Training in progress, step 2290, 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 sha256:7ce29d2588b90c14feb57bb12dc97b1193701ddea791aee7c41dae356365f3ef
|
| 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 sha256:8aa36fe3f58e32f81d07502b604f2cd4466c265d00dd7023b483c57947e910d5
|
| 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 sha256:614e90d114c8a4e94573a05bbd71d39d78cb6590630dc8a6c6f3099371ad3df9
|
| 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": 17.
|
| 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,
|
|
@@ -4112,6 +4112,24 @@
|
|
| 4112 |
"mean_token_accuracy": 0.6444843232631683,
|
| 4113 |
"num_tokens": 8316630.0,
|
| 4114 |
"step": 2280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4115 |
}
|
| 4116 |
],
|
| 4117 |
"logging_steps": 5,
|
|
@@ -4131,7 +4149,7 @@
|
|
| 4131 |
"attributes": {}
|
| 4132 |
}
|
| 4133 |
},
|
| 4134 |
-
"total_flos": 4.
|
| 4135 |
"train_batch_size": 4,
|
| 4136 |
"trial_name": null,
|
| 4137 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4112 |
"mean_token_accuracy": 0.6444843232631683,
|
| 4113 |
"num_tokens": 8316630.0,
|
| 4114 |
"step": 2280
|
| 4115 |
+
},
|
| 4116 |
+
{
|
| 4117 |
+
"epoch": 17.576923076923077,
|
| 4118 |
+
"grad_norm": 0.0,
|
| 4119 |
+
"learning_rate": 3.858e-05,
|
| 4120 |
+
"loss": 1.6235,
|
| 4121 |
+
"mean_token_accuracy": 0.6704483658075333,
|
| 4122 |
+
"num_tokens": 8335880.0,
|
| 4123 |
+
"step": 2285
|
| 4124 |
+
},
|
| 4125 |
+
{
|
| 4126 |
+
"epoch": 17.615384615384617,
|
| 4127 |
+
"grad_norm": 0.0,
|
| 4128 |
+
"learning_rate": 3.8555e-05,
|
| 4129 |
+
"loss": 1.7432,
|
| 4130 |
+
"mean_token_accuracy": 0.6476155072450638,
|
| 4131 |
+
"num_tokens": 8354016.0,
|
| 4132 |
+
"step": 2290
|
| 4133 |
}
|
| 4134 |
],
|
| 4135 |
"logging_steps": 5,
|
|
|
|
| 4149 |
"attributes": {}
|
| 4150 |
}
|
| 4151 |
},
|
| 4152 |
+
"total_flos": 4.234484226657485e+17,
|
| 4153 |
"train_batch_size": 4,
|
| 4154 |
"trial_name": null,
|
| 4155 |
"trial_params": null
|