Instructions to use obss/bsm-pegasus-xsum-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use obss/bsm-pegasus-xsum-multi with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("obss/bsm-pegasus-xsum-multi") model = AutoModelForSeq2SeqLM.from_pretrained("obss/bsm-pegasus-xsum-multi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 56000
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4549998883
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:851cc16ae17e62c3bec9ed24535d87036630bb4ec714e33419955dc744963513
|
| 3 |
size 4549998883
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2279605745
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07b254afd36cea1fe84b602e4b9363976cc284ba7f1d23c5c951d3935ebd6baa
|
| 3 |
size 2279605745
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b6102a3a46ad88b16b2840fa7342294c9f6cda05f8df6dcec290201494d420e
|
| 3 |
+
size 14503
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:059bedb72f80ae08e9c40427666d03dedc9c90d71efcf88e68d29baaa088206c
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aead4d29ec9938715d40277ef0bd4bcc3ac49630fe4ccce67c268aef4be20669
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -672,11 +672,17 @@
|
|
| 672 |
"learning_rate": 1.718028111631697e-05,
|
| 673 |
"loss": 2.3924,
|
| 674 |
"step": 55500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 675 |
}
|
| 676 |
],
|
| 677 |
"max_steps": 392720,
|
| 678 |
"num_train_epochs": 20,
|
| 679 |
-
"total_flos": 2.
|
| 680 |
"trial_name": null,
|
| 681 |
"trial_params": null
|
| 682 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.851904664901202,
|
| 5 |
+
"global_step": 56000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 672 |
"learning_rate": 1.718028111631697e-05,
|
| 673 |
"loss": 2.3924,
|
| 674 |
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.85,
|
| 678 |
+
"learning_rate": 1.715486860867794e-05,
|
| 679 |
+
"loss": 2.4041,
|
| 680 |
+
"step": 56000
|
| 681 |
}
|
| 682 |
],
|
| 683 |
"max_steps": 392720,
|
| 684 |
"num_train_epochs": 20,
|
| 685 |
+
"total_flos": 2.1413973712143974e+17,
|
| 686 |
"trial_name": null,
|
| 687 |
"trial_params": null
|
| 688 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2279605745
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07b254afd36cea1fe84b602e4b9363976cc284ba7f1d23c5c951d3935ebd6baa
|
| 3 |
size 2279605745
|