Francesco0101
commited on
Commit
•
a2cd5cf
1
Parent(s):
03df576
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 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c808475ef21e058693edab788f7732c8f7e68bf5cafca868b958716451ec0144
|
3 |
size 498615900
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997351674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1aedc6950d3b3fb19b031a9167a1fade50d5dce31f54cb161dfaeb26e0e1e31
|
3 |
size 997351674
|
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 sha256:052183e50b1b5ae1798367b38b1751bac816715b41cae2d732d506663586f370
|
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": 0.7624731472235634,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-6000",
|
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": 48.153,
|
179 |
"eval_steps_per_second": 6.019,
|
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": 0.7624731472235634,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-6000",
|
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": 48.153,
|
179 |
"eval_steps_per_second": 6.019,
|
180 |
"step": 9000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.5659254619480114,
|
184 |
+
"grad_norm": 5.539546489715576,
|
185 |
+
"learning_rate": 8.500631313131314e-06,
|
186 |
+
"loss": 0.401,
|
187 |
+
"step": 10000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 1.5659254619480114,
|
191 |
+
"eval_accuracy": 0.7622377622377622,
|
192 |
+
"eval_f1": 0.7562280560821415,
|
193 |
+
"eval_loss": 0.951400876045227,
|
194 |
+
"eval_precision": 0.760121427774359,
|
195 |
+
"eval_recall": 0.7622377622377622,
|
196 |
+
"eval_runtime": 47.6294,
|
197 |
+
"eval_samples_per_second": 48.038,
|
198 |
+
"eval_steps_per_second": 6.005,
|
199 |
+
"step": 10000
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 1000,
|
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
+
"total_flos": 2.0475444028334652e+16,
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|