Training in progress, step 5630, 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:a46a1fdd2f9ee61b3ab120d59619c2336102630f4f74d161c99a3441a93e3d9b
|
| 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 sha256:66635de7f2ebeb576c1857564723b8913c83f6a666aefbed0393654ba045edf4
|
| 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 sha256:76e70d5f14dcbf0b1555cbf4f9a2eccf485653d6ca9adea1f2dd808c368136a8
|
| 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,
|
|
@@ -10124,6 +10124,24 @@
|
|
| 10124 |
"mean_token_accuracy": 0.650734207034111,
|
| 10125 |
"num_tokens": 20497721.0,
|
| 10126 |
"step": 5620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10127 |
}
|
| 10128 |
],
|
| 10129 |
"logging_steps": 5,
|
|
@@ -10143,7 +10161,7 @@
|
|
| 10143 |
"attributes": {}
|
| 10144 |
}
|
| 10145 |
},
|
| 10146 |
-
"total_flos": 1.
|
| 10147 |
"train_batch_size": 4,
|
| 10148 |
"trial_name": null,
|
| 10149 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10124 |
"mean_token_accuracy": 0.650734207034111,
|
| 10125 |
"num_tokens": 20497721.0,
|
| 10126 |
"step": 5620
|
| 10127 |
+
},
|
| 10128 |
+
{
|
| 10129 |
+
"epoch": 43.26923076923077,
|
| 10130 |
+
"grad_norm": 0.0,
|
| 10131 |
+
"learning_rate": 2.188e-05,
|
| 10132 |
+
"loss": 1.7549,
|
| 10133 |
+
"mean_token_accuracy": 0.6470336526632309,
|
| 10134 |
+
"num_tokens": 20515794.0,
|
| 10135 |
+
"step": 5625
|
| 10136 |
+
},
|
| 10137 |
+
{
|
| 10138 |
+
"epoch": 43.30769230769231,
|
| 10139 |
+
"grad_norm": 0.0,
|
| 10140 |
+
"learning_rate": 2.1855e-05,
|
| 10141 |
+
"loss": 1.7582,
|
| 10142 |
+
"mean_token_accuracy": 0.6463449627161026,
|
| 10143 |
+
"num_tokens": 20533916.0,
|
| 10144 |
+
"step": 5630
|
| 10145 |
}
|
| 10146 |
],
|
| 10147 |
"logging_steps": 5,
|
|
|
|
| 10161 |
"attributes": {}
|
| 10162 |
}
|
| 10163 |
},
|
| 10164 |
+
"total_flos": 1.0405712020989542e+18,
|
| 10165 |
"train_batch_size": 4,
|
| 10166 |
"trial_name": null,
|
| 10167 |
"trial_params": null
|