Training in progress, step 8470, 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:f97529fa40efa5c7d177ee006d7d5699d231c2b55729429f4cc76e528d23e13a
|
| 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 sha256:996f4ad2df8c580d3b4bf4f790f49b18d4ac60c58821f323b2d39cd48d75b699
|
| 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 sha256:4f19c20fa980ddc80f5ac6b580f99f8b1c2c7edbc0c81d9627b58b9cbc4fa833
|
| 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": 65.
|
| 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,
|
|
@@ -15236,6 +15236,24 @@
|
|
| 15236 |
"mean_token_accuracy": 0.6389808714389801,
|
| 15237 |
"num_tokens": 30853070.0,
|
| 15238 |
"step": 8460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15239 |
}
|
| 15240 |
],
|
| 15241 |
"logging_steps": 5,
|
|
@@ -15255,7 +15273,7 @@
|
|
| 15255 |
"attributes": {}
|
| 15256 |
}
|
| 15257 |
},
|
| 15258 |
-
"total_flos": 1.
|
| 15259 |
"train_batch_size": 4,
|
| 15260 |
"trial_name": null,
|
| 15261 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15236 |
"mean_token_accuracy": 0.6389808714389801,
|
| 15237 |
"num_tokens": 30853070.0,
|
| 15238 |
"step": 8460
|
| 15239 |
+
},
|
| 15240 |
+
{
|
| 15241 |
+
"epoch": 65.11538461538461,
|
| 15242 |
+
"grad_norm": 0.0,
|
| 15243 |
+
"learning_rate": 7.68e-06,
|
| 15244 |
+
"loss": 1.697,
|
| 15245 |
+
"mean_token_accuracy": 0.6605163842439652,
|
| 15246 |
+
"num_tokens": 30872040.0,
|
| 15247 |
+
"step": 8465
|
| 15248 |
+
},
|
| 15249 |
+
{
|
| 15250 |
+
"epoch": 65.15384615384616,
|
| 15251 |
+
"grad_norm": 0.0,
|
| 15252 |
+
"learning_rate": 7.655e-06,
|
| 15253 |
+
"loss": 1.7485,
|
| 15254 |
+
"mean_token_accuracy": 0.6444921791553497,
|
| 15255 |
+
"num_tokens": 30890649.0,
|
| 15256 |
+
"step": 8470
|
| 15257 |
}
|
| 15258 |
],
|
| 15259 |
"logging_steps": 5,
|
|
|
|
| 15273 |
"attributes": {}
|
| 15274 |
}
|
| 15275 |
},
|
| 15276 |
+
"total_flos": 1.5662727598266778e+18,
|
| 15277 |
"train_batch_size": 4,
|
| 15278 |
"trial_name": null,
|
| 15279 |
"trial_params": null
|