Training in progress, step 2060, 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 sha256:91bb3770d253b1a24bad7741fddee6dc5b4f40846e40b7e40278ed99b37a8bfa
|
| 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 sha256:8fc32d45c2881816c9c3ac1b828ed2821c49751cd59e80405407443dbae93fa9
|
| 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 sha256:92f264adc34fc7515262c2ee598436495113a5f616c855380ef9662306d6c453
|
| 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 sha256:06e3174d1cda2eaa851aca799d52a3fb5daa9a31a0deff161ae38844159690f0
|
| 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,
|
|
@@ -2068,6 +2068,16 @@
|
|
| 2068 |
"mean_token_accuracy": 0.7708889573812485,
|
| 2069 |
"num_tokens": 9498718.0,
|
| 2070 |
"step": 2050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2071 |
}
|
| 2072 |
],
|
| 2073 |
"logging_steps": 10,
|
|
@@ -2087,7 +2097,7 @@
|
|
| 2087 |
"attributes": {}
|
| 2088 |
}
|
| 2089 |
},
|
| 2090 |
-
"total_flos": 4.
|
| 2091 |
"train_batch_size": 4,
|
| 2092 |
"trial_name": null,
|
| 2093 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.43946666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2068 |
"mean_token_accuracy": 0.7708889573812485,
|
| 2069 |
"num_tokens": 9498718.0,
|
| 2070 |
"step": 2050
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"entropy": 0.9274381674826145,
|
| 2074 |
+
"epoch": 0.43946666666666667,
|
| 2075 |
+
"grad_norm": 0.29058581590652466,
|
| 2076 |
+
"learning_rate": 9.101487609049181e-05,
|
| 2077 |
+
"loss": 0.9976702690124511,
|
| 2078 |
+
"mean_token_accuracy": 0.7693670354783535,
|
| 2079 |
+
"num_tokens": 9537791.0,
|
| 2080 |
+
"step": 2060
|
| 2081 |
}
|
| 2082 |
],
|
| 2083 |
"logging_steps": 10,
|
|
|
|
| 2097 |
"attributes": {}
|
| 2098 |
}
|
| 2099 |
},
|
| 2100 |
+
"total_flos": 4.527589856418816e+16,
|
| 2101 |
"train_batch_size": 4,
|
| 2102 |
"trial_name": null,
|
| 2103 |
"trial_params": null
|