ikno commited on
Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +413 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
model-index:
|
| 10 |
+
- name: rinko_300_labeling
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# rinko_300_labeling
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.0068
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-06
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 5
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 2.3912 | 0.9897 | 48 | 2.2464 |
|
| 57 |
+
| 2.2442 | 2.0 | 97 | 2.1167 |
|
| 58 |
+
| 2.1047 | 2.9897 | 145 | 2.0317 |
|
| 59 |
+
| 2.05 | 4.0 | 194 | 2.0067 |
|
| 60 |
+
| 2.0626 | 4.9485 | 240 | 2.0068 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.7.1
|
| 66 |
+
- Transformers 4.40.1
|
| 67 |
+
- Pytorch 2.2.1+cu121
|
| 68 |
+
- Datasets 2.19.0
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.948453608247423,
|
| 3 |
+
"total_flos": 1.0715672433026662e+17,
|
| 4 |
+
"train_loss": 2.205865615606308,
|
| 5 |
+
"train_runtime": 7479.3037,
|
| 6 |
+
"train_samples": 385,
|
| 7 |
+
"train_samples_per_second": 0.257,
|
| 8 |
+
"train_steps_per_second": 0.032
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.948453608247423,
|
| 3 |
+
"total_flos": 1.0715672433026662e+17,
|
| 4 |
+
"train_loss": 2.205865615606308,
|
| 5 |
+
"train_runtime": 7479.3037,
|
| 6 |
+
"train_samples": 385,
|
| 7 |
+
"train_samples_per_second": 0.257,
|
| 8 |
+
"train_steps_per_second": 0.032
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,413 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.948453608247423,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 240,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020618556701030927,
|
| 13 |
+
"grad_norm": 1.546875,
|
| 14 |
+
"learning_rate": 8.333333333333333e-08,
|
| 15 |
+
"loss": 2.5196,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10309278350515463,
|
| 20 |
+
"grad_norm": 1.5390625,
|
| 21 |
+
"learning_rate": 4.1666666666666667e-07,
|
| 22 |
+
"loss": 2.458,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.20618556701030927,
|
| 27 |
+
"grad_norm": 1.4375,
|
| 28 |
+
"learning_rate": 8.333333333333333e-07,
|
| 29 |
+
"loss": 2.4466,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.30927835051546393,
|
| 34 |
+
"grad_norm": 1.515625,
|
| 35 |
+
"learning_rate": 1.2499999999999999e-06,
|
| 36 |
+
"loss": 2.4248,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41237113402061853,
|
| 41 |
+
"grad_norm": 1.6171875,
|
| 42 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 43 |
+
"loss": 2.4622,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5154639175257731,
|
| 48 |
+
"grad_norm": 1.4921875,
|
| 49 |
+
"learning_rate": 1.9998942319271077e-06,
|
| 50 |
+
"loss": 2.4147,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6185567010309279,
|
| 55 |
+
"grad_norm": 1.46875,
|
| 56 |
+
"learning_rate": 1.9961946980917456e-06,
|
| 57 |
+
"loss": 2.3747,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7216494845360825,
|
| 62 |
+
"grad_norm": 1.453125,
|
| 63 |
+
"learning_rate": 1.987229113117374e-06,
|
| 64 |
+
"loss": 2.4189,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8247422680412371,
|
| 69 |
+
"grad_norm": 1.578125,
|
| 70 |
+
"learning_rate": 1.9730448705798236e-06,
|
| 71 |
+
"loss": 2.4126,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9278350515463918,
