Training in progress, step 6750, 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 sha256:8af6f0926f8e9877f02be2597005900486b2d58f878ab5560f68e822dae5c244
|
| 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 sha256:1d74d71b56494debd210f1c7830ba08db6335906d014d05d442a05014026e897
|
| 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 sha256:95778cca0c67eb858050c2ead93ca4adbb5b2c94bbba764c9dc1035e932a85d9
|
| 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": 51.
|
| 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,
|
|
@@ -12140,6 +12140,24 @@
|
|
| 12140 |
"mean_token_accuracy": 0.6389773488044739,
|
| 12141 |
"num_tokens": 24581168.0,
|
| 12142 |
"step": 6740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12143 |
}
|
| 12144 |
],
|
| 12145 |
"logging_steps": 5,
|
|
@@ -12159,7 +12177,7 @@
|
|
| 12159 |
"attributes": {}
|
| 12160 |
}
|
| 12161 |
},
|
| 12162 |
-
"total_flos": 1.
|
| 12163 |
"train_batch_size": 4,
|
| 12164 |
"trial_name": null,
|
| 12165 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12140 |
"mean_token_accuracy": 0.6389773488044739,
|
| 12141 |
"num_tokens": 24581168.0,
|
| 12142 |
"step": 6740
|
| 12143 |
+
},
|
| 12144 |
+
{
|
| 12145 |
+
"epoch": 51.88461538461539,
|
| 12146 |
+
"grad_norm": 0.0,
|
| 12147 |
+
"learning_rate": 1.628e-05,
|
| 12148 |
+
"loss": 1.7425,
|
| 12149 |
+
"mean_token_accuracy": 0.6551438093185424,
|
| 12150 |
+
"num_tokens": 24599489.0,
|
| 12151 |
+
"step": 6745
|
| 12152 |
+
},
|
| 12153 |
+
{
|
| 12154 |
+
"epoch": 51.92307692307692,
|
| 12155 |
+
"grad_norm": 0.0,
|
| 12156 |
+
"learning_rate": 1.6255e-05,
|
| 12157 |
+
"loss": 1.735,
|
| 12158 |
+
"mean_token_accuracy": 0.6468292713165283,
|
| 12159 |
+
"num_tokens": 24617539.0,
|
| 12160 |
+
"step": 6750
|
| 12161 |
}
|
| 12162 |
],
|
| 12163 |
"logging_steps": 5,
|
|
|
|
| 12177 |
"attributes": {}
|
| 12178 |
}
|
| 12179 |
},
|
| 12180 |
+
"total_flos": 1.2481168226402304e+18,
|
| 12181 |
"train_batch_size": 4,
|
| 12182 |
"trial_name": null,
|
| 12183 |
"trial_params": null
|