End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +534 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_qwen_epoch2_dcftv1.2
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_qwen_epoch2_dcftv1.2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6332
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_qwen_epoch2_dcftv1.2
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_qwen_epoch2_dcftv1.2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6332
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9967081199707388,
|
| 3 |
+
"eval_loss": 0.6331745386123657,
|
| 4 |
+
"eval_runtime": 344.4391,
|
| 5 |
+
"eval_samples_per_second": 26.736,
|
| 6 |
+
"eval_steps_per_second": 0.418,
|
| 7 |
+
"total_flos": 1429904000286720.0,
|
| 8 |
+
"train_loss": 0.6341017776570362,
|
| 9 |
+
"train_runtime": 36533.8026,
|
| 10 |
+
"train_samples_per_second": 9.578,
|
| 11 |
+
"train_steps_per_second": 0.019
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9967081199707388,
|
| 3 |
+
"eval_loss": 0.6331745386123657,
|
| 4 |
+
"eval_runtime": 344.4391,
|
| 5 |
+
"eval_samples_per_second": 26.736,
|
| 6 |
+
"eval_steps_per_second": 0.418
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9967081199707388,
|
| 3 |
+
"total_flos": 1429904000286720.0,
|
| 4 |
+
"train_loss": 0.6341017776570362,
|
| 5 |
+
"train_runtime": 36533.8026,
|
| 6 |
+
"train_samples_per_second": 9.578,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9967081199707388,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 682,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.029261155815654718,
|
| 13 |
+
"grad_norm": 3.175921153645058,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.8015,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.058522311631309436,
|
| 20 |
+
"grad_norm": 1.3396777412592173,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7413,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08778346744696415,
|
| 27 |
+
"grad_norm": 1.2916710481318188,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7082,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11704462326261887,
|
| 34 |
+
"grad_norm": 1.0905232711210158,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6969,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.14630577907827358,
|
| 41 |
+
"grad_norm": 1.1424161224062557,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.687,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1755669348939283,
|
| 48 |
+
"grad_norm": 0.8849186232279377,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6763,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.20482809070958302,
|
| 55 |
+
"grad_norm": 0.5905751294504246,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6697,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23408924652523774,
|
| 62 |
+
"grad_norm": 0.401552296803231,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6646,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26335040234089246,
|
| 69 |
+
"grad_norm": 0.41681057235289837,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6618,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.29261155815654716,
|
| 76 |
+
"grad_norm": 0.42307500226012484,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6543,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3218727139722019,
|
| 83 |
+
"grad_norm": 0.4153399483829215,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6631,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3511338697878566,
|
| 90 |
+
"grad_norm": 0.3802571943412753,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.668,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.38039502560351135,
|
| 97 |
+
"grad_norm": 0.3888172781548047,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6518,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.40965618141916604,
|
| 104 |
+
"grad_norm": 0.3637230321906593,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6525,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4389173372348208,
|
| 111 |
+
"grad_norm": 0.3510916975433033,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6479,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4681784930504755,
|
| 118 |
+
"grad_norm": 0.38320736963066604,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6498,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.49743964886613024,
|
| 125 |
+
"grad_norm": 0.3675280277212547,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6549,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5267008046817849,
|
| 132 |
+
"grad_norm": 0.33533114288412946,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6545,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5559619604974396,
|
| 139 |
+
"grad_norm": 0.35908138669562806,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.643,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5852231163130943,
|
| 146 |
+
"grad_norm": 0.34531459956691446,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6442,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6144842721287491,
|
| 153 |
+
"grad_norm": 0.3410477096323079,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6508,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6437454279444038,
|
| 160 |
+
"grad_norm": 0.35442684790995665,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6388,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6730065837600585,
|
| 167 |
+
"grad_norm": 0.36210107670842623,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6387,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7022677395757132,
|
| 174 |
+
"grad_norm": 0.3320010813437129,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6456,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.731528895391368,
|
| 181 |
+
"grad_norm": 0.3431211501390758,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.644,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7607900512070227,
|
| 188 |
+
"grad_norm": 0.34117908000054753,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6466,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7900512070226774,
|
| 195 |
+
"grad_norm": 0.3767554348039686,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6489,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8193123628383321,
|
| 202 |
+
"grad_norm": 0.3445121930815649,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6477,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8485735186539868,
|
| 209 |
+
"grad_norm": 0.334717792180829,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6399,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8778346744696416,
|
| 216 |
+
"grad_norm": 0.35014998369274103,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6318,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9070958302852963,
|
| 223 |
+
"grad_norm": 0.35107697366353213,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6448,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.936356986100951,
|
| 230 |
+
"grad_norm": 0.33329010626592986,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6368,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9656181419166057,
|
| 237 |
+
"grad_norm": 0.375641145522458,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6401,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9948792977322605,
|
| 244 |
+
"grad_norm": 0.35063232128414173,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6361,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9978054133138259,