|
| 76 |
+
"grad_norm": 1.4765625,
|
| 77 |
+
"learning_rate": 1.953716950748227e-06,
|
| 78 |
+
"loss": 2.3912,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9896907216494846,
|
| 83 |
+
"eval_loss": 2.246396064758301,
|
| 84 |
+
"eval_runtime": 1335.3788,
|
| 85 |
+
"eval_samples_per_second": 4.423,
|
| 86 |
+
"eval_steps_per_second": 0.553,
|
| 87 |
+
"step": 48
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.0309278350515463,
|
| 91 |
+
"grad_norm": 1.4453125,
|
| 92 |
+
"learning_rate": 1.929347524226822e-06,
|
| 93 |
+
"loss": 2.3653,
|
| 94 |
+
"step": 50
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.134020618556701,
|
| 98 |
+
"grad_norm": 1.546875,
|
| 99 |
+
"learning_rate": 1.900065411864121e-06,
|
| 100 |
+
"loss": 2.3567,
|
| 101 |
+
"step": 55
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.2371134020618557,
|
| 105 |
+
"grad_norm": 1.5,
|
| 106 |
+
"learning_rate": 1.8660254037844386e-06,
|
| 107 |
+
"loss": 2.3555,
|
| 108 |
+
"step": 60
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.3402061855670104,
|
| 112 |
+
"grad_norm": 1.6015625,
|
| 113 |
+
"learning_rate": 1.8274074411415103e-06,
|
| 114 |
+
"loss": 2.2988,
|
| 115 |
+
"step": 65
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.443298969072165,
|
| 119 |
+
"grad_norm": 1.53125,
|
| 120 |
+
"learning_rate": 1.7844156649195757e-06,
|
| 121 |
+
"loss": 2.288,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.5463917525773194,
|
| 126 |
+
"grad_norm": 1.3671875,
|
| 127 |
+
"learning_rate": 1.737277336810124e-06,
|
| 128 |
+
"loss": 2.2871,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.6494845360824741,
|
| 133 |
+
"grad_norm": 1.59375,
|
| 134 |
+
"learning_rate": 1.6862416378687337e-06,
|
| 135 |
+
"loss": 2.2903,
|
| 136 |
+
"step": 80
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.7525773195876289,
|
| 140 |
+
"grad_norm": 1.484375,
|
| 141 |
+
"learning_rate": 1.6315783513024974e-06,
|
| 142 |
+
"loss": 2.2465,
|
| 143 |
+
"step": 85
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.8556701030927836,
|
| 147 |
+
"grad_norm": 1.484375,
|
| 148 |
+
"learning_rate": 1.573576436351046e-06,
|
| 149 |
+
"loss": 2.2434,
|
| 150 |
+
"step": 90
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.9587628865979383,
|
| 154 |
+
"grad_norm": 1.421875,
|
| 155 |
+
"learning_rate": 1.5125425007998652e-06,
|
| 156 |
+
"loss": 2.2442,
|
| 157 |
+
"step": 95
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.0,
|
| 161 |
+
"eval_loss": 2.1167430877685547,
|
| 162 |
+
"eval_runtime": 1327.822,
|
| 163 |
+
"eval_samples_per_second": 4.449,
|
| 164 |
+
"eval_steps_per_second": 0.557,
|
| 165 |
+
"step": 97
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0618556701030926,
|
| 169 |
+
"grad_norm": 1.4765625,
|
| 170 |
+
"learning_rate": 1.4487991802004622e-06,
|
| 171 |
+
"loss": 2.2931,
|
| 172 |
+
"step": 100
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.1649484536082473,
|
| 176 |
+
"grad_norm": 1.390625,
|
| 177 |
+
"learning_rate": 1.3826834323650898e-06,
|
| 178 |
+
"loss": 2.2062,
|
| 179 |
+
"step": 105
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.268041237113402,
|
| 183 |
+
"grad_norm": 1.4921875,
|
| 184 |
+
"learning_rate": 1.3145447561516136e-06,
|
| 185 |
+
"loss": 2.1501,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.3711340206185567,
|
