Training in progress, step 5500
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 sha256:4e57715167d240df7fc7cf0704b4c18005230c7c2666bb66d0e804962deaab63
|
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 sha256:4a1a1af2c7b3c5ce8e8003d4e6d5fa54414094b11f77179b260f13bdc3e0a32a
|
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:de40522a13a8992c65a0d95b0b52c71178563f4f5994a4b4cd60df4488b016b9
|
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 sha256:76359f656fe33c4fedb39f8ff11bff9852c34259f4aeb2f99cd5aca99489390f
|
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 sha256:723817439dac10e06757698e0f33aaa7ad2b3a86199428682cb885b219c70200
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -196,11 +196,30 @@
|
|
196 |
"eval_samples_per_second": 53.681,
|
197 |
"eval_steps_per_second": 1.691,
|
198 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
199 |
}
|
200 |
],
|
201 |
"max_steps": 62500,
|
202 |
"num_train_epochs": 20,
|
203 |
-
"total_flos": 2.
|
204 |
"trial_name": null,
|
205 |
"trial_params": null
|
206 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7979766726493835,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-5500",
|
4 |
+
"epoch": 1.76,
|
5 |
+
"global_step": 5500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
196 |
"eval_samples_per_second": 53.681,
|
197 |
"eval_steps_per_second": 1.691,
|
198 |
"step": 5000
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.76,
|
202 |
+
"learning_rate": 0.00048002526315789475,
|
203 |
+
"loss": 0.7246,
|
204 |
+
"step": 5500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.76,
|
208 |
+
"eval_bleu": 0.06360201700239017,
|
209 |
+
"eval_exact_match": 0.096,
|
210 |
+
"eval_loss": 0.7979766726493835,
|
211 |
+
"eval_rouge1": 0.49459857323152784,
|
212 |
+
"eval_rouge2": 0.32742424566936434,
|
213 |
+
"eval_rougeL": 0.4795144854855635,
|
214 |
+
"eval_runtime": 38.3013,
|
215 |
+
"eval_samples_per_second": 52.218,
|
216 |
+
"eval_steps_per_second": 1.645,
|
217 |
+
"step": 5500
|
218 |
}
|
219 |
],
|
220 |
"max_steps": 62500,
|
221 |
"num_train_epochs": 20,
|
222 |
+
"total_flos": 2.304004691538739e+16,
|
223 |
"trial_name": null,
|
224 |
"trial_params": null
|
225 |
}
|
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 sha256:4a1a1af2c7b3c5ce8e8003d4e6d5fa54414094b11f77179b260f13bdc3e0a32a
|
3 |
size 242031355
|