Training in progress, step 2890, 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 sha256:0ce2a10827e89ea26b9e02a3bdf4bacac9317726899efc726a6b04f1e1fae25a
|
| 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 sha256:4d5346f24ab2a8c7082f079a286ea1e63663d67482ae18c4d5d543eeaca463c2
|
| 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 sha256:7cdcfa1e4b7c66269da2710ef6629d037651debbba71e8c4740ee754b9e0c959
|
| 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": 22.
|
| 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,
|
|
@@ -5192,6 +5192,24 @@
|
|
| 5192 |
"mean_token_accuracy": 0.6608535885810852,
|
| 5193 |
"num_tokens": 10502391.0,
|
| 5194 |
"step": 2880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5195 |
}
|
| 5196 |
],
|
| 5197 |
"logging_steps": 5,
|
|
@@ -5211,7 +5229,7 @@
|
|
| 5211 |
"attributes": {}
|
| 5212 |
}
|
| 5213 |
},
|
| 5214 |
-
"total_flos": 5.
|
| 5215 |
"train_batch_size": 4,
|
| 5216 |
"trial_name": null,
|
| 5217 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5192 |
"mean_token_accuracy": 0.6608535885810852,
|
| 5193 |
"num_tokens": 10502391.0,
|
| 5194 |
"step": 2880
|
| 5195 |
+
},
|
| 5196 |
+
{
|
| 5197 |
+
"epoch": 22.192307692307693,
|
| 5198 |
+
"grad_norm": 0.0,
|
| 5199 |
+
"learning_rate": 3.558e-05,
|
| 5200 |
+
"loss": 1.7783,
|
| 5201 |
+
"mean_token_accuracy": 0.6480051964521408,
|
| 5202 |
+
"num_tokens": 10520184.0,
|
| 5203 |
+
"step": 2885
|
| 5204 |
+
},
|
| 5205 |
+
{
|
| 5206 |
+
"epoch": 22.23076923076923,
|
| 5207 |
+
"grad_norm": 0.0,
|
| 5208 |
+
"learning_rate": 3.5555e-05,
|
| 5209 |
+
"loss": 1.7946,
|
| 5210 |
+
"mean_token_accuracy": 0.6426310211420059,
|
| 5211 |
+
"num_tokens": 10537625.0,
|
| 5212 |
+
"step": 2890
|
| 5213 |
}
|
| 5214 |
],
|
| 5215 |
"logging_steps": 5,
|
|
|
|
| 5229 |
"attributes": {}
|
| 5230 |
}
|
| 5231 |
},
|
| 5232 |
+
"total_flos": 5.33930604539904e+17,
|
| 5233 |
"train_batch_size": 4,
|
| 5234 |
"trial_name": null,
|
| 5235 |
"trial_params": null
|