Training in progress, step 120, 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 sha256:4ba8c5b756dd7b36974fade86518be7e6c5131f6d294af94e83cd862947d5630
|
| 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:b359c4aeb11bfe8618a8e81758034fcaddab53adf225a1372c921b7a687d7aab
|
| 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 sha256:23a178c9893d384eb6aa6bec653580080417caeee729cb2c2a352c74a3a292c1
|
| 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,
|
|
@@ -206,6 +206,24 @@
|
|
| 206 |
"mean_token_accuracy": 0.6579539209604264,
|
| 207 |
"num_tokens": 401596.0,
|
| 208 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
}
|
| 210 |
],
|
| 211 |
"logging_steps": 5,
|
|
@@ -225,7 +243,7 @@
|
|
| 225 |
"attributes": {}
|
| 226 |
}
|
| 227 |
},
|
| 228 |
-
"total_flos": 2.
|
| 229 |
"train_batch_size": 4,
|
| 230 |
"trial_name": null,
|
| 231 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 206 |
"mean_token_accuracy": 0.6579539209604264,
|
| 207 |
"num_tokens": 401596.0,
|
| 208 |
"step": 110
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.8846153846153846,
|
| 212 |
+
"grad_norm": 0.0,
|
| 213 |
+
"learning_rate": 4.9430000000000006e-05,
|
| 214 |
+
"loss": 1.7604,
|
| 215 |
+
"mean_token_accuracy": 0.6474329262971878,
|
| 216 |
+
"num_tokens": 419595.0,
|
| 217 |
+
"step": 115
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.9230769230769231,
|
| 221 |
+
"grad_norm": 0.0,
|
| 222 |
+
"learning_rate": 4.9405e-05,
|
| 223 |
+
"loss": 1.761,
|
| 224 |
+
"mean_token_accuracy": 0.644348555803299,
|
| 225 |
+
"num_tokens": 437633.0,
|
| 226 |
+
"step": 120
|
| 227 |
}
|
| 228 |
],
|
| 229 |
"logging_steps": 5,
|
|
|
|
| 243 |
"attributes": {}
|
| 244 |
}
|
| 245 |
},
|
| 246 |
+
"total_flos": 2.214064048914432e+16,
|
| 247 |
"train_batch_size": 4,
|
| 248 |
"trial_name": null,
|
| 249 |
"trial_params": null
|