Training in progress, step 3990, 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 sha256:441c3bdee3cf5cbaf23d8e2b67aabd0b7bfd9ee09c6d02f035d2142be522a81e
|
| 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 sha256:141fc8f14d11bb72e5c6f6ad23a2377b27dabf58158624e1fd99d862042e1d47
|
| 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 sha256:8d04deada2e856b92f70b30af9bda8e25fc0eb98a8c27c914a0a2db25d7c99a1
|
| 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,
|
|
@@ -7172,6 +7172,24 @@
|
|
| 7172 |
"mean_token_accuracy": 0.644034668803215,
|
| 7173 |
"num_tokens": 14515634.0,
|
| 7174 |
"step": 3980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7175 |
}
|
| 7176 |
],
|
| 7177 |
"logging_steps": 5,
|
|
@@ -7191,7 +7209,7 @@
|
|
| 7191 |
"attributes": {}
|
| 7192 |
}
|
| 7193 |
},
|
| 7194 |
-
"total_flos": 7.
|
| 7195 |
"train_batch_size": 4,
|
| 7196 |
"trial_name": null,
|
| 7197 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7172 |
"mean_token_accuracy": 0.644034668803215,
|
| 7173 |
"num_tokens": 14515634.0,
|
| 7174 |
"step": 3980
|
| 7175 |
+
},
|
| 7176 |
+
{
|
| 7177 |
+
"epoch": 30.653846153846153,
|
| 7178 |
+
"grad_norm": 0.0,
|
| 7179 |
+
"learning_rate": 3.0080000000000003e-05,
|
| 7180 |
+
"loss": 1.6789,
|
| 7181 |
+
"mean_token_accuracy": 0.6613237649202347,
|
| 7182 |
+
"num_tokens": 14534370.0,
|
| 7183 |
+
"step": 3985
|
| 7184 |
+
},
|
| 7185 |
+
{
|
| 7186 |
+
"epoch": 30.692307692307693,
|
| 7187 |
+
"grad_norm": 0.0,
|
| 7188 |
+
"learning_rate": 3.0055e-05,
|
| 7189 |
+
"loss": 1.7542,
|
| 7190 |
+
"mean_token_accuracy": 0.645700478553772,
|
| 7191 |
+
"num_tokens": 14552442.0,
|
| 7192 |
+
"step": 3990
|
| 7193 |
}
|
| 7194 |
],
|
| 7195 |
"logging_steps": 5,
|
|
|
|
| 7209 |
"attributes": {}
|
| 7210 |
}
|
| 7211 |
},
|
| 7212 |
+
"total_flos": 7.375426305122304e+17,
|
| 7213 |
"train_batch_size": 4,
|
| 7214 |
"trial_name": null,
|
| 7215 |
"trial_params": null
|