Training in progress, step 4010, 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:b5aefd1209826e2253afad70c126a91edd67391d5f76ff2d398d49252815ebef
|
| 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:c1c49babc143c8e0ac9b9236ba50269d4fd3ce07312e013ea2431c6e07f1fb48
|
| 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 sha256:45b1ba895f2bc1d5b2217cd39a529b295f03d31c2c1bcf59a956d4a1b80f8e9e
|
| 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,
|
|
@@ -7208,6 +7208,24 @@
|
|
| 7208 |
"mean_token_accuracy": 0.6627134591341018,
|
| 7209 |
"num_tokens": 14588659.0,
|
| 7210 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7211 |
}
|
| 7212 |
],
|
| 7213 |
"logging_steps": 5,
|
|
@@ -7227,7 +7245,7 @@
|
|
| 7227 |
"attributes": {}
|
| 7228 |
}
|
| 7229 |
},
|
| 7230 |
-
"total_flos": 7.
|
| 7231 |
"train_batch_size": 4,
|
| 7232 |
"trial_name": null,
|
| 7233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7208 |
"mean_token_accuracy": 0.6627134591341018,
|
| 7209 |
"num_tokens": 14588659.0,
|
| 7210 |
"step": 4000
|
| 7211 |
+
},
|
| 7212 |
+
{
|
| 7213 |
+
"epoch": 30.807692307692307,
|
| 7214 |
+
"grad_norm": 0.0,
|
| 7215 |
+
"learning_rate": 2.998e-05,
|
| 7216 |
+
"loss": 1.7661,
|
| 7217 |
+
"mean_token_accuracy": 0.6492778122425079,
|
| 7218 |
+
"num_tokens": 14606860.0,
|
| 7219 |
+
"step": 4005
|
| 7220 |
+
},
|
| 7221 |
+
{
|
| 7222 |
+
"epoch": 30.846153846153847,
|
| 7223 |
+
"grad_norm": 0.0,
|
| 7224 |
+
"learning_rate": 2.9955e-05,
|
| 7225 |
+
"loss": 1.771,
|
| 7226 |
+
"mean_token_accuracy": 0.6434893846511841,
|
| 7227 |
+
"num_tokens": 14624861.0,
|
| 7228 |
+
"step": 4010
|
| 7229 |
}
|
| 7230 |
],
|
| 7231 |
"logging_steps": 5,
|
|
|
|
| 7245 |
"attributes": {}
|
| 7246 |
}
|
| 7247 |
},
|
| 7248 |
+
"total_flos": 7.412050302994022e+17,
|
| 7249 |
"train_batch_size": 4,
|
| 7250 |
"trial_name": null,
|
| 7251 |
"trial_params": null
|