Training in progress, step 3250, 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 sha256:35ee12f8da9dbda3540418bc409eb6a5b0067065f094e856430f475c18c66ad2
|
| 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 sha256:2f7d77e1d7545ff995d4cf28223231b15e559e65a9591d4285a3f4270c414cca
|
| 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 sha256:3b5f6079ff171599b3cf397f776f4e420ebfbe3392bf64d0a12bb8b84aece43c
|
| 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,
|
|
@@ -5840,6 +5840,24 @@
|
|
| 5840 |
"mean_token_accuracy": 0.6732263565063477,
|
| 5841 |
"num_tokens": 11816590.0,
|
| 5842 |
"step": 3240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5843 |
}
|
| 5844 |
],
|
| 5845 |
"logging_steps": 5,
|
|
@@ -5859,7 +5877,7 @@
|
|
| 5859 |
"attributes": {}
|
| 5860 |
}
|
| 5861 |
},
|
| 5862 |
-
"total_flos":
|
| 5863 |
"train_batch_size": 4,
|
| 5864 |
"trial_name": null,
|
| 5865 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5840 |
"mean_token_accuracy": 0.6732263565063477,
|
| 5841 |
"num_tokens": 11816590.0,
|
| 5842 |
"step": 3240
|
| 5843 |
+
},
|
| 5844 |
+
{
|
| 5845 |
+
"epoch": 24.96153846153846,
|
| 5846 |
+
"grad_norm": 0.0,
|
| 5847 |
+
"learning_rate": 3.378e-05,
|
| 5848 |
+
"loss": 1.8309,
|
| 5849 |
+
"mean_token_accuracy": 0.634924265742302,
|
| 5850 |
+
"num_tokens": 11833413.0,
|
| 5851 |
+
"step": 3245
|
| 5852 |
+
},
|
| 5853 |
+
{
|
| 5854 |
+
"epoch": 25.0,
|
| 5855 |
+
"grad_norm": 0.0,
|
| 5856 |
+
"learning_rate": 3.3755000000000005e-05,
|
| 5857 |
+
"loss": 1.6911,
|
| 5858 |
+
"mean_token_accuracy": 0.6547602891921998,
|
| 5859 |
+
"num_tokens": 11852625.0,
|
| 5860 |
+
"step": 3250
|
| 5861 |
}
|
| 5862 |
],
|
| 5863 |
"logging_steps": 5,
|
|
|
|
| 5877 |
"attributes": {}
|
| 5878 |
}
|
| 5879 |
},
|
| 5880 |
+
"total_flos": 6.005495709278208e+17,
|
| 5881 |
"train_batch_size": 4,
|
| 5882 |
"trial_name": null,
|
| 5883 |
"trial_params": null
|