Training in progress, step 141
Browse files- model.safetensors +1 -1
- run-knhtrdyo/checkpoint-141/config.json +22 -0
- run-knhtrdyo/checkpoint-141/model.safetensors +3 -0
- run-knhtrdyo/checkpoint-141/optimizer.pt +3 -0
- run-knhtrdyo/checkpoint-141/rng_state.pth +3 -0
- run-knhtrdyo/checkpoint-141/scheduler.pt +3 -0
- run-knhtrdyo/checkpoint-141/trainer_state.json +745 -0
- run-knhtrdyo/checkpoint-141/training_args.bin +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 605156676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905a43307f614d4f5d5bc9343535d19dfe7851432eb2dd6fa364e60c0180fd0c
|
| 3 |
size 605156676
|
run-knhtrdyo/checkpoint-141/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"model_type": "clip_text_model"
|
| 15 |
+
},
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"transformers_version": "4.42.0.dev0",
|
| 18 |
+
"vision_config": {
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"model_type": "clip_vision_model"
|
| 21 |
+
}
|
| 22 |
+
}
|
run-knhtrdyo/checkpoint-141/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905a43307f614d4f5d5bc9343535d19dfe7851432eb2dd6fa364e60c0180fd0c
|
| 3 |
+
size 605156676
|
run-knhtrdyo/checkpoint-141/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25f25d9edbbbcd9f0437c8a41332e1d15751f6cb92c7c853f35ed0b821ae271b
|
| 3 |
+
size 1210551612
|
run-knhtrdyo/checkpoint-141/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62c07c8744379eb786eff44fab8c913f61ee58d12b31db96d56a74fd477c3546
|
| 3 |
+
size 14244
|
run-knhtrdyo/checkpoint-141/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee36591f8697822e7a352101522d56f69310ef393a950d7f95d0c4afec9bfbd1
|
| 3 |
+
size 1064
|
run-knhtrdyo/checkpoint-141/trainer_state.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 3,
|
| 6 |
+
"global_step": 141,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06382978723404255,
|
| 13 |
+
"grad_norm": 80.34429931640625,
|
| 14 |
+
"learning_rate": 3.887121421183269e-05,
|
| 15 |
+
"loss": 2.3944,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06382978723404255,
|
| 20 |
+
"eval_loss": 1.3597443103790283,
|
| 21 |
+
"eval_runtime": 42.8414,
|
| 22 |
+
"eval_samples_per_second": 7.003,
|
| 23 |
+
"eval_steps_per_second": 0.233,
|
| 24 |
+
"step": 3
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1276595744680851,
|
| 28 |
+
"grad_norm": 80.95482635498047,
|
| 29 |
+
"learning_rate": 3.802618781592329e-05,
|
| 30 |
+
"loss": 1.7519,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1276595744680851,
|
| 35 |
+
"eval_loss": 1.3402976989746094,
|
| 36 |
+
"eval_runtime": 43.3224,
|
| 37 |
+
"eval_samples_per_second": 6.925,
|
| 38 |
+
"eval_steps_per_second": 0.231,
|
| 39 |
+
"step": 6
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19148936170212766,
|
| 43 |
+
"grad_norm": 53.1098518371582,
|
| 44 |
+
"learning_rate": 3.718116142001388e-05,
|
| 45 |
+
"loss": 2.0232,
|
| 46 |
+
"step": 9
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.19148936170212766,
|
| 50 |
+
"eval_loss": 1.2916953563690186,
|
| 51 |
+
"eval_runtime": 43.9726,
|
| 52 |
+
"eval_samples_per_second": 6.822,
|
| 53 |
+
"eval_steps_per_second": 0.227,
|
| 54 |
+
"step": 9
