Training in progress, step 22000
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 sha256:135000150ade6fed4a894a50261da6cbe624d7fc5fbb15a08b78515158c552a7
|
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 sha256:30a9c03b54e7d115d5b3d78156bb19d603c9754dc44e9af658676ee0eb5915f3
|
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 sha256:4ccca1874478248a47a5c95f71816cf15cd3153b122ab2929c2a52b826e1a84b
|
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 sha256:00fc20b07457d2e67c7b293ab93cf0b2991ff2beeb6ad8da7e6a4999309dc031
|
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,
|
@@ -226,11 +226,33 @@
|
|
226 |
"eval_samples_per_second": 59.128,
|
227 |
"eval_steps_per_second": 0.925,
|
228 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
229 |
}
|
230 |
],
|
231 |
"max_steps": 85840,
|
232 |
"num_train_epochs": 10,
|
233 |
-
"total_flos": 3.
|
234 |
"trial_name": null,
|
235 |
"trial_params": null
|
236 |
}
|
|
|
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": 2.562907735321528,
|
5 |
+
"global_step": 22000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
226 |
"eval_samples_per_second": 59.128,
|
227 |
"eval_steps_per_second": 0.925,
|
228 |
"step": 20000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.56,
|
232 |
+
"learning_rate": 0.000782851817334576,
|
233 |
+
"loss": 1.1755,
|
234 |
+
"step": 22000
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 2.56,
|
238 |
+
"eval_accuracy": null,
|
239 |
+
"eval_bertscore_f1": 0.9346324508266705,
|
240 |
+
"eval_bleu": 0.40634655287582505,
|
241 |
+
"eval_f1": null,
|
242 |
+
"eval_loss": 1.7524782419204712,
|
243 |
+
"eval_rouge1": 0.6135893786369074,
|
244 |
+
"eval_rouge2": 0.40424644238900054,
|
245 |
+
"eval_rougeL": 0.5569845265395319,
|
246 |
+
"eval_rougeLsum": 0.5589737599230747,
|
247 |
+
"eval_runtime": 160.1533,
|
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": 3.3257404068194304e+16,
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|
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 sha256:30a9c03b54e7d115d5b3d78156bb19d603c9754dc44e9af658676ee0eb5915f3
|
3 |
size 307910149
|