Training in progress, step 5670, 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 sha256:3aca3a2e2d86c8cf28182cde0ca00f874676368626262b3353d9fbbc9f0c9495
|
| 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 sha256:8309d2aae453eb18d7f9aec58de03cf3cffe0bbff9351aaa0158858871f1eff1
|
| 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 sha256:0c975f40da5c023e851cdcd37983a352fecc4f8ab9aa388c96361cc92803c4f4
|
| 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": 43.
|
| 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,
|
|
@@ -10196,6 +10196,24 @@
|
|
| 10196 |
"mean_token_accuracy": 0.6583232104778289,
|
| 10197 |
"num_tokens": 20644265.0,
|
| 10198 |
"step": 5660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10199 |
}
|
| 10200 |
],
|
| 10201 |
"logging_steps": 5,
|
|
@@ -10215,7 +10233,7 @@
|
|
| 10215 |
"attributes": {}
|
| 10216 |
}
|
| 10217 |
},
|
| 10218 |
-
"total_flos": 1.
|
| 10219 |
"train_batch_size": 4,
|
| 10220 |
"trial_name": null,
|
| 10221 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10196 |
"mean_token_accuracy": 0.6583232104778289,
|
| 10197 |
"num_tokens": 20644265.0,
|
| 10198 |
"step": 5660
|
| 10199 |
+
},
|
| 10200 |
+
{
|
| 10201 |
+
"epoch": 43.57692307692308,
|
| 10202 |
+
"grad_norm": 0.0,
|
| 10203 |
+
"learning_rate": 2.168e-05,
|
| 10204 |
+
"loss": 1.7284,
|
| 10205 |
+
"mean_token_accuracy": 0.6528914481401443,
|
| 10206 |
+
"num_tokens": 20662528.0,
|
| 10207 |
+
"step": 5665
|
| 10208 |
+
},
|
| 10209 |
+
{
|
| 10210 |
+
"epoch": 43.61538461538461,
|
| 10211 |
+
"grad_norm": 0.0,
|
| 10212 |
+
"learning_rate": 2.1655000000000002e-05,
|
| 10213 |
+
"loss": 1.6837,
|
| 10214 |
+
"mean_token_accuracy": 0.6582222819328308,
|
| 10215 |
+
"num_tokens": 20681100.0,
|
| 10216 |
+
"step": 5670
|
| 10217 |
}
|
| 10218 |
],
|
| 10219 |
"logging_steps": 5,
|
|
|
|
| 10233 |
"attributes": {}
|
| 10234 |
}
|
| 10235 |
},
|
| 10236 |
+
"total_flos": 1.0481197214903501e+18,
|
| 10237 |
"train_batch_size": 4,
|
| 10238 |
"trial_name": null,
|
| 10239 |
"trial_params": null
|