Training in progress, step 8390, 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 sha256:1c2c081136d87b8b710ab91600fc6562f0150ad9ada2e5dc8bd72ebe4bccbab7
|
| 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 sha256:4d82ad2062fc3068511b06b805c83e5c7b85cb0feee8da1e1f458c44438d2565
|
| 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 sha256:8bbf50c9e97fa59548309b64711c4fad4ac372db1cb5d517c620fe9001a3b3ff
|
| 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": 64.
|
| 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,
|
|
@@ -15092,6 +15092,24 @@
|
|
| 15092 |
"mean_token_accuracy": 0.649326092004776,
|
| 15093 |
"num_tokens": 30563300.0,
|
| 15094 |
"step": 8380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15095 |
}
|
| 15096 |
],
|
| 15097 |
"logging_steps": 5,
|
|
@@ -15111,7 +15129,7 @@
|
|
| 15111 |
"attributes": {}
|
| 15112 |
}
|
| 15113 |
},
|
| 15114 |
-
"total_flos": 1.
|
| 15115 |
"train_batch_size": 4,
|
| 15116 |
"trial_name": null,
|
| 15117 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15092 |
"mean_token_accuracy": 0.649326092004776,
|
| 15093 |
"num_tokens": 30563300.0,
|
| 15094 |
"step": 8380
|
| 15095 |
+
},
|
| 15096 |
+
{
|
| 15097 |
+
"epoch": 64.5,
|
| 15098 |
+
"grad_norm": 0.0,
|
| 15099 |
+
"learning_rate": 8.08e-06,
|
| 15100 |
+
"loss": 1.7657,
|
| 15101 |
+
"mean_token_accuracy": 0.6501888036727905,
|
| 15102 |
+
"num_tokens": 30581217.0,
|
| 15103 |
+
"step": 8385
|
| 15104 |
+
},
|
| 15105 |
+
{
|
| 15106 |
+
"epoch": 64.53846153846153,
|
| 15107 |
+
"grad_norm": 0.0,
|
| 15108 |
+
"learning_rate": 8.055e-06,
|
| 15109 |
+
"loss": 1.6891,
|
| 15110 |
+
"mean_token_accuracy": 0.6601796567440033,
|
| 15111 |
+
"num_tokens": 30600060.0,
|
| 15112 |
+
"step": 8390
|
| 15113 |
}
|
| 15114 |
],
|
| 15115 |
"logging_steps": 5,
|
|
|
|
| 15129 |
"attributes": {}
|
| 15130 |
}
|
| 15131 |
},
|
| 15132 |
+
"total_flos": 1.5514791479923507e+18,
|
| 15133 |
"train_batch_size": 4,
|
| 15134 |
"trial_name": null,
|
| 15135 |
"trial_params": null
|