Training in progress, step 130, 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 sha256:7129ccdcff78912d1c08d1c04d384ef253f9e1d976dbd2b12a5d87312b73e57c
|
| 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 sha256:850e04957ea33c3269b74e4ef4b0e1601c61690924cc13777205f0dd1549ec25
|
| 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 sha256:00c087533b013e0f536aafc3d080331834d8b062eea645248355903b9115cc45
|
| 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":
|
| 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,
|
|
@@ -224,6 +224,24 @@
|
|
| 224 |
"mean_token_accuracy": 0.644348555803299,
|
| 225 |
"num_tokens": 437633.0,
|
| 226 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
}
|
| 228 |
],
|
| 229 |
"logging_steps": 5,
|
|
@@ -243,7 +261,7 @@
|
|
| 243 |
"attributes": {}
|
| 244 |
}
|
| 245 |
},
|
| 246 |
-
"total_flos": 2.
|
| 247 |
"train_batch_size": 4,
|
| 248 |
"trial_name": null,
|
| 249 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 224 |
"mean_token_accuracy": 0.644348555803299,
|
| 225 |
"num_tokens": 437633.0,
|
| 226 |
"step": 120
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9615384615384616,
|
| 230 |
+
"grad_norm": 0.0,
|
| 231 |
+
"learning_rate": 4.9380000000000005e-05,
|
| 232 |
+
"loss": 1.7521,
|
| 233 |
+
"mean_token_accuracy": 0.6455009877681732,
|
| 234 |
+
"num_tokens": 455648.0,
|
| 235 |
+
"step": 125
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.0,
|
| 239 |
+
"grad_norm": 0.0,
|
| 240 |
+
"learning_rate": 4.9355000000000004e-05,
|
| 241 |
+
"loss": 1.7483,
|
| 242 |
+
"mean_token_accuracy": 0.6529789954423905,
|
| 243 |
+
"num_tokens": 474105.0,
|
| 244 |
+
"step": 130
|
| 245 |
}
|
| 246 |
],
|
| 247 |
"logging_steps": 5,
|
|
|
|
| 261 |
"attributes": {}
|
| 262 |
}
|
| 263 |
},
|
| 264 |
+
"total_flos": 2.395437467664384e+16,
|
| 265 |
"train_batch_size": 4,
|
| 266 |
"trial_name": null,
|
| 267 |
"trial_params": null
|