Commit
•
bd66d88
1
Parent(s):
5d2b5dc
Training in progress, step 11000, 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 sha256:6c6bc66d4b06be01722ead53718cdb38f760258e27b606dda260284c694f6516
|
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 sha256:0d7efed836b0a7a09c864c26b9572f9547494689160dc13e5d77f14817033216
|
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:ae59f0f934189fcaa1a1041dd640da3c651fe2389123125ddf12471b0819bde8
|
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:e82a21c3091e4958c484cdc7bf981ac78cd588dced7632b6352c65dac794dad2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7187402398550484,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-10000",
|
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,
|
@@ -197,6 +197,25 @@
|
|
197 |
"eval_samples_per_second": 87.848,
|
198 |
"eval_steps_per_second": 10.981,
|
199 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 1000,
|
@@ -216,7 +235,7 @@
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
-
"total_flos":
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7187402398550484,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-10000",
|
4 |
+
"epoch": 1.165624668856628,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 11000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
197 |
"eval_samples_per_second": 87.848,
|
198 |
"eval_steps_per_second": 10.981,
|
199 |
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 1.165624668856628,
|
203 |
+
"grad_norm": 5.598655700683594,
|
204 |
+
"learning_rate": 8.881431767337809e-06,
|
205 |
+
"loss": 0.3778,
|
206 |
+
"step": 11000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.165624668856628,
|
210 |
+
"eval_accuracy": 0.7202797202797203,
|
211 |
+
"eval_f1": 0.7064609677451916,
|
212 |
+
"eval_loss": 1.072676420211792,
|
213 |
+
"eval_precision": 0.7267989053042323,
|
214 |
+
"eval_recall": 0.7202797202797203,
|
215 |
+
"eval_runtime": 26.0924,
|
216 |
+
"eval_samples_per_second": 87.688,
|
217 |
+
"eval_steps_per_second": 10.961,
|
218 |
+
"step": 11000
|
219 |
}
|
220 |
],
|
221 |
"logging_steps": 1000,
|
|
|
235 |
"attributes": {}
|
236 |
}
|
237 |
},
|
238 |
+
"total_flos": 1.0678923524708784e+16,
|
239 |
"train_batch_size": 8,
|
240 |
"trial_name": null,
|
241 |
"trial_params": null
|