Training in progress, step 6190, 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 sha256:6e21a26314ebefc73f1ed3bd97926751afac6e6a12c0ac378b686eb771048f6d
|
| 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:ace1b6f557e42945cd007eeedca83c0a6c1eb637b528b1bf470f9a082fd57c60
|
| 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 sha256:0587ed9d987a530e0bc0a05e2703754630dff36158c6c48865a9d8a39a6f9392
|
| 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": 47.
|
| 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,
|
|
@@ -11132,6 +11132,24 @@
|
|
| 11132 |
"mean_token_accuracy": 0.6506534874439239,
|
| 11133 |
"num_tokens": 22539795.0,
|
| 11134 |
"step": 6180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11135 |
}
|
| 11136 |
],
|
| 11137 |
"logging_steps": 5,
|
|
@@ -11151,7 +11169,7 @@
|
|
| 11151 |
"attributes": {}
|
| 11152 |
}
|
| 11153 |
},
|
| 11154 |
-
"total_flos": 1.
|
| 11155 |
"train_batch_size": 4,
|
| 11156 |
"trial_name": null,
|
| 11157 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11132 |
"mean_token_accuracy": 0.6506534874439239,
|
| 11133 |
"num_tokens": 22539795.0,
|
| 11134 |
"step": 6180
|
| 11135 |
+
},
|
| 11136 |
+
{
|
| 11137 |
+
"epoch": 47.57692307692308,
|
| 11138 |
+
"grad_norm": 0.0,
|
| 11139 |
+
"learning_rate": 1.908e-05,
|
| 11140 |
+
"loss": 1.6702,
|
| 11141 |
+
"mean_token_accuracy": 0.6614595890045166,
|
| 11142 |
+
"num_tokens": 22558751.0,
|
| 11143 |
+
"step": 6185
|
| 11144 |
+
},
|
| 11145 |
+
{
|
| 11146 |
+
"epoch": 47.61538461538461,
|
| 11147 |
+
"grad_norm": 0.0,
|
| 11148 |
+
"learning_rate": 1.9055e-05,
|
| 11149 |
+
"loss": 1.7339,
|
| 11150 |
+
"mean_token_accuracy": 0.6529056757688523,
|
| 11151 |
+
"num_tokens": 22576706.0,
|
| 11152 |
+
"step": 6190
|
| 11153 |
}
|
| 11154 |
],
|
| 11155 |
"logging_steps": 5,
|
|
|
|
| 11169 |
"attributes": {}
|
| 11170 |
}
|
| 11171 |
},
|
| 11172 |
+
"total_flos": 1.1443106687488819e+18,
|
| 11173 |
"train_batch_size": 4,
|
| 11174 |
"trial_name": null,
|
| 11175 |
"trial_params": null
|