Training in progress, step 8350, 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:d65f0ff24c2a513589b4e6d39ca20c75f951d18705f92d488b03a335c49d6879
|
| 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 sha256:37340fb017930b9bef81ef404b3634ffda2d0f4865bd98bd619d0dc5d8820dce
|
| 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 sha256:248519a475a82982a417b9eb5519acdd63c7a5477f880fa19a99f3046b0df018
|
| 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": 64.
|
| 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,
|
|
@@ -15020,6 +15020,24 @@
|
|
| 15020 |
"mean_token_accuracy": 0.6381383389234543,
|
| 15021 |
"num_tokens": 30416271.0,
|
| 15022 |
"step": 8340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15023 |
}
|
| 15024 |
],
|
| 15025 |
"logging_steps": 5,
|
|
@@ -15039,7 +15057,7 @@
|
|
| 15039 |
"attributes": {}
|
| 15040 |
}
|
| 15041 |
},
|
| 15042 |
-
"total_flos": 1.
|
| 15043 |
"train_batch_size": 4,
|
| 15044 |
"trial_name": null,
|
| 15045 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15020 |
"mean_token_accuracy": 0.6381383389234543,
|
| 15021 |
"num_tokens": 30416271.0,
|
| 15022 |
"step": 8340
|
| 15023 |
+
},
|
| 15024 |
+
{
|
| 15025 |
+
"epoch": 64.1923076923077,
|
| 15026 |
+
"grad_norm": 0.0,
|
| 15027 |
+
"learning_rate": 8.28e-06,
|
| 15028 |
+
"loss": 1.7004,
|
| 15029 |
+
"mean_token_accuracy": 0.6580903172492981,
|
| 15030 |
+
"num_tokens": 30434471.0,
|
| 15031 |
+
"step": 8345
|
| 15032 |
+
},
|
| 15033 |
+
{
|
| 15034 |
+
"epoch": 64.23076923076923,
|
| 15035 |
+
"grad_norm": 0.0,
|
| 15036 |
+
"learning_rate": 8.255e-06,
|
| 15037 |
+
"loss": 1.6885,
|
| 15038 |
+
"mean_token_accuracy": 0.6602605700492858,
|
| 15039 |
+
"num_tokens": 30453103.0,
|
| 15040 |
+
"step": 8350
|
| 15041 |
}
|
| 15042 |
],
|
| 15043 |
"logging_steps": 5,
|
|
|
|
| 15057 |
"attributes": {}
|
| 15058 |
}
|
| 15059 |
},
|
| 15060 |
+
"total_flos": 1.5440744825074483e+18,
|
| 15061 |
"train_batch_size": 4,
|
| 15062 |
"trial_name": null,
|
| 15063 |
"trial_params": null
|