End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +707 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: other
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: ex43_qwen2.5_3b_61k_source_16kcw_2ep_cuda_amd_os
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# ex43_qwen2.5_3b_61k_source_16kcw_2ep_cuda_amd_os
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: ex43_qwen2.5_3b_61k_source_16kcw_2ep_cuda_amd_os
|
|
|
|
| 16 |
|
| 17 |
# ex43_qwen2.5_3b_61k_source_16kcw_2ep_cuda_amd_os
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the cuda_61k_source dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9963379544860058,
|
| 3 |
+
"total_flos": 841298254757888.0,
|
| 4 |
+
"train_loss": 0.001730952451793395,
|
| 5 |
+
"train_runtime": 49706.0079,
|
| 6 |
+
"train_samples_per_second": 2.461,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9963379544860058,
|
| 3 |
+
"total_flos": 841298254757888.0,
|
| 4 |
+
"train_loss": 0.001730952451793395,
|
| 5 |
+
"train_runtime": 49706.0079,
|
| 6 |
+
"train_samples_per_second": 2.461,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,707 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9963379544860058,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 954,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020925974365681402,
|
| 13 |
+
"grad_norm": 0.5565130669449413,
|
| 14 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 15 |
+
"loss": 0.0288,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.041851948731362804,
|
| 20 |
+
"grad_norm": 0.18606951178093903,
|
| 21 |
+
"learning_rate": 4.166666666666667e-06,
|
| 22 |
+
"loss": 0.0118,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0627779230970442,
|
| 27 |
+
"grad_norm": 0.03950245765434584,
|
| 28 |
+
"learning_rate": 6.25e-06,
|
| 29 |
+
"loss": 0.0039,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08370389746272561,
|
| 34 |
+
"grad_norm": 0.03819057800914349,
|
| 35 |
+
"learning_rate": 8.333333333333334e-06,
|
| 36 |
+
"loss": 0.0029,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10462987182840701,
|
| 41 |
+
"grad_norm": 0.0544544775809417,
|
| 42 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 43 |
+
"loss": 0.0028,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1255558461940884,
|
| 48 |
+
"grad_norm": 0.017750069891728056,
|
| 49 |
+
"learning_rate": 1.25e-05,
|
| 50 |
+
"loss": 0.0024,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14648182055976983,
|
| 55 |
+
"grad_norm": 0.025688827192495198,
|
| 56 |
+
"learning_rate": 1.4583333333333333e-05,
|
| 57 |
+
"loss": 0.0021,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16740779492545121,
|
| 62 |
+
"grad_norm": 0.009892162090487124,
|
| 63 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 64 |
+
"loss": 0.0013,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18833376929113263,
|
| 69 |
+
"grad_norm": 0.013992833360284824,
|
| 70 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 71 |
+
"loss": 0.0006,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20925974365681402,
|
| 76 |
+
"grad_norm": 0.009570194364057852,
|
| 77 |
+
"learning_rate": 1.9998927475076107e-05,
|
| 78 |
+
"loss": 0.0029,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.23018571802249543,
|
| 83 |
+
"grad_norm": 0.011885486768552911,
|
| 84 |
+
"learning_rate": 1.998686421164407e-05,
|
| 85 |
+
"loss": 0.0019,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2511116923881768,
|
| 90 |
+
"grad_norm": 0.00535124159298834,
