Training in progress, step 3970, 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 sha256:7ec64327ef29de15d43668ea770173d41cd53d1df91e6aa0b011303f7d720dd9
|
| 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 sha256:094ffeb3892eca09c571455b220635fd8b5f64478e3db17cd89877a0a3c134aa
|
| 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:e81747bf6bab22911f8c9614bd71a78cc911b01032a3bceedd223c800e3db9b7
|
| 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": 30.
|
| 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,
|
|
@@ -7136,6 +7136,24 @@
|
|
| 7136 |
"mean_token_accuracy": 0.6599725693464279,
|
| 7137 |
"num_tokens": 14443837.0,
|
| 7138 |
"step": 3960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7139 |
}
|
| 7140 |
],
|
| 7141 |
"logging_steps": 5,
|
|
@@ -7155,7 +7173,7 @@
|
|
| 7155 |
"attributes": {}
|
| 7156 |
}
|
| 7157 |
},
|
| 7158 |
-
"total_flos": 7.
|
| 7159 |
"train_batch_size": 4,
|
| 7160 |
"trial_name": null,
|
| 7161 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7136 |
"mean_token_accuracy": 0.6599725693464279,
|
| 7137 |
"num_tokens": 14443837.0,
|
| 7138 |
"step": 3960
|
| 7139 |
+
},
|
| 7140 |
+
{
|
| 7141 |
+
"epoch": 30.5,
|
| 7142 |
+
"grad_norm": 0.0,
|
| 7143 |
+
"learning_rate": 3.0180000000000002e-05,
|
| 7144 |
+
"loss": 1.8198,
|
| 7145 |
+
"mean_token_accuracy": 0.6380291700363159,
|
| 7146 |
+
"num_tokens": 14461559.0,
|
| 7147 |
+
"step": 3965
|
| 7148 |
+
},
|
| 7149 |
+
{
|
| 7150 |
+
"epoch": 30.53846153846154,
|
| 7151 |
+
"grad_norm": 0.0,
|
| 7152 |
+
"learning_rate": 3.0155e-05,
|
| 7153 |
+
"loss": 1.7347,
|
| 7154 |
+
"mean_token_accuracy": 0.6505941689014435,
|
| 7155 |
+
"num_tokens": 14479670.0,
|
| 7156 |
+
"step": 3970
|
| 7157 |
}
|
| 7158 |
],
|
| 7159 |
"logging_steps": 5,
|
|
|
|
| 7173 |
"attributes": {}
|
| 7174 |
}
|
| 7175 |
},
|
| 7176 |
+
"total_flos": 7.338703864179917e+17,
|
| 7177 |
"train_batch_size": 4,
|
| 7178 |
"trial_name": null,
|
| 7179 |
"trial_params": null
|