End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +693 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: qwen_s1ablation_length_filter_3k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# qwen_s1ablation_length_filter_3k
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: qwen_s1ablation_length_filter_3k
|
|
|
|
| 16 |
|
| 17 |
# qwen_s1ablation_length_filter_3k
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/s1_ablation_length_filtering_3k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9680851063829787,
|
| 3 |
+
"total_flos": 9.972328744511078e+16,
|
| 4 |
+
"train_loss": 0.572150158305322,
|
| 5 |
+
"train_runtime": 6573.3158,
|
| 6 |
+
"train_samples_per_second": 1.367,
|
| 7 |
+
"train_steps_per_second": 0.014
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9680851063829787,
|
| 3 |
+
"total_flos": 9.972328744511078e+16,
|
| 4 |
+
"train_loss": 0.572150158305322,
|
| 5 |
+
"train_runtime": 6573.3158,
|
| 6 |
+
"train_samples_per_second": 1.367,
|
| 7 |
+
"train_steps_per_second": 0.014
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,693 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9680851063829787,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 93,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.031914893617021274,
|
| 13 |
+
"grad_norm": 6.8550578526278265,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 0.932,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06382978723404255,
|
| 20 |
+
"grad_norm": 7.013355232346343,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 0.9473,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09574468085106383,
|
| 27 |
+
"grad_norm": 6.797491326295946,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 0.9455,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1276595744680851,
|
| 34 |
+
"grad_norm": 6.006779186550102,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 0.8771,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1595744680851064,
|
| 41 |
+
"grad_norm": 4.718397810977314,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.8497,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19148936170212766,
|
| 48 |
+
"grad_norm": 3.0155370941612145,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 0.7963,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22340425531914893,
|
| 55 |
+
"grad_norm": 2.623490752888302,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 0.8012,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2553191489361702,
|
| 62 |
+
"grad_norm": 4.869836279548957,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 0.817,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2872340425531915,
|
| 69 |
+
"grad_norm": 5.372434349228002,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 0.8346,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3191489361702128,
|
| 76 |
+
"grad_norm": 5.994234938255509,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 0.7893,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.35106382978723405,
|
| 83 |
+
"grad_norm": 5.733745579946726,
|
| 84 |
+
"learning_rate": 9.996418774081658e-06,
|
| 85 |
+
"loss": 0.7422,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3829787234042553,
|
| 90 |
+
"grad_norm": 4.4204248453136135,
|
| 91 |
+
"learning_rate": 9.985680226398261e-06,
|
| 92 |
+
"loss": 0.7908,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4148936170212766,
|
| 97 |
+
"grad_norm": 2.430090308570094,
|
| 98 |
+
"learning_rate": 9.967799739815925e-06,
|
| 99 |
+
"loss": 0.7172,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.44680851063829785,
|
| 104 |
+
"grad_norm": 1.992528375231062,
|
| 105 |
+
"learning_rate": 9.942802927959444e-06,
|
| 106 |
+
"loss": 0.6443,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4787234042553192,
|
| 111 |
+
"grad_norm": 2.073404546274239,
|
| 112 |
+
"learning_rate": 9.910725598521014e-06,
|
| 113 |
+
"loss": 0.6794,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5106382978723404,
|
| 118 |
+
"grad_norm": 1.6518913245895768,
