Training in progress, step 6150, 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 sha256:61cb98b78b4595d861274993228d40e67de4e8b72a3179d026729afaafc6e902
|
| 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 sha256:0bd6e0fc19af96192311ff2ffead1b938980a148dd1e601fbf63527f0b9a4493
|
| 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 sha256:654ad3ad40c7dec8dabaa5c9f8df4867b0cff76990e29bb466125cc35b1cd4fe
|
| 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": 47.
|
| 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,
|
|
@@ -11060,6 +11060,24 @@
|
|
| 11060 |
"mean_token_accuracy": 0.6670328795909881,
|
| 11061 |
"num_tokens": 22394135.0,
|
| 11062 |
"step": 6140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11063 |
}
|
| 11064 |
],
|
| 11065 |
"logging_steps": 5,
|
|
@@ -11079,7 +11097,7 @@
|
|
| 11079 |
"attributes": {}
|
| 11080 |
}
|
| 11081 |
},
|
| 11082 |
-
"total_flos": 1.
|
| 11083 |
"train_batch_size": 4,
|
| 11084 |
"trial_name": null,
|
| 11085 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11060 |
"mean_token_accuracy": 0.6670328795909881,
|
| 11061 |
"num_tokens": 22394135.0,
|
| 11062 |
"step": 6140
|
| 11063 |
+
},
|
| 11064 |
+
{
|
| 11065 |
+
"epoch": 47.26923076923077,
|
| 11066 |
+
"grad_norm": 0.0,
|
| 11067 |
+
"learning_rate": 1.9280000000000002e-05,
|
| 11068 |
+
"loss": 1.6467,
|
| 11069 |
+
"mean_token_accuracy": 0.6665792822837829,
|
| 11070 |
+
"num_tokens": 22413510.0,
|
| 11071 |
+
"step": 6145
|
| 11072 |
+
},
|
| 11073 |
+
{
|
| 11074 |
+
"epoch": 47.30769230769231,
|
| 11075 |
+
"grad_norm": 0.0,
|
| 11076 |
+
"learning_rate": 1.9255e-05,
|
| 11077 |
+
"loss": 1.7692,
|
| 11078 |
+
"mean_token_accuracy": 0.6390243858098984,
|
| 11079 |
+
"num_tokens": 22432228.0,
|
| 11080 |
+
"step": 6150
|
| 11081 |
}
|
| 11082 |
],
|
| 11083 |
"logging_steps": 5,
|
|
|
|
| 11097 |
"attributes": {}
|
| 11098 |
}
|
| 11099 |
},
|
| 11100 |
+
"total_flos": 1.1370212769241498e+18,
|
| 11101 |
"train_batch_size": 4,
|
| 11102 |
"trial_name": null,
|
| 11103 |
"trial_params": null
|