Training in progress, step 4150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbbf3cb74449c1fb00f6cced019f5cac931feb324532596c8ff7d9981f29ab8e
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2f09867c7a44f12d9f418427867af27a502d2f679e452151826a69ca69ec9c5
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f931c65218e2e42356f0dcfba8c99b75e4e17a08bac9754d89d4a4cb7910e51
|
| 3 |
size 14645
|
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:a507875b41156ea48cfe523fdd7edca9d8f12789371723835ecee113587bb063
|
| 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": 0.
|
| 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,
|
|
@@ -4158,6 +4158,16 @@
|
|
| 4158 |
"mean_token_accuracy": 0.7940000563859939,
|
| 4159 |
"num_tokens": 19293212.0,
|
| 4160 |
"step": 4140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4161 |
}
|
| 4162 |
],
|
| 4163 |
"logging_steps": 10,
|
|
@@ -4177,7 +4187,7 @@
|
|
| 4177 |
"attributes": {}
|
| 4178 |
}
|
| 4179 |
},
|
| 4180 |
-
"total_flos": 9.
|
| 4181 |
"train_batch_size": 4,
|
| 4182 |
"trial_name": null,
|
| 4183 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8853333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4158 |
"mean_token_accuracy": 0.7940000563859939,
|
| 4159 |
"num_tokens": 19293212.0,
|
| 4160 |
"step": 4140
|
| 4161 |
+
},
|
| 4162 |
+
{
|
| 4163 |
+
"entropy": 0.8676056079566479,
|
| 4164 |
+
"epoch": 0.8853333333333333,
|
| 4165 |
+
"grad_norm": 0.307106614112854,
|
| 4166 |
+
"learning_rate": 6.181190007711497e-05,
|
| 4167 |
+
"loss": 0.9692766189575195,
|
| 4168 |
+
"mean_token_accuracy": 0.7774873107671738,
|
| 4169 |
+
"num_tokens": 19339257.0,
|
| 4170 |
+
"step": 4150
|
| 4171 |
}
|
| 4172 |
],
|
| 4173 |
"logging_steps": 10,
|
|
|
|
| 4187 |
"attributes": {}
|
| 4188 |
}
|
| 4189 |
},
|
| 4190 |
+
"total_flos": 9.151275070860902e+16,
|
| 4191 |
"train_batch_size": 4,
|
| 4192 |
"trial_name": null,
|
| 4193 |
"trial_params": null
|