|
| 119 |
+
"learning_rate": 9.871613701966067e-06,
|
| 120 |
+
"loss": 0.6596,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5425531914893617,
|
| 125 |
+
"grad_norm": 1.143582271461263,
|
| 126 |
+
"learning_rate": 9.825523265709667e-06,
|
| 127 |
+
"loss": 0.6276,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.574468085106383,
|
| 132 |
+
"grad_norm": 1.034648182185072,
|
| 133 |
+
"learning_rate": 9.772520313857777e-06,
|
| 134 |
+
"loss": 0.662,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6063829787234043,
|
| 139 |
+
"grad_norm": 0.9765973240996026,
|
| 140 |
+
"learning_rate": 9.712680772628365e-06,
|
| 141 |
+
"loss": 0.6119,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6382978723404256,
|
| 146 |
+
"grad_norm": 0.9718196871111608,
|
| 147 |
+
"learning_rate": 9.646090361587828e-06,
|
| 148 |
+
"loss": 0.6675,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6702127659574468,
|
| 153 |
+
"grad_norm": 0.82255237947582,
|
| 154 |
+
"learning_rate": 9.572844470858537e-06,
|
| 155 |
+
"loss": 0.6297,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7021276595744681,
|
| 160 |
+
"grad_norm": 0.8338965765348003,
|
| 161 |
+
"learning_rate": 9.493048024473413e-06,
|
| 162 |
+
"loss": 0.629,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7340425531914894,
|
| 167 |
+
"grad_norm": 0.7198317816442094,
|
| 168 |
+
"learning_rate": 9.406815330073244e-06,
|
| 169 |
+
"loss": 0.5871,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7659574468085106,
|
| 174 |
+
"grad_norm": 0.7144369764666283,
|
| 175 |
+
"learning_rate": 9.314269915162115e-06,
|
| 176 |
+
"loss": 0.607,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7978723404255319,
|
| 181 |
+
"grad_norm": 0.7473201677780328,
|
| 182 |
+
"learning_rate": 9.215544350155423e-06,
|
| 183 |
+
"loss": 0.5947,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8297872340425532,
|
| 188 |
+
"grad_norm": 0.7200026693118129,
|
| 189 |
+
"learning_rate": 9.110780058474052e-06,
|
| 190 |
+
"loss": 0.5902,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8617021276595744,
|
| 195 |
+
"grad_norm": 0.6320571574175119,
|
| 196 |
+
"learning_rate": 9.000127113956673e-06,
|
| 197 |
+
"loss": 0.5953,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8936170212765957,
|
| 202 |
+
"grad_norm": 0.7230280439527185,
|
| 203 |
+
"learning_rate": 8.883744025880429e-06,
|
| 204 |
+
"loss": 0.5942,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.925531914893617,
|
| 209 |
+
"grad_norm": 0.699296371807209,
|
| 210 |
+
"learning_rate": 8.761797511897907e-06,
|
| 211 |
+
"loss": 0.5787,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9574468085106383,
|
| 216 |
+
"grad_norm": 0.6499742051883518,
|
| 217 |
+
"learning_rate": 8.634462259215719e-06,
|
| 218 |
+
"loss": 0.6022,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9893617021276596,
|
| 223 |
+
"grad_norm": 0.6778398448184699,
|
| 224 |
+
"learning_rate": 8.501920674356755e-06,
|
| 225 |
+
"loss": 0.5748,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0212765957446808,
|
| 230 |
+
"grad_norm": 0.6696674206751512,
|
| 231 |
+
"learning_rate": 8.364362621864595e-06,
|
| 232 |
+
"loss": 0.5552,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.053191489361702,
|
| 237 |
+
"grad_norm": 0.6773862074318041,
|
| 238 |
+
"learning_rate": 8.221985152324385e-06,
|
| 239 |
+
"loss": 0.5632,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.0851063829787233,
|
| 244 |
+
"grad_norm": 0.5629648871964821,
|
| 245 |
+
"learning_rate": 8.07499222008977e-06,
|
| 246 |
+
"loss": 0.5421,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.1170212765957448,
|
| 251 |
+
"grad_norm": 0.6097565580951771,
|
| 252 |
+
"learning_rate": 7.923594391120237e-06,
|
| 253 |
+
"loss": 0.5369,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.148936170212766,
|
| 258 |
+
"grad_norm": 0.6129555219116115,
|
| 259 |
+
"learning_rate": 7.768008541347423e-06,
|
| 260 |
+
"loss": 0.5343,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.1808510638297873,
