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 62000
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 sha256:7eee07976983d0a228670e172497b5fdf980637f65b551918cd3b338227a4a8d
|
| 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 sha256:0169d1fb1fcd67ac4601eeec2ee503ebf5c119b7b93871a045f8acb1e25ab62e
|
| 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 sha256:406aed1808d36b6a98e27292b8104e9859ab37debbac59132ac39eb7a3460d5c
|
| 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:d075d91537c8a1d657ac120b78c132663e43dad968fdd440e7c87f5b73a50cfa
|
| 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":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -666,11 +666,33 @@
|
|
| 666 |
"eval_samples_per_second": 69.287,
|
| 667 |
"eval_steps_per_second": 1.084,
|
| 668 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 669 |
}
|
| 670 |
],
|
| 671 |
"max_steps": 85840,
|
| 672 |
"num_train_epochs": 10,
|
| 673 |
-
"total_flos":
|
| 674 |
"trial_name": null,
|
| 675 |
"trial_params": null
|
| 676 |
}
|
|
|
|
| 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": 7.222739981360671,
|
| 5 |
+
"global_step": 62000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 666 |
"eval_samples_per_second": 69.287,
|
| 667 |
"eval_steps_per_second": 1.084,
|
| 668 |
"step": 60000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.22,
|
| 672 |
+
"learning_rate": 0.00029234315985677146,
|
| 673 |
+
"loss": 1.0711,
|
| 674 |
+
"step": 62000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.22,
|
| 678 |
+
"eval_accuracy": null,
|
| 679 |
+
"eval_bertscore_f1": 0.9346298167519491,
|
| 680 |
+
"eval_bleu": 0.40834821818709055,
|
| 681 |
+
"eval_f1": null,
|
| 682 |
+
"eval_loss": 1.7485404014587402,
|
| 683 |
+
"eval_rouge1": 0.6197656710094954,
|
| 684 |
+
"eval_rouge2": 0.41278766530342237,
|
| 685 |
+
"eval_rougeL": 0.5630552402252382,
|
| 686 |
+
"eval_rougeLsum": 0.5650759439058759,
|
| 687 |
+
"eval_runtime": 146.6193,
|
| 688 |
+
"eval_samples_per_second": 67.126,
|
| 689 |
+
"eval_steps_per_second": 1.05,
|
| 690 |
+
"step": 62000
|
| 691 |
}
|
| 692 |
],
|
| 693 |
"max_steps": 85840,
|
| 694 |
"num_train_epochs": 10,
|
| 695 |
+
"total_flos": 6.19155236708352e+16,
|
| 696 |
"trial_name": null,
|
| 697 |
"trial_params": null
|
| 698 |
}
|
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 sha256:0169d1fb1fcd67ac4601eeec2ee503ebf5c119b7b93871a045f8acb1e25ab62e
|
| 3 |
size 242071641
|