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2553191489361702,
|
| 58 |
+
"grad_norm": 53.377994537353516,
|
| 59 |
+
"learning_rate": 3.633613502410447e-05,
|
| 60 |
+
"loss": 1.6641,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.2553191489361702,
|
| 65 |
+
"eval_loss": 1.2752994298934937,
|
| 66 |
+
"eval_runtime": 43.2266,
|
| 67 |
+
"eval_samples_per_second": 6.94,
|
| 68 |
+
"eval_steps_per_second": 0.231,
|
| 69 |
+
"step": 12
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3191489361702128,
|
| 73 |
+
"grad_norm": 53.05588912963867,
|
| 74 |
+
"learning_rate": 3.549110862819506e-05,
|
| 75 |
+
"loss": 1.7703,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.3191489361702128,
|
| 80 |
+
"eval_loss": 1.3723009824752808,
|
| 81 |
+
"eval_runtime": 42.8294,
|
| 82 |
+
"eval_samples_per_second": 7.005,
|
| 83 |
+
"eval_steps_per_second": 0.233,
|
| 84 |
+
"step": 15
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.3829787234042553,
|
| 88 |
+
"grad_norm": 62.77140426635742,
|
| 89 |
+
"learning_rate": 3.464608223228566e-05,
|
| 90 |
+
"loss": 1.8673,
|
| 91 |
+
"step": 18
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.3829787234042553,
|
| 95 |
+
"eval_loss": 1.2411926984786987,
|
| 96 |
+
"eval_runtime": 42.9096,
|
| 97 |
+
"eval_samples_per_second": 6.991,
|
| 98 |
+
"eval_steps_per_second": 0.233,
|
| 99 |
+
"step": 18
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.44680851063829785,
|
| 103 |
+
"grad_norm": 47.35882568359375,
|
| 104 |
+
"learning_rate": 3.380105583637625e-05,
|
| 105 |
+
"loss": 1.6474,
|
| 106 |
+
"step": 21
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.44680851063829785,
|
| 110 |
+
"eval_loss": 1.26935613155365,
|
| 111 |
+
"eval_runtime": 42.8918,
|
| 112 |
+
"eval_samples_per_second": 6.994,
|
| 113 |
+
"eval_steps_per_second": 0.233,
|
| 114 |
+
"step": 21
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5106382978723404,
|
| 118 |
+
"grad_norm": 46.5376091003418,
|
| 119 |
+
"learning_rate": 3.295602944046684e-05,
|
| 120 |
+
"loss": 1.8483,
|
| 121 |
+
"step": 24
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5106382978723404,
|
| 125 |
+
"eval_loss": 1.2977941036224365,
|
| 126 |
+
"eval_runtime": 57.8311,
|
| 127 |
+
"eval_samples_per_second": 5.188,
|
| 128 |
+
"eval_steps_per_second": 0.173,
|
| 129 |
+
"step": 24
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.574468085106383,
|
| 133 |
+
"grad_norm": 48.203128814697266,
|
| 134 |
+
"learning_rate": 3.2111003044557436e-05,
|
| 135 |
+
"loss": 1.9855,
|
| 136 |
+
"step": 27
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.574468085106383,
|
| 140 |
+
"eval_loss": 1.2468695640563965,
|
| 141 |
+
"eval_runtime": 42.4489,
|
| 142 |
+
"eval_samples_per_second": 7.067,
|
| 143 |
+
"eval_steps_per_second": 0.236,
|
| 144 |
+
"step": 27
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6382978723404256,
|
| 148 |
+
"grad_norm": 41.71063232421875,
|
| 149 |
+
"learning_rate": 3.1265976648648035e-05,
|
| 150 |
+
"loss": 1.6176,
|
| 151 |
+
"step": 30
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6382978723404256,
|
| 155 |
+
"eval_loss": 1.183661937713623,
|
| 156 |
+
"eval_runtime": 42.834,
