Training in progress, step 26000
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:cf0a7e66c07cedbfa7a6f533a63696eb1e50f06c16cd6d73731a57befdc52ece
|
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 sha256:8b74a162c61e55614ed9eb2677d7694de994a1c375b65e4178befa43b29b1d49
|
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:e5db5a92bb996eb3fcc170f894aa71fe532ff0c6149a5a76e554e4e7f285a0bb
|
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:a11e5c174a0a481c5093560eac3ef77d341871a0e1df788ef5246aa276c5707f
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -270,11 +270,33 @@
|
|
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.
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
|
|
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": 3.0288909599254428,
|
5 |
+
"global_step": 26000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
270 |
"eval_samples_per_second": 58.559,
|
271 |
"eval_steps_per_second": 0.916,
|
272 |
"step": 24000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.03,
|
276 |
+
"learning_rate": 0.0007338009515867955,
|
277 |
+
"loss": 1.1627,
|
278 |
+
"step": 26000
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.03,
|
282 |
+
"eval_accuracy": null,
|
283 |
+
"eval_bertscore_f1": 0.9365227118034573,
|
284 |
+
"eval_bleu": 0.42188586391601435,
|
285 |
+
"eval_f1": null,
|
286 |
+
"eval_loss": 1.7493563890457153,
|
287 |
+
"eval_rouge1": 0.6268137047490179,
|
288 |
+
"eval_rouge2": 0.42133389000894483,
|
289 |
+
"eval_rougeL": 0.5704007507856375,
|
290 |
+
"eval_rougeLsum": 0.5723283103728103,
|
291 |
+
"eval_runtime": 165.0375,
|
292 |
+
"eval_samples_per_second": 59.635,
|
293 |
+
"eval_steps_per_second": 0.933,
|
294 |
+
"step": 26000
|
295 |
}
|
296 |
],
|
297 |
"max_steps": 85840,
|
298 |
"num_train_epochs": 10,
|
299 |
+
"total_flos": 3.929051016988877e+16,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|
302 |
}
|
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 sha256:8b74a162c61e55614ed9eb2677d7694de994a1c375b65e4178befa43b29b1d49
|
3 |
size 307910149
|