Training in progress, step 7830, 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 sha256:645508c48f9b2fc61cad4a9b35c08a2a0096e6cf8100084d8dca02829b1061cd
|
| 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 sha256:0f951d7d5d5dd02e5e9228f4448d5f7ca6fe0cbc5b5565d412827e1c395566cb
|
| 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 sha256:11de61b692573554948db20d0fbb10f6ec456f29180e1aaa1b7b538fe4de94f7
|
| 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": 60.
|
| 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,
|
|
@@ -14084,6 +14084,24 @@
|
|
| 14084 |
"mean_token_accuracy": 0.635945051908493,
|
| 14085 |
"num_tokens": 28517958.0,
|
| 14086 |
"step": 7820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14087 |
}
|
| 14088 |
],
|
| 14089 |
"logging_steps": 5,
|
|
@@ -14103,7 +14121,7 @@
|
|
| 14103 |
"attributes": {}
|
| 14104 |
}
|
| 14105 |
},
|
| 14106 |
-
"total_flos": 1.
|
| 14107 |
"train_batch_size": 4,
|
| 14108 |
"trial_name": null,
|
| 14109 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14084 |
"mean_token_accuracy": 0.635945051908493,
|
| 14085 |
"num_tokens": 28517958.0,
|
| 14086 |
"step": 7820
|
| 14087 |
+
},
|
| 14088 |
+
{
|
| 14089 |
+
"epoch": 60.19230769230769,
|
| 14090 |
+
"grad_norm": 0.0,
|
| 14091 |
+
"learning_rate": 1.088e-05,
|
| 14092 |
+
"loss": 1.7217,
|
| 14093 |
+
"mean_token_accuracy": 0.6568192034959793,
|
| 14094 |
+
"num_tokens": 28536147.0,
|
| 14095 |
+
"step": 7825
|
| 14096 |
+
},
|
| 14097 |
+
{
|
| 14098 |
+
"epoch": 60.23076923076923,
|
| 14099 |
+
"grad_norm": 0.0,
|
| 14100 |
+
"learning_rate": 1.0855e-05,
|
| 14101 |
+
"loss": 1.7808,
|
| 14102 |
+
"mean_token_accuracy": 0.6401394218206405,
|
| 14103 |
+
"num_tokens": 28554578.0,
|
| 14104 |
+
"step": 7830
|
| 14105 |
}
|
| 14106 |
],
|
| 14107 |
"logging_steps": 5,
|
|
|
|
| 14121 |
"attributes": {}
|
| 14122 |
}
|
| 14123 |
},
|
| 14124 |
+
"total_flos": 1.447872579487826e+18,
|
| 14125 |
"train_batch_size": 4,
|
| 14126 |
"trial_name": null,
|
| 14127 |
"trial_params": null
|