Training in progress, step 28000
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:a940821166a8f383499d4f840c8f6964131834ee53ef73d8b18edeff0232b3f3
|
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:dae7957233206b5692a394859405b07c20bd9b0cedb8591cec51234098c6c3e9
|
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 sha256:1968726a02b085a7225de9fdf54dfab46e5dcafed0f114d52e7520801cac6175
|
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 sha256:2205f7ae4e05695eaa6f3999cd90337ec1f041934d0888712b6d545d3628b23a
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7533162832260132,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-24000",
|
4 |
-
"epoch": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -292,11 +292,33 @@
|
|
292 |
"eval_samples_per_second": 77.579,
|
293 |
"eval_steps_per_second": 1.214,
|
294 |
"step": 26000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
295 |
}
|
296 |
],
|
297 |
"max_steps": 85840,
|
298 |
"num_train_epochs": 10,
|
299 |
-
"total_flos": 2.
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|
302 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7533162832260132,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-24000",
|
4 |
+
"epoch": 3.2618825722273996,
|
5 |
+
"global_step": 28000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
292 |
"eval_samples_per_second": 77.579,
|
293 |
"eval_steps_per_second": 1.214,
|
294 |
"step": 26000
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 3.26,
|
298 |
+
"learning_rate": 0.0007092755187129053,
|
299 |
+
"loss": 1.2049,
|
300 |
+
"step": 28000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 3.26,
|
304 |
+
"eval_accuracy": null,
|
305 |
+
"eval_bertscore_f1": 0.9329962301511053,
|
306 |
+
"eval_bleu": 0.4018379705338028,
|
307 |
+
"eval_f1": null,
|
308 |
+
"eval_loss": 1.7540892362594604,
|
309 |
+
"eval_rouge1": 0.6126118264923794,
|
310 |
+
"eval_rouge2": 0.401721192722568,
|
311 |
+
"eval_rougeL": 0.5560492232539358,
|
312 |
+
"eval_rougeLsum": 0.5578878696736621,
|
313 |
+
"eval_runtime": 127.0162,
|
314 |
+
"eval_samples_per_second": 77.486,
|
315 |
+
"eval_steps_per_second": 1.212,
|
316 |
+
"step": 28000
|
317 |
}
|
318 |
],
|
319 |
"max_steps": 85840,
|
320 |
"num_train_epochs": 10,
|
321 |
+
"total_flos": 2.794982082890957e+16,
|
322 |
"trial_name": null,
|
323 |
"trial_params": null
|
324 |
}
|
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:dae7957233206b5692a394859405b07c20bd9b0cedb8591cec51234098c6c3e9
|
3 |
size 242071641
|