Training in progress, step 9060, 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:f84053051406c9c47b16d975828b66370824eed022fb422ef1bf559818d06697
|
| 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 sha256:93aaf8701fb21180203ea076282cac6c15454907c36ee9ddb5ca399ad474c6e6
|
| 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 sha256:67dd28c075fc105f19b4f00e9197d92ec86de87301e0556f67a4ab41150c4a83
|
| 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": 69.
|
| 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,
|
|
@@ -16298,6 +16298,24 @@
|
|
| 16298 |
"mean_token_accuracy": 0.6435191184282303,
|
| 16299 |
"num_tokens": 33003912.0,
|
| 16300 |
"step": 9050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16301 |
}
|
| 16302 |
],
|
| 16303 |
"logging_steps": 5,
|
|
@@ -16317,7 +16335,7 @@
|
|
| 16317 |
"attributes": {}
|
| 16318 |
}
|
| 16319 |
},
|
| 16320 |
-
"total_flos": 1.
|
| 16321 |
"train_batch_size": 4,
|
| 16322 |
"trial_name": null,
|
| 16323 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16298 |
"mean_token_accuracy": 0.6435191184282303,
|
| 16299 |
"num_tokens": 33003912.0,
|
| 16300 |
"step": 9050
|
| 16301 |
+
},
|
| 16302 |
+
{
|
| 16303 |
+
"epoch": 69.65384615384616,
|
| 16304 |
+
"grad_norm": 0.0,
|
| 16305 |
+
"learning_rate": 4.7300000000000005e-06,
|
| 16306 |
+
"loss": 1.6889,
|
| 16307 |
+
"mean_token_accuracy": 0.6613710403442383,
|
| 16308 |
+
"num_tokens": 33022739.0,
|
| 16309 |
+
"step": 9055
|
| 16310 |
+
},
|
| 16311 |
+
{
|
| 16312 |
+
"epoch": 69.6923076923077,
|
| 16313 |
+
"grad_norm": 0.0,
|
| 16314 |
+
"learning_rate": 4.705000000000001e-06,
|
| 16315 |
+
"loss": 1.7765,
|
| 16316 |
+
"mean_token_accuracy": 0.6455245047807694,
|
| 16317 |
+
"num_tokens": 33040528.0,
|
| 16318 |
+
"step": 9060
|
| 16319 |
}
|
| 16320 |
],
|
| 16321 |
"logging_steps": 5,
|
|
|
|
| 16335 |
"attributes": {}
|
| 16336 |
}
|
| 16337 |
},
|
| 16338 |
+
"total_flos": 1.6752997308255437e+18,
|
| 16339 |
"train_batch_size": 4,
|
| 16340 |
"trial_name": null,
|
| 16341 |
"trial_params": null
|