Training in progress, step 9530, 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:ebc9be62d7237f0767f2f48611d43fe6d651a0ec1b1e0e1fdb15f3c8328e423a
|
| 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 sha256:64ae4e7568655572e8edaa98d78fead4e1b4b88e7abd823aad716da6ca514898
|
| 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 sha256:84d927ca661e9e9a673f42f53ce31275ac8e5a10987e3a7545973aa93be23d9c
|
| 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": 73.
|
| 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,
|
|
@@ -17144,6 +17144,24 @@
|
|
| 17144 |
"mean_token_accuracy": 0.648136830329895,
|
| 17145 |
"num_tokens": 34718585.0,
|
| 17146 |
"step": 9520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17147 |
}
|
| 17148 |
],
|
| 17149 |
"logging_steps": 5,
|
|
@@ -17163,7 +17181,7 @@
|
|
| 17163 |
"attributes": {}
|
| 17164 |
}
|
| 17165 |
},
|
| 17166 |
-
"total_flos": 1.
|
| 17167 |
"train_batch_size": 4,
|
| 17168 |
"trial_name": null,
|
| 17169 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17144 |
"mean_token_accuracy": 0.648136830329895,
|
| 17145 |
"num_tokens": 34718585.0,
|
| 17146 |
"step": 9520
|
| 17147 |
+
},
|
| 17148 |
+
{
|
| 17149 |
+
"epoch": 73.26923076923077,
|
| 17150 |
+
"grad_norm": 0.0,
|
| 17151 |
+
"learning_rate": 2.38e-06,
|
| 17152 |
+
"loss": 1.8001,
|
| 17153 |
+
"mean_token_accuracy": 0.6407902717590332,
|
| 17154 |
+
"num_tokens": 34736230.0,
|
| 17155 |
+
"step": 9525
|
| 17156 |
+
},
|
| 17157 |
+
{
|
| 17158 |
+
"epoch": 73.3076923076923,
|
| 17159 |
+
"grad_norm": 0.0,
|
| 17160 |
+
"learning_rate": 2.3550000000000003e-06,
|
| 17161 |
+
"loss": 1.7617,
|
| 17162 |
+
"mean_token_accuracy": 0.6459957540035248,
|
| 17163 |
+
"num_tokens": 34754509.0,
|
| 17164 |
+
"step": 9530
|
| 17165 |
}
|
| 17166 |
],
|
| 17167 |
"logging_steps": 5,
|
|
|
|
| 17181 |
"attributes": {}
|
| 17182 |
}
|
| 17183 |
},
|
| 17184 |
+
"total_flos": 1.7624218483674317e+18,
|
| 17185 |
"train_batch_size": 4,
|
| 17186 |
"trial_name": null,
|
| 17187 |
"trial_params": null
|