Training in progress, step 6160, 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 sha256:38e10101eef78ebb70cd2115f29ce3d2c9fb817e23f43eb92fe7a08c610a6b3e
|
| 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:cc3c5255feb9022d6f89998ad338fe3331ac4a471c235f8051589b86d75f462d
|
| 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:e9547d634cef5da07e405ad32a7f6397683770d21e8cba0bdfd8723bd952107b
|
| 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,
|
|
@@ -11078,6 +11078,24 @@
|
|
| 11078 |
"mean_token_accuracy": 0.6390243858098984,
|
| 11079 |
"num_tokens": 22432228.0,
|
| 11080 |
"step": 6150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11081 |
}
|
| 11082 |
],
|
| 11083 |
"logging_steps": 5,
|
|
@@ -11097,7 +11115,7 @@
|
|
| 11097 |
"attributes": {}
|
| 11098 |
}
|
| 11099 |
},
|
| 11100 |
-
"total_flos": 1.
|
| 11101 |
"train_batch_size": 4,
|
| 11102 |
"trial_name": null,
|
| 11103 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11078 |
"mean_token_accuracy": 0.6390243858098984,
|
| 11079 |
"num_tokens": 22432228.0,
|
| 11080 |
"step": 6150
|
| 11081 |
+
},
|
| 11082 |
+
{
|
| 11083 |
+
"epoch": 47.34615384615385,
|
| 11084 |
+
"grad_norm": 0.0,
|
| 11085 |
+
"learning_rate": 1.923e-05,
|
| 11086 |
+
"loss": 1.7202,
|
| 11087 |
+
"mean_token_accuracy": 0.6546848744153977,
|
| 11088 |
+
"num_tokens": 22450356.0,
|
| 11089 |
+
"step": 6155
|
| 11090 |
+
},
|
| 11091 |
+
{
|
| 11092 |
+
"epoch": 47.38461538461539,
|
| 11093 |
+
"grad_norm": 0.0,
|
| 11094 |
+
"learning_rate": 1.9205e-05,
|
| 11095 |
+
"loss": 1.8106,
|
| 11096 |
+
"mean_token_accuracy": 0.6357954889535904,
|
| 11097 |
+
"num_tokens": 22467696.0,
|
| 11098 |
+
"step": 6160
|
| 11099 |
}
|
| 11100 |
],
|
| 11101 |
"logging_steps": 5,
|
|
|
|
| 11115 |
"attributes": {}
|
| 11116 |
}
|
| 11117 |
},
|
| 11118 |
+
"total_flos": 1.1388092888899584e+18,
|
| 11119 |
"train_batch_size": 4,
|
| 11120 |
"trial_name": null,
|
| 11121 |
"trial_params": null
|