Training in progress, step 8410, 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 sha256:3f849ccec333835c66fa0936abfd89fb97b34e2acf8bb6a381984722162b642e
|
| 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:ec3474a9debe86430482640f38537d29f350a4609323a5cc00c701fc39eace8f
|
| 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:e4aece4f019c2a2447c86bcd8420cb3216250a101c4273689aa65db401098da8
|
| 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": 64.
|
| 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,
|
|
@@ -15128,6 +15128,24 @@
|
|
| 15128 |
"mean_token_accuracy": 0.6539681345224381,
|
| 15129 |
"num_tokens": 30636302.0,
|
| 15130 |
"step": 8400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15131 |
}
|
| 15132 |
],
|
| 15133 |
"logging_steps": 5,
|
|
@@ -15147,7 +15165,7 @@
|
|
| 15147 |
"attributes": {}
|
| 15148 |
}
|
| 15149 |
},
|
| 15150 |
-
"total_flos": 1.
|
| 15151 |
"train_batch_size": 4,
|
| 15152 |
"trial_name": null,
|
| 15153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15128 |
"mean_token_accuracy": 0.6539681345224381,
|
| 15129 |
"num_tokens": 30636302.0,
|
| 15130 |
"step": 8400
|
| 15131 |
+
},
|
| 15132 |
+
{
|
| 15133 |
+
"epoch": 64.65384615384616,
|
| 15134 |
+
"grad_norm": 0.0,
|
| 15135 |
+
"learning_rate": 7.98e-06,
|
| 15136 |
+
"loss": 1.732,
|
| 15137 |
+
"mean_token_accuracy": 0.653337499499321,
|
| 15138 |
+
"num_tokens": 30654393.0,
|
| 15139 |
+
"step": 8405
|
| 15140 |
+
},
|
| 15141 |
+
{
|
| 15142 |
+
"epoch": 64.6923076923077,
|
| 15143 |
+
"grad_norm": 0.0,
|
| 15144 |
+
"learning_rate": 7.955e-06,
|
| 15145 |
+
"loss": 1.7691,
|
| 15146 |
+
"mean_token_accuracy": 0.649465736746788,
|
| 15147 |
+
"num_tokens": 30672362.0,
|
| 15148 |
+
"step": 8410
|
| 15149 |
}
|
| 15150 |
],
|
| 15151 |
"logging_steps": 5,
|
|
|
|
| 15165 |
"attributes": {}
|
| 15166 |
}
|
| 15167 |
},
|
| 15168 |
+
"total_flos": 1.5551264637606298e+18,
|
| 15169 |
"train_batch_size": 4,
|
| 15170 |
"trial_name": null,
|
| 15171 |
"trial_params": null
|