Training in progress, step 7370, 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 sha256:701dafa62c33244b4e142c6b023b4b00a209ce8876f66fde5a76690ebfbcf168
|
| 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:cda6e628eec9302daa419f1db9612780a0306cb8effba0259edcb383414888c7
|
| 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 sha256:1fae3e73e44cbdc674ec5185273bc5dcde3dc2ad5277c3a14edb773ced72e99f
|
| 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": 56.
|
| 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,
|
|
@@ -13256,6 +13256,24 @@
|
|
| 13256 |
"mean_token_accuracy": 0.6572036474943161,
|
| 13257 |
"num_tokens": 26840558.0,
|
| 13258 |
"step": 7360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13259 |
}
|
| 13260 |
],
|
| 13261 |
"logging_steps": 5,
|
|
@@ -13275,7 +13293,7 @@
|
|
| 13275 |
"attributes": {}
|
| 13276 |
}
|
| 13277 |
},
|
| 13278 |
-
"total_flos": 1.
|
| 13279 |
"train_batch_size": 4,
|
| 13280 |
"trial_name": null,
|
| 13281 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13256 |
"mean_token_accuracy": 0.6572036474943161,
|
| 13257 |
"num_tokens": 26840558.0,
|
| 13258 |
"step": 7360
|
| 13259 |
+
},
|
| 13260 |
+
{
|
| 13261 |
+
"epoch": 56.65384615384615,
|
| 13262 |
+
"grad_norm": 0.0,
|
| 13263 |
+
"learning_rate": 1.3180000000000001e-05,
|
| 13264 |
+
"loss": 1.7503,
|
| 13265 |
+
"mean_token_accuracy": 0.6493770986795425,
|
| 13266 |
+
"num_tokens": 26859028.0,
|
| 13267 |
+
"step": 7365
|
| 13268 |
+
},
|
| 13269 |
+
{
|
| 13270 |
+
"epoch": 56.69230769230769,
|
| 13271 |
+
"grad_norm": 0.0,
|
| 13272 |
+
"learning_rate": 1.3155e-05,
|
| 13273 |
+
"loss": 1.7131,
|
| 13274 |
+
"mean_token_accuracy": 0.6502207726240158,
|
| 13275 |
+
"num_tokens": 26877909.0,
|
| 13276 |
+
"step": 7370
|
| 13277 |
}
|
| 13278 |
],
|
| 13279 |
"logging_steps": 5,
|
|
|
|
| 13293 |
"attributes": {}
|
| 13294 |
}
|
| 13295 |
},
|
| 13296 |
+
"total_flos": 1.3628455527805747e+18,
|
| 13297 |
"train_batch_size": 4,
|
| 13298 |
"trial_name": null,
|
| 13299 |
"trial_params": null
|