Model save
Browse files- README.md +64 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +492 -0
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: problem39_model_more_aug_30
|
| 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 |
+
# problem39_model_more_aug_30
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0029
|
| 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: 5e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 2
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.0 | 1.0 | 31 | 0.0026 |
|
| 55 |
+
| 0.0001 | 2.0 | 62 | 0.0029 |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- PEFT 0.13.2
|
| 61 |
+
- Transformers 4.47.0.dev0
|
| 62 |
+
- Pytorch 2.4.0+cu121
|
| 63 |
+
- Datasets 3.1.0
|
| 64 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1144521031680.0,
|
| 4 |
+
"train_loss": 0.0004356121934755896,
|
| 5 |
+
"train_runtime": 331.8626,
|
| 6 |
+
"train_samples": 62,
|
| 7 |
+
"train_samples_per_second": 0.374,
|
| 8 |
+
"train_steps_per_second": 0.187
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1144521031680.0,
|
| 4 |
+
"train_loss": 0.0004356121934755896,
|
| 5 |
+
"train_runtime": 331.8626,
|
| 6 |
+
"train_samples": 62,
|
| 7 |
+
"train_samples_per_second": 0.374,
|
| 8 |
+
"train_steps_per_second": 0.187
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 62,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03225806451612903,
|
| 13 |
+
"grad_norm": 0.0003888311526422569,
|
| 14 |
+
"learning_rate": 7.142857142857143e-06,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06451612903225806,
|
| 20 |
+
"grad_norm": 0.006705866500275534,
|
| 21 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 22 |
+
"loss": 0.0018,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0967741935483871,
|
| 27 |
+
"grad_norm": 0.0004288404580521471,
|
| 28 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 29 |
+
"loss": 0.0001,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12903225806451613,
|
| 34 |
+
"grad_norm": 0.006721843317752399,
|
| 35 |
+
"learning_rate": 2.857142857142857e-05,
|
| 36 |
+
"loss": 0.0019,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16129032258064516,
|
| 41 |
+
"grad_norm": 0.009519105488016918,
|
| 42 |
+
"learning_rate": 3.571428571428572e-05,
|
| 43 |
+
"loss": 0.0032,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1935483870967742,
|
| 48 |
+
"grad_norm": 0.009983139237850786,
|
| 49 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 50 |
+
"loss": 0.003,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22580645161290322,
|
| 55 |
+
"grad_norm": 0.006711102239168073,
|
| 56 |
+
"learning_rate": 5e-05,
|
| 57 |
+
"loss": 0.0014,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.25806451612903225,
|
| 62 |
+
"grad_norm": 0.0001960930857351409,
|
| 63 |
+
"learning_rate": 4.995922759815339e-05,
|
| 64 |
+
"loss": 0.0,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2903225806451613,
|
| 69 |
+
"grad_norm": 9.143550595543499e-05,
|
| 70 |
+
"learning_rate": 4.9837043383713753e-05,
|
| 71 |
+
"loss": 0.0,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3225806451612903,
|
| 76 |
+
"grad_norm": 0.007417075139109489,
|
| 77 |
+
"learning_rate": 4.963384589619233e-05,
|
| 78 |
+
"loss": 0.0017,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3548387096774194,
|
| 83 |
+
"grad_norm": 0.002566821879916539,
|
| 84 |
+
"learning_rate": 4.935029792355834e-05,
|
| 85 |
+
"loss": 0.0006,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3870967741935484,
|
| 90 |
+
"grad_norm": 0.007642635295730325,
|
| 91 |
+
"learning_rate": 4.898732434036244e-05,
|
| 92 |
+
"loss": 0.0009,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.41935483870967744,
|
| 97 |
+
"grad_norm": 0.00826117485142426,
|
| 98 |
+
"learning_rate": 4.854610909098812e-05,
|
| 99 |
+
"loss": 0.0011,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.45161290322580644,
|
| 104 |
+
"grad_norm": 0.005359952597223366,
|
| 105 |
+
"learning_rate": 4.802809132787125e-05,
|
| 106 |
+
"loss": 0.0005,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4838709677419355,
|
| 111 |
+
"grad_norm": 0.002749396030753739,
|
| 112 |
+
"learning_rate": 4.743496071728396e-05,
|
| 113 |
+
"loss": 0.0002,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5161290322580645,
|
| 118 |
+
"grad_norm": 0.0011744439020923403,
|
| 119 |
+
"learning_rate": 4.6768651927994434e-05,
|
| 120 |
+
"loss": 0.0002,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5483870967741935,
|
| 125 |
+
"grad_norm": 0.0017986768332600579,
|
| 126 |
+
"learning_rate": 4.6031338320779534e-05,
|
| 127 |
+
"loss": 0.0003,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5806451612903226,
|
| 132 |
+
"grad_norm": 0.0027352310170441737,
|
| 133 |
+
"learning_rate": 4.522542485937369e-05,
