Training in progress, step 4030, 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 sha256:5004d0bc93011547e83654b1c8f6c7b6535bd4d62c24d732cc7286818d9693f4
|
| 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 sha256:7861e3cc681453b7a4a1e1ad71f116fec6a8f92bb77e7f69183c0f03c973eb88
|
| 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 sha256:259c5997cebf870a574a43bff1049fed89f339c79d109681ac73f61f763535c5
|
| 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:fd08e6b9696c3aa35942d342712abd2cec1915bac86a882f56ef1aa7001dddf2
|
| 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,
|
|
@@ -4038,6 +4038,16 @@
|
|
| 4038 |
"mean_token_accuracy": 0.7677365422248841,
|
| 4039 |
"num_tokens": 18749563.0,
|
| 4040 |
"step": 4020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4041 |
}
|
| 4042 |
],
|
| 4043 |
"logging_steps": 10,
|
|
@@ -4057,7 +4067,7 @@
|
|
| 4057 |
"attributes": {}
|
| 4058 |
}
|
| 4059 |
},
|
| 4060 |
-
"total_flos": 8.
|
| 4061 |
"train_batch_size": 4,
|
| 4062 |
"trial_name": null,
|
| 4063 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8597333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4038 |
"mean_token_accuracy": 0.7677365422248841,
|
| 4039 |
"num_tokens": 18749563.0,
|
| 4040 |
"step": 4020
|
| 4041 |
+
},
|
| 4042 |
+
{
|
| 4043 |
+
"entropy": 0.9408772967755794,
|
| 4044 |
+
"epoch": 0.8597333333333333,
|
| 4045 |
+
"grad_norm": 0.215755894780159,
|
| 4046 |
+
"learning_rate": 6.381920376318951e-05,
|
| 4047 |
+
"loss": 1.0272337913513183,
|
| 4048 |
+
"mean_token_accuracy": 0.7659091472625732,
|
| 4049 |
+
"num_tokens": 18793365.0,
|
| 4050 |
+
"step": 4030
|
| 4051 |
}
|
| 4052 |
],
|
| 4053 |
"logging_steps": 10,
|
|
|
|
| 4067 |
"attributes": {}
|
| 4068 |
}
|
| 4069 |
},
|
| 4070 |
+
"total_flos": 8.898411948980122e+16,
|
| 4071 |
"train_batch_size": 4,
|
| 4072 |
"trial_name": null,
|
| 4073 |
"trial_params": null
|