|
| 157 |
+
"eval_samples_per_second": 7.004,
|
| 158 |
+
"eval_steps_per_second": 0.233,
|
| 159 |
+
"step": 30
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7021276595744681,
|
| 163 |
+
"grad_norm": 52.453773498535156,
|
| 164 |
+
"learning_rate": 3.0420950252738625e-05,
|
| 165 |
+
"loss": 1.8235,
|
| 166 |
+
"step": 33
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7021276595744681,
|
| 170 |
+
"eval_loss": 1.1166750192642212,
|
| 171 |
+
"eval_runtime": 44.7724,
|
| 172 |
+
"eval_samples_per_second": 6.701,
|
| 173 |
+
"eval_steps_per_second": 0.223,
|
| 174 |
+
"step": 33
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.7659574468085106,
|
| 178 |
+
"grad_norm": 52.157142639160156,
|
| 179 |
+
"learning_rate": 2.9575923856829217e-05,
|
| 180 |
+
"loss": 1.9279,
|
| 181 |
+
"step": 36
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7659574468085106,
|
| 185 |
+
"eval_loss": 1.088130235671997,
|
| 186 |
+
"eval_runtime": 42.5129,
|
| 187 |
+
"eval_samples_per_second": 7.057,
|
| 188 |
+
"eval_steps_per_second": 0.235,
|
| 189 |
+
"step": 36
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.8297872340425532,
|
| 193 |
+
"grad_norm": 43.151649475097656,
|
| 194 |
+
"learning_rate": 2.8730897460919814e-05,
|
| 195 |
+
"loss": 1.7259,
|
| 196 |
+
"step": 39
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8297872340425532,
|
| 200 |
+
"eval_loss": 1.0796281099319458,
|
| 201 |
+
"eval_runtime": 44.2103,
|
| 202 |
+
"eval_samples_per_second": 6.786,
|
| 203 |
+
"eval_steps_per_second": 0.226,
|
| 204 |
+
"step": 39
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.8936170212765957,
|
| 208 |
+
"grad_norm": 38.12554168701172,
|
| 209 |
+
"learning_rate": 2.7885871065010406e-05,
|
| 210 |
+
"loss": 1.6895,
|
| 211 |
+
"step": 42
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.8936170212765957,
|
| 215 |
+
"eval_loss": 1.0776959657669067,
|
| 216 |
+
"eval_runtime": 42.9414,
|
| 217 |
+
"eval_samples_per_second": 6.986,
|
| 218 |
+
"eval_steps_per_second": 0.233,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9574468085106383,
|
| 223 |
+
"grad_norm": 42.756072998046875,
|
| 224 |
+
"learning_rate": 2.7040844669101e-05,
|
| 225 |
+
"loss": 1.4091,
|
| 226 |
+
"step": 45
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9574468085106383,
|
| 230 |
+
"eval_loss": 1.0285353660583496,
|
| 231 |
+
"eval_runtime": 43.4938,
|
| 232 |
+
"eval_samples_per_second": 6.898,
|
| 233 |
+
"eval_steps_per_second": 0.23,
|
| 234 |
+
"step": 45
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0212765957446808,
|
| 238 |
+
"grad_norm": 23.573442459106445,
|
| 239 |
+
"learning_rate": 2.6195818273191592e-05,
|
| 240 |
+
"loss": 1.0737,
|
| 241 |
+
"step": 48
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0212765957446808,
|
| 245 |
+
"eval_loss": 0.978798508644104,
|
| 246 |
+
"eval_runtime": 43.5576,
|
| 247 |
+
"eval_samples_per_second": 6.887,
|
| 248 |
+
"eval_steps_per_second": 0.23,
|
| 249 |
+
"step": 48
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0851063829787233,
|
| 253 |
+
"grad_norm": 30.33362579345703,
|
| 254 |
+
"learning_rate": 2.5350791877282188e-05,
|
| 255 |
+
