Training in progress, step 2730, 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:db2076909420608d50c4f681fadf4cc1750b2c11a827d83573bff57d1f5fb7dc
|
| 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 sha256:8c4514f55966c86a3b6946dbfff14d13eed77e6d0bf7066779a4e0c4f99bdfe0
|
| 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 sha256:007a879042d18a65f86a07bb0ef22b7d5900275805ddd29164a3ccdd43d418fc
|
| 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":
|
| 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,
|
|
@@ -4904,6 +4904,24 @@
|
|
| 4904 |
"mean_token_accuracy": 0.6442853361368179,
|
| 4905 |
"num_tokens": 9918308.0,
|
| 4906 |
"step": 2720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4907 |
}
|
| 4908 |
],
|
| 4909 |
"logging_steps": 5,
|
|
@@ -4923,7 +4941,7 @@
|
|
| 4923 |
"attributes": {}
|
| 4924 |
}
|
| 4925 |
},
|
| 4926 |
-
"total_flos": 5.
|
| 4927 |
"train_batch_size": 4,
|
| 4928 |
"trial_name": null,
|
| 4929 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4904 |
"mean_token_accuracy": 0.6442853361368179,
|
| 4905 |
"num_tokens": 9918308.0,
|
| 4906 |
"step": 2720
|
| 4907 |
+
},
|
| 4908 |
+
{
|
| 4909 |
+
"epoch": 20.96153846153846,
|
| 4910 |
+
"grad_norm": 0.0,
|
| 4911 |
+
"learning_rate": 3.638e-05,
|
| 4912 |
+
"loss": 1.7022,
|
| 4913 |
+
"mean_token_accuracy": 0.6568427920341492,
|
| 4914 |
+
"num_tokens": 9937402.0,
|
| 4915 |
+
"step": 2725
|
| 4916 |
+
},
|
| 4917 |
+
{
|
| 4918 |
+
"epoch": 21.0,
|
| 4919 |
+
"grad_norm": 0.0,
|
| 4920 |
+
"learning_rate": 3.6355e-05,
|
| 4921 |
+
"loss": 1.7716,
|
| 4922 |
+
"mean_token_accuracy": 0.6476004511117935,
|
| 4923 |
+
"num_tokens": 9956205.0,
|
| 4924 |
+
"step": 2730
|
| 4925 |
}
|
| 4926 |
],
|
| 4927 |
"logging_steps": 5,
|
|
|
|
| 4941 |
"attributes": {}
|
| 4942 |
}
|
| 4943 |
},
|
| 4944 |
+
"total_flos": 5.0442483457327104e+17,
|
| 4945 |
"train_batch_size": 4,
|
| 4946 |
"trial_name": null,
|
| 4947 |
"trial_params": null
|