Training in progress, step 9, 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 50899792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd59e523a9a64e26d6faee8010141bdaacac1c5447785582578f186272197cd0
|
| 3 |
size 50899792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 26231300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba053e778284285d0878ca5ee1e24c2999c084521ed364a8c50b0c922aced25b
|
| 3 |
size 26231300
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 3,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -73,6 +73,35 @@
|
|
| 73 |
"eval_samples_per_second": 31.805,
|
| 74 |
"eval_steps_per_second": 15.902,
|
| 75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 1,
|
|
@@ -92,7 +121,7 @@
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
-
"total_flos":
|
| 96 |
"train_batch_size": 2,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0057553956834532375,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 73 |
"eval_samples_per_second": 31.805,
|
| 74 |
"eval_steps_per_second": 15.902,
|
| 75 |
"step": 6
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.004476418864908073,
|
| 79 |
+
"grad_norm": 0.630357027053833,
|
| 80 |
+
"learning_rate": 7e-05,
|
| 81 |
+
"loss": 2.6365,
|
| 82 |
+
"step": 7
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.005115907274180656,
|
| 86 |
+
"grad_norm": 0.6484892964363098,
|
| 87 |
+
"learning_rate": 8e-05,
|
| 88 |
+
"loss": 2.5914,
|
| 89 |
+
"step": 8
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.0057553956834532375,
|
| 93 |
+
"grad_norm": 0.7151474952697754,
|
| 94 |
+
"learning_rate": 9e-05,
|
| 95 |
+
"loss": 2.5751,
|
| 96 |
+
"step": 9
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.0057553956834532375,
|
| 100 |
+
"eval_loss": 2.7833847999572754,
|
| 101 |
+
"eval_runtime": 101.2113,
|
| 102 |
+
"eval_samples_per_second": 26.025,
|
| 103 |
+
"eval_steps_per_second": 13.012,
|
| 104 |
+
"step": 9
|
| 105 |
}
|
| 106 |
],
|
| 107 |
"logging_steps": 1,
|
|
|
|
| 121 |
"attributes": {}
|
| 122 |
}
|
| 123 |
},
|
| 124 |
+
"total_flos": 3526209259438080.0,
|
| 125 |
"train_batch_size": 2,
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|