Training in progress, step 8000
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:b91762f8e28a7b868c7178d72e87565871d662d0576d40830306bb59f4713a11
|
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:b23119849f1f62acf381d60e969982036c4a248a5151a44d14cc766289febb55
|
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 sha256:9fb317bb467a23441d7b516bac89c1d9f2112551cc47c23e9776e642c058ae08
|
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 sha256:90987bc51f8976ed310ca3515844afb8e2102daaca6b2b136bdb768c8788e7ee
|
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 sha256:61fdfaacb99365fd62b344859a701500b79fb903e45f80d8ff64702ae0c1523a
|
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,
|
@@ -291,11 +291,30 @@
|
|
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.
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
301 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7461714148521423,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-8000",
|
4 |
+
"epoch": 2.56,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
291 |
"eval_samples_per_second": 54.248,
|
292 |
"eval_steps_per_second": 1.709,
|
293 |
"step": 7500
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 2.56,
|
297 |
+
"learning_rate": 0.0004589726315789474,
|
298 |
+
"loss": 0.6337,
|
299 |
+
"step": 8000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 2.56,
|
303 |
+
"eval_bleu": 0.06513339878553655,
|
304 |
+
"eval_exact_match": 0.1015,
|
305 |
+
"eval_loss": 0.7461714148521423,
|
306 |
+
"eval_rouge1": 0.4982517321430179,
|
307 |
+
"eval_rouge2": 0.33681326926227717,
|
308 |
+
"eval_rougeL": 0.4849838232405096,
|
309 |
+
"eval_runtime": 36.8056,
|
310 |
+
"eval_samples_per_second": 54.34,
|
311 |
+
"eval_steps_per_second": 1.712,
|
312 |
+
"step": 8000
|
313 |
}
|
314 |
],
|
315 |
"max_steps": 62500,
|
316 |
"num_train_epochs": 20,
|
317 |
+
"total_flos": 3.348965206523904e+16,
|
318 |
"trial_name": null,
|
319 |
"trial_params": null
|
320 |
}
|
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:b23119849f1f62acf381d60e969982036c4a248a5151a44d14cc766289febb55
|
3 |
size 242031355
|