Training in progress, step 2900, 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 sha256:7f2790f3128152698aa85fdee650b4ccac224904cc5fd70de3f230b84d755ffe
|
| 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 sha256:538867124fc2502be1200efe41b52481a80a7e151919e60dd61aa40cfb0cbdac
|
| 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 sha256:88ae0f02e605c92e8f4962eeec1c8ff46aa88630b7070dccf72e9c644aaff679
|
| 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,
|
|
@@ -5210,6 +5210,24 @@
|
|
| 5210 |
"mean_token_accuracy": 0.6426310211420059,
|
| 5211 |
"num_tokens": 10537625.0,
|
| 5212 |
"step": 2890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5213 |
}
|
| 5214 |
],
|
| 5215 |
"logging_steps": 5,
|
|
@@ -5229,7 +5247,7 @@
|
|
| 5229 |
"attributes": {}
|
| 5230 |
}
|
| 5231 |
},
|
| 5232 |
-
"total_flos": 5.
|
| 5233 |
"train_batch_size": 4,
|
| 5234 |
"trial_name": null,
|
| 5235 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5210 |
"mean_token_accuracy": 0.6426310211420059,
|
| 5211 |
"num_tokens": 10537625.0,
|
| 5212 |
"step": 2890
|
| 5213 |
+
},
|
| 5214 |
+
{
|
| 5215 |
+
"epoch": 22.26923076923077,
|
| 5216 |
+
"grad_norm": 0.0,
|
| 5217 |
+
"learning_rate": 3.553e-05,
|
| 5218 |
+
"loss": 1.8393,
|
| 5219 |
+
"mean_token_accuracy": 0.6324712634086609,
|
| 5220 |
+
"num_tokens": 10554726.0,
|
| 5221 |
+
"step": 2895
|
| 5222 |
+
},
|
| 5223 |
+
{
|
| 5224 |
+
"epoch": 22.307692307692307,
|
| 5225 |
+
"grad_norm": 0.0,
|
| 5226 |
+
"learning_rate": 3.5505e-05,
|
| 5227 |
+
"loss": 1.7677,
|
| 5228 |
+
"mean_token_accuracy": 0.6496516615152359,
|
| 5229 |
+
"num_tokens": 10572379.0,
|
| 5230 |
+
"step": 2900
|
| 5231 |
}
|
| 5232 |
],
|
| 5233 |
"logging_steps": 5,
|
|
|
|
| 5247 |
"attributes": {}
|
| 5248 |
}
|
| 5249 |
},
|
| 5250 |
+
"total_flos": 5.3570035690389504e+17,
|
| 5251 |
"train_batch_size": 4,
|
| 5252 |
"trial_name": null,
|
| 5253 |
"trial_params": null
|