Model save
Browse files- README.md +68 -0
- all_results.json +9 -0
- generation_config.json +7 -0
- train_results.json +9 -0
- trainer_state.json +386 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: gemma
|
| 4 |
+
base_model: google/gemma-7b
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma7b-gpt4o_1k_classification-fft
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# gemma7b-gpt4o_1k_classification-fft
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 5.7345
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0003
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- total_eval_batch_size: 16
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 4.3115 | 0.9979 | 239 | 5.7345 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.45.1
|
| 66 |
+
- Pytorch 2.4.1+cu121
|
| 67 |
+
- Datasets 3.0.1
|
| 68 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9979123173277662,
|
| 3 |
+
"total_flos": 8193589641216.0,
|
| 4 |
+
"train_loss": 2.8353221366595025,
|
| 5 |
+
"train_runtime": 2240.0339,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 3.416,
|
| 8 |
+
"train_steps_per_second": 0.107
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.1"
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9979123173277662,
|
| 3 |
+
"total_flos": 8193589641216.0,
|
| 4 |
+
"train_loss": 2.8353221366595025,
|
| 5 |
+
"train_runtime": 2240.0339,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 3.416,
|
| 8 |
+
"train_steps_per_second": 0.107
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9979123173277662,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 239,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0041753653444676405,
|
| 13 |
+
"grad_norm": 14820.435529068707,
|
| 14 |
+
"learning_rate": 1.2499999999999999e-05,
|
| 15 |
+
"loss": 60.135,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.020876826722338204,
|
| 20 |
+
"grad_norm": 1628.1311380537702,
|
| 21 |
+
"learning_rate": 6.25e-05,
|
| 22 |
+
"loss": 50.6887,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04175365344467641,
|
| 27 |
+
"grad_norm": 3033.800304830903,
|
| 28 |
+
"learning_rate": 0.000125,
|
| 29 |
+
"loss": 42.1741,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06263048016701461,
|
| 34 |
+
"grad_norm": 6954.121232870651,
|
| 35 |
+
"learning_rate": 0.00018749999999999998,
|
| 36 |
+
"loss": 161.1634,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08350730688935282,
|
| 41 |
+
"grad_norm": 850.7915596439383,
|
| 42 |
+
"learning_rate": 0.00025,
|
| 43 |
+
"loss": 187.8921,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10438413361169102,
|
| 48 |
+
"grad_norm": 51.008981364388355,
|
| 49 |
+
"learning_rate": 0.0002999839868651235,
|
| 50 |
+
"loss": 27.0222,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12526096033402923,
|
| 55 |
+
"grad_norm": 41.28593832910529,
|
| 56 |
+
"learning_rate": 0.000299423886051382,
|
| 57 |
+
"loss": 40.1282,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14613778705636743,
|
| 62 |
+
"grad_norm": 94.54405893422229,
|
| 63 |
+
"learning_rate": 0.0002980665441538907,
|
| 64 |
+
"loss": 22.8182,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16701461377870563,
|
| 69 |
+
"grad_norm": 117.0436511760194,
|
| 70 |
+
"learning_rate": 0.0002959192031789579,
|
| 71 |
+
"loss": 19.1922,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.18789144050104384,
|
| 76 |
+
"grad_norm": 23.24704464882293,
|
| 77 |
+
"learning_rate": 0.00029299332011978107,
|
| 78 |
+
"loss": 17.9784,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.20876826722338204,
|
| 83 |
+
"grad_norm": 67.09115479950934,
|
| 84 |
+
"learning_rate": 0.0002893045058284311,
|
| 85 |
+
"loss": 13.938,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22964509394572025,
|
| 90 |
+
"grad_norm": 74.81050241825953,
|
| 91 |
+
"learning_rate": 0.00028487244172520246,
|
| 92 |
+
"loss": 12.678,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25052192066805845,
|
| 97 |
+
"grad_norm": 36.783670859376656,
|
| 98 |
+
"learning_rate": 0.0002797207747897198,
|
