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 +535 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: original_tiger_dataset_small
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# original_tiger_dataset_small
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.3978
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: original_tiger_dataset_small
|
|
|
|
| 16 |
|
| 17 |
# original_tiger_dataset_small
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/original_tiger_dataset_small dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.3978
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9916897506925206,
|
| 3 |
+
"eval_loss": 0.39780595898628235,
|
| 4 |
+
"eval_runtime": 151.2883,
|
| 5 |
+
"eval_samples_per_second": 40.175,
|
| 6 |
+
"eval_steps_per_second": 0.628,
|
| 7 |
+
"total_flos": 1130440761016320.0,
|
| 8 |
+
"train_loss": 0.3879174453240854,
|
| 9 |
+
"train_runtime": 22444.4408,
|
| 10 |
+
"train_samples_per_second": 15.435,
|
| 11 |
+
"train_steps_per_second": 0.03
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9916897506925206,
|
| 3 |
+
"eval_loss": 0.39780595898628235,
|
| 4 |
+
"eval_runtime": 151.2883,
|
| 5 |
+
"eval_samples_per_second": 40.175,
|
| 6 |
+
"eval_steps_per_second": 0.628
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9916897506925206,
|
| 3 |
+
"total_flos": 1130440761016320.0,
|
| 4 |
+
"train_loss": 0.3879174453240854,
|
| 5 |
+
"train_runtime": 22444.4408,
|
| 6 |
+
"train_samples_per_second": 15.435,
|
| 7 |
+
"train_steps_per_second": 0.03
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9916897506925206,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 675,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0443213296398892,
|
| 13 |
+
"grad_norm": 7.052213448686623,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.5829,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0886426592797784,
|
| 20 |
+
"grad_norm": 1.5459335266979457,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.513,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1329639889196676,
|
| 27 |
+
"grad_norm": 0.719225680086632,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.4887,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1772853185595568,
|
| 34 |
+
"grad_norm": 0.8892381207222515,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.4649,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22160664819944598,
|
| 41 |
+
"grad_norm": 0.7186105716522034,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.4513,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2659279778393352,
|
| 48 |
+
"grad_norm": 0.6156329427239773,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.4487,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31024930747922436,
|
| 55 |
+
"grad_norm": 0.5853871188550711,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.4406,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3545706371191136,
|
| 62 |
+
"grad_norm": 0.5482082304131989,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.4359,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3988919667590028,
|
| 69 |
+
"grad_norm": 0.4424843900141646,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.4278,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.44321329639889195,
|
| 76 |
+
"grad_norm": 0.5500270978536973,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.4266,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.48753462603878117,
|
| 83 |
+
"grad_norm": 0.4890554413822,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.4198,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5318559556786704,
|
| 90 |
+
"grad_norm": 0.3929640794177042,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.4201,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5761772853185596,
|
| 97 |
+
"grad_norm": 0.5298403296766302,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.4198,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6204986149584487,
|
| 104 |
+
"grad_norm": 0.3477088076642203,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.4181,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6648199445983379,
|
| 111 |
+
"grad_norm": 0.4351495846909543,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.4147,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7091412742382271,
|
| 118 |
+
"grad_norm": 0.381148974745445,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.412,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7534626038781164,
|
| 125 |
+
"grad_norm": 0.34662500124731266,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.4166,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7977839335180056,
|
| 132 |
+
"grad_norm": 0.45421320442815966,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.4132,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8421052631578947,
|
| 139 |
+
"grad_norm": 0.3659178106228611,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.4136,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8864265927977839,
|
| 146 |
+