| 190 |
+
"grad_norm": 1.1875,
|
| 191 |
+
"learning_rate": 1.2447433439543238e-06,
|
| 192 |
+
"loss": 2.1248,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.4742268041237114,
|
| 197 |
+
"grad_norm": 1.3984375,
|
| 198 |
+
"learning_rate": 1.1736481776669305e-06,
|
| 199 |
+
"loss": 2.1624,
|
| 200 |
+
"step": 120
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.5773195876288657,
|
| 204 |
+
"grad_norm": 1.2265625,
|
| 205 |
+
"learning_rate": 1.101635078182802e-06,
|
| 206 |
+
"loss": 2.1479,
|
| 207 |
+
"step": 125
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.680412371134021,
|
| 211 |
+
"grad_norm": 1.3359375,
|
| 212 |
+
"learning_rate": 1.0290847187431114e-06,
|
| 213 |
+
"loss": 2.1655,
|
| 214 |
+
"step": 130
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.783505154639175,
|
| 218 |
+
"grad_norm": 1.3203125,
|
| 219 |
+
"learning_rate": 9.56380612634664e-07,
|
| 220 |
+
"loss": 2.1369,
|
| 221 |
+
"step": 135
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.88659793814433,
|
| 225 |
+
"grad_norm": 1.28125,
|
| 226 |
+
"learning_rate": 8.839070858747696e-07,
|
| 227 |
+
"loss": 2.1003,
|
| 228 |
+
"step": 140
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.9896907216494846,
|
| 232 |
+
"grad_norm": 1.2109375,
|
| 233 |
+
"learning_rate": 8.120472455998881e-07,
|
| 234 |
+
"loss": 2.1047,
|
| 235 |
+
"step": 145
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.9896907216494846,
|
| 239 |
+
"eval_loss": 2.0316832065582275,
|
| 240 |
+
"eval_runtime": 1327.2975,
|
| 241 |
+
"eval_samples_per_second": 4.45,
|
| 242 |
+
"eval_steps_per_second": 0.557,
|
| 243 |
+
"step": 145
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.0927835051546393,
|
| 247 |
+
"grad_norm": 1.25,
|
| 248 |
+
"learning_rate": 7.411809548974791e-07,
|
| 249 |
+
"loss": 2.0675,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.195876288659794,
|
| 254 |
+
"grad_norm": 1.3125,
|
| 255 |
+
"learning_rate": 6.71682824786439e-07,
|
| 256 |
+
"loss": 2.0934,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.2989690721649483,
|
| 261 |
+
"grad_norm": 1.0234375,
|
| 262 |
+
"learning_rate": 6.039202339608431e-07,
|
| 263 |
+
"loss": 2.081,
|
| 264 |
+
"step": 160
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.402061855670103,
|
| 268 |
+
"grad_norm": 1.0625,
|
| 269 |
+
"learning_rate": 5.382513867649663e-07,
|
| 270 |
+
"loss": 2.0219,
|
| 271 |
+
"step": 165
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 3.5051546391752577,
|
| 275 |
+
"grad_norm": 1.3203125,
|
| 276 |
+
"learning_rate": 4.750234196654399e-07,
|
| 277 |
+
"loss": 2.0877,
|
| 278 |
+
"step": 170
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.6082474226804124,
|
| 282 |
+
"grad_norm": 1.2890625,
|
| 283 |
+
"learning_rate": 4.1457056623005947e-07,
|
| 284 |
+
"loss": 2.1019,
|
| 285 |
+
"step": 175
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.711340206185567,
|
| 289 |
+
"grad_norm": 1.1328125,
|
| 290 |
+
"learning_rate": 3.5721239031346063e-07,
|
| 291 |
+
"loss": 2.0828,
|
| 292 |
+
"step": 180
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.8144329896907214,
|
| 296 |
+
"grad_norm": 1.2421875,
|
| 297 |
+
"learning_rate": 3.032520967893453e-07,
|
| 298 |
+
"loss": 2.09,
|
| 299 |
+
"step": 185
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.917525773195876,
|
| 303 |
+
"grad_norm": 1.3125,
