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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1f19e6383aec12c4eae5349170895bace32595111245030923642d5f5d59319
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43122580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a74721c65b74ae4d6f0639d48f5ce0caceab61cdd36cf0d5aaacb54cd7862313
|
| 3 |
size 43122580
|
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": 27.993,
|
| 38 |
"eval_steps_per_second": 13.997,
|
| 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": 0.000342405290161733,
|
| 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": 27.993,
|
| 38 |
"eval_steps_per_second": 13.997,
|
| 39 |
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.00025680396762129976,
|
| 43 |
+
"grad_norm": 3.9653892517089844,
|
| 44 |
+
"learning_rate": 3e-05,
|
| 45 |
+
"loss": 3.3246,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.000342405290161733,
|
| 50 |
+
"grad_norm": 4.707035064697266,
|
| 51 |
+
"learning_rate": 4e-05,
|
| 52 |
+
"loss": 3.1096,
|
| 53 |
+
"step": 4
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.000342405290161733,
|
| 57 |
+
"eval_loss": 3.2205007076263428,
|
| 58 |
+
"eval_runtime": 698.1994,
|
| 59 |
+
"eval_samples_per_second": 28.181,
|
| 60 |
+
"eval_steps_per_second": 14.091,
|
| 61 |
+
"step": 4
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"logging_steps": 1,
|
|
|
|
| 78 |
"attributes": {}
|
| 79 |
}
|
| 80 |
},
|
| 81 |
+
"total_flos": 2959354336641024.0,
|
| 82 |
"train_batch_size": 2,
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|