000
+    },
+    {
+      "epoch": 1.903475377624954,
+      "grad_norm": 0.0932171419262886,
+      "learning_rate": 4.874431915635338e-05,
+      "loss": 0.1508,
+      "step": 15500
+    },
+    {
+      "epoch": 1.9648778091612429,
+      "grad_norm": 0.08440640568733215,
+      "learning_rate": 4.819254118169078e-05,
+      "loss": 0.1493,
+      "step": 16000
+    },
+    {
+      "epoch": 1.9992631708215645,
+      "eval_avg": 0.05104936846864332,
+      "eval_cer": 0.03196083873281993,
+      "eval_der": 0.04519598184101095,
+      "eval_loss": 0.1432473361492157,
+      "eval_runtime": 1163.7456,
+      "eval_samples_per_second": 44.481,
+      "eval_steps_per_second": 0.348,
+      "eval_wer": 0.07599128483209908,
+      "step": 16280
     }
   ],
   "logging_steps": 500,
-  "max_steps": 5571,
+  "max_steps": 24429,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1114,
+  "num_train_epochs": 3,
+  "save_steps": 1628,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,13 +366,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.522138159281603e+17,
-  "train_batch_size": 384,
+  "total_flos": 1.8107754052964844e+18,
+  "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bce4c2a570e5406234205443c86622d09135dc71fc8963eb2e85ed7f5af2b7c
-size 5841
+oid sha256:994dcd51f10df37a598334a01dc75b4d6c85da6c809dc43933bd3b4a8f34c7ee
+size 5905