"loss": 0.4698,
|
| 256 |
+
"step": 51
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0851063829787233,
|
| 260 |
+
"eval_loss": 0.9652482271194458,
|
| 261 |
+
"eval_runtime": 43.4723,
|
| 262 |
+
"eval_samples_per_second": 6.901,
|
| 263 |
+
"eval_steps_per_second": 0.23,
|
| 264 |
+
"step": 51
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.148936170212766,
|
| 268 |
+
"grad_norm": 35.88121795654297,
|
| 269 |
+
"learning_rate": 2.450576548137278e-05,
|
| 270 |
+
"loss": 0.3656,
|
| 271 |
+
"step": 54
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.148936170212766,
|
| 275 |
+
"eval_loss": 1.0351228713989258,
|
| 276 |
+
"eval_runtime": 42.8523,
|
| 277 |
+
"eval_samples_per_second": 7.001,
|
| 278 |
+
"eval_steps_per_second": 0.233,
|
| 279 |
+
"step": 54
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.2127659574468086,
|
| 283 |
+
"grad_norm": 34.332733154296875,
|
| 284 |
+
"learning_rate": 2.3660739085463373e-05,
|
| 285 |
+
"loss": 0.367,
|
| 286 |
+
"step": 57
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.2127659574468086,
|
| 290 |
+
"eval_loss": 1.0503636598587036,
|
| 291 |
+
"eval_runtime": 42.5022,
|
| 292 |
+
"eval_samples_per_second": 7.058,
|
| 293 |
+
"eval_steps_per_second": 0.235,
|
| 294 |
+
"step": 57
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.2765957446808511,
|
| 298 |
+
"grad_norm": 26.370752334594727,
|
| 299 |
+
"learning_rate": 2.2815712689553973e-05,
|
| 300 |
+
"loss": 0.3007,
|
| 301 |
+
"step": 60
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.2765957446808511,
|
| 305 |
+
"eval_loss": 1.1509090662002563,
|
| 306 |
+
"eval_runtime": 42.1053,
|
| 307 |
+
"eval_samples_per_second": 7.125,
|
| 308 |
+
"eval_steps_per_second": 0.237,
|
| 309 |
+
"step": 60
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3404255319148937,
|
| 313 |
+
"grad_norm": 32.67679977416992,
|
| 314 |
+
"learning_rate": 2.1970686293644566e-05,
|
| 315 |
+
"loss": 0.2617,
|
| 316 |
+
"step": 63
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.3404255319148937,
|
| 320 |
+
"eval_loss": 1.2563477754592896,
|
| 321 |
+
"eval_runtime": 42.6658,
|
| 322 |
+
"eval_samples_per_second": 7.031,
|
| 323 |
+
"eval_steps_per_second": 0.234,
|
| 324 |
+
"step": 63
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4042553191489362,
|
| 328 |
+
"grad_norm": 30.998994827270508,
|
| 329 |
+
"learning_rate": 2.1125659897735155e-05,
|
| 330 |
+
"loss": 0.3067,
|
| 331 |
+
"step": 66
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4042553191489362,
|
| 335 |
+
"eval_loss": 1.2702378034591675,
|
| 336 |
+
"eval_runtime": 42.9938,
|
| 337 |
+
"eval_samples_per_second": 6.978,
|
| 338 |
+
"eval_steps_per_second": 0.233,
|
| 339 |
+
"step": 66
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4680851063829787,
|
| 343 |
+
"grad_norm": 39.6378173828125,
|
| 344 |
+
"learning_rate": 2.0280633501825748e-05,
|
| 345 |
+
"loss": 0.4341,
|
| 346 |
+
"step": 69
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4680851063829787,
|
| 350 |
+
"eval_loss": 1.2797026634216309,
|
| 351 |
+
"eval_runtime": 42.7243,
|
| 352 |
+
"eval_samples_per_second": 7.022,
|
| 353 |
+
"eval_steps_per_second": 0.234,
