Training in progress, step 4, 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 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29ade429eba1c54e519f2b5c18cd0396a6fd212e7b189aece487d11d0f16843d
|
| 3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41119636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f386991ba7f458e5fc07a4e64d285f814bdbc0d94363d6f0cf7a74cdec3f9eb6
|
| 3 |
size 41119636
|
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:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
|
| 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:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
|
| 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": 2,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -37,6 +37,28 @@
|
|
| 37 |
"eval_samples_per_second": 27.863,
|
| 38 |
"eval_steps_per_second": 13.932,
|
| 39 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 1,
|
|
@@ -56,7 +78,7 @@
|
|
| 56 |
"attributes": {}
|
| 57 |
}
|
| 58 |
},
|
| 59 |
-
"total_flos":
|
| 60 |
"train_batch_size": 2,
|
| 61 |
"trial_name": null,
|
| 62 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.008235748294942736,
|
| 5 |
"eval_steps": 2,
|
| 6 |
+
"global_step": 4,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 37 |
"eval_samples_per_second": 27.863,
|
| 38 |
"eval_steps_per_second": 13.932,
|
| 39 |
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.006176811221207052,
|
| 43 |
+
"grad_norm": 1.4818819761276245,
|
| 44 |
+
"learning_rate": 3e-05,
|
| 45 |
+
"loss": 40.1928,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.008235748294942736,
|
| 50 |
+
"grad_norm": 1.505240559577942,
|
| 51 |
+
"learning_rate": 4e-05,
|
| 52 |
+
"loss": 38.817,
|
| 53 |
+
"step": 4
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.008235748294942736,
|
| 57 |
+
"eval_loss": 2.5333926677703857,
|
| 58 |
+
"eval_runtime": 29.4792,
|
| 59 |
+
"eval_samples_per_second": 27.748,
|
| 60 |
+
"eval_steps_per_second": 13.874,
|
| 61 |
+
"step": 4
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"logging_steps": 1,
|
|
|
|
| 78 |
"attributes": {}
|
| 79 |
}
|
| 80 |
},
|
| 81 |
+
"total_flos": 4438341684559872.0,
|
| 82 |
"train_batch_size": 2,
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|