Training in progress, step 1720, 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 sha256:4a7d0efbe03c4d450337daaf2965f555aadb4e2be480e7bcb38e5c5bf3d76774
|
| 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 sha256:1fe3175e5403a302de59428cd60b3a03848b3a62646b4ce57f26130682627fea
|
| 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:c74f73758ab8fea255acdfe7e158c379b7109557daa5b5ea97a42e73ff10fbbc
|
| 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": 13.
|
| 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,
|
|
@@ -3086,6 +3086,24 @@
|
|
| 3086 |
"mean_token_accuracy": 0.6536228835582734,
|
| 3087 |
"num_tokens": 6235654.0,
|
| 3088 |
"step": 1710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3089 |
}
|
| 3090 |
],
|
| 3091 |
"logging_steps": 5,
|
|
@@ -3105,7 +3123,7 @@
|
|
| 3105 |
"attributes": {}
|
| 3106 |
}
|
| 3107 |
},
|
| 3108 |
-
"total_flos": 3.
|
| 3109 |
"train_batch_size": 4,
|
| 3110 |
"trial_name": null,
|
| 3111 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3086 |
"mean_token_accuracy": 0.6536228835582734,
|
| 3087 |
"num_tokens": 6235654.0,
|
| 3088 |
"step": 1710
|
| 3089 |
+
},
|
| 3090 |
+
{
|
| 3091 |
+
"epoch": 13.192307692307692,
|
| 3092 |
+
"grad_norm": 0.0,
|
| 3093 |
+
"learning_rate": 4.143e-05,
|
| 3094 |
+
"loss": 1.8063,
|
| 3095 |
+
"mean_token_accuracy": 0.6444395124912262,
|
| 3096 |
+
"num_tokens": 6253216.0,
|
| 3097 |
+
"step": 1715
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 13.23076923076923,
|
| 3101 |
+
"grad_norm": 0.0,
|
| 3102 |
+
"learning_rate": 4.1405e-05,
|
| 3103 |
+
"loss": 1.7436,
|
| 3104 |
+
"mean_token_accuracy": 0.6505606740713119,
|
| 3105 |
+
"num_tokens": 6270726.0,
|
| 3106 |
+
"step": 1720
|
| 3107 |
}
|
| 3108 |
],
|
| 3109 |
"logging_steps": 5,
|
|
|
|
| 3123 |
"attributes": {}
|
| 3124 |
}
|
| 3125 |
},
|
| 3126 |
+
"total_flos": 3.176035445366784e+17,
|
| 3127 |
"train_batch_size": 4,
|
| 3128 |
"trial_name": null,
|
| 3129 |
"trial_params": null
|