Training in progress, step 2000, 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 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b35451dd7360715ae863af7120dda5d7fc2bbd626c9fb758684acaa3cd6f788
|
3 |
size 160285149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:038e0e9b03dce20f31830a28ed6c6c117e9aaccbaa8a7bf8a3350824f2df080e
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5200b825cc4dc17aebed9fc4560364bf9274ccd027923f8a91cf4235243813c
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -254,13 +254,26 @@
|
|
254 |
"eval_samples_per_second": 1.904,
|
255 |
"eval_steps_per_second": 0.239,
|
256 |
"step": 1900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
257 |
}
|
258 |
],
|
259 |
"logging_steps": 100,
|
260 |
"max_steps": 2025,
|
261 |
"num_train_epochs": 3,
|
262 |
"save_steps": 100,
|
263 |
-
"total_flos":
|
264 |
"trial_name": null,
|
265 |
"trial_params": null
|
266 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.962962962962963,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
254 |
"eval_samples_per_second": 1.904,
|
255 |
"eval_steps_per_second": 0.239,
|
256 |
"step": 1900
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.96,
|
260 |
+
"learning_rate": 0.0,
|
261 |
+
"loss": 8.5097,
|
262 |
+
"step": 2000
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 2.96,
|
266 |
+
"eval_runtime": 786.5132,
|
267 |
+
"eval_samples_per_second": 1.907,
|
268 |
+
"eval_steps_per_second": 0.239,
|
269 |
+
"step": 2000
|
270 |
}
|
271 |
],
|
272 |
"logging_steps": 100,
|
273 |
"max_steps": 2025,
|
274 |
"num_train_epochs": 3,
|
275 |
"save_steps": 100,
|
276 |
+
"total_flos": 4.1648079765504e+17,
|
277 |
"trial_name": null,
|
278 |
"trial_params": null
|
279 |
}
|