| 99 |
+
"loss": 11.5948,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.27139874739039666,
|
| 104 |
+
"grad_norm": 42.67794856216472,
|
| 105 |
+
"learning_rate": 0.0002738769913940706,
|
| 106 |
+
"loss": 9.6311,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.29227557411273486,
|
| 111 |
+
"grad_norm": 20.131225618062707,
|
| 112 |
+
"learning_rate": 0.0002673722706511174,
|
| 113 |
+
"loss": 8.6553,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.31315240083507306,
|
| 118 |
+
"grad_norm": 16.501356621775457,
|
| 119 |
+
"learning_rate": 0.0002602413180604401,
|
| 120 |
+
"loss": 7.8996,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.33402922755741127,
|
| 125 |
+
"grad_norm": 17.24824317039284,
|
| 126 |
+
"learning_rate": 0.00025252218033947993,
|
| 127 |
+
"loss": 7.1388,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.35490605427974947,
|
| 132 |
+
"grad_norm": 23.28427284101539,
|
| 133 |
+
"learning_rate": 0.0002442560424278399,
|
| 134 |
+
"loss": 6.7571,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3757828810020877,
|
| 139 |
+
"grad_norm": 19.752003570940577,
|
| 140 |
+
"learning_rate": 0.00023548700774781242,
|
| 141 |
+
"loss": 6.4415,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3966597077244259,
|
| 146 |
+
"grad_norm": 16.62982088461208,
|
| 147 |
+
"learning_rate": 0.00022626186289353913,
|
| 148 |
+
"loss": 6.4479,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4175365344467641,
|
| 153 |
+
"grad_norm": 23.009578526601246,
|
| 154 |
+
"learning_rate": 0.0002166298280042877,
|
| 155 |
+
"loss": 6.1347,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4384133611691023,
|
| 160 |
+
"grad_norm": 9.902525054887667,
|
| 161 |
+
"learning_rate": 0.00020664229415371266,
|
| 162 |
+
"loss": 5.868,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4592901878914405,
|
| 167 |
+
"grad_norm": 18.872092670717567,
|
| 168 |
+
"learning_rate": 0.0001963525491562421,
|
| 169 |
+
"loss": 5.8684,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4801670146137787,
|
| 174 |
+
"grad_norm": 10.396862801643927,
|
| 175 |
+
"learning_rate": 0.00018581549325353126,
|
| 176 |
+
"loss": 5.6768,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5010438413361169,
|
| 181 |
+
"grad_norm": 6.643173772718449,
|
| 182 |
+
"learning_rate": 0.00017508734619791966,
|
| 183 |
+
"loss": 5.5378,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5219206680584552,
|
| 188 |
+
"grad_norm": 13.620597347405528,
|
| 189 |
+
"learning_rate": 0.00016422534729572738,
|
| 190 |
+
"loss": 5.4243,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5427974947807933,
|
| 195 |
+
"grad_norm": 12.675575738004211,
|
| 196 |
+
"learning_rate": 0.0001532874500107902,
|
| 197 |
+
"loss": 5.4237,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5636743215031316,
|
| 202 |
+
"grad_norm": 10.600479885243871,
|
| 203 |
+
"learning_rate": 0.00014233201275765494,
|
| 204 |
+
"loss": 5.3795,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5845511482254697,
|
| 209 |
+
"grad_norm": 14.207759763111122,
|
| 210 |
+
"learning_rate": 0.0001314174875341878,
|
| 211 |
+
"loss": 5.2682,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.605427974947808,
|
| 216 |
+
"grad_norm": 10.28585644469174,
|
| 217 |
+
"learning_rate": 0.00012060210805487529,
|
| 218 |
+
"loss": 5.1446,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6263048016701461,
|
| 223 |
+
"grad_norm": 9.411071111902643,
|
| 224 |
+
"learning_rate": 0.00010994357904876106,
|
| 225 |
+
"loss": 5.0323,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6471816283924844,
|
| 230 |
+
"grad_norm": 4.20316220773891,
|
| 231 |
+
"learning_rate": 9.949876837974944e-05,
|
| 232 |
+
"loss": 4.9314,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6680584551148225,
|
| 237 |
+
"grad_norm": 6.642144688442386,
|
| 238 |
+
"learning_rate": 8.932340363194595e-05,
|
| 239 |
+
"loss": 4.9206,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6889352818371608,
|
| 244 |
+
"grad_norm": 7.2411357694832255,
|
| 245 |
+
