Hugging Face's logo

k4black
/
google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
k4black commited on
Commit
a6032d5
•
1 Parent(s): ea049be

Training in progress, step 32000

Browse files
Files changed (8) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +25 -3
  6. last-checkpoint/training_args.bin +1 -1
  7. pytorch_model.bin +1 -1
  8. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d84430446db4d99c3febcd7069c01b881fdf59602a6b2f386c6aa6f6088e31c
3
  size 1135685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b354211a1d9c670b81fd0ecd6056feb2f9c29341924a000e30adb156c4ebd5
3
  size 1135685
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99d2e4c5815635fa81968b10f073c84d641b574540c97062b58e265dfd90d2cf
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bead796af54e6a798b2476681fe32e4fa4c12367bb7fc793f25a73a56399d04f
3
  size 307910149
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b562ad0fe42141b4131900487ab29531dae5f3b66e799e44aa1bac6297445f4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e3602e95f81e6fcc4f4c618ffe0b7ed5c45d4297c480d0d0ecb7a0c6a159f38
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c253821127e6e97cecd3e16899e80bf0898ae3dcd40b71b5a507f5ae44245fdf
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f9b786c971400e73aabd90273ab2962113ae1b76e787f7a0e6e5885da736e3
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 1.6879340410232544,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
4
- "epoch": 3.494874184529357,
5
- "global_step": 30000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -336,11 +336,33 @@
336
  "eval_samples_per_second": 61.825,
337
  "eval_steps_per_second": 0.967,
338
  "step": 30000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
339
  }
340
  ],
341
  "max_steps": 85840,
342
  "num_train_epochs": 10,
343
- "total_flos": 4.532149523187917e+16,
344
  "trial_name": null,
345
  "trial_params": null
346
  }
 
1
  {
2
  "best_metric": 1.6879340410232544,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
4
+ "epoch": 3.7278657968313142,
5
+ "global_step": 32000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
336
  "eval_samples_per_second": 61.825,
337
  "eval_steps_per_second": 0.967,
338
  "step": 30000
339
+ },
340
+ {
341
+ "epoch": 3.73,
342
+ "learning_rate": 0.0006602246529651248,
343
+ "loss": 1.1252,
344
+ "step": 32000
345
+ },
346
+ {
347
+ "epoch": 3.73,
348
+ "eval_accuracy": null,
349
+ "eval_bertscore_f1": 0.9359545163678532,
350
+ "eval_bleu": 0.42344383498507465,
351
+ "eval_f1": null,
352
+ "eval_loss": 1.709180474281311,
353
+ "eval_rouge1": 0.6240469583047095,
354
+ "eval_rouge2": 0.4172449697108748,
355
+ "eval_rougeL": 0.5686400389756898,
356
+ "eval_rougeLsum": 0.5707285873482231,
357
+ "eval_runtime": 166.6453,
358
+ "eval_samples_per_second": 59.06,
359
+ "eval_steps_per_second": 0.924,
360
+ "step": 32000
361
  }
362
  ],
363
  "max_steps": 85840,
364
  "num_train_epochs": 10,
365
+ "total_flos": 4.834995362557747e+16,
366
  "trial_name": null,
367
  "trial_params": null
368
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c42a26a0bb6e8f7212f31a745bfbbb3e9f64d18051d5dd2dab687a29b239b4ef
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747a9b2ee82d7a06bdd4d9105b301d8065743981b8f890d40d4a35c774071245
3
  size 3963
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99d2e4c5815635fa81968b10f073c84d641b574540c97062b58e265dfd90d2cf
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bead796af54e6a798b2476681fe32e4fa4c12367bb7fc793f25a73a56399d04f
3
  size 307910149
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c42a26a0bb6e8f7212f31a745bfbbb3e9f64d18051d5dd2dab687a29b239b4ef
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747a9b2ee82d7a06bdd4d9105b301d8065743981b8f890d40d4a35c774071245
3
  size 3963