Training in progress, step 1140, 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 sha256:9be267a67600aea3a6d3be4f8c85362c6221204d041fed91b204fdd77a1b62cf
|
| 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:e745df8177e06decd39f24f4a4bc2e0f793e29a9230943c5ba10152af920c963
|
| 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:e3d18227dc036148b28f9c97ce2cd3953574e0cf85880e1b984083e1c05a67c2
|
| 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": 8.
|
| 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,
|
|
@@ -2042,6 +2042,24 @@
|
|
| 2042 |
"mean_token_accuracy": 0.6499712377786636,
|
| 2043 |
"num_tokens": 4120160.0,
|
| 2044 |
"step": 1130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2045 |
}
|
| 2046 |
],
|
| 2047 |
"logging_steps": 5,
|
|
@@ -2061,7 +2079,7 @@
|
|
| 2061 |
"attributes": {}
|
| 2062 |
}
|
| 2063 |
},
|
| 2064 |
-
"total_flos": 2.
|
| 2065 |
"train_batch_size": 4,
|
| 2066 |
"trial_name": null,
|
| 2067 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2042 |
"mean_token_accuracy": 0.6499712377786636,
|
| 2043 |
"num_tokens": 4120160.0,
|
| 2044 |
"step": 1130
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 8.73076923076923,
|
| 2048 |
+
"grad_norm": 0.0,
|
| 2049 |
+
"learning_rate": 4.4330000000000004e-05,
|
| 2050 |
+
"loss": 1.7363,
|
| 2051 |
+
"mean_token_accuracy": 0.6554156959056854,
|
| 2052 |
+
"num_tokens": 4138405.0,
|
| 2053 |
+
"step": 1135
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 8.76923076923077,
|
| 2057 |
+
"grad_norm": 0.0,
|
| 2058 |
+
"learning_rate": 4.4305000000000004e-05,
|
| 2059 |
+
"loss": 1.6461,
|
| 2060 |
+
"mean_token_accuracy": 0.6685263246297837,
|
| 2061 |
+
"num_tokens": 4157763.0,
|
| 2062 |
+
"step": 1140
|
| 2063 |
}
|
| 2064 |
],
|
| 2065 |
"logging_steps": 5,
|
|
|
|
| 2079 |
"attributes": {}
|
| 2080 |
}
|
| 2081 |
},
|
| 2082 |
+
"total_flos": 2.1090729262546944e+17,
|
| 2083 |
"train_batch_size": 4,
|
| 2084 |
"trial_name": null,
|
| 2085 |
"trial_params": null
|