Training in progress, step 4000, 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:bebd2c15f35ca529471d8740f8b37a31a01f66646cda1ceb2a3ffc95662cef77
|
| 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:b66fa4ace09bf5b94a2f7e4cf0e6d5c5a21894f1d6e976f64cf4321e395ee351
|
| 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 sha256:261a1cabe7bdc6ef219a259053c089dfff7732b6f0e54ed71f2ddb6861fd0b64
|
| 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": 30.
|
| 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,
|
|
@@ -7190,6 +7190,24 @@
|
|
| 7190 |
"mean_token_accuracy": 0.645700478553772,
|
| 7191 |
"num_tokens": 14552442.0,
|
| 7192 |
"step": 3990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7193 |
}
|
| 7194 |
],
|
| 7195 |
"logging_steps": 5,
|
|
@@ -7209,7 +7227,7 @@
|
|
| 7209 |
"attributes": {}
|
| 7210 |
}
|
| 7211 |
},
|
| 7212 |
-
"total_flos": 7.
|
| 7213 |
"train_batch_size": 4,
|
| 7214 |
"trial_name": null,
|
| 7215 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7190 |
"mean_token_accuracy": 0.645700478553772,
|
| 7191 |
"num_tokens": 14552442.0,
|
| 7192 |
"step": 3990
|
| 7193 |
+
},
|
| 7194 |
+
{
|
| 7195 |
+
"epoch": 30.73076923076923,
|
| 7196 |
+
"grad_norm": 0.0,
|
| 7197 |
+
"learning_rate": 3.0030000000000002e-05,
|
| 7198 |
+
"loss": 1.8189,
|
| 7199 |
+
"mean_token_accuracy": 0.6313192546367645,
|
| 7200 |
+
"num_tokens": 14569871.0,
|
| 7201 |
+
"step": 3995
|
| 7202 |
+
},
|
| 7203 |
+
{
|
| 7204 |
+
"epoch": 30.76923076923077,
|
| 7205 |
+
"grad_norm": 0.0,
|
| 7206 |
+
"learning_rate": 3.0004999999999998e-05,
|
| 7207 |
+
"loss": 1.6918,
|
| 7208 |
+
"mean_token_accuracy": 0.6627134591341018,
|
| 7209 |
+
"num_tokens": 14588659.0,
|
| 7210 |
+
"step": 4000
|
| 7211 |
}
|
| 7212 |
],
|
| 7213 |
"logging_steps": 5,
|
|
|
|
| 7227 |
"attributes": {}
|
| 7228 |
}
|
| 7229 |
},
|
| 7230 |
+
"total_flos": 7.393724013935002e+17,
|
| 7231 |
"train_batch_size": 4,
|
| 7232 |
"trial_name": null,
|
| 7233 |
"trial_params": null
|