|
| 354 |
+
"step": 69
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.5319148936170213,
|
| 358 |
+
"grad_norm": 31.207704544067383,
|
| 359 |
+
"learning_rate": 1.9435607105916344e-05,
|
| 360 |
+
"loss": 0.2593,
|
| 361 |
+
"step": 72
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5319148936170213,
|
| 365 |
+
"eval_loss": 1.2919628620147705,
|
| 366 |
+
"eval_runtime": 42.6582,
|
| 367 |
+
"eval_samples_per_second": 7.033,
|
| 368 |
+
"eval_steps_per_second": 0.234,
|
| 369 |
+
"step": 72
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.5957446808510638,
|
| 373 |
+
"grad_norm": 40.96000671386719,
|
| 374 |
+
"learning_rate": 1.859058071000694e-05,
|
| 375 |
+
"loss": 0.3883,
|
| 376 |
+
"step": 75
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.5957446808510638,
|
| 380 |
+
"eval_loss": 1.3112432956695557,
|
| 381 |
+
"eval_runtime": 42.5003,
|
| 382 |
+
"eval_samples_per_second": 7.059,
|
| 383 |
+
"eval_steps_per_second": 0.235,
|
| 384 |
+
"step": 75
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.6595744680851063,
|
| 388 |
+
"grad_norm": 35.7375602722168,
|
| 389 |
+
"learning_rate": 1.774555431409753e-05,
|
| 390 |
+
"loss": 0.2884,
|
| 391 |
+
"step": 78
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.6595744680851063,
|
| 395 |
+
"eval_loss": 1.2621341943740845,
|
| 396 |
+
"eval_runtime": 42.7524,
|
| 397 |
+
"eval_samples_per_second": 7.017,
|
| 398 |
+
"eval_steps_per_second": 0.234,
|
| 399 |
+
"step": 78
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.7234042553191489,
|
| 403 |
+
"grad_norm": 44.75884246826172,
|
| 404 |
+
"learning_rate": 1.6900527918188125e-05,
|
| 405 |
+
"loss": 0.3337,
|
| 406 |
+
"step": 81
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.7234042553191489,
|
| 410 |
+
"eval_loss": 1.2016278505325317,
|
| 411 |
+
"eval_runtime": 42.4112,
|
| 412 |
+
"eval_samples_per_second": 7.074,
|
| 413 |
+
"eval_steps_per_second": 0.236,
|
| 414 |
+
"step": 81
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.7872340425531914,
|
| 418 |
+
"grad_norm": 33.257354736328125,
|
| 419 |
+
"learning_rate": 1.6055501522278718e-05,
|
| 420 |
+
"loss": 0.2944,
|
| 421 |
+
"step": 84
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.7872340425531914,
|
| 425 |
+
"eval_loss": 1.2495335340499878,
|
| 426 |
+
"eval_runtime": 42.3782,
|
| 427 |
+
"eval_samples_per_second": 7.079,
|
| 428 |
+
"eval_steps_per_second": 0.236,
|
| 429 |
+
"step": 84
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.851063829787234,
|
| 433 |
+
"grad_norm": 35.243255615234375,
|
| 434 |
+
"learning_rate": 1.5210475126369312e-05,
|
| 435 |
+
"loss": 0.3281,
|
| 436 |
+
"step": 87
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.851063829787234,
|
| 440 |
+
"eval_loss": 1.2671111822128296,
|
| 441 |
+
"eval_runtime": 42.4639,
|
| 442 |
+
"eval_samples_per_second": 7.065,
|
| 443 |
+
"eval_steps_per_second": 0.235,
|
| 444 |
+
"step": 87
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9148936170212765,
|
| 448 |
+
"grad_norm": 40.47667694091797,
|
| 449 |
+
"learning_rate": 1.4365448730459907e-05,
|
| 450 |
+
"loss": 0.3468,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9148936170212765,