"learning_rate": 7.947177477888472e-05,
|
| 246 |
+
"loss": 4.8218,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7098121085594989,
|
| 251 |
+
"grad_norm": 6.883273869392802,
|
| 252 |
+
"learning_rate": 6.999644452302975e-05,
|
| 253 |
+
"loss": 4.6982,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7306889352818372,
|
| 258 |
+
"grad_norm": 5.045481934015123,
|
| 259 |
+
"learning_rate": 6.0947967851014405e-05,
|
| 260 |
+
"loss": 4.6601,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7515657620041754,
|
| 265 |
+
"grad_norm": 4.832077424408084,
|
| 266 |
+
"learning_rate": 5.237462230091467e-05,
|
| 267 |
+
"loss": 4.5969,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7724425887265136,
|
| 272 |
+
"grad_norm": 4.500645176472541,
|
| 273 |
+
"learning_rate": 4.432215038069449e-05,
|
| 274 |
+
"loss": 4.548,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7933194154488518,
|
| 279 |
+
"grad_norm": 3.503698684667856,
|
| 280 |
+
"learning_rate": 3.6833515512134606e-05,
|
| 281 |
+
"loss": 4.5618,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.81419624217119,
|
| 286 |
+
"grad_norm": 3.680197433632794,
|
| 287 |
+
"learning_rate": 2.9948672802388135e-05,
|
| 288 |
+
"loss": 4.5023,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8350730688935282,
|
| 293 |
+
"grad_norm": 2.8773090613106302,
|
| 294 |
+
"learning_rate": 2.3704355866196373e-05,
|
| 295 |
+
"loss": 4.5226,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8559498956158664,
|
| 300 |
+
"grad_norm": 2.5614101608626467,
|
| 301 |
+
"learning_rate": 1.813388083616068e-05,
|
| 302 |
+
"loss": 4.4463,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8768267223382046,
|
| 307 |
+
"grad_norm": 2.2102224877308676,
|
| 308 |
+
"learning_rate": 1.326696860675981e-05,
|
| 309 |
+
"loss": 4.3724,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8977035490605428,
|
| 314 |
+
"grad_norm": 2.056590025798714,
|
| 315 |
+
"learning_rate": 9.129586260518634e-06,
|
| 316 |
+
"loss": 4.3747,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.918580375782881,
|
| 321 |
+
"grad_norm": 1.7949115931981623,
|
| 322 |
+
"learning_rate": 5.743808522387544e-06,
|
| 323 |
+
"loss": 4.3585,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9394572025052192,
|
| 328 |
+
"grad_norm": 1.5441796176488383,
|
| 329 |
+
"learning_rate": 3.1276999815337544e-06,
|
| 330 |
+
"loss": 4.3784,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9603340292275574,
|
| 335 |
+
"grad_norm": 1.549016859105234,
|
| 336 |
+
"learning_rate": 1.2952187089419642e-06,
|
| 337 |
+
"loss": 4.3766,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9812108559498957,
|
| 342 |
+
"grad_norm": 1.5003100935642444,
|
| 343 |
+
"learning_rate": 2.5614178506644934e-07,
|
| 344 |
+
"loss": 4.3115,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9979123173277662,
|
| 349 |
+
"eval_loss": 5.734466552734375,
|
| 350 |
+
"eval_runtime": 1.4349,
|
| 351 |
+
"eval_samples_per_second": 1.394,
|
| 352 |
+
"eval_steps_per_second": 0.697,
|
| 353 |
+
"step": 239
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.9979123173277662,
|
| 357 |
+
"step": 239,
|
| 358 |
+
"total_flos": 8193589641216.0,
|
| 359 |
+
"train_loss": 2.8353221366595025,
|
| 360 |
+
"train_runtime": 2240.0339,
|
| 361 |
+
"train_samples_per_second": 3.416,
|
| 362 |
+
"train_steps_per_second": 0.107
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"logging_steps": 5,
|
| 366 |
+
"max_steps": 239,
|
| 367 |
+
"num_input_tokens_seen": 0,
|
| 368 |
+
"num_train_epochs": 1,
|
| 369 |
+
"save_steps": 100,
|
| 370 |
+
"stateful_callbacks": {
|
| 371 |
+
"TrainerControl": {
|
| 372 |
+
"args": {
|
| 373 |
+
"should_epoch_stop": false,
|
| 374 |
+
"should_evaluate": false,
|
| 375 |
+
"should_log": false,
|
| 376 |
+
"should_save": true,
|
| 377 |
+
"should_training_stop": true
|
| 378 |
+
},
|
| 379 |
+
"attributes": {}
|
| 380 |
+
}
|
| 381 |
+
},
|
| 382 |
+
"total_flos": 8193589641216.0,
|
| 383 |
+
"train_batch_size": 2,
|
| 384 |
+
"trial_name": null,
|
| 385 |
+
"trial_params": null
|
| 386 |
+
}
|