Training in progress, step 1630, 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 sha256:1452f8693e578d180c193919d40821426bf75dfaf83246a184015006af7b71c6
|
| 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 sha256:9a51a7419aea9467a9316d89e9c9c69570191f47a10907e0eb431b20fe302244
|
| 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 sha256:84de6f44483b870eb7fcbe7fccd9a134e2941ef77923c6decac67f3b4bdd9570
|
| 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": 12.
|
| 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,
|
|
@@ -2924,6 +2924,24 @@
|
|
| 2924 |
"mean_token_accuracy": 0.651836696267128,
|
| 2925 |
"num_tokens": 5906272.0,
|
| 2926 |
"step": 1620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2927 |
}
|
| 2928 |
],
|
| 2929 |
"logging_steps": 5,
|
|
@@ -2943,7 +2961,7 @@
|
|
| 2943 |
"attributes": {}
|
| 2944 |
}
|
| 2945 |
},
|
| 2946 |
-
"total_flos":
|
| 2947 |
"train_batch_size": 4,
|
| 2948 |
"trial_name": null,
|
| 2949 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2924 |
"mean_token_accuracy": 0.651836696267128,
|
| 2925 |
"num_tokens": 5906272.0,
|
| 2926 |
"step": 1620
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 12.5,
|
| 2930 |
+
"grad_norm": 0.0,
|
| 2931 |
+
"learning_rate": 4.1880000000000006e-05,
|
| 2932 |
+
"loss": 1.7005,
|
| 2933 |
+
"mean_token_accuracy": 0.6608695417642594,
|
| 2934 |
+
"num_tokens": 5924826.0,
|
| 2935 |
+
"step": 1625
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 12.538461538461538,
|
| 2939 |
+
"grad_norm": 0.0,
|
| 2940 |
+
"learning_rate": 4.1855e-05,
|
| 2941 |
+
"loss": 1.6497,
|
| 2942 |
+
"mean_token_accuracy": 0.6752032458782196,
|
| 2943 |
+
"num_tokens": 5944267.0,
|
| 2944 |
+
"step": 1630
|
| 2945 |
}
|
| 2946 |
],
|
| 2947 |
"logging_steps": 5,
|
|
|
|
| 2961 |
"attributes": {}
|
| 2962 |
}
|
| 2963 |
},
|
| 2964 |
+
"total_flos": 3.010306535895859e+17,
|
| 2965 |
"train_batch_size": 4,
|
| 2966 |
"trial_name": null,
|
| 2967 |
"trial_params": null
|