|
| 455 |
+
"eval_loss": 1.2560263872146606,
|
| 456 |
+
"eval_runtime": 42.1118,
|
| 457 |
+
"eval_samples_per_second": 7.124,
|
| 458 |
+
"eval_steps_per_second": 0.237,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.978723404255319,
|
| 463 |
+
"grad_norm": 30.257667541503906,
|
| 464 |
+
"learning_rate": 1.35204223345505e-05,
|
| 465 |
+
"loss": 0.2954,
|
| 466 |
+
"step": 93
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.978723404255319,
|
| 470 |
+
"eval_loss": 1.237885594367981,
|
| 471 |
+
"eval_runtime": 42.0457,
|
| 472 |
+
"eval_samples_per_second": 7.135,
|
| 473 |
+
"eval_steps_per_second": 0.238,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0425531914893615,
|
| 478 |
+
"grad_norm": 18.296720504760742,
|
| 479 |
+
"learning_rate": 1.2675395938641094e-05,
|
| 480 |
+
"loss": 0.1694,
|
| 481 |
+
"step": 96
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.0425531914893615,
|
| 485 |
+
"eval_loss": 1.2138055562973022,
|
| 486 |
+
"eval_runtime": 42.7863,
|
| 487 |
+
"eval_samples_per_second": 7.012,
|
| 488 |
+
"eval_steps_per_second": 0.234,
|
| 489 |
+
"step": 96
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.106382978723404,
|
| 493 |
+
"grad_norm": 7.274190902709961,
|
| 494 |
+
"learning_rate": 1.1830369542731687e-05,
|
| 495 |
+
"loss": 0.0778,
|
| 496 |
+
"step": 99
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.106382978723404,
|
| 500 |
+
"eval_loss": 1.2286603450775146,
|
| 501 |
+
"eval_runtime": 42.3621,
|
| 502 |
+
"eval_samples_per_second": 7.082,
|
| 503 |
+
"eval_steps_per_second": 0.236,
|
| 504 |
+
"step": 99
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.1702127659574466,
|
| 508 |
+
"grad_norm": 14.274185180664062,
|
| 509 |
+
"learning_rate": 1.0985343146822283e-05,
|
| 510 |
+
"loss": 0.0793,
|
| 511 |
+
"step": 102
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.1702127659574466,
|
| 515 |
+
"eval_loss": 1.2490485906600952,
|
| 516 |
+
"eval_runtime": 42.2779,
|
| 517 |
+
"eval_samples_per_second": 7.096,
|
| 518 |
+
"eval_steps_per_second": 0.237,
|
| 519 |
+
"step": 102
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.2340425531914896,
|
| 523 |
+
"grad_norm": 15.038166046142578,
|
| 524 |
+
"learning_rate": 1.0140316750912874e-05,
|
| 525 |
+
"loss": 0.1298,
|
| 526 |
+
"step": 105
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.2340425531914896,
|
| 530 |
+
"eval_loss": 1.2638708353042603,
|
| 531 |
+
"eval_runtime": 42.0836,
|
| 532 |
+
"eval_samples_per_second": 7.129,
|
| 533 |
+
"eval_steps_per_second": 0.238,
|
| 534 |
+
"step": 105
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.297872340425532,
|
| 538 |
+
"grad_norm": 8.163881301879883,
|
| 539 |
+
"learning_rate": 9.29529035500347e-06,
|
| 540 |
+
"loss": 0.0644,
|
| 541 |
+
"step": 108
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.297872340425532,
|
| 545 |
+
"eval_loss": 1.2883939743041992,
|
| 546 |
+
"eval_runtime": 42.5151,
|
| 547 |
+
"eval_samples_per_second": 7.056,
|
| 548 |
+
"eval_steps_per_second": 0.235,
|
| 549 |
+
"step": 108
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.3617021276595747,
|
| 553 |
+
"grad_norm": 8.98543930053711,