|
| 251 |
+
"eval_loss": 0.6406120657920837,
|
| 252 |
+
"eval_runtime": 342.7414,
|
| 253 |
+
"eval_samples_per_second": 26.869,
|
| 254 |
+
"eval_steps_per_second": 0.42,
|
| 255 |
+
"step": 341
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.025237746891002,
|
| 259 |
+
"grad_norm": 0.3689065333115297,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.6512,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.054498902706657,
|
| 266 |
+
"grad_norm": 0.35245512949324603,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.6053,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.0837600585223117,
|
| 273 |
+
"grad_norm": 0.4097569215434824,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.6087,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1130212143379663,
|
| 280 |
+
"grad_norm": 0.33409266355289313,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6061,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.142282370153621,
|
| 287 |
+
"grad_norm": 0.39236431067207433,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6114,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.1715435259692757,
|
| 294 |
+
"grad_norm": 0.35552129157860685,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6129,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2008046817849305,
|
| 301 |
+
"grad_norm": 0.3510300665384777,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6125,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2300658376005853,
|
| 308 |
+
"grad_norm": 0.40194969560487526,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6007,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2593269934162399,
|
| 315 |
+
"grad_norm": 0.3583207046748375,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6108,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.2885881492318947,
|
| 322 |
+
"grad_norm": 0.344522115799079,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6036,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3178493050475493,
|
| 329 |
+
"grad_norm": 0.36157379087095487,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6073,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.347110460863204,
|
| 336 |
+
"grad_norm": 0.3791515880385353,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6049,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3763716166788589,
|
| 343 |
+
"grad_norm": 0.3220281951589229,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6023,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4056327724945135,
|
| 350 |
+
"grad_norm": 0.3692472075176485,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6031,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4348939283101683,
|
| 357 |
+
"grad_norm": 0.3464968328092362,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6095,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.464155084125823,
|
| 364 |
+
"grad_norm": 0.3395757657902888,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5978,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4934162399414777,
|
| 371 |
+
"grad_norm": 0.3472100724313473,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6059,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5226773957571325,
|
| 378 |
+
"grad_norm": 0.3853659527551535,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6082,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5519385515727873,
|
| 385 |
+
"grad_norm": 0.35016819999626914,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6068,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5811997073884418,
|
| 392 |
+
"grad_norm": 0.36893370536117037,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6134,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6104608632040964,
|
| 399 |
+
"grad_norm": 0.35806464799349075,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6044,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6397220190197512,
|
| 406 |
+
"grad_norm": 0.34859310509445396,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6061,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.668983174835406,
|
| 413 |
+
"grad_norm": 0.3249373585587818,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5968,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.6982443306510606,
|
| 420 |
+
"grad_norm": 0.35605026962044284,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6061,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.7275054864667154,
|
| 427 |
+
"grad_norm": 0.40161934702478636,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6063,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.7567666422823702,
|
| 434 |
+
"grad_norm": 0.33968611303586627,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6032,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.7860277980980248,
|
| 441 |
+
"grad_norm": 0.343315623639703,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6056,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8152889539136796,
|
| 448 |
+
"grad_norm": 0.32594291618046917,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6061,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.8445501097293344,
|
| 455 |
+
"grad_norm": 0.35524107661998305,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6052,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.873811265544989,
|
| 462 |
+
"grad_norm": 0.32891502990480825,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9030724213606436,
|
| 469 |
+
"grad_norm": 0.362729694863619,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.6057,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9323335771762986,
|
| 476 |
+
"grad_norm": 0.3500563113476431,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.6062,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.9615947329919532,
|
| 483 |
+
"grad_norm": 0.33206893588035147,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.595,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.9908558888076078,
|
| 490 |
+
"grad_norm": 0.35566741239182464,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.6095,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.9967081199707388,
|
| 497 |
+
"eval_loss": 0.6331745386123657,
|
| 498 |
+
"eval_runtime": 342.0192,
|
| 499 |
+
"eval_samples_per_second": 26.925,
|
| 500 |
+
"eval_steps_per_second": 0.421,
|
| 501 |
+
"step": 682
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.9967081199707388,
|
| 505 |
+
"step": 682,
|
| 506 |
+
"total_flos": 1429904000286720.0,
|
| 507 |
+
"train_loss": 0.6341017776570362,
|
| 508 |
+
"train_runtime": 36533.8026,
|
| 509 |
+
"train_samples_per_second": 9.578,
|
| 510 |
+
"train_steps_per_second": 0.019
|
| 511 |
+
}
|
| 512 |
+
],
|
| 513 |
+
"logging_steps": 10,
|
| 514 |
+
"max_steps": 682,
|
| 515 |
+
"num_input_tokens_seen": 0,
|
| 516 |
+
"num_train_epochs": 2,
|
| 517 |
+
"save_steps": 500,
|
| 518 |
+
"stateful_callbacks": {
|
| 519 |
+
"TrainerControl": {
|
| 520 |
+
"args": {
|
| 521 |
+
"should_epoch_stop": false,
|
| 522 |
+
"should_evaluate": false,
|
| 523 |
+
"should_log": false,
|
| 524 |
+
"should_save": true,
|
| 525 |
+
"should_training_stop": true
|
| 526 |
+
},
|
| 527 |
+
"attributes": {}
|
| 528 |
+
}
|
| 529 |
+
},
|
| 530 |
+
"total_flos": 1429904000286720.0,
|
| 531 |
+
"train_batch_size": 8,
|
| 532 |
+
"trial_name": null,
|
| 533 |
+
"trial_params": null
|
| 534 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|