"grad_norm": 0.6021107216904796,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.4041,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9307479224376731,
|
| 153 |
+
"grad_norm": 0.5276638445937896,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.411,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9750692520775623,
|
| 160 |
+
"grad_norm": 0.37923132404108995,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.4061,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.997229916897507,
|
| 167 |
+
"eval_loss": 0.4077036678791046,
|
| 168 |
+
"eval_runtime": 158.0392,
|
| 169 |
+
"eval_samples_per_second": 38.459,
|
| 170 |
+
"eval_steps_per_second": 0.601,
|
| 171 |
+
"step": 225
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0193905817174516,
|
| 175 |
+
"grad_norm": 0.4441527989618394,
|
| 176 |
+
"learning_rate": 5e-06,
|
| 177 |
+
"loss": 0.4093,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.0637119113573408,
|
| 182 |
+
"grad_norm": 0.383360121111077,
|
| 183 |
+
"learning_rate": 5e-06,
|
| 184 |
+
"loss": 0.3815,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.10803324099723,
|
| 189 |
+
"grad_norm": 0.3990576858944248,
|
| 190 |
+
"learning_rate": 5e-06,
|
| 191 |
+
"loss": 0.3761,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.1523545706371192,
|
| 196 |
+
"grad_norm": 0.503954633758602,
|
| 197 |
+
"learning_rate": 5e-06,
|
| 198 |
+
"loss": 0.3818,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.1966759002770084,
|
| 203 |
+
"grad_norm": 0.4527787565971453,
|
| 204 |
+
"learning_rate": 5e-06,
|
| 205 |
+
"loss": 0.3792,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.2409972299168974,
|
| 210 |
+
"grad_norm": 0.3939361247356342,
|
| 211 |
+
"learning_rate": 5e-06,
|
| 212 |
+
"loss": 0.3768,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.2853185595567866,
|
| 217 |
+
"grad_norm": 0.41328816849632577,
|
| 218 |
+
"learning_rate": 5e-06,
|
| 219 |
+
"loss": 0.3813,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.3296398891966759,
|
| 224 |
+
"grad_norm": 0.47753446079826084,
|
| 225 |
+
"learning_rate": 5e-06,
|
| 226 |
+
"loss": 0.3819,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.373961218836565,
|
| 231 |
+
"grad_norm": 0.38082453273018374,
|
| 232 |
+
"learning_rate": 5e-06,
|
| 233 |
+
"loss": 0.38,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.4182825484764543,
|
| 238 |
+
"grad_norm": 0.5159796944766167,
|
| 239 |
+
"learning_rate": 5e-06,
|
| 240 |
+
"loss": 0.3755,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.4626038781163435,
|
| 245 |
+
"grad_norm": 0.3829464355523,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.3808,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.5069252077562327,
|
| 252 |
+
"grad_norm": 0.3492766964963765,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.3778,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.5512465373961217,
|
| 259 |
+
"grad_norm": 0.36812848860180375,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.3779,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.595567867036011,
|
| 266 |
+
"grad_norm": 0.41462318446315016,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.374,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.6398891966759002,
|
| 273 |
+
"grad_norm": 0.42749575402289264,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.3776,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.6842105263157894,
|
| 280 |
+
"grad_norm": 0.4420757091228596,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.3805,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.7285318559556786,
|
| 287 |
+
"grad_norm": 0.39320471180120625,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.3776,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.7728531855955678,
|
| 294 |
+
"grad_norm": 0.4455011162465814,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.3759,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.817174515235457,
|
| 301 |
+
"grad_norm": 0.3564174208371923,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.3797,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.8614958448753463,
|
| 308 |
+
"grad_norm": 0.3965273061639582,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.3736,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.9058171745152355,
|
| 315 |
+
"grad_norm": 0.3593250927656118,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.3761,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.9501385041551247,
|
| 322 |
+
"grad_norm": 0.38504819696326603,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.3731,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.994459833795014,
|
| 329 |
+
"grad_norm": 0.3949630765714435,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.3726,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.9988919667590028,
|
| 336 |
+
"eval_loss": 0.3975733816623688,
|
| 337 |
+
"eval_runtime": 156.1473,
|
| 338 |
+
"eval_samples_per_second": 38.925,
|
| 339 |
+
"eval_steps_per_second": 0.608,
|
| 340 |
+
"step": 451
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.038781163434903,
|
| 344 |
+
"grad_norm": 0.4124343429602089,
|
| 345 |
+
"learning_rate": 5e-06,
|
