End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +532 -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: b2_math_embedding_1k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# b2_math_embedding_1k
|
| 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: b2_math_embedding_1k
|
|
|
|
| 16 |
|
| 17 |
# b2_math_embedding_1k
|
| 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/b2_math_embedding_1k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.72,
|
| 3 |
+
"total_flos": 1.9513650159026176e+17,
|
| 4 |
+
"train_loss": 0.42438117819172994,
|
| 5 |
+
"train_runtime": 7377.4458,
|
| 6 |
+
"train_samples_per_second": 0.949,
|
| 7 |
+
"train_steps_per_second": 0.009
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.72,
|
| 3 |
+
"total_flos": 1.9513650159026176e+17,
|
| 4 |
+
"train_loss": 0.42438117819172994,
|
| 5 |
+
"train_runtime": 7377.4458,
|
| 6 |
+
"train_samples_per_second": 0.949,
|
| 7 |
+
"train_steps_per_second": 0.009
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,532 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.72,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 70,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.096,
|
| 13 |
+
"grad_norm": 6.69682433774339,
|
| 14 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 15 |
+
"loss": 0.8235,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.192,
|
| 20 |
+
"grad_norm": 6.820791264320967,
|
| 21 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 22 |
+
"loss": 0.8306,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.288,
|
| 27 |
+
"grad_norm": 6.322804635049165,
|
| 28 |
+
"learning_rate": 8.571428571428571e-06,
|
| 29 |
+
"loss": 0.8297,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.384,
|
| 34 |
+
"grad_norm": 2.472632030510256,
|
| 35 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 36 |
+
"loss": 0.7122,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.48,
|
| 41 |
+
"grad_norm": 4.187407567277096,
|
| 42 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 43 |
+
"loss": 0.7495,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.576,
|
| 48 |
+
"grad_norm": 4.127923097786966,
|
| 49 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 50 |
+
"loss": 0.7047,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.672,
|
| 55 |
+
"grad_norm": 4.521738027671271,
|
| 56 |
+
"learning_rate": 2e-05,
|
| 57 |
+
"loss": 0.6879,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.768,
|
| 62 |
+
"grad_norm": 2.8722090441276964,
|
| 63 |
+
"learning_rate": 1.9987569212189224e-05,
|
| 64 |
+
"loss": 0.6501,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.864,
|
| 69 |
+
"grad_norm": 3.205752204333251,
|
| 70 |
+
"learning_rate": 1.9950307753654016e-05,
|
| 71 |
+
"loss": 0.6424,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.96,
|
| 76 |
+
"grad_norm": 2.3440533944879114,
|
| 77 |
+
"learning_rate": 1.9888308262251286e-05,
|
| 78 |
+
"loss": 0.6099,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.056,
|
| 83 |
+
"grad_norm": 1.406500695894257,
|
| 84 |
+
"learning_rate": 1.9801724878485438e-05,
|
| 85 |
+
"loss": 0.5589,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.152,
|
| 90 |
+
"grad_norm": 1.4077957022951328,
|
| 91 |
+
"learning_rate": 1.969077286229078e-05,
|
| 92 |
+
"loss": 0.5525,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.248,
|
| 97 |
+
"grad_norm": 0.9609146818956278,
|
| 98 |
+
"learning_rate": 1.955572805786141e-05,
|
| 99 |
+
"loss": 0.5324,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.3439999999999999,
|
| 104 |
+
"grad_norm": 0.9390767254599207,
|
| 105 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 106 |
+
"loss": 0.5404,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.44,
|
| 111 |
+
"grad_norm": 0.7368581646966733,
