Training in progress, step 7000
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:d51a8e0ca60f031b2e1ad81f4ce718e8fe99eb022207c12a0a5e0a5f0899eeff
|
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:e0e8d4866c4fa19f0fc899d5e2e17e65f2a8e5b8fc3e4e0f1f491bdc007294ea
|
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:cf197b7760a25a35d8d71ed35dfa64efae43baa6d65044890da5fa6b0dff65c9
|
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:e552adc6cc870ee6720036f9f355dc6945a3e1f8113aad45166e45da9f874f7e
|
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:ecc3acc34e8079c080a20215d0b9cc32c38a771e9e853b47e1d80472ebcf035d
|
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,
|
@@ -253,11 +253,30 @@
|
|
253 |
"eval_samples_per_second": 54.232,
|
254 |
"eval_steps_per_second": 1.708,
|
255 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
256 |
}
|
257 |
],
|
258 |
"max_steps": 62500,
|
259 |
"num_train_epochs": 20,
|
260 |
-
"total_flos": 2.
|
261 |
"trial_name": null,
|
262 |
"trial_params": null
|
263 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7700557708740234,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-7000",
|
4 |
+
"epoch": 2.24,
|
5 |
+
"global_step": 7000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
253 |
"eval_samples_per_second": 54.232,
|
254 |
"eval_steps_per_second": 1.708,
|
255 |
"step": 6500
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 2.24,
|
259 |
+
"learning_rate": 0.0004673936842105263,
|
260 |
+
"loss": 0.652,
|
261 |
+
"step": 7000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.24,
|
265 |
+
"eval_bleu": 0.06603832460136996,
|
266 |
+
"eval_exact_match": 0.0945,
|
267 |
+
"eval_loss": 0.7700557708740234,
|
268 |
+
"eval_rouge1": 0.5007155856518921,
|
269 |
+
"eval_rouge2": 0.33660838962730144,
|
270 |
+
"eval_rougeL": 0.48704095883836096,
|
271 |
+
"eval_runtime": 36.0428,
|
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": 2.930512887073997e+16,
|
280 |
"trial_name": null,
|
281 |
"trial_params": null
|
282 |
}
|
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:e0e8d4866c4fa19f0fc899d5e2e17e65f2a8e5b8fc3e4e0f1f491bdc007294ea
|
3 |
size 242031355
|