Training in progress, step 20, 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 sha256:105a2929b7f625833a1e1ee9dfda0bd93c28af9790d71f49f81c8540d2c781c9
|
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 sha256:3f702dd588a5bba2ade46677a34077e2e3708d3a72875526a7df953d4d028660
|
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 sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
|
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,
|
@@ -213,6 +213,28 @@
|
|
213 |
"eval_samples_per_second": 4.117,
|
214 |
"eval_steps_per_second": 4.117,
|
215 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
@@ -232,7 +254,7 @@
|
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
-
"total_flos": 1.
|
236 |
"train_batch_size": 1,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0006261691752569251,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
213 |
"eval_samples_per_second": 4.117,
|
214 |
"eval_steps_per_second": 4.117,
|
215 |
"step": 18
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.0005948607164940788,
|
219 |
+
"grad_norm": NaN,
|
220 |
+
"learning_rate": 6.909830056250527e-05,
|
221 |
+
"loss": 0.0,
|
222 |
+
"step": 19
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.0006261691752569251,
|
226 |
+
"grad_norm": NaN,
|
227 |
+
"learning_rate": 5.000000000000002e-05,
|
228 |
+
"loss": 0.0,
|
229 |
+
"step": 20
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.0006261691752569251,
|
233 |
+
"eval_loss": NaN,
|
234 |
+
"eval_runtime": 3211.5506,
|
235 |
+
"eval_samples_per_second": 4.188,
|
236 |
+
"eval_steps_per_second": 4.188,
|
237 |
+
"step": 20
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1,
|
|
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
+
"total_flos": 1.406258997362688e+16,
|
258 |
"train_batch_size": 1,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|