Training in progress, step 4160, 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:aaa1aff895909357c44b573ec0398e815d0c193c67f6bfa729c43cef731a961f
|
| 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:b0814b042d85845cd3e60cea5526bc76ccfce20863f8155bc29ec1425745fb36
|
| 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 sha256:86b0fb6ec03bb62ad28e8db71f76e05ff97d321967538f6fbb900f70e388757a
|
| 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 sha256:6f52c47069f2ea2fa68023d25c01778c684b9f67ab4160ebd0ff0b45183ef6e5
|
| 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,
|
|
@@ -4168,6 +4168,16 @@
|
|
| 4168 |
"mean_token_accuracy": 0.7774873107671738,
|
| 4169 |
"num_tokens": 19339257.0,
|
| 4170 |
"step": 4150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4171 |
}
|
| 4172 |
],
|
| 4173 |
"logging_steps": 10,
|
|
@@ -4187,7 +4197,7 @@
|
|
| 4187 |
"attributes": {}
|
| 4188 |
}
|
| 4189 |
},
|
| 4190 |
-
"total_flos": 9.
|
| 4191 |
"train_batch_size": 4,
|
| 4192 |
"trial_name": null,
|
| 4193 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8874666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4168 |
"mean_token_accuracy": 0.7774873107671738,
|
| 4169 |
"num_tokens": 19339257.0,
|
| 4170 |
"step": 4150
|
| 4171 |
+
},
|
| 4172 |
+
{
|
| 4173 |
+
"entropy": 1.0086314499378204,
|
| 4174 |
+
"epoch": 0.8874666666666666,
|
| 4175 |
+
"grad_norm": 0.24890249967575073,
|
| 4176 |
+
"learning_rate": 6.16436569661412e-05,
|
| 4177 |
+
"loss": 1.1359784126281738,
|
| 4178 |
+
"mean_token_accuracy": 0.7473259434103966,
|
| 4179 |
+
"num_tokens": 19389016.0,
|
| 4180 |
+
"step": 4160
|
| 4181 |
}
|
| 4182 |
],
|
| 4183 |
"logging_steps": 10,
|
|
|
|
| 4197 |
"attributes": {}
|
| 4198 |
}
|
| 4199 |
},
|
| 4200 |
+
"total_flos": 9.172663839967027e+16,
|
| 4201 |
"train_batch_size": 4,
|
| 4202 |
"trial_name": null,
|
| 4203 |
"trial_params": null
|