Training in progress, step 3370, 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:d5eaa59f7c12ccc9addb2fcb47210d33cd253e6f751b2ccce52d9e5d9d2220e9
|
| 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 sha256:15286dabbb536842bd06feec86fd28ef2415796d092bca1c0f41bd359cfacf9f
|
| 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 sha256:26132b1aa940abb6ba0764993d84bf4b5f405edbd5ab516d9f1aeb23d8a7e5f2
|
| 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": 25.
|
| 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,
|
|
@@ -6056,6 +6056,24 @@
|
|
| 6056 |
"mean_token_accuracy": 0.6686410069465637,
|
| 6057 |
"num_tokens": 12253662.0,
|
| 6058 |
"step": 3360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6059 |
}
|
| 6060 |
],
|
| 6061 |
"logging_steps": 5,
|
|
@@ -6075,7 +6093,7 @@
|
|
| 6075 |
"attributes": {}
|
| 6076 |
}
|
| 6077 |
},
|
| 6078 |
-
"total_flos": 6.
|
| 6079 |
"train_batch_size": 4,
|
| 6080 |
"trial_name": null,
|
| 6081 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6056 |
"mean_token_accuracy": 0.6686410069465637,
|
| 6057 |
"num_tokens": 12253662.0,
|
| 6058 |
"step": 3360
|
| 6059 |
+
},
|
| 6060 |
+
{
|
| 6061 |
+
"epoch": 25.884615384615383,
|
| 6062 |
+
"grad_norm": 0.0,
|
| 6063 |
+
"learning_rate": 3.318e-05,
|
| 6064 |
+
"loss": 1.7287,
|
| 6065 |
+
"mean_token_accuracy": 0.653440797328949,
|
| 6066 |
+
"num_tokens": 12271662.0,
|
| 6067 |
+
"step": 3365
|
| 6068 |
+
},
|
| 6069 |
+
{
|
| 6070 |
+
"epoch": 25.923076923076923,
|
| 6071 |
+
"grad_norm": 0.0,
|
| 6072 |
+
"learning_rate": 3.3155000000000004e-05,
|
| 6073 |
+
"loss": 1.7753,
|
| 6074 |
+
"mean_token_accuracy": 0.6468665450811386,
|
| 6075 |
+
"num_tokens": 12289329.0,
|
| 6076 |
+
"step": 3370
|
| 6077 |
}
|
| 6078 |
],
|
| 6079 |
"logging_steps": 5,
|
|
|
|
| 6093 |
"attributes": {}
|
| 6094 |
}
|
| 6095 |
},
|
| 6096 |
+
"total_flos": 6.225733499653325e+17,
|
| 6097 |
"train_batch_size": 4,
|
| 6098 |
"trial_name": null,
|
| 6099 |
"trial_params": null
|