Training in progress, step 2240, 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 sha256:468b4e3269f8089814276714432f3964a1cc40abbcbde0436bbe9f9c308c5869
|
| 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 sha256:279db9aeb2d90f490b27101d2ed2ebe6db713c30cd682cd12ccf8a54d1371450
|
| 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:d6a4bb9b5142d96a57f0bb169b62fc411866a04f2826764bc895ca29545b9c25
|
| 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,
|
|
@@ -4022,6 +4022,24 @@
|
|
| 4022 |
"mean_token_accuracy": 0.6576298594474792,
|
| 4023 |
"num_tokens": 8133880.0,
|
| 4024 |
"step": 2230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4025 |
}
|
| 4026 |
],
|
| 4027 |
"logging_steps": 5,
|
|
@@ -4041,7 +4059,7 @@
|
|
| 4041 |
"attributes": {}
|
| 4042 |
}
|
| 4043 |
},
|
| 4044 |
-
"total_flos": 4.
|
| 4045 |
"train_batch_size": 4,
|
| 4046 |
"trial_name": null,
|
| 4047 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4022 |
"mean_token_accuracy": 0.6576298594474792,
|
| 4023 |
"num_tokens": 8133880.0,
|
| 4024 |
"step": 2230
|
| 4025 |
+
},
|
| 4026 |
+
{
|
| 4027 |
+
"epoch": 17.192307692307693,
|
| 4028 |
+
"grad_norm": 0.0,
|
| 4029 |
+
"learning_rate": 3.883e-05,
|
| 4030 |
+
"loss": 1.78,
|
| 4031 |
+
"mean_token_accuracy": 0.6426860511302948,
|
| 4032 |
+
"num_tokens": 8151540.0,
|
| 4033 |
+
"step": 2235
|
| 4034 |
+
},
|
| 4035 |
+
{
|
| 4036 |
+
"epoch": 17.23076923076923,
|
| 4037 |
+
"grad_norm": 0.0,
|
| 4038 |
+
"learning_rate": 3.8805000000000005e-05,
|
| 4039 |
+
"loss": 1.7545,
|
| 4040 |
+
"mean_token_accuracy": 0.6476239621639251,
|
| 4041 |
+
"num_tokens": 8170218.0,
|
| 4042 |
+
"step": 2240
|
| 4043 |
}
|
| 4044 |
],
|
| 4045 |
"logging_steps": 5,
|
|
|
|
| 4059 |
"attributes": {}
|
| 4060 |
}
|
| 4061 |
},
|
| 4062 |
+
"total_flos": 4.1401281312129024e+17,
|
| 4063 |
"train_batch_size": 4,
|
| 4064 |
"trial_name": null,
|
| 4065 |
"trial_params": null
|