Training in progress, step 22, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b1620b372b059d1acf1d8d8f8e7ed129fd3d08d3555671a805512a5f946e36c
|
3 |
size 335922386
|
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 sha256:6f70c56bbf1df2389440cc9d92d46fa3ba9afcb52998f573ea87fd1fd3118270
|
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 sha256:23b9d3742ef16544005722539fe9914bac40273bcf4801b3134df389839d2871
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -235,6 +235,28 @@
|
|
235 |
"eval_samples_per_second": 4.188,
|
236 |
"eval_steps_per_second": 4.188,
|
237 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1,
|
@@ -254,7 +276,7 @@
|
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
-
"total_flos": 1.
|
258 |
"train_batch_size": 1,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0006887860927826176,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 22,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
235 |
"eval_samples_per_second": 4.188,
|
236 |
"eval_steps_per_second": 4.188,
|
237 |
"step": 20
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.0006574776340197713,
|
241 |
+
"grad_norm": NaN,
|
242 |
+
"learning_rate": 3.308693936411421e-05,
|
243 |
+
"loss": 0.0,
|
244 |
+
"step": 21
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.0006887860927826176,
|
248 |
+
"grad_norm": NaN,
|
249 |
+
"learning_rate": 1.9098300562505266e-05,
|
250 |
+
"loss": 0.0,
|
251 |
+
"step": 22
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.0006887860927826176,
|
255 |
+
"eval_loss": NaN,
|
256 |
+
"eval_runtime": 3316.0191,
|
257 |
+
"eval_samples_per_second": 4.056,
|
258 |
+
"eval_steps_per_second": 4.056,
|
259 |
+
"step": 22
|
260 |
}
|
261 |
],
|
262 |
"logging_steps": 1,
|
|
|
276 |
"attributes": {}
|
277 |
}
|
278 |
},
|
279 |
+
"total_flos": 1.5468848970989568e+16,
|
280 |
"train_batch_size": 1,
|
281 |
"trial_name": null,
|
282 |
"trial_params": null
|