|
| 554 |
+
"learning_rate": 8.450263959094063e-06,
|
| 555 |
+
"loss": 0.0544,
|
| 556 |
+
"step": 111
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.3617021276595747,
|
| 560 |
+
"eval_loss": 1.2966901063919067,
|
| 561 |
+
"eval_runtime": 42.3737,
|
| 562 |
+
"eval_samples_per_second": 7.08,
|
| 563 |
+
"eval_steps_per_second": 0.236,
|
| 564 |
+
"step": 111
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.425531914893617,
|
| 568 |
+
"grad_norm": 6.994283676147461,
|
| 569 |
+
"learning_rate": 7.605237563184656e-06,
|
| 570 |
+
"loss": 0.0746,
|
| 571 |
+
"step": 114
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.425531914893617,
|
| 575 |
+
"eval_loss": 1.2750900983810425,
|
| 576 |
+
"eval_runtime": 44.4271,
|
| 577 |
+
"eval_samples_per_second": 6.753,
|
| 578 |
+
"eval_steps_per_second": 0.225,
|
| 579 |
+
"step": 114
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.4893617021276597,
|
| 583 |
+
"grad_norm": 19.321447372436523,
|
| 584 |
+
"learning_rate": 6.76021116727525e-06,
|
| 585 |
+
"loss": 0.0802,
|
| 586 |
+
"step": 117
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.4893617021276597,
|
| 590 |
+
"eval_loss": 1.25408935546875,
|
| 591 |
+
"eval_runtime": 42.5035,
|
| 592 |
+
"eval_samples_per_second": 7.058,
|
| 593 |
+
"eval_steps_per_second": 0.235,
|
| 594 |
+
"step": 117
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.5531914893617023,
|
| 598 |
+
"grad_norm": 11.252699851989746,
|
| 599 |
+
"learning_rate": 5.915184771365843e-06,
|
| 600 |
+
"loss": 0.0823,
|
| 601 |
+
"step": 120
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.5531914893617023,
|
| 605 |
+
"eval_loss": 1.238397479057312,
|
| 606 |
+
"eval_runtime": 43.1378,
|
| 607 |
+
"eval_samples_per_second": 6.954,
|
| 608 |
+
"eval_steps_per_second": 0.232,
|
| 609 |
+
"step": 120
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.617021276595745,
|
| 613 |
+
"grad_norm": 25.77452278137207,
|
| 614 |
+
"learning_rate": 5.070158375456437e-06,
|
| 615 |
+
"loss": 0.0724,
|
| 616 |
+
"step": 123
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.617021276595745,
|
| 620 |
+
"eval_loss": 1.2397345304489136,
|
| 621 |
+
"eval_runtime": 42.4151,
|
| 622 |
+
"eval_samples_per_second": 7.073,
|
| 623 |
+
"eval_steps_per_second": 0.236,
|
| 624 |
+
"step": 123
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.6808510638297873,
|
| 628 |
+
"grad_norm": 11.949565887451172,
|
| 629 |
+
"learning_rate": 4.225131979547031e-06,
|
| 630 |
+
"loss": 0.0471,
|
| 631 |
+
"step": 126
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.6808510638297873,
|
| 635 |
+
"eval_loss": 1.254788875579834,
|
| 636 |
+
"eval_runtime": 42.7067,
|
| 637 |
+
"eval_samples_per_second": 7.025,
|
| 638 |
+
"eval_steps_per_second": 0.234,
|
| 639 |
+
"step": 126
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.74468085106383,
|
| 643 |
+
"grad_norm": 21.035245895385742,
|
| 644 |
+
"learning_rate": 3.380105583637625e-06,
|
| 645 |
+
"loss": 0.12,
|
| 646 |
+
"step": 129
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.74468085106383,
|
| 650 |
+
"eval_loss": 1.268523097038269,
|
| 651 |
+
"eval_runtime": 53.7383,
|
| 652 |
+
