Training in progress, step 9560, 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 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fca82be9aa195e4d80e2ce5223fb810dafd59bdf1e2a5c0c6a1a73bb25cbe288
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:865dc2ab6409439be98f23644101de7fe6a7cfd77f8ecf2b662349a445dc4a5e
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5b2a5f47b73a559247ebe53615c6b1a11a73eeff7258fafb2db1248b260cd46
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 73.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -17198,6 +17198,24 @@
|
|
| 17198 |
"mean_token_accuracy": 0.639983183145523,
|
| 17199 |
"num_tokens": 34826362.0,
|
| 17200 |
"step": 9550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17201 |
}
|
| 17202 |
],
|
| 17203 |
"logging_steps": 5,
|
|
@@ -17217,7 +17235,7 @@
|
|
| 17217 |
"attributes": {}
|
| 17218 |
}
|
| 17219 |
},
|
| 17220 |
-
"total_flos": 1.
|
| 17221 |
"train_batch_size": 4,
|
| 17222 |
"trial_name": null,
|
| 17223 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17198 |
"mean_token_accuracy": 0.639983183145523,
|
| 17199 |
"num_tokens": 34826362.0,
|
| 17200 |
"step": 9550
|
| 17201 |
+
},
|
| 17202 |
+
{
|
| 17203 |
+
"epoch": 73.5,
|
| 17204 |
+
"grad_norm": 0.0,
|
| 17205 |
+
"learning_rate": 2.2300000000000002e-06,
|
| 17206 |
+
"loss": 1.7264,
|
| 17207 |
+
"mean_token_accuracy": 0.6542590230703353,
|
| 17208 |
+
"num_tokens": 34844689.0,
|
| 17209 |
+
"step": 9555
|
| 17210 |
+
},
|
| 17211 |
+
{
|
| 17212 |
+
"epoch": 73.53846153846153,
|
| 17213 |
+
"grad_norm": 0.0,
|
| 17214 |
+
"learning_rate": 2.205e-06,
|
| 17215 |
+
"loss": 1.7352,
|
| 17216 |
+
"mean_token_accuracy": 0.6505734384059906,
|
| 17217 |
+
"num_tokens": 34863598.0,
|
| 17218 |
+
"step": 9560
|
| 17219 |
}
|
| 17220 |
],
|
| 17221 |
"logging_steps": 5,
|
|
|
|
| 17235 |
"attributes": {}
|
| 17236 |
}
|
| 17237 |
},
|
| 17238 |
+
"total_flos": 1.7679530787058483e+18,
|
| 17239 |
"train_batch_size": 4,
|
| 17240 |
"trial_name": null,
|
| 17241 |
"trial_params": null
|