Training in progress, step 7500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +24 -5
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d48a085fd64d029c543fb164ccce121c7378d3ffb9bae603a78bdc16dc122577
|
3 |
size 484083951
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56bf833ca4393d915e9e2fefda52ba60a19c8a4a7d32b4cbb8260b144e68ed0f
|
3 |
size 242031355
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dddfbcb58a8aad0713b4f30a167c1aa037cc5d10bc01af84b8789bbcc64753d
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fccda41cf05d0c2582a5ae864ddced240b945973cac170056ad38621f56c053
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa6ad39b02b247b3eab6efb8415cb1a92c3c2962ab9b3561767114b410eda9b9
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -272,11 +272,30 @@
|
|
272 |
"eval_samples_per_second": 55.49,
|
273 |
"eval_steps_per_second": 1.748,
|
274 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
275 |
}
|
276 |
],
|
277 |
"max_steps": 62500,
|
278 |
"num_train_epochs": 20,
|
279 |
-
"total_flos":
|
280 |
"trial_name": null,
|
281 |
"trial_params": null
|
282 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7626734375953674,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-7500",
|
4 |
+
"epoch": 2.4,
|
5 |
+
"global_step": 7500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
272 |
"eval_samples_per_second": 55.49,
|
273 |
"eval_steps_per_second": 1.748,
|
274 |
"step": 7000
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 2.4,
|
278 |
+
"learning_rate": 0.0004631831578947369,
|
279 |
+
"loss": 0.6477,
|
280 |
+
"step": 7500
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 2.4,
|
284 |
+
"eval_bleu": 0.0637326815837752,
|
285 |
+
"eval_exact_match": 0.1015,
|
286 |
+
"eval_loss": 0.7626734375953674,
|
287 |
+
"eval_rouge1": 0.5067175865244784,
|
288 |
+
"eval_rouge2": 0.3418343311421686,
|
289 |
+
"eval_rougeL": 0.4932440074450731,
|
290 |
+
"eval_runtime": 36.8678,
|
291 |
+
"eval_samples_per_second": 54.248,
|
292 |
+
"eval_steps_per_second": 1.709,
|
293 |
+
"step": 7500
|
294 |
}
|
295 |
],
|
296 |
"max_steps": 62500,
|
297 |
"num_train_epochs": 20,
|
298 |
+
"total_flos": 3.1395389946986496e+16,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
301 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56bf833ca4393d915e9e2fefda52ba60a19c8a4a7d32b4cbb8260b144e68ed0f
|
3 |
size 242031355
|