|
| 265 |
+
"grad_norm": 0.6402775021111746,
|
| 266 |
+
"learning_rate": 7.608457546002423e-06,
|
| 267 |
+
"loss": 0.5202,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.2127659574468086,
|
| 272 |
+
"grad_norm": 0.559032797722852,
|
| 273 |
+
"learning_rate": 7.445169960349167e-06,
|
| 274 |
+
"loss": 0.5513,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.2446808510638299,
|
| 279 |
+
"grad_norm": 0.5850891116512755,
|
| 280 |
+
"learning_rate": 7.278379692281209e-06,
|
| 281 |
+
"loss": 0.5359,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.2765957446808511,
|
| 286 |
+
"grad_norm": 0.5733779918532645,
|
| 287 |
+
"learning_rate": 7.10832566725092e-06,
|
| 288 |
+
"loss": 0.5326,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.3085106382978724,
|
| 293 |
+
"grad_norm": 0.5312066368171158,
|
| 294 |
+
"learning_rate": 6.9352514860110876e-06,
|
| 295 |
+
"loss": 0.543,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.3404255319148937,
|
| 300 |
+
"grad_norm": 0.6140381787535019,
|
| 301 |
+
"learning_rate": 6.759405075659165e-06,
|
| 302 |
+
"loss": 0.5466,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.372340425531915,
|
| 307 |
+
"grad_norm": 0.5516055127598528,
|
| 308 |
+
"learning_rate": 6.58103833448412e-06,
|
| 309 |
+
"loss": 0.5602,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.4042553191489362,
|
| 314 |
+
"grad_norm": 0.5563199731221804,
|
| 315 |
+
"learning_rate": 6.4004067711245366e-06,
|
| 316 |
+
"loss": 0.5071,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.4361702127659575,
|
| 321 |
+
"grad_norm": 0.5852422360524406,
|
| 322 |
+
"learning_rate": 6.2177691385549595e-06,
|
| 323 |
+
"loss": 0.5326,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4680851063829787,
|
| 328 |
+
"grad_norm": 0.5374337960941657,
|
| 329 |
+
"learning_rate": 6.033387063424765e-06,
|
| 330 |
+
"loss": 0.5118,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5,
|
| 335 |
+
"grad_norm": 0.536239110053256,
|
| 336 |
+
"learning_rate": 5.8475246712804845e-06,
|
| 337 |
+
"loss": 0.5272,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5319148936170213,
|
| 342 |
+
"grad_norm": 0.5911351047236098,
|
| 343 |
+
"learning_rate": 5.660448208208513e-06,
|
| 344 |
+
"loss": 0.5239,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.5638297872340425,
|
| 349 |
+
"grad_norm": 0.5999414579533445,
|
| 350 |
+
"learning_rate": 5.472425659440157e-06,
|
| 351 |
+
"loss": 0.5308,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.5957446808510638,
|
| 356 |
+
"grad_norm": 0.515941007245184,
|
| 357 |
+
"learning_rate": 5.2837263654653715e-06,
|
| 358 |
+
"loss": 0.5389,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.627659574468085,
|
| 363 |
+
"grad_norm": 0.5504997051047129,
|
| 364 |
+
"learning_rate": 5.094620636205096e-06,
|
| 365 |
+
"loss": 0.5305,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.6595744680851063,
|
| 370 |
+
"grad_norm": 0.572355284727229,
|
| 371 |
+
"learning_rate": 4.905379363794907e-06,
|
| 372 |
+
"loss": 0.5103,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.6914893617021276,
|
| 377 |
+
"grad_norm": 0.47241480561578947,
|
| 378 |
+
"learning_rate": 4.71627363453463e-06,
|
| 379 |
+
"loss": 0.5269,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.7234042553191489,
|
| 384 |
+
"grad_norm": 0.5395261535947259,
|
| 385 |
+
"learning_rate": 4.527574340559844e-06,
|
| 386 |
+
"loss": 0.51,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.7553191489361701,
|
| 391 |
+
"grad_norm": 0.5367986294902605,
|
| 392 |
+
"learning_rate": 4.33955179179149e-06,
|
| 393 |
+
"loss": 0.5164,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.7872340425531914,
|
| 398 |
+
"grad_norm": 0.5641812955609208,
|
| 399 |
+
"learning_rate": 4.152475328719517e-06,
|
| 400 |
+
"loss": 0.5564,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.8191489361702127,
|
| 405 |
+
"grad_norm": 0.47776480789357195,
|
| 406 |
+
"learning_rate": 3.966612936575235e-06,
|
| 407 |
+
