Commit
•
80576b8
1
Parent(s):
9031a95
Training in progress, step 10000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf9880d96a86df526af2581930438d89880e300ecdc4bef1a55d85f888f89073
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1772e3c93bae9f3496c8b26bc91c354020c3df87ce73758f9047a700a19f43a7
|
3 |
size 535733434
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:405962457206f8e1fb8df318cb7d0e755c7b9e0fa0fe32525b189f837ff53cb7
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8409b85759d90925b91547cef68cf8d92d7246de5d32ea5c6e2cb9cb720fc23
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -178,6 +178,25 @@
|
|
178 |
"eval_samples_per_second": 75.707,
|
179 |
"eval_steps_per_second": 9.463,
|
180 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
}
|
182 |
],
|
183 |
"logging_steps": 1000,
|
@@ -197,7 +216,7 @@
|
|
197 |
"attributes": {}
|
198 |
}
|
199 |
},
|
200 |
-
"total_flos":
|
201 |
"train_batch_size": 8,
|
202 |
"trial_name": null,
|
203 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7351907898564811,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-10000",
|
4 |
+
"epoch": 1.5659254619480114,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 10000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
178 |
"eval_samples_per_second": 75.707,
|
179 |
"eval_steps_per_second": 9.463,
|
180 |
"step": 9000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.5659254619480114,
|
184 |
+
"grad_norm": 9.159900665283203,
|
185 |
+
"learning_rate": 8.500631313131314e-06,
|
186 |
+
"loss": 0.3932,
|
187 |
+
"step": 10000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 1.5659254619480114,
|
191 |
+
"eval_accuracy": 0.7443181818181818,
|
192 |
+
"eval_f1": 0.7351907898564811,
|
193 |
+
"eval_loss": 0.9013388156890869,
|
194 |
+
"eval_precision": 0.7458339781734145,
|
195 |
+
"eval_recall": 0.7443181818181818,
|
196 |
+
"eval_runtime": 29.7576,
|
197 |
+
"eval_samples_per_second": 76.888,
|
198 |
+
"eval_steps_per_second": 9.611,
|
199 |
+
"step": 10000
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 1000,
|
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
+
"total_flos": 1.0072339831839852e+16,
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|