Training in progress, step 24000
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 1135685
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a5b0c69013b4a14f7aebc2f0cde42fea7d8602bd28db21cfc978196f4a2f53
|
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:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e2f6aaf54dab56c40c5497d997d38d59fa2ca79239b4a2eb6332a18cf722a3f
|
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:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36100e9e2e9a97679303e09a016e103ddb0ae4e4ec84186ba5790fef32e0c00b
|
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 sha256:0f4dab7d180014a8330092d2d90d94431a4162b83dd5369cb7313e2941ad1da6
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.692925214767456,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -248,11 +248,33 @@
|
|
248 |
"eval_samples_per_second": 61.454,
|
249 |
"eval_steps_per_second": 0.962,
|
250 |
"step": 22000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
251 |
}
|
252 |
],
|
253 |
"max_steps": 85840,
|
254 |
"num_train_epochs": 10,
|
255 |
-
"total_flos": 3.
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.692925214767456,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
|
4 |
+
"epoch": 2.7958993476234855,
|
5 |
+
"global_step": 24000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
248 |
"eval_samples_per_second": 61.454,
|
249 |
"eval_steps_per_second": 0.962,
|
250 |
"step": 22000
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 2.8,
|
254 |
+
"learning_rate": 0.0007583263844606856,
|
255 |
+
"loss": 1.177,
|
256 |
+
"step": 24000
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.8,
|
260 |
+
"eval_accuracy": null,
|
261 |
+
"eval_bertscore_f1": 0.9357648674997463,
|
262 |
+
"eval_bleu": 0.4166788473251748,
|
263 |
+
"eval_f1": null,
|
264 |
+
"eval_loss": 1.6996724605560303,
|
265 |
+
"eval_rouge1": 0.6259385124974665,
|
266 |
+
"eval_rouge2": 0.4221804267801674,
|
267 |
+
"eval_rougeL": 0.5702138311702792,
|
268 |
+
"eval_rougeLsum": 0.5724783022726267,
|
269 |
+
"eval_runtime": 168.0704,
|
270 |
+
"eval_samples_per_second": 58.559,
|
271 |
+
"eval_steps_per_second": 0.916,
|
272 |
+
"step": 24000
|
273 |
}
|
274 |
],
|
275 |
"max_steps": 85840,
|
276 |
"num_train_epochs": 10,
|
277 |
+
"total_flos": 3.628075047301325e+16,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e2f6aaf54dab56c40c5497d997d38d59fa2ca79239b4a2eb6332a18cf722a3f
|
3 |
size 307910149
|