Training in progress, step 2, 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 14194992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eadeb8358d31ac88cc01651643637e022efb49415c267f3724e50eb00bc1625
|
| 3 |
size 14194992
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7525204
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f23e7e6519ff1dce0150fdaefdf4777b3798f1ab2a2394f105eabb42adabd9
|
| 3 |
size 7525204
|
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 sha256:9879c127c4c486e57968dbcc930d96812e83ddc9b2717ffc64e25d1907d0af29
|
| 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:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
|
| 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": 1,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -22,6 +22,21 @@
|
|
| 22 |
"eval_samples_per_second": 23.08,
|
| 23 |
"eval_steps_per_second": 23.08,
|
| 24 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 1,
|
|
@@ -36,12 +51,12 @@
|
|
| 36 |
"should_evaluate": false,
|
| 37 |
"should_log": false,
|
| 38 |
"should_save": true,
|
| 39 |
-
"should_training_stop":
|
| 40 |
},
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"total_flos":
|
| 45 |
"train_batch_size": 1,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0002170374389582203,
|
| 5 |
"eval_steps": 1,
|
| 6 |
+
"global_step": 2,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 22 |
"eval_samples_per_second": 23.08,
|
| 23 |
"eval_steps_per_second": 23.08,
|
| 24 |
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0002170374389582203,
|
| 28 |
+
"grad_norm": 0.6113675236701965,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 1.9784,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0002170374389582203,
|
| 35 |
+
"eval_loss": 1.9339277744293213,
|
| 36 |
+
"eval_runtime": 20.0726,
|
| 37 |
+
"eval_samples_per_second": 24.162,
|
| 38 |
+
"eval_steps_per_second": 24.162,
|
| 39 |
+
"step": 2
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 1,
|
|
|
|
| 51 |
"should_evaluate": false,
|
| 52 |
"should_log": false,
|
| 53 |
"should_save": true,
|
| 54 |
+
"should_training_stop": true
|
| 55 |
},
|
| 56 |
"attributes": {}
|
| 57 |
}
|
| 58 |
},
|
| 59 |
+
"total_flos": 7447397793792.0,
|
| 60 |
"train_batch_size": 1,
|
| 61 |
"trial_name": null,
|
| 62 |
"trial_params": null
|