"loss": 0.5157,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.851063829787234,
|
| 412 |
+
"grad_norm": 0.5611942864879007,
|
| 413 |
+
"learning_rate": 3.782230861445041e-06,
|
| 414 |
+
"loss": 0.539,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.8829787234042552,
|
| 419 |
+
"grad_norm": 0.5430640327485702,
|
| 420 |
+
"learning_rate": 3.5995932288754655e-06,
|
| 421 |
+
"loss": 0.4988,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.9148936170212765,
|
| 426 |
+
"grad_norm": 0.46459650156871163,
|
| 427 |
+
"learning_rate": 3.4189616655158803e-06,
|
| 428 |
+
"loss": 0.5095,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.9468085106382977,
|
| 433 |
+
"grad_norm": 0.4779195926661924,
|
| 434 |
+
"learning_rate": 3.240594924340835e-06,
|
| 435 |
+
"loss": 0.5123,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.978723404255319,
|
| 440 |
+
"grad_norm": 0.47237241921269846,
|
| 441 |
+
"learning_rate": 3.0647485139889145e-06,
|
| 442 |
+
"loss": 0.5324,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.0106382978723403,
|
| 447 |
+
"grad_norm": 0.4404936191513744,
|
| 448 |
+
"learning_rate": 2.89167433274908e-06,
|
| 449 |
+
"loss": 0.4947,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.0425531914893615,
|
| 454 |
+
"grad_norm": 0.49673935110331274,
|
| 455 |
+
"learning_rate": 2.721620307718793e-06,
|
| 456 |
+
"loss": 0.4666,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.074468085106383,
|
| 461 |
+
"grad_norm": 0.5020251675444986,
|
| 462 |
+
"learning_rate": 2.554830039650834e-06,
|
| 463 |
+
"loss": 0.5076,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.106382978723404,
|
| 468 |
+
"grad_norm": 0.48884396672881497,
|
| 469 |
+
"learning_rate": 2.391542453997578e-06,
|
| 470 |
+
"loss": 0.4387,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.1382978723404253,
|
| 475 |
+
"grad_norm": 0.44230905814020405,
|
| 476 |
+
"learning_rate": 2.2319914586525776e-06,
|
| 477 |
+
"loss": 0.4966,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.1702127659574466,
|
| 482 |
+
"grad_norm": 0.47526227786785014,
|
| 483 |
+
"learning_rate": 2.0764056088797646e-06,
|
| 484 |
+
"loss": 0.4922,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.202127659574468,
|
| 489 |
+
"grad_norm": 0.49237352965822306,
|
| 490 |
+
"learning_rate": 1.9250077799102323e-06,
|
| 491 |
+
"loss": 0.4669,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.2340425531914896,
|
| 496 |
+
"grad_norm": 0.4502453875913607,
|
| 497 |
+
"learning_rate": 1.7780148476756148e-06,
|
| 498 |
+
"loss": 0.4857,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.2659574468085104,
|
| 503 |
+
"grad_norm": 0.4662280662287629,
|
| 504 |
+
"learning_rate": 1.6356373781354058e-06,
|
| 505 |
+
"loss": 0.5172,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.297872340425532,
|
| 510 |
+
"grad_norm": 0.4453202462098244,
|
| 511 |
+
"learning_rate": 1.4980793256432474e-06,
|
| 512 |
+
"loss": 0.4854,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.329787234042553,
|
| 517 |
+
"grad_norm": 0.4214229445538365,
|
| 518 |
+
"learning_rate": 1.3655377407842813e-06,
|
| 519 |
+
"loss": 0.4804,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.3617021276595747,
|
| 524 |
+
"grad_norm": 0.4481289932432995,
|
| 525 |
+
"learning_rate": 1.2382024881020937e-06,
|
| 526 |
+
"loss": 0.4605,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.393617021276596,
|
| 531 |
+
"grad_norm": 0.4787024313670513,
|
| 532 |
+
"learning_rate": 1.1162559741195733e-06,
|
| 533 |
+
"loss": 0.4792,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.425531914893617,
|
| 538 |
+
"grad_norm": 0.42755817777456007,
|
| 539 |
+
"learning_rate": 9.998728860433277e-07,
|
| 540 |
+
"loss": 0.4638,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.4574468085106385,
|
| 545 |
+
"grad_norm": 0.4503230179095763,
|
| 546 |
+
"learning_rate": 8.892199415259501e-07,
|
| 547 |
+
"loss": 0.4869,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.4893617021276597,
|
| 552 |
+
"grad_norm": 0.46380219844862847,
|
| 553 |
