Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3781033488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71da7002112c64ec930e3605392282bcb2dccf0e5464837da64b8dcb46b7a7d5
|
| 3 |
size 3781033488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1921132493
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46c9dbaeda72f52226f0fce21e8109962bae0cf483430894a5216ab40fc62b3c
|
| 3 |
size 1921132493
|
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 sha256:0eefb9b9a8453187c3fe62147572c519bfac2b4d292272645dfd69ce7622dfd9
|
| 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": 0.
|
| 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,
|
|
@@ -43,6 +43,41 @@
|
|
| 43 |
"learning_rate": 9.96057350657239e-05,
|
| 44 |
"loss": 0.46511335372924806,
|
| 45 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
}
|
| 47 |
],
|
| 48 |
"logging_steps": 5,
|
|
@@ -62,7 +97,7 @@
|
|
| 62 |
"attributes": {}
|
| 63 |
}
|
| 64 |
},
|
| 65 |
-
"total_flos":
|
| 66 |
"train_batch_size": 1,
|
| 67 |
"trial_name": null,
|
| 68 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.38058991436726924,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 43 |
"learning_rate": 9.96057350657239e-05,
|
| 44 |
"loss": 0.46511335372924806,
|
| 45 |
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22835394862036157,
|
| 49 |
+
"grad_norm": 0.16359396278858185,
|
| 50 |
+
"learning_rate": 9.911436253643445e-05,
|
| 51 |
+
"loss": 0.3231180191040039,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2664129400570885,
|
| 56 |
+
"grad_norm": 0.15149523317813873,
|
| 57 |
+
"learning_rate": 9.842915805643155e-05,
|
| 58 |
+
"loss": 0.23352174758911132,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3044719314938154,
|
| 63 |
+
"grad_norm": 0.13363446295261383,
|
| 64 |
+
"learning_rate": 9.755282581475769e-05,
|
| 65 |
+
"loss": 0.2920512676239014,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3425309229305423,
|
| 70 |
+
"grad_norm": 0.17602847516536713,
|
| 71 |
+
"learning_rate": 9.648882429441257e-05,
|
| 72 |
+
"loss": 0.24277076721191407,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.38058991436726924,
|
| 77 |
+
"grad_norm": 0.12714512646198273,
|
| 78 |
+
"learning_rate": 9.524135262330098e-05,
|
| 79 |
+
"loss": 0.24068830013275147,
|
| 80 |
+
"step": 50
|
| 81 |
}
|
| 82 |
],
|
| 83 |
"logging_steps": 5,
|
|
|
|
| 97 |
"attributes": {}
|
| 98 |
}
|
| 99 |
},
|
| 100 |
+
"total_flos": 1.0812040250229366e+18,
|
| 101 |
"train_batch_size": 1,
|
| 102 |
"trial_name": null,
|
| 103 |
"trial_params": null
|