| 346 |
+
"loss": 0.3629,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.0831024930747923,
|
| 351 |
+
"grad_norm": 0.43159824833217403,
|
| 352 |
+
"learning_rate": 5e-06,
|
| 353 |
+
"loss": 0.3425,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.1274238227146816,
|
| 358 |
+
"grad_norm": 0.4156394960465829,
|
| 359 |
+
"learning_rate": 5e-06,
|
| 360 |
+
"loss": 0.3458,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.1717451523545708,
|
| 365 |
+
"grad_norm": 0.439672844432952,
|
| 366 |
+
"learning_rate": 5e-06,
|
| 367 |
+
"loss": 0.3487,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.21606648199446,
|
| 372 |
+
"grad_norm": 0.3756131515472198,
|
| 373 |
+
"learning_rate": 5e-06,
|
| 374 |
+
"loss": 0.344,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.260387811634349,
|
| 379 |
+
"grad_norm": 0.4320607459725008,
|
| 380 |
+
"learning_rate": 5e-06,
|
| 381 |
+
"loss": 0.3469,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.3047091412742384,
|
| 386 |
+
"grad_norm": 0.48325455407748324,
|
| 387 |
+
"learning_rate": 5e-06,
|
| 388 |
+
"loss": 0.344,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.349030470914127,
|
| 393 |
+
"grad_norm": 0.509688954969155,
|
| 394 |
+
"learning_rate": 5e-06,
|
| 395 |
+
"loss": 0.3422,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.393351800554017,
|
| 400 |
+
"grad_norm": 0.47004871752405086,
|
| 401 |
+
"learning_rate": 5e-06,
|
| 402 |
+
"loss": 0.3481,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.4376731301939056,
|
| 407 |
+
"grad_norm": 0.37357609406356407,
|
| 408 |
+
"learning_rate": 5e-06,
|
| 409 |
+
"loss": 0.3475,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.481994459833795,
|
| 414 |
+
"grad_norm": 0.37773993115530186,
|
| 415 |
+
"learning_rate": 5e-06,
|
| 416 |
+
"loss": 0.35,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.526315789473684,
|
| 421 |
+
"grad_norm": 0.3918590091549487,
|
| 422 |
+
"learning_rate": 5e-06,
|
| 423 |
+
"loss": 0.3466,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.5706371191135733,
|
| 428 |
+
"grad_norm": 0.376355539356745,
|
| 429 |
+
"learning_rate": 5e-06,
|
| 430 |
+
"loss": 0.3459,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.6149584487534625,
|
| 435 |
+
"grad_norm": 0.39220517786717213,
|
| 436 |
+
"learning_rate": 5e-06,
|
| 437 |
+
"loss": 0.3448,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.6592797783933517,
|
| 442 |
+
"grad_norm": 0.40029072930864157,
|
| 443 |
+
"learning_rate": 5e-06,
|
| 444 |
+
"loss": 0.3482,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.703601108033241,
|
| 449 |
+
"grad_norm": 0.38197937787666936,
|
| 450 |
+
"learning_rate": 5e-06,
|
| 451 |
+
"loss": 0.3481,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.74792243767313,
|
| 456 |
+
"grad_norm": 0.4857867587877145,
|
| 457 |
+
"learning_rate": 5e-06,
|
| 458 |
+
"loss": 0.3474,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.7922437673130194,
|
| 463 |
+
"grad_norm": 0.4816618353336751,
|
| 464 |
+
"learning_rate": 5e-06,
|
| 465 |
+
"loss": 0.3429,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.8365650969529086,
|
| 470 |
+
"grad_norm": 0.4843151337200677,
|
| 471 |
+
"learning_rate": 5e-06,
|
| 472 |
+
"loss": 0.3491,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.880886426592798,
|
| 477 |
+
"grad_norm": 0.3849874491982438,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.3479,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.925207756232687,
|
| 484 |
+
"grad_norm": 0.42190162748247967,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.3472,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.9695290858725762,
|
| 491 |
+
"grad_norm": 0.42143659183843213,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.3467,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.9916897506925206,
|
| 498 |
+
"eval_loss": 0.39780595898628235,
|
| 499 |
+
"eval_runtime": 154.2343,
|
| 500 |
+
"eval_samples_per_second": 39.408,
|
| 501 |
+
"eval_steps_per_second": 0.616,
|
| 502 |
+
"step": 675
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.9916897506925206,
|
| 506 |
+
"step": 675,
|
| 507 |
+
"total_flos": 1130440761016320.0,
|
| 508 |
+
"train_loss": 0.3879174453240854,
|
| 509 |
+
"train_runtime": 22444.4408,
|
| 510 |
+
"train_samples_per_second": 15.435,
|
| 511 |
+
"train_steps_per_second": 0.03
|
| 512 |
+
}
|
| 513 |
+
],
|
| 514 |
+
"logging_steps": 10,
|
| 515 |
+
"max_steps": 675,
|
| 516 |
+
"num_input_tokens_seen": 0,
|
| 517 |
+
"num_train_epochs": 3,
|
| 518 |
+
"save_steps": 500,
|
| 519 |
+
"stateful_callbacks": {
|
| 520 |
+
"TrainerControl": {
|
| 521 |
+
"args": {
|
| 522 |
+
"should_epoch_stop": false,
|
| 523 |
+
"should_evaluate": false,
|
| 524 |
+
"should_log": false,
|
| 525 |
+
"should_save": true,
|
| 526 |
+
"should_training_stop": true
|
| 527 |
+
},
|
| 528 |
+
"attributes": {}
|
| 529 |
+
}
|
| 530 |
+
},
|
| 531 |
+
"total_flos": 1130440761016320.0,
|
| 532 |
+
"train_batch_size": 8,
|
| 533 |
+
"trial_name": null,
|
| 534 |
+
"trial_params": null
|
| 535 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|