|
| 112 |
+
"learning_rate": 1.921476211870408e-05,
|
| 113 |
+
"loss": 0.5369,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.536,
|
| 118 |
+
"grad_norm": 0.9198074796580378,
|
| 119 |
+
"learning_rate": 1.900968867902419e-05,
|
| 120 |
+
"loss": 0.5264,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.6320000000000001,
|
| 125 |
+
"grad_norm": 0.7746810211059445,
|
| 126 |
+
"learning_rate": 1.8782215733702286e-05,
|
| 127 |
+
"loss": 0.5126,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.728,
|
| 132 |
+
"grad_norm": 0.8845831361925726,
|
| 133 |
+
"learning_rate": 1.8532908816321557e-05,
|
| 134 |
+
"loss": 0.5104,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.8239999999999998,
|
| 139 |
+
"grad_norm": 0.6965950145045844,
|
| 140 |
+
"learning_rate": 1.826238774315995e-05,
|
| 141 |
+
"loss": 0.4835,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.92,
|
| 146 |
+
"grad_norm": 1.0122725504532324,
|
| 147 |
+
"learning_rate": 1.7971325072229227e-05,
|
| 148 |
+
"loss": 0.5171,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.016,
|
| 153 |
+
"grad_norm": 0.7468081604536398,
|
| 154 |
+
"learning_rate": 1.766044443118978e-05,
|
| 155 |
+
"loss": 0.4976,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.112,
|
| 160 |
+
"grad_norm": 0.7513412208969773,
|
| 161 |
+
"learning_rate": 1.7330518718298263e-05,
|
| 162 |
+
"loss": 0.4402,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.208,
|
| 167 |
+
"grad_norm": 0.5329871297523793,
|
| 168 |
+
"learning_rate": 1.698236818086073e-05,
|
| 169 |
+
"loss": 0.4257,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.304,
|
| 174 |
+
"grad_norm": 0.6258427310045804,
|
| 175 |
+
"learning_rate": 1.6616858375968596e-05,
|
| 176 |
+
"loss": 0.4246,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.4,
|
| 181 |
+
"grad_norm": 0.5166941168314442,
|
| 182 |
+
"learning_rate": 1.6234898018587336e-05,
|
| 183 |
+
"loss": 0.4416,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.496,
|
| 188 |
+
"grad_norm": 0.5950611023205173,
|
| 189 |
+
"learning_rate": 1.5837436722347902e-05,
|
| 190 |
+
"loss": 0.4309,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.592,
|
| 195 |
+
"grad_norm": 0.5695526470343111,
|
| 196 |
+
"learning_rate": 1.5425462638657597e-05,
|
| 197 |
+
"loss": 0.4255,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.6879999999999997,
|
| 202 |
+
"grad_norm": 0.5032516469486215,
|
| 203 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 204 |
+
"loss": 0.4347,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.784,
|
| 209 |
+
"grad_norm": 0.5781528561926846,
|
| 210 |
+
"learning_rate": 1.4562106573531632e-05,
|
| 211 |
+
"loss": 0.4245,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.88,
|
| 216 |
+
"grad_norm": 0.48743707363283684,
|
| 217 |
+
"learning_rate": 1.4112871031306118e-05,
|
| 218 |
+
"loss": 0.4157,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.976,
|
| 223 |
+
"grad_norm": 0.5079208604258143,
|
| 224 |
+
"learning_rate": 1.3653410243663953e-05,
|
| 225 |
+
"loss": 0.4263,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.072,
|
| 230 |
+
"grad_norm": 0.5025094503599609,
|
| 231 |
+
"learning_rate": 1.3184866502516846e-05,
|
| 232 |
+
"loss": 0.3794,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.168,
|
| 237 |
+
"grad_norm": 0.4338503782776642,
|
| 238 |
+
"learning_rate": 1.2708404681430054e-05,
|
| 239 |
+
"loss": 0.376,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.2640000000000002,
|
| 244 |
+
"grad_norm": 0.46038474762114817,
|
| 245 |
+
"learning_rate": 1.2225209339563144e-05,
|
| 246 |
+
"loss": 0.3645,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.36,
|
| 251 |
+
"grad_norm": 0.5045918051187733,
|
| 252 |
+
"learning_rate": 1.1736481776669307e-05,
