Training in progress, step 2270, 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 sha256:495d4de88ff7f5dd79872f38f38e501ac9b377f7470c200fa96636d0abd47084
|
| 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:d924e8c0bc6bd4c3c7429b2915fc71898960dfd040292aece939cb16ab8d8e48
|
| 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 sha256:90f09701b37202cbc89aa03b0575a031dc2c718550998eca1c3d73ad0bc27e01
|
| 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": 17.
|
| 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,
|
|
@@ -4076,6 +4076,24 @@
|
|
| 4076 |
"mean_token_accuracy": 0.6534038037061691,
|
| 4077 |
"num_tokens": 8242421.0,
|
| 4078 |
"step": 2260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4079 |
}
|
| 4080 |
],
|
| 4081 |
"logging_steps": 5,
|
|
@@ -4095,7 +4113,7 @@
|
|
| 4095 |
"attributes": {}
|
| 4096 |
}
|
| 4097 |
},
|
| 4098 |
-
"total_flos": 4.
|
| 4099 |
"train_batch_size": 4,
|
| 4100 |
"trial_name": null,
|
| 4101 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4076 |
"mean_token_accuracy": 0.6534038037061691,
|
| 4077 |
"num_tokens": 8242421.0,
|
| 4078 |
"step": 2260
|
| 4079 |
+
},
|
| 4080 |
+
{
|
| 4081 |
+
"epoch": 17.423076923076923,
|
| 4082 |
+
"grad_norm": 0.0,
|
| 4083 |
+
"learning_rate": 3.868e-05,
|
| 4084 |
+
"loss": 1.6841,
|
| 4085 |
+
"mean_token_accuracy": 0.659113222360611,
|
| 4086 |
+
"num_tokens": 8261508.0,
|
| 4087 |
+
"step": 2265
|
| 4088 |
+
},
|
| 4089 |
+
{
|
| 4090 |
+
"epoch": 17.46153846153846,
|
| 4091 |
+
"grad_norm": 0.0,
|
| 4092 |
+
"learning_rate": 3.8655e-05,
|
| 4093 |
+
"loss": 1.7875,
|
| 4094 |
+
"mean_token_accuracy": 0.6438043415546417,
|
| 4095 |
+
"num_tokens": 8279321.0,
|
| 4096 |
+
"step": 2270
|
| 4097 |
}
|
| 4098 |
],
|
| 4099 |
"logging_steps": 5,
|
|
|
|
| 4113 |
"attributes": {}
|
| 4114 |
}
|
| 4115 |
},
|
| 4116 |
+
"total_flos": 4.1954150299336704e+17,
|
| 4117 |
"train_batch_size": 4,
|
| 4118 |
"trial_name": null,
|
| 4119 |
"trial_params": null
|