|
| 91 |
+
"learning_rate": 1.9961413253717214e-05,
|
| 92 |
+
"loss": 0.0007,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2720376667538582,
|
| 97 |
+
"grad_norm": 0.014087761849564343,
|
| 98 |
+
"learning_rate": 1.9922608719076874e-05,
|
| 99 |
+
"loss": 0.002,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.29296364111953965,
|
| 104 |
+
"grad_norm": 0.014243222134916782,
|
| 105 |
+
"learning_rate": 1.9870502626379127e-05,
|
| 106 |
+
"loss": 0.0011,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.31388961548522104,
|
| 111 |
+
"grad_norm": 0.02081790679071402,
|
| 112 |
+
"learning_rate": 1.980516482542224e-05,
|
| 113 |
+
"loss": 0.0019,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.33481558985090243,
|
| 118 |
+
"grad_norm": 0.017403596614001808,
|
| 119 |
+
"learning_rate": 1.972668290351084e-05,
|
| 120 |
+
"loss": 0.0022,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3557415642165838,
|
| 125 |
+
"grad_norm": 0.014181950638291016,
|
| 126 |
+
"learning_rate": 1.9635162068042547e-05,
|
| 127 |
+
"loss": 0.0013,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.37666753858226526,
|
| 132 |
+
"grad_norm": 0.004266630945852344,
|
| 133 |
+
"learning_rate": 1.9530725005474195e-05,
|
| 134 |
+
"loss": 0.0016,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39759351294794665,
|
| 139 |
+
"grad_norm": 0.003584919486125673,
|
| 140 |
+
"learning_rate": 1.9413511716856973e-05,
|
| 141 |
+
"loss": 0.0017,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.41851948731362804,
|
| 146 |
+
"grad_norm": 0.010407187744097775,
|
| 147 |
+
"learning_rate": 1.9283679330160726e-05,
|
| 148 |
+
"loss": 0.0006,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4394454616793094,
|
| 153 |
+
"grad_norm": 0.011994286058888401,
|
| 154 |
+
"learning_rate": 1.9141401889639167e-05,
|
| 155 |
+
"loss": 0.004,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.46037143604499087,
|
| 160 |
+
"grad_norm": 0.002559284420598525,
|
| 161 |
+
"learning_rate": 1.898687012251826e-05,
|
| 162 |
+
"loss": 0.0014,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.48129741041067226,
|
| 167 |
+
"grad_norm": 0.01635207542112704,
|
| 168 |
+
"learning_rate": 1.8820291183320602e-05,
|
| 169 |
+
"loss": 0.0035,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5022233847763536,
|
| 174 |
+
"grad_norm": 0.019845090979002694,
|
| 175 |
+
"learning_rate": 1.8641888376168483e-05,
|
| 176 |
+
"loss": 0.0004,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5231493591420351,
|
| 181 |
+
"grad_norm": 0.037240037127226344,
|
| 182 |
+
"learning_rate": 1.845190085543795e-05,
|
| 183 |
+
"loss": 0.0032,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5440753335077164,
|
| 188 |
+
"grad_norm": 0.006653507161649646,
|
| 189 |
+
"learning_rate": 1.8250583305165098e-05,
|
| 190 |
+
"loss": 0.0009,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5650013078733979,
|
| 195 |
+
"grad_norm": 0.6020150741013875,
|
| 196 |
+
"learning_rate": 1.8038205597634392e-05,
|
| 197 |
+
"loss": 0.0011,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5859272822390793,
|
| 202 |
+
"grad_norm": 0.05961677548525192,
|
| 203 |
+
"learning_rate": 1.7815052431606702e-05,
|
| 204 |
+
"loss": 0.0042,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6068532566047606,
|
| 209 |
+
"grad_norm": 0.03667937697835753,
|
| 210 |
+
"learning_rate": 1.7581422950671942e-05,
|
| 211 |
+
"loss": 0.0029,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6277792309704421,
