Training in progress, step 9460, 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 sha256:49ea2e264b45d1321c06b757ddccbdcd95ec9decbfb3e9906f32fb9ab66c495c
|
| 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 sha256:1e4ad4e6987cc691e7ffe8556df9077ba304de24cfb0acedcb583c87beeabea6
|
| 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 sha256:95bb5db9cd7022ade12a8a071d1bb9e8f476aa950b1c61817c95c4fc5ab30be8
|
| 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": 72.
|
| 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,
|
|
@@ -17018,6 +17018,24 @@
|
|
| 17018 |
"mean_token_accuracy": 0.6450568825006485,
|
| 17019 |
"num_tokens": 34462759.0,
|
| 17020 |
"step": 9450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17021 |
}
|
| 17022 |
],
|
| 17023 |
"logging_steps": 5,
|
|
@@ -17037,7 +17055,7 @@
|
|
| 17037 |
"attributes": {}
|
| 17038 |
}
|
| 17039 |
},
|
| 17040 |
-
"total_flos": 1.
|
| 17041 |
"train_batch_size": 4,
|
| 17042 |
"trial_name": null,
|
| 17043 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17018 |
"mean_token_accuracy": 0.6450568825006485,
|
| 17019 |
"num_tokens": 34462759.0,
|
| 17020 |
"step": 9450
|
| 17021 |
+
},
|
| 17022 |
+
{
|
| 17023 |
+
"epoch": 72.73076923076923,
|
| 17024 |
+
"grad_norm": 0.0,
|
| 17025 |
+
"learning_rate": 2.73e-06,
|
| 17026 |
+
"loss": 1.791,
|
| 17027 |
+
"mean_token_accuracy": 0.6397794485092163,
|
| 17028 |
+
"num_tokens": 34480097.0,
|
| 17029 |
+
"step": 9455
|
| 17030 |
+
},
|
| 17031 |
+
{
|
| 17032 |
+
"epoch": 72.76923076923077,
|
| 17033 |
+
"grad_norm": 0.0,
|
| 17034 |
+
"learning_rate": 2.7050000000000004e-06,
|
| 17035 |
+
"loss": 1.7267,
|
| 17036 |
+
"mean_token_accuracy": 0.6520882248878479,
|
| 17037 |
+
"num_tokens": 34498104.0,
|
| 17038 |
+
"step": 9460
|
| 17039 |
}
|
| 17040 |
],
|
| 17041 |
"logging_steps": 5,
|
|
|
|
| 17055 |
"attributes": {}
|
| 17056 |
}
|
| 17057 |
},
|
| 17058 |
+
"total_flos": 1.7492985931515494e+18,
|
| 17059 |
"train_batch_size": 4,
|
| 17060 |
"trial_name": null,
|
| 17061 |
"trial_params": null
|