+
"learning_rate": 7.844556498445788e-07,
|
| 554 |
+
"loss": 0.4829,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.521276595744681,
|
| 559 |
+
"grad_norm": 0.4312376136274964,
|
| 560 |
+
"learning_rate": 6.857300848378857e-07,
|
| 561 |
+
"loss": 0.4851,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.5531914893617023,
|
| 566 |
+
"grad_norm": 0.44216206159723803,
|
| 567 |
+
"learning_rate": 5.931846699267558e-07,
|
| 568 |
+
"loss": 0.4586,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.5851063829787235,
|
| 573 |
+
"grad_norm": 0.43806592381083187,
|
| 574 |
+
"learning_rate": 5.0695197552659e-07,
|
| 575 |
+
"loss": 0.4825,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.617021276595745,
|
| 580 |
+
"grad_norm": 0.44704124469732137,
|
| 581 |
+
"learning_rate": 4.271555291414636e-07,
|
| 582 |
+
"loss": 0.4735,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.648936170212766,
|
| 587 |
+
"grad_norm": 0.41748932073536293,
|
| 588 |
+
"learning_rate": 3.539096384121743e-07,
|
| 589 |
+
"loss": 0.479,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.6808510638297873,
|
| 594 |
+
"grad_norm": 0.4257066986234634,
|
| 595 |
+
"learning_rate": 2.873192273716369e-07,
|
| 596 |
+
"loss": 0.4769,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.7127659574468086,
|
| 601 |
+
"grad_norm": 0.4106480522900997,
|
| 602 |
+
"learning_rate": 2.274796861422246e-07,
|
| 603 |
+
"loss": 0.4837,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.74468085106383,
|
| 608 |
+
"grad_norm": 0.4003124811751833,
|
| 609 |
+
"learning_rate": 1.7447673429033361e-07,
|
| 610 |
+
"loss": 0.4664,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.776595744680851,
|
| 615 |
+
"grad_norm": 0.416026013618055,
|
| 616 |
+
"learning_rate": 1.2838629803393343e-07,
|
| 617 |
+
"loss": 0.4794,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.8085106382978724,
|
| 622 |
+
"grad_norm": 0.4203294534133312,
|
| 623 |
+
"learning_rate": 8.927440147898703e-08,
|
| 624 |
+
"loss": 0.4776,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.8404255319148937,
|
| 629 |
+
"grad_norm": 0.41184497425847133,
|
| 630 |
+
"learning_rate": 5.7197072040557356e-08,
|
| 631 |
+
"loss": 0.456,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.872340425531915,
|
| 636 |
+
"grad_norm": 0.40502177596219247,
|
| 637 |
+
"learning_rate": 3.220026018407541e-08,
|
| 638 |
+
"loss": 0.461,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.904255319148936,
|
| 643 |
+
"grad_norm": 0.4095890383598189,
|
| 644 |
+
"learning_rate": 1.431977360173975e-08,
|
| 645 |
+
"loss": 0.4751,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.9361702127659575,
|
| 650 |
+
"grad_norm": 0.42995029806707724,
|
| 651 |
+
"learning_rate": 3.5812259183426457e-09,
|
| 652 |
+
"loss": 0.4725,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.9680851063829787,
|
| 657 |
+
"grad_norm": 0.38318012501126997,
|
| 658 |
+
"learning_rate": 0.0,
|
| 659 |
+
"loss": 0.4504,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.9680851063829787,
|
| 664 |
+
"step": 93,
|
| 665 |
+
"total_flos": 9.972328744511078e+16,
|
| 666 |
+
"train_loss": 0.572150158305322,
|
| 667 |
+
"train_runtime": 6573.3158,
|
| 668 |
+
"train_samples_per_second": 1.367,
|
| 669 |
+
"train_steps_per_second": 0.014
|
| 670 |
+
}
|
| 671 |
+
],
|
| 672 |
+
"logging_steps": 1,
|
| 673 |
+
"max_steps": 93,
|
| 674 |
+
"num_input_tokens_seen": 0,
|
| 675 |
+
"num_train_epochs": 3,
|
| 676 |
+
"save_steps": 10,
|
| 677 |
+
"stateful_callbacks": {
|
| 678 |
+
"TrainerControl": {
|
| 679 |
+
"args": {
|
| 680 |
+
"should_epoch_stop": false,
|
| 681 |
+
"should_evaluate": false,
|
| 682 |
+
"should_log": false,
|
| 683 |
+
"should_save": true,
|
| 684 |
+
"should_training_stop": true
|
| 685 |
+
},
|
| 686 |
+
"attributes": {}
|
| 687 |
+
}
|
| 688 |
+
},
|
| 689 |
+
"total_flos": 9.972328744511078e+16,
|
| 690 |
+
"train_batch_size": 2,
|
| 691 |
+
"trial_name": null,
|
| 692 |
+
"trial_params": null
|
| 693 |
+
}
|
training_loss.png
ADDED
|