|
| 253 |
+
"loss": 0.3695,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.456,
|
| 258 |
+
"grad_norm": 0.409440218663504,
|
| 259 |
+
"learning_rate": 1.1243437046474854e-05,
|
| 260 |
+
"loss": 0.3818,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.552,
|
| 265 |
+
"grad_norm": 0.4750973143689976,
|
| 266 |
+
"learning_rate": 1.0747300935864245e-05,
|
| 267 |
+
"loss": 0.378,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.648,
|
| 272 |
+
"grad_norm": 0.46256313666880916,
|
| 273 |
+
"learning_rate": 1.0249306917380731e-05,
|
| 274 |
+
"loss": 0.3856,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.7439999999999998,
|
| 279 |
+
"grad_norm": 0.47939130012121134,
|
| 280 |
+
"learning_rate": 9.750693082619274e-06,
|
| 281 |
+
"loss": 0.3301,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.84,
|
| 286 |
+
"grad_norm": 0.3967295619591175,
|
| 287 |
+
"learning_rate": 9.252699064135759e-06,
|
| 288 |
+
"loss": 0.3453,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.936,
|
| 293 |
+
"grad_norm": 0.4750307179546361,
|
| 294 |
+
"learning_rate": 8.756562953525151e-06,
|
| 295 |
+
"loss": 0.3571,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.032,
|
| 300 |
+
"grad_norm": 0.36009864949668763,
|
| 301 |
+
"learning_rate": 8.263518223330698e-06,
|
| 302 |
+
"loss": 0.3371,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.128,
|
| 307 |
+
"grad_norm": 0.4432875404112238,
|
| 308 |
+
"learning_rate": 7.774790660436857e-06,
|
| 309 |
+
"loss": 0.3242,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.224,
|
| 314 |
+
"grad_norm": 0.4125592958130361,
|
| 315 |
+
"learning_rate": 7.291595318569951e-06,
|
| 316 |
+
"loss": 0.2997,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.32,
|
| 321 |
+
"grad_norm": 0.4090431955706633,
|
| 322 |
+
"learning_rate": 6.815133497483157e-06,
|
| 323 |
+
"loss": 0.2988,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.416,
|
| 328 |
+
"grad_norm": 0.431826554150315,
|
| 329 |
+
"learning_rate": 6.34658975633605e-06,
|
| 330 |
+
"loss": 0.3318,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.5120000000000005,
|
| 335 |
+
"grad_norm": 0.3948197686514902,
|
| 336 |
+
"learning_rate": 5.887128968693887e-06,
|
| 337 |
+
"loss": 0.3196,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.608,
|
| 342 |
+
"grad_norm": 0.4087890302933139,
|
| 343 |
+
"learning_rate": 5.43789342646837e-06,
|
| 344 |
+
"loss": 0.338,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.704,
|
| 349 |
+
"grad_norm": 0.4139164516484091,
|
| 350 |
+
"learning_rate": 5.000000000000003e-06,
|
| 351 |
+
"loss": 0.3061,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.8,
|
| 356 |
+
"grad_norm": 0.3498692572270399,
|
| 357 |
+
"learning_rate": 4.5745373613424075e-06,
|
| 358 |
+
"loss": 0.3303,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.896,
|
| 363 |
+
"grad_norm": 0.352617439899582,
|
| 364 |
+
"learning_rate": 4.162563277652104e-06,
|
| 365 |
+
"loss": 0.3181,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.992,
|
| 370 |
+
"grad_norm": 0.3754502985187873,
|
| 371 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 372 |
+
"loss": 0.3161,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 5.088,
|
| 377 |
+
"grad_norm": 0.34136014782937907,
|
| 378 |
+
"learning_rate": 3.3831416240314085e-06,
|
| 379 |
+
"loss": 0.275,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.184,
|
| 384 |
+
"grad_norm": 0.308487213476843,
|
| 385 |
+
"learning_rate": 3.017631819139273e-06,
|
| 386 |
+
"loss": 0.2954,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.28,
|
| 391 |
+
"grad_norm": 0.3195176445752236,
|
| 392 |
+
"learning_rate": 2.669481281701739e-06,
|
| 393 |
+
"loss": 0.3038,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.376,