|
| 216 |
+
"grad_norm": 0.02203193747208106,
|
| 217 |
+
"learning_rate": 1.733763034223804e-05,
|
| 218 |
+
"loss": 0.0017,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6487052053361234,
|
| 223 |
+
"grad_norm": 0.03047813653712161,
|
| 224 |
+
"learning_rate": 1.7084001417693702e-05,
|
| 225 |
+
"loss": 0.0013,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6696311797018049,
|
| 230 |
+
"grad_norm": 0.02403172913701344,
|
| 231 |
+
"learning_rate": 1.682087617430782e-05,
|
| 232 |
+
"loss": 0.001,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6905571540674863,
|
| 237 |
+
"grad_norm": 0.020885112433327038,
|
| 238 |
+
"learning_rate": 1.6548607339452853e-05,
|
| 239 |
+
"loss": 0.0009,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7114831284331676,
|
| 244 |
+
"grad_norm": 0.02143325180735118,
|
| 245 |
+
"learning_rate": 1.626755989776303e-05,
|
| 246 |
+
"loss": 0.0007,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7324091027988491,
|
| 251 |
+
"grad_norm": 0.028502523632724423,
|
| 252 |
+
"learning_rate": 1.5978110601861408e-05,
|
| 253 |
+
"loss": 0.0016,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7533350771645305,
|
| 258 |
+
"grad_norm": 0.00832352415812105,
|
| 259 |
+
"learning_rate": 1.568064746731156e-05,
|
| 260 |
+
"loss": 0.0009,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7742610515302119,
|
| 265 |
+
"grad_norm": 0.009527918206519135,
|
| 266 |
+
"learning_rate": 1.5375569252470897e-05,
|
| 267 |
+
"loss": 0.0018,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7951870258958933,
|
| 272 |
+
"grad_norm": 0.025970668054977514,
|
| 273 |
+
"learning_rate": 1.506328492394303e-05,
|
| 274 |
+
"loss": 0.0006,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8161130002615746,
|
| 279 |
+
"grad_norm": 0.026371283237352123,
|
| 280 |
+
"learning_rate": 1.4744213108345605e-05,
|
| 281 |
+
"loss": 0.0023,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8370389746272561,
|
| 286 |
+
"grad_norm": 0.030148449665476192,
|
| 287 |
+
"learning_rate": 1.4418781531128636e-05,
|
| 288 |
+
"loss": 0.0021,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8579649489929375,
|
| 293 |
+
"grad_norm": 0.009123367946997817,
|
| 294 |
+
"learning_rate": 1.4087426443195549e-05,
|
| 295 |
+
"loss": 0.0009,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8788909233586188,
|
| 300 |
+
"grad_norm": 0.033901495227343266,
|
| 301 |
+
"learning_rate": 1.375059203609562e-05,
|
| 302 |
+
"loss": 0.0023,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8998168977243003,
|
| 307 |
+
"grad_norm": 0.007725818014371622,
|
| 308 |
+
"learning_rate": 1.3408729846571716e-05,
|
| 309 |
+
"loss": 0.0006,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9207428720899817,
|
| 314 |
+
"grad_norm": 0.01076304174801131,
|
| 315 |
+
"learning_rate": 1.3062298151261592e-05,
|
| 316 |
+
"loss": 0.0009,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9416688464556631,
|
| 321 |
+
"grad_norm": 0.08792335870716929,
|
| 322 |
+
"learning_rate": 1.2711761352364172e-05,
|
| 323 |
+
"loss": 0.0016,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9625948208213445,
|
| 328 |
+
"grad_norm": 0.019193508970073957,
|
| 329 |
+
"learning_rate": 1.2357589355094275e-05,
|
| 330 |
+
"loss": 0.0005,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9835207951870258,
|
| 335 |
+
"grad_norm": 0.008676099200769616,
|
| 336 |
+
"learning_rate": 1.2000256937760446e-05,
|
| 337 |
+