|
| 304 |
+
"learning_rate": 2.5297492875900415e-07,
|
| 305 |
+
"loss": 2.05,
|
| 306 |
+
"step": 190
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.0,
|
| 310 |
+
"eval_loss": 2.0067081451416016,
|
| 311 |
+
"eval_runtime": 1327.277,
|
| 312 |
+
"eval_samples_per_second": 4.45,
|
| 313 |
+
"eval_steps_per_second": 0.557,
|
| 314 |
+
"step": 194
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.020618556701031,
|
| 318 |
+
"grad_norm": 1.1796875,
|
| 319 |
+
"learning_rate": 2.0664665970876495e-07,
|
| 320 |
+
"loss": 2.1246,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.123711340206185,
|
| 325 |
+
"grad_norm": 1.1796875,
|
| 326 |
+
"learning_rate": 1.6451218858706372e-07,
|
| 327 |
+
"loss": 2.0933,
|
| 328 |
+
"step": 200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.22680412371134,
|
| 332 |
+
"grad_norm": 1.1328125,
|
| 333 |
+
"learning_rate": 1.2679424522780425e-07,
|
| 334 |
+
"loss": 2.0561,
|
| 335 |
+
"step": 205
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 4.329896907216495,
|
| 339 |
+
"grad_norm": 1.1640625,
|
| 340 |
+
"learning_rate": 9.369221296335006e-08,
|
| 341 |
+
"loss": 2.0946,
|
| 342 |
+
"step": 210
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 4.43298969072165,
|
| 346 |
+
"grad_norm": 1.125,
|
| 347 |
+
"learning_rate": 6.538107465101162e-08,
|
| 348 |
+
"loss": 2.0797,
|
| 349 |
+
"step": 215
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 4.536082474226804,
|
| 353 |
+
"grad_norm": 1.125,
|
| 354 |
+
"learning_rate": 4.20104876845111e-08,
|
| 355 |
+
"loss": 2.0907,
|
| 356 |
+
"step": 220
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.639175257731958,
|
| 360 |
+
"grad_norm": 1.171875,
|
| 361 |
+
"learning_rate": 2.3703992880066636e-08,
|
| 362 |
+
"loss": 2.1295,
|
| 363 |
+
"step": 225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.742268041237113,
|
| 367 |
+
"grad_norm": 1.1640625,
|
| 368 |
+
"learning_rate": 1.0558361419055529e-08,
|
| 369 |
+
"loss": 2.0247,
|
| 370 |
+
"step": 230
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.845360824742268,
|
| 374 |
+
"grad_norm": 1.046875,
|
| 375 |
+
"learning_rate": 2.643083299427751e-09,
|
| 376 |
+
"loss": 2.0658,
|
| 377 |
+
"step": 235
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.948453608247423,
|
| 381 |
+
"grad_norm": 1.046875,
|
| 382 |
+
"learning_rate": 0.0,
|
| 383 |
+
"loss": 2.0626,
|
| 384 |
+
"step": 240
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.948453608247423,
|
| 388 |
+
"eval_loss": 2.0068044662475586,
|
| 389 |
+
"eval_runtime": 1327.4294,
|
| 390 |
+
"eval_samples_per_second": 4.45,
|
| 391 |
+
"eval_steps_per_second": 0.557,
|
| 392 |
+
"step": 240
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.948453608247423,
|
| 396 |
+
"step": 240,
|
| 397 |
+
"total_flos": 1.0715672433026662e+17,
|
| 398 |
+
"train_loss": 2.205865615606308,
|
| 399 |
+
"train_runtime": 7479.3037,
|
| 400 |
+
"train_samples_per_second": 0.257,
|
| 401 |
+
"train_steps_per_second": 0.032
|
| 402 |
+
}
|
| 403 |
+
],
|
| 404 |
+
"logging_steps": 5,
|
| 405 |
+
"max_steps": 240,
|
| 406 |
+
"num_input_tokens_seen": 0,
|
| 407 |
+
"num_train_epochs": 5,
|
| 408 |
+
"save_steps": 1,
|
| 409 |
+
"total_flos": 1.0715672433026662e+17,
|
| 410 |
+
"train_batch_size": 4,
|
| 411 |
+
"trial_name": null,
|
| 412 |
+
"trial_params": null
|
| 413 |
+
}
|