|
| 398 |
+
"grad_norm": 0.3411639286400715,
|
| 399 |
+
"learning_rate": 2.339555568810221e-06,
|
| 400 |
+
"loss": 0.3176,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.4719999999999995,
|
| 405 |
+
"grad_norm": 0.3143250746845179,
|
| 406 |
+
"learning_rate": 2.0286749277707783e-06,
|
| 407 |
+
"loss": 0.2997,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.568,
|
| 412 |
+
"grad_norm": 0.27877379915030537,
|
| 413 |
+
"learning_rate": 1.7376122568400533e-06,
|
| 414 |
+
"loss": 0.3059,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.664,
|
| 419 |
+
"grad_norm": 0.29798308341062885,
|
| 420 |
+
"learning_rate": 1.467091183678444e-06,
|
| 421 |
+
"loss": 0.2886,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.76,
|
| 426 |
+
"grad_norm": 0.27786785743438297,
|
| 427 |
+
"learning_rate": 1.2177842662977136e-06,
|
| 428 |
+
"loss": 0.2874,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.856,
|
| 433 |
+
"grad_norm": 0.28342211810278356,
|
| 434 |
+
"learning_rate": 9.903113209758098e-07,
|
| 435 |
+
"loss": 0.2492,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.952,
|
| 440 |
+
"grad_norm": 0.2684798496491014,
|
| 441 |
+
"learning_rate": 7.852378812959227e-07,
|
| 442 |
+
"loss": 0.3046,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.048,
|
| 447 |
+
"grad_norm": 0.27444826285192886,
|
| 448 |
+
"learning_rate": 6.030737921409169e-07,
|
| 449 |
+
"loss": 0.2887,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.144,
|
| 454 |
+
"grad_norm": 0.26240835982434846,
|
| 455 |
+
"learning_rate": 4.4427194213859216e-07,
|
| 456 |
+
"loss": 0.2742,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.24,
|
| 461 |
+
"grad_norm": 0.26705696173946836,
|
| 462 |
+
"learning_rate": 3.0922713770922155e-07,
|
| 463 |
+
"loss": 0.3097,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.336,
|
| 468 |
+
"grad_norm": 0.24650300025059024,
|
| 469 |
+
"learning_rate": 1.9827512151456175e-07,
|
| 470 |
+
"loss": 0.27,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.432,
|
| 475 |
+
"grad_norm": 0.2520254213374591,
|
| 476 |
+
"learning_rate": 1.1169173774871478e-07,
|
| 477 |
+
"loss": 0.2814,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.5280000000000005,
|
| 482 |
+
"grad_norm": 0.2431616105111216,
|
| 483 |
+
"learning_rate": 4.9692246345985905e-08,
|
| 484 |
+
"loss": 0.2857,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 6.624,
|
| 489 |
+
"grad_norm": 0.2400134909876856,
|
| 490 |
+
"learning_rate": 1.2430787810776556e-08,
|
| 491 |
+
"loss": 0.2889,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 6.72,
|
| 496 |
+
"grad_norm": 0.24399999272288897,
|
| 497 |
+
"learning_rate": 0.0,
|
| 498 |
+
"loss": 0.2944,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 6.72,
|
| 503 |
+
"step": 70,
|
| 504 |
+
"total_flos": 1.9513650159026176e+17,
|
| 505 |
+
"train_loss": 0.42438117819172994,
|
| 506 |
+
"train_runtime": 7377.4458,
|
| 507 |
+
"train_samples_per_second": 0.949,
|
| 508 |
+
"train_steps_per_second": 0.009
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"logging_steps": 1,
|
| 512 |
+
"max_steps": 70,
|
| 513 |
+
"num_input_tokens_seen": 0,
|
| 514 |
+
"num_train_epochs": 7,
|
| 515 |
+
"save_steps": 500,
|
| 516 |
+
"stateful_callbacks": {
|
| 517 |
+
"TrainerControl": {
|
| 518 |
+
"args": {
|
| 519 |
+
"should_epoch_stop": false,
|
| 520 |
+
"should_evaluate": false,
|
| 521 |
+
"should_log": false,
|
| 522 |
+
"should_save": true,
|
| 523 |
+
"should_training_stop": true
|
| 524 |
+
},
|
| 525 |
+
"attributes": {}
|
| 526 |
+
}
|
| 527 |
+
},
|
| 528 |
+
"total_flos": 1.9513650159026176e+17,
|
| 529 |
+
"train_batch_size": 1,
|
| 530 |
+
"trial_name": null,
|
| 531 |
+
"trial_params": null
|
| 532 |
+
}
|
training_loss.png
ADDED
|