Training in progress, step 4000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68ef2cc357e334b7cad60da13e7b18d535567433003ea00f23bd0488be410fee
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5eb9ce9c22c77903baa47a533de8ee839001407b24098aaffed6ff3d7a3e583
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1df6435006d15a8b7d09818f92631653559555b49a3ebc1947e10ab5b709bf04
|
| 3 |
size 14645
|
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 sha256:7c6234c59f9b6c21a5de476be7a0561593c0fdc52d479d1e4485dd66fe66c4a3
|
| 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": 0.
|
| 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,
|
|
@@ -4008,6 +4008,16 @@
|
|
| 4008 |
"mean_token_accuracy": 0.7698814913630485,
|
| 4009 |
"num_tokens": 18608764.0,
|
| 4010 |
"step": 3990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4011 |
}
|
| 4012 |
],
|
| 4013 |
"logging_steps": 10,
|
|
@@ -4027,7 +4037,7 @@
|
|
| 4027 |
"attributes": {}
|
| 4028 |
}
|
| 4029 |
},
|
| 4030 |
-
"total_flos": 8.
|
| 4031 |
"train_batch_size": 4,
|
| 4032 |
"trial_name": null,
|
| 4033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8533333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4008 |
"mean_token_accuracy": 0.7698814913630485,
|
| 4009 |
"num_tokens": 18608764.0,
|
| 4010 |
"step": 3990
|
| 4011 |
+
},
|
| 4012 |
+
{
|
| 4013 |
+
"entropy": 0.9310038618743419,
|
| 4014 |
+
"epoch": 0.8533333333333334,
|
| 4015 |
+
"grad_norm": 0.3000566065311432,
|
| 4016 |
+
"learning_rate": 6.431743919772218e-05,
|
| 4017 |
+
"loss": 1.0243574142456056,
|
| 4018 |
+
"mean_token_accuracy": 0.7703951939940452,
|
| 4019 |
+
"num_tokens": 18653703.0,
|
| 4020 |
+
"step": 4000
|
| 4021 |
}
|
| 4022 |
],
|
| 4023 |
"logging_steps": 10,
|
|
|
|
| 4037 |
"attributes": {}
|
| 4038 |
}
|
| 4039 |
},
|
| 4040 |
+
"total_flos": 8.832539694922138e+16,
|
| 4041 |
"train_batch_size": 4,
|
| 4042 |
"trial_name": null,
|
| 4043 |
"trial_params": null
|