Training in progress, step 2230, 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 sha256:0915f2a8c2314b9fbd2c78420b5c7783d40a625c7fdd286d7e1ad35cf2e21fff
|
| 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 sha256:1d92aed2a96950ba2222a9c391f229a382f675917d7264bbf65fe86a8e2e5c40
|
| 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 sha256:2eca3602386470a7240cd0da711f0d13b2b006f405c7935fca93762bd46f5d91
|
| 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": 17.
|
| 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,
|
|
@@ -4004,6 +4004,24 @@
|
|
| 4004 |
"mean_token_accuracy": 0.6510017067193985,
|
| 4005 |
"num_tokens": 8096780.0,
|
| 4006 |
"step": 2220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4007 |
}
|
| 4008 |
],
|
| 4009 |
"logging_steps": 5,
|
|
@@ -4023,7 +4041,7 @@
|
|
| 4023 |
"attributes": {}
|
| 4024 |
}
|
| 4025 |
},
|
| 4026 |
-
"total_flos": 4.
|
| 4027 |
"train_batch_size": 4,
|
| 4028 |
"trial_name": null,
|
| 4029 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4004 |
"mean_token_accuracy": 0.6510017067193985,
|
| 4005 |
"num_tokens": 8096780.0,
|
| 4006 |
"step": 2220
|
| 4007 |
+
},
|
| 4008 |
+
{
|
| 4009 |
+
"epoch": 17.115384615384617,
|
| 4010 |
+
"grad_norm": 0.0,
|
| 4011 |
+
"learning_rate": 3.888e-05,
|
| 4012 |
+
"loss": 1.7209,
|
| 4013 |
+
"mean_token_accuracy": 0.6596309930086136,
|
| 4014 |
+
"num_tokens": 8114668.0,
|
| 4015 |
+
"step": 2225
|
| 4016 |
+
},
|
| 4017 |
+
{
|
| 4018 |
+
"epoch": 17.153846153846153,
|
| 4019 |
+
"grad_norm": 0.0,
|
| 4020 |
+
"learning_rate": 3.8855e-05,
|
| 4021 |
+
"loss": 1.6939,
|
| 4022 |
+
"mean_token_accuracy": 0.6576298594474792,
|
| 4023 |
+
"num_tokens": 8133880.0,
|
| 4024 |
+
"step": 2230
|
| 4025 |
}
|
| 4026 |
],
|
| 4027 |
"logging_steps": 5,
|
|
|
|
| 4041 |
"attributes": {}
|
| 4042 |
}
|
| 4043 |
},
|
| 4044 |
+
"total_flos": 4.1222416603889664e+17,
|
| 4045 |
"train_batch_size": 4,
|
| 4046 |
"trial_name": null,
|
| 4047 |
"trial_params": null
|