Training in progress, step 5000
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 sha256:0351257ad60c14e9b6108d1c73d0a0c6e87fd9dfb6c296fd86838bd29c763ae0
|
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 sha256:9d1a1c35745cbaf4458a34240f6d826b1bff2eb9ab17a38939536b848596829b
|
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 sha256:94dd36fe0aedc607f4d72e754454c9b6b6d248054487c59b04f2a922a571ca95
|
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:a2365d2f7d6d17d401755b5d0e71791ff68b94486ddb37364e00319aeebc6c91
|
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:dee1bb096dc897ade62a94c5c81d8abd03a8a101bf8f2cf03bb2b65a09af1b3a
|
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,
|
@@ -177,11 +177,30 @@
|
|
177 |
"eval_samples_per_second": 56.135,
|
178 |
"eval_steps_per_second": 1.768,
|
179 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
}
|
181 |
],
|
182 |
"max_steps": 62500,
|
183 |
"num_train_epochs": 20,
|
184 |
-
"total_flos":
|
185 |
"trial_name": null,
|
186 |
"trial_params": null
|
187 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8199761509895325,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-5000",
|
4 |
+
"epoch": 1.6,
|
5 |
+
"global_step": 5000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
177 |
"eval_samples_per_second": 56.135,
|
178 |
"eval_steps_per_second": 1.768,
|
179 |
"step": 4500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.6,
|
183 |
+
"learning_rate": 0.00048423578947368425,
|
184 |
+
"loss": 0.7556,
|
185 |
+
"step": 5000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.6,
|
189 |
+
"eval_bleu": 0.062181241480247514,
|
190 |
+
"eval_exact_match": 0.094,
|
191 |
+
"eval_loss": 0.8199761509895325,
|
192 |
+
"eval_rouge1": 0.49335199051744105,
|
193 |
+
"eval_rouge2": 0.3273247481525058,
|
194 |
+
"eval_rougeL": 0.47992085377826155,
|
195 |
+
"eval_runtime": 37.2571,
|
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": 2.094711283856179e+16,
|
204 |
"trial_name": null,
|
205 |
"trial_params": null
|
206 |
}
|
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 sha256:9d1a1c35745cbaf4458a34240f6d826b1bff2eb9ab17a38939536b848596829b
|
3 |
size 242031355
|