Training in progress, step 2740, 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:d39934a8d0f2f6052e2497570ea3313de015656800a2a2e58bd0e3305a780c11
|
| 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 sha256:89c77db542627f864675f5dd6ea458dcdba0377273f9f8134ec267e11f8fc095
|
| 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 sha256:52e8efb7c93f2ccb1ae4e7b68875a1569ca7626a5f5cf5cd95012f63c7825ee5
|
| 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": 21.
|
| 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,
|
|
@@ -4922,6 +4922,24 @@
|
|
| 4922 |
"mean_token_accuracy": 0.6476004511117935,
|
| 4923 |
"num_tokens": 9956205.0,
|
| 4924 |
"step": 2730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4925 |
}
|
| 4926 |
],
|
| 4927 |
"logging_steps": 5,
|
|
@@ -4941,7 +4959,7 @@
|
|
| 4941 |
"attributes": {}
|
| 4942 |
}
|
| 4943 |
},
|
| 4944 |
-
"total_flos": 5.
|
| 4945 |
"train_batch_size": 4,
|
| 4946 |
"trial_name": null,
|
| 4947 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4922 |
"mean_token_accuracy": 0.6476004511117935,
|
| 4923 |
"num_tokens": 9956205.0,
|
| 4924 |
"step": 2730
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 21.03846153846154,
|
| 4928 |
+
"grad_norm": 0.0,
|
| 4929 |
+
"learning_rate": 3.6330000000000006e-05,
|
| 4930 |
+
"loss": 1.7709,
|
| 4931 |
+
"mean_token_accuracy": 0.6501421749591827,
|
| 4932 |
+
"num_tokens": 9973863.0,
|
| 4933 |
+
"step": 2735
|
| 4934 |
+
},
|
| 4935 |
+
{
|
| 4936 |
+
"epoch": 21.076923076923077,
|
| 4937 |
+
"grad_norm": 0.0,
|
| 4938 |
+
"learning_rate": 3.6305e-05,
|
| 4939 |
+
"loss": 1.7418,
|
| 4940 |
+
"mean_token_accuracy": 0.6446869194507598,
|
| 4941 |
+
"num_tokens": 9991767.0,
|
| 4942 |
+
"step": 2740
|
| 4943 |
}
|
| 4944 |
],
|
| 4945 |
"logging_steps": 5,
|
|
|
|
| 4959 |
"attributes": {}
|
| 4960 |
}
|
| 4961 |
},
|
| 4962 |
+
"total_flos": 5.0626587877392384e+17,
|
| 4963 |
"train_batch_size": 4,
|
| 4964 |
"trial_name": null,
|
| 4965 |
"trial_params": null
|