"loss": 0.0019,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0044467695527073,
|
| 342 |
+
"grad_norm": 0.0014044382775048332,
|
| 343 |
+
"learning_rate": 1.1640243115310219e-05,
|
| 344 |
+
"loss": 0.0013,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0253727439183886,
|
| 349 |
+
"grad_norm": 0.0047799061066043395,
|
| 350 |
+
"learning_rate": 1.127803049719605e-05,
|
| 351 |
+
"loss": 0.0008,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0462987182840702,
|
| 356 |
+
"grad_norm": 0.006651240484213586,
|
| 357 |
+
"learning_rate": 1.091410464042268e-05,
|
| 358 |
+
"loss": 0.0004,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.0672246926497515,
|
| 363 |
+
"grad_norm": 0.007370492651937019,
|
| 364 |
+
"learning_rate": 1.0548953398643276e-05,
|
| 365 |
+
"loss": 0.0002,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.0881506670154328,
|
| 370 |
+
"grad_norm": 0.004999091099852188,
|
| 371 |
+
"learning_rate": 1.0183066268176775e-05,
|
| 372 |
+
"loss": 0.0013,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.1090766413811144,
|
| 377 |
+
"grad_norm": 0.0067648135423557494,
|
| 378 |
+
"learning_rate": 9.81693373182323e-06,
|
| 379 |
+
"loss": 0.0004,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.1300026157467957,
|
| 384 |
+
"grad_norm": 0.006355010008632378,
|
| 385 |
+
"learning_rate": 9.451046601356725e-06,
|
| 386 |
+
"loss": 0.0005,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.150928590112477,
|
| 391 |
+
"grad_norm": 0.0019993701626922662,
|
| 392 |
+
"learning_rate": 9.085895359577324e-06,
|
| 393 |
+
"loss": 0.0012,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.1718545644781586,
|
| 398 |
+
"grad_norm": 0.07841604107285226,
|
| 399 |
+
"learning_rate": 8.721969502803954e-06,
|
| 400 |
+
"loss": 0.0007,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.19278053884384,
|
| 405 |
+
"grad_norm": 0.008878084655677647,
|
| 406 |
+
"learning_rate": 8.359756884689785e-06,
|
| 407 |
+
"loss": 0.0006,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.2137065132095213,
|
| 412 |
+
"grad_norm": 0.022433859996456522,
|
| 413 |
+
"learning_rate": 7.999743062239557e-06,
|
| 414 |
+
"loss": 0.001,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.2346324875752028,
|
| 419 |
+
"grad_norm": 0.007321094493119974,
|
| 420 |
+
"learning_rate": 7.642410644905726e-06,
|
| 421 |
+
"loss": 0.0002,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.2555584619408842,
|
| 426 |
+
"grad_norm": 0.004130666592411099,
|
| 427 |
+
"learning_rate": 7.2882386476358304e-06,
|
| 428 |
+
"loss": 0.0008,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.2764844363065655,
|
| 433 |
+
"grad_norm": 0.009136384794392362,
|
| 434 |
+
"learning_rate": 6.937701848738407e-06,
|
| 435 |
+
"loss": 0.0005,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.297410410672247,
|
| 440 |
+
"grad_norm": 0.014936959834984399,
|
| 441 |
+
"learning_rate": 6.591270153428288e-06,
|
| 442 |
+
"loss": 0.0015,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.3183363850379284,
|
| 447 |
+
"grad_norm": 0.00995968283183629,
|
| 448 |
+
"learning_rate": 6.249407963904381e-06,
|
| 449 |
+
"loss": 0.0003,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.3392623594036097,
|
| 454 |
+
"grad_norm": 0.007922264005744792,
|
| 455 |
+
"learning_rate": 5.912573556804453e-06,
|
| 456 |
+
"loss": 0.002,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.3601883337692913,
|
| 461 |
+
"grad_norm": 0.009732474218704226,
|
| 462 |
+
"learning_rate": 5.581218468871365e-06,
|