"eval_samples_per_second": 5.583,
|
| 653 |
+
"eval_steps_per_second": 0.186,
|
| 654 |
+
"step": 129
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.8085106382978724,
|
| 658 |
+
"grad_norm": 10.42072582244873,
|
| 659 |
+
"learning_rate": 2.5350791877282184e-06,
|
| 660 |
+
"loss": 0.0438,
|
| 661 |
+
"step": 132
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.8085106382978724,
|
| 665 |
+
"eval_loss": 1.2748510837554932,
|
| 666 |
+
"eval_runtime": 42.6228,
|
| 667 |
+
"eval_samples_per_second": 7.038,
|
| 668 |
+
"eval_steps_per_second": 0.235,
|
| 669 |
+
"step": 132
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.872340425531915,
|
| 673 |
+
"grad_norm": 6.091249942779541,
|
| 674 |
+
"learning_rate": 1.6900527918188124e-06,
|
| 675 |
+
"loss": 0.09,
|
| 676 |
+
"step": 135
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.872340425531915,
|
| 680 |
+
"eval_loss": 1.2775297164916992,
|
| 681 |
+
"eval_runtime": 51.0919,
|
| 682 |
+
"eval_samples_per_second": 5.872,
|
| 683 |
+
"eval_steps_per_second": 0.196,
|
| 684 |
+
"step": 135
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.9361702127659575,
|
| 688 |
+
"grad_norm": 15.66469669342041,
|
| 689 |
+
"learning_rate": 8.450263959094062e-07,
|
| 690 |
+
"loss": 0.0699,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.9361702127659575,
|
| 695 |
+
"eval_loss": 1.2776027917861938,
|
| 696 |
+
"eval_runtime": 42.9499,
|
| 697 |
+
"eval_samples_per_second": 6.985,
|
| 698 |
+
"eval_steps_per_second": 0.233,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.0,
|
| 703 |
+
"grad_norm": 3.4863240718841553,
|
| 704 |
+
"learning_rate": 0.0,
|
| 705 |
+
"loss": 0.0984,
|
| 706 |
+
"step": 141
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.0,
|
| 710 |
+
"eval_loss": 1.2764135599136353,
|
| 711 |
+
"eval_runtime": 42.6511,
|
| 712 |
+
"eval_samples_per_second": 7.034,
|
| 713 |
+
"eval_steps_per_second": 0.234,
|
| 714 |
+
"step": 141
|
| 715 |
+
}
|
| 716 |
+
],
|
| 717 |
+
"logging_steps": 3,
|
| 718 |
+
"max_steps": 141,
|
| 719 |
+
"num_input_tokens_seen": 0,
|
| 720 |
+
"num_train_epochs": 3,
|
| 721 |
+
"save_steps": 500,
|
| 722 |
+
"stateful_callbacks": {
|
| 723 |
+
"TrainerControl": {
|
| 724 |
+
"args": {
|
| 725 |
+
"should_epoch_stop": false,
|
| 726 |
+
"should_evaluate": false,
|
| 727 |
+
"should_log": false,
|
| 728 |
+
"should_save": true,
|
| 729 |
+
"should_training_stop": true
|
| 730 |
+
},
|
| 731 |
+
"attributes": {}
|
| 732 |
+
}
|
| 733 |
+
},
|
| 734 |
+
"total_flos": 523328480700102.0,
|
| 735 |
+
"train_batch_size": 64,
|
| 736 |
+
"trial_name": null,
|
| 737 |
+
"trial_params": {
|
| 738 |
+
"_wandb": {},
|
| 739 |
+
"assignments": {},
|
| 740 |
+
"decay": 0.001,
|
| 741 |
+
"learning_rate": 3.9716240607742095e-05,
|
| 742 |
+
"metric": "eval/loss",
|
| 743 |
+
"per_device_train_batch_size": 64
|
| 744 |
+
}
|
| 745 |
+
}
|
run-knhtrdyo/checkpoint-141/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8dac4926eb2a580edb47f1290a3e9a1126fe3c128c5136263e3409a2c3f1104
|
| 3 |
+
size 5112
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8dac4926eb2a580edb47f1290a3e9a1126fe3c128c5136263e3409a2c3f1104
|
| 3 |
size 5112
|