Commit
•
28f3714
1
Parent(s):
13564e5
Training in progress, step 13000, 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 sha256:07394dd2da2fc8953cab465ecc516b2b637a9ad1e5f80b5e3ea2227894fa654a
|
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 sha256:78de506312ed56afb09869d301b9813ec41093ce0949b835b41413fe2335de94
|
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:d92adf6dbb6d04b5365a21d7e5c277f9e5493f67b515b76e0f0b04c6e28d7e18
|
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:efac40282b6ccc72dd2d6d02d04092dc1f619670b356e71b004fd44491288981
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7260786855980778,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-12000",
|
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,
|
@@ -235,6 +235,25 @@
|
|
235 |
"eval_samples_per_second": 87.491,
|
236 |
"eval_steps_per_second": 10.936,
|
237 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1000,
|
@@ -254,7 +273,7 @@
|
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
-
"total_flos": 1.
|
258 |
"train_batch_size": 8,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7260786855980778,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-12000",
|
4 |
+
"epoch": 1.3775564268305605,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 13000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
235 |
"eval_samples_per_second": 87.491,
|
236 |
"eval_steps_per_second": 10.936,
|
237 |
"step": 12000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.3775564268305605,
|
241 |
+
"grad_norm": 15.350415229797363,
|
242 |
+
"learning_rate": 8.668371151592628e-06,
|
243 |
+
"loss": 0.3868,
|
244 |
+
"step": 13000
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.3775564268305605,
|
248 |
+
"eval_accuracy": 0.7268356643356644,
|
249 |
+
"eval_f1": 0.7121431239588121,
|
250 |
+
"eval_loss": 0.9578595161437988,
|
251 |
+
"eval_precision": 0.7318944469113846,
|
252 |
+
"eval_recall": 0.7268356643356644,
|
253 |
+
"eval_runtime": 25.9641,
|
254 |
+
"eval_samples_per_second": 88.122,
|
255 |
+
"eval_steps_per_second": 11.015,
|
256 |
+
"step": 13000
|
257 |
}
|
258 |
],
|
259 |
"logging_steps": 1000,
|
|
|
273 |
"attributes": {}
|
274 |
}
|
275 |
},
|
276 |
+
"total_flos": 1.2625401075755184e+16,
|
277 |
"train_batch_size": 8,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|