Instructions to use k4black/t5-small-e-snli-generation-explanation_only-selected-b64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use k4black/t5-small-e-snli-generation-explanation_only-selected-b64 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("k4black/t5-small-e-snli-generation-explanation_only-selected-b64") model = AutoModelForSeq2SeqLM.from_pretrained("k4black/t5-small-e-snli-generation-explanation_only-selected-b64", 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 839109
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e6aa3e66807e498b9d8f39225ef4167acbc77f8a7f70d19d87711f380cd196a
|
| 3 |
size 839109
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242071641
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad88ac04fa0f726af37ebbb5b49e8c7d862cb70bd5ef2e060bc4c15e385a23d5
|
| 3 |
size 242071641
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fa2b408c1e50e9d7b7e939886f8a60abfce107c6172eb3d4556a5c9064e1fcd
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42b72f80459e4f75521b358111933075785a7f41b311516ef666f06d8acca278
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.7131295204162598,
|
| 3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
| 4 |
-
"epoch": 6.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -600,11 +600,33 @@
|
|
| 600 |
"eval_samples_per_second": 70.04,
|
| 601 |
"eval_steps_per_second": 1.096,
|
| 602 |
"step": 54000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 603 |
}
|
| 604 |
],
|
| 605 |
"max_steps": 85840,
|
| 606 |
"num_train_epochs": 10,
|
| 607 |
-
"total_flos": 5.
|
| 608 |
"trial_name": null,
|
| 609 |
"trial_params": null
|
| 610 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.7131295204162598,
|
| 3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
| 4 |
+
"epoch": 6.523765144454799,
|
| 5 |
+
"global_step": 56000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 600 |
"eval_samples_per_second": 70.04,
|
| 601 |
"eval_steps_per_second": 1.096,
|
| 602 |
"step": 54000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.52,
|
| 606 |
+
"learning_rate": 0.00036591945847844215,
|
| 607 |
+
"loss": 1.1034,
|
| 608 |
+
"step": 56000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.52,
|
| 612 |
+
"eval_accuracy": null,
|
| 613 |
+
"eval_bertscore_f1": 0.9348069845879133,
|
| 614 |
+
"eval_bleu": 0.4108533042307904,
|
| 615 |
+
"eval_f1": null,
|
| 616 |
+
"eval_loss": 1.7296594381332397,
|
| 617 |
+
"eval_rouge1": 0.6208000465641403,
|
| 618 |
+
"eval_rouge2": 0.4153571257641863,
|
| 619 |
+
"eval_rougeL": 0.5634391781002251,
|
| 620 |
+
"eval_rougeLsum": 0.5653490268367348,
|
| 621 |
+
"eval_runtime": 144.1405,
|
| 622 |
+
"eval_samples_per_second": 68.281,
|
| 623 |
+
"eval_steps_per_second": 1.068,
|
| 624 |
+
"step": 56000
|
| 625 |
}
|
| 626 |
],
|
| 627 |
"max_steps": 85840,
|
| 628 |
"num_train_epochs": 10,
|
| 629 |
+
"total_flos": 5.593651859796787e+16,
|
| 630 |
"trial_name": null,
|
| 631 |
"trial_params": null
|
| 632 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242071641
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad88ac04fa0f726af37ebbb5b49e8c7d862cb70bd5ef2e060bc4c15e385a23d5
|
| 3 |
size 242071641
|