Training in progress, step 1130, 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 sha256:3790ab8725c516c796bc223e83d0446071e8e0380b3811b3a8a75db1e27482cf
|
| 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 sha256:8f89a241053e0ec58bbda80335426b08f92f55244e82ac33213ba3513321ce81
|
| 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 sha256:41f70e3dc7cb0b0e1ad191690671d0cccb9e24f334b117a1e98fec09cbfd2873
|
| 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,
|
|
@@ -2024,6 +2024,24 @@
|
|
| 2024 |
"mean_token_accuracy": 0.6423143684864044,
|
| 2025 |
"num_tokens": 4083327.0,
|
| 2026 |
"step": 1120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2027 |
}
|
| 2028 |
],
|
| 2029 |
"logging_steps": 5,
|
|
@@ -2043,7 +2061,7 @@
|
|
| 2043 |
"attributes": {}
|
| 2044 |
}
|
| 2045 |
},
|
| 2046 |
-
"total_flos": 2.
|
| 2047 |
"train_batch_size": 4,
|
| 2048 |
"trial_name": null,
|
| 2049 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2024 |
"mean_token_accuracy": 0.6423143684864044,
|
| 2025 |
"num_tokens": 4083327.0,
|
| 2026 |
"step": 1120
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 8.653846153846153,
|
| 2030 |
+
"grad_norm": 0.0,
|
| 2031 |
+
"learning_rate": 4.438e-05,
|
| 2032 |
+
"loss": 1.746,
|
| 2033 |
+
"mean_token_accuracy": 0.646085262298584,
|
| 2034 |
+
"num_tokens": 4101731.0,
|
| 2035 |
+
"step": 1125
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 8.692307692307692,
|
| 2039 |
+
"grad_norm": 0.0,
|
| 2040 |
+
"learning_rate": 4.4355000000000005e-05,
|
| 2041 |
+
"loss": 1.7223,
|
| 2042 |
+
"mean_token_accuracy": 0.6499712377786636,
|
| 2043 |
+
"num_tokens": 4120160.0,
|
| 2044 |
+
"step": 1130
|
| 2045 |
}
|
| 2046 |
],
|
| 2047 |
"logging_steps": 5,
|
|
|
|
| 2061 |
"attributes": {}
|
| 2062 |
}
|
| 2063 |
},
|
| 2064 |
+
"total_flos": 2.089660587835392e+17,
|
| 2065 |
"train_batch_size": 4,
|
| 2066 |
"trial_name": null,
|
| 2067 |
"trial_params": null
|