Training in progress, step 8920, 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:bfb89757f1e14d502406bd882288bf9c5fa87f532db06c1a3657701876cce742
|
| 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 sha256:5600ddf875a496dfc58dd632638a1e91889a8ffbab4aff35846f35ef0814dcf4
|
| 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 sha256:4655d2a65849e8e71418f90be28163d1b3b88549943d89a51f920a71c924b911
|
| 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": 68.
|
| 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,
|
|
@@ -16046,6 +16046,24 @@
|
|
| 16046 |
"mean_token_accuracy": 0.6506960332393646,
|
| 16047 |
"num_tokens": 32493791.0,
|
| 16048 |
"step": 8910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16049 |
}
|
| 16050 |
],
|
| 16051 |
"logging_steps": 5,
|
|
@@ -16065,7 +16083,7 @@
|
|
| 16065 |
"attributes": {}
|
| 16066 |
}
|
| 16067 |
},
|
| 16068 |
-
"total_flos": 1.
|
| 16069 |
"train_batch_size": 4,
|
| 16070 |
"trial_name": null,
|
| 16071 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16046 |
"mean_token_accuracy": 0.6506960332393646,
|
| 16047 |
"num_tokens": 32493791.0,
|
| 16048 |
"step": 8910
|
| 16049 |
+
},
|
| 16050 |
+
{
|
| 16051 |
+
"epoch": 68.57692307692308,
|
| 16052 |
+
"grad_norm": 0.0,
|
| 16053 |
+
"learning_rate": 5.4300000000000005e-06,
|
| 16054 |
+
"loss": 1.7171,
|
| 16055 |
+
"mean_token_accuracy": 0.6513607323169708,
|
| 16056 |
+
"num_tokens": 32512069.0,
|
| 16057 |
+
"step": 8915
|
| 16058 |
+
},
|
| 16059 |
+
{
|
| 16060 |
+
"epoch": 68.61538461538461,
|
| 16061 |
+
"grad_norm": 0.0,
|
| 16062 |
+
"learning_rate": 5.405e-06,
|
| 16063 |
+
"loss": 1.6989,
|
| 16064 |
+
"mean_token_accuracy": 0.6555921375751496,
|
| 16065 |
+
"num_tokens": 32530853.0,
|
| 16066 |
+
"step": 8920
|
| 16067 |
}
|
| 16068 |
],
|
| 16069 |
"logging_steps": 5,
|
|
|
|
| 16083 |
"attributes": {}
|
| 16084 |
}
|
| 16085 |
},
|
| 16086 |
+
"total_flos": 1.6495852893128294e+18,
|
| 16087 |
"train_batch_size": 4,
|
| 16088 |
"trial_name": null,
|
| 16089 |
"trial_params": null
|