| 463 |
+
"loss": 0.0015,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.3811143081349726,
|
| 468 |
+
"grad_norm": 0.029322482465715245,
|
| 469 |
+
"learning_rate": 5.2557868916543996e-06,
|
| 470 |
+
"loss": 0.0004,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.402040282500654,
|
| 475 |
+
"grad_norm": 0.002219147933917833,
|
| 476 |
+
"learning_rate": 4.9367150760569746e-06,
|
| 477 |
+
"loss": 0.0013,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.4229662568663353,
|
| 482 |
+
"grad_norm": 0.016601760824032873,
|
| 483 |
+
"learning_rate": 4.6244307475291025e-06,
|
| 484 |
+
"loss": 0.0007,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.4438922312320168,
|
| 489 |
+
"grad_norm": 0.03618373662395389,
|
| 490 |
+
"learning_rate": 4.319352532688444e-06,
|
| 491 |
+
"loss": 0.0016,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4648182055976982,
|
| 496 |
+
"grad_norm": 0.008705175714719602,
|
| 497 |
+
"learning_rate": 4.0218893981385935e-06,
|
| 498 |
+
"loss": 0.0009,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.4857441799633795,
|
| 503 |
+
"grad_norm": 0.0029313903115019873,
|
| 504 |
+
"learning_rate": 3.732440102236975e-06,
|
| 505 |
+
"loss": 0.0002,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.5066701543290608,
|
| 510 |
+
"grad_norm": 0.020710402409599028,
|
| 511 |
+
"learning_rate": 3.4513926605471504e-06,
|
| 512 |
+
"loss": 0.0007,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.5275961286947424,
|
| 517 |
+
"grad_norm": 0.03507089834475249,
|
| 518 |
+
"learning_rate": 3.1791238256921785e-06,
|
| 519 |
+
"loss": 0.0021,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.5485221030604237,
|
| 524 |
+
"grad_norm": 0.07040984119700786,
|
| 525 |
+
"learning_rate": 2.9159985823062997e-06,
|
| 526 |
+
"loss": 0.0012,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.569448077426105,
|
| 531 |
+
"grad_norm": 0.0046045007369338465,
|
| 532 |
+
"learning_rate": 2.662369657761963e-06,
|
| 533 |
+
"loss": 0.0005,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.5903740517917866,
|
| 538 |
+
"grad_norm": 0.044927829447691095,
|
| 539 |
+
"learning_rate": 2.418577049328058e-06,
|
| 540 |
+
"loss": 0.001,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.611300026157468,
|
| 545 |
+
"grad_norm": 0.005367586480852439,
|
| 546 |
+
"learning_rate": 2.1849475683932996e-06,
|
| 547 |
+
"loss": 0.0005,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.6322260005231493,
|
| 552 |
+
"grad_norm": 0.014755038810438978,
|
| 553 |
+
"learning_rate": 1.961794402365611e-06,
|
| 554 |
+
"loss": 0.0012,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.6531519748888308,
|
| 559 |
+
"grad_norm": 0.007586271120637286,
|
| 560 |
+
"learning_rate": 1.7494166948349057e-06,
|
| 561 |
+
"loss": 0.0023,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.6740779492545121,
|
| 566 |
+
"grad_norm": 0.01450560934843513,
|
| 567 |
+
"learning_rate": 1.5480991445620541e-06,
|
| 568 |
+
"loss": 0.001,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.6950039236201935,
|
| 573 |
+
"grad_norm": 0.007197310242295822,
|
| 574 |
+
"learning_rate": 1.3581116238315194e-06,
|
| 575 |
+
"loss": 0.0004,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.715929897985875,
|
| 580 |
+
"grad_norm": 0.011429665649141593,
|
| 581 |
+
"learning_rate": 1.1797088166794002e-06,
|
| 582 |
+
"loss": 0.0009,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.7368558723515564,
|
| 587 |
+
"grad_norm": 0.005479589436376736,
|
| 588 |
+
"learning_rate": 1.013129877481741e-06,
|
| 589 |
+
"loss": 0.0015,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.7577818467172377,
|
| 594 |
+
"grad_norm": 0.010284806366489312,
|
| 595 |
+
"learning_rate": 8.585981103608343e-07,
|
| 596 |
+
"loss": 0.0003,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.7787078210829192,
|
| 601 |
+
"grad_norm": 0.004805391506128972,
|
| 602 |
+
"learning_rate": 7.163206698392744e-07,
|
| 603 |
+
"loss": 0.0007,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.7996337954486006,
|
| 608 |
+
"grad_norm": 0.00832006380541767,
|
| 609 |
+
"learning_rate": 5.864882831430274e-07,
|
| 610 |
+
"loss": 0.0013,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.820559769814282,
|
| 615 |
+
"grad_norm": 0.0016488023765299498,
|
| 616 |
+
"learning_rate": 4.6927499452580574e-07,
|
| 617 |
+
"loss": 0.0004,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.8414857441799635,
|
| 622 |
+
"grad_norm": 0.010828047107950923,
|
| 623 |
+
"learning_rate": 3.6483793195745686e-07,
|
| 624 |
+
"loss": 0.002,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.8624117185456448,
|
| 629 |
+
"grad_norm": 0.00029272379323776047,
|
| 630 |
+
"learning_rate": 2.733170964891607e-07,
|
| 631 |
+
"loss": 0.0008,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.8833376929113261,
|
| 636 |
+
"grad_norm": 0.011245028659871065,
|
| 637 |
+
"learning_rate": 1.9483517457776436e-07,
|
| 638 |
+
"loss": 0.0013,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.9042636672770077,
|
| 643 |
+
"grad_norm": 0.005356139523384608,
|
| 644 |
+
"learning_rate": 1.2949737362087156e-07,
|
| 645 |
+
"loss": 0.0009,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.925189641642689,
|
| 650 |
+
"grad_norm": 0.006490951580098314,
|
| 651 |
+
"learning_rate": 7.73912809231292e-08,
|
| 652 |
+
"loss": 0.0005,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.9461156160083704,
|
| 657 |
+
"grad_norm": 0.003383501070683301,
|
| 658 |
+
"learning_rate": 3.858674628278825e-08,
|
| 659 |
+
"loss": 0.003,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.967041590374052,
|
| 664 |
+
"grad_norm": 0.012526402652665877,
|
| 665 |
+
"learning_rate": 1.3135788355934652e-08,
|
| 666 |
+
"loss": 0.0004,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.9879675647397332,
|
| 671 |
+
"grad_norm": 0.016656680718419487,
|
| 672 |
+
"learning_rate": 1.0725249238940916e-09,
|
| 673 |
+
"loss": 0.0006,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.9963379544860058,
|
| 678 |
+
"step": 954,
|
| 679 |
+
"total_flos": 841298254757888.0,
|
| 680 |
+
"train_loss": 0.001730952451793395,
|
| 681 |
+
"train_runtime": 49706.0079,
|
| 682 |
+
"train_samples_per_second": 2.461,
|
| 683 |
+
"train_steps_per_second": 0.019
|
| 684 |
+
}
|
| 685 |
+
],
|
| 686 |
+
"logging_steps": 10,
|
| 687 |
+
"max_steps": 954,
|
| 688 |
+
"num_input_tokens_seen": 0,
|
| 689 |
+
"num_train_epochs": 2,
|
| 690 |
+
"save_steps": 500,
|
| 691 |
+
"stateful_callbacks": {
|
| 692 |
+
"TrainerControl": {
|
| 693 |
+
"args": {
|
| 694 |
+
"should_epoch_stop": false,
|
| 695 |
+
"should_evaluate": false,
|
| 696 |
+
"should_log": false,
|
| 697 |
+
"should_save": true,
|
| 698 |
+
"should_training_stop": true
|
| 699 |
+
},
|
| 700 |
+
"attributes": {}
|
| 701 |
+
}
|
| 702 |
+
},
|
| 703 |
+
"total_flos": 841298254757888.0,
|
| 704 |
+
"train_batch_size": 8,
|
| 705 |
+
"trial_name": null,
|
| 706 |
+
"trial_params": null
|
| 707 |
+
}
|
training_loss.png
ADDED
|