|
| 134 |
+
"loss": 0.0006,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6129032258064516,
|
| 139 |
+
"grad_norm": 0.00021274929498089895,
|
| 140 |
+
"learning_rate": 4.4353540265977064e-05,
|
| 141 |
+
"loss": 0.0,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6451612903225806,
|
| 146 |
+
"grad_norm": 0.00015254003122006633,
|
| 147 |
+
"learning_rate": 4.341852844691012e-05,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6774193548387096,
|
| 153 |
+
"grad_norm": 0.00014754669500526948,
|
| 154 |
+
"learning_rate": 4.242343921638234e-05,
|
| 155 |
+
"loss": 0.0,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7096774193548387,
|
| 160 |
+
"grad_norm": 0.014701207072580798,
|
| 161 |
+
"learning_rate": 4.137151834863213e-05,
|
| 162 |
+
"loss": 0.0053,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7419354838709677,
|
| 167 |
+
"grad_norm": 0.00040132537069888165,
|
| 168 |
+
"learning_rate": 4.0266196990885955e-05,
|
| 169 |
+
"loss": 0.0001,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7741935483870968,
|
| 174 |
+
"grad_norm": 0.000310253267324018,
|
| 175 |
+
"learning_rate": 3.911108047166924e-05,
|
| 176 |
+
"loss": 0.0,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8064516129032258,
|
| 181 |
+
"grad_norm": 0.0032453162218567663,
|
| 182 |
+
"learning_rate": 3.790993654097405e-05,
|
| 183 |
+
"loss": 0.0004,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8387096774193549,
|
| 188 |
+
"grad_norm": 0.0011259240533704532,
|
| 189 |
+
"learning_rate": 3.6666683080641846e-05,
|
| 190 |
+
"loss": 0.0002,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8709677419354839,
|
| 195 |
+
"grad_norm": 6.593340410831557e-05,
|
| 196 |
+
"learning_rate": 3.5385375325047166e-05,
|
| 197 |
+
"loss": 0.0,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9032258064516129,
|
| 202 |
+
"grad_norm": 5.1984982035018296e-05,
|
| 203 |
+
"learning_rate": 3.4070192633766025e-05,
|
| 204 |
+
"loss": 0.0,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9354838709677419,
|
| 209 |
+
"grad_norm": 0.0012978852470741332,
|
| 210 |
+
"learning_rate": 3.272542485937369e-05,
|
| 211 |
+
"loss": 0.0002,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.967741935483871,
|
| 216 |
+
"grad_norm": 0.0011559129352493,
|
| 217 |
+
"learning_rate": 3.135545835483718e-05,
|
| 218 |
+
"loss": 0.0001,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"grad_norm": 0.00016768764915493187,
|
| 224 |
+
"learning_rate": 2.996476166614364e-05,
|
| 225 |
+
"loss": 0.0,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0,
|
| 230 |
+
"eval_loss": 0.002580386819317937,
|
| 231 |
+
"eval_runtime": 0.6554,
|
| 232 |
+
"eval_samples_per_second": 1.526,
|
| 233 |
+
"eval_steps_per_second": 1.526,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.032258064516129,
|
| 238 |
+
"grad_norm": 9.698020571956317e-05,
|
| 239 |
+
"learning_rate": 2.8557870956832132e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.064516129032258,
|
| 245 |
+
"grad_norm": 0.0017065509209019311,
|
| 246 |
+
"learning_rate": 2.7139375211970996e-05,
|
| 247 |
+
"loss": 0.0001,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.096774193548387,
|
| 252 |
+
"grad_norm": 0.008080666632729714,
|
| 253 |
+
"learning_rate": 2.5713901269842404e-05,
|
| 254 |
+
"loss": 0.0022,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.129032258064516,
|
| 259 |
+
"grad_norm": 0.00014016671601073153,
|
| 260 |
+
"learning_rate": 2.42860987301576e-05,
|
| 261 |
+
"loss": 0.0,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1612903225806452,
|
| 266 |
+
"grad_norm": 0.0002183282791861122,
|
| 267 |
+
"learning_rate": 2.2860624788029013e-05,
|
| 268 |
+
"loss": 0.0,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1935483870967742,
|
| 273 |
+
"grad_norm": 3.4706191979932056e-05,
|
| 274 |
+
"learning_rate": 2.1442129043167874e-05,
|
| 275 |
+
"loss": 0.0,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.2258064516129032,
|
| 280 |
+
"grad_norm": 6.274199180955771e-05,
|
| 281 |
+
"learning_rate": 2.003523833385637e-05,
|
| 282 |
+
"loss": 0.0,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.2580645161290323,
|
| 287 |
+
"grad_norm": 0.00011240971099287573,
|
| 288 |
+
"learning_rate": 1.8644541645162834e-05,
|
| 289 |
+
"loss": 0.0,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2903225806451613,
|
| 294 |
+
"grad_norm": 8.379442890594463e-05,
|
| 295 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 296 |
+
"loss": 0.0,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.3225806451612903,
|
| 301 |
+
"grad_norm": 0.0006950311671464802,
|
| 302 |
+
"learning_rate": 1.5929807366233977e-05,
|
| 303 |
+
"loss": 0.0001,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.3548387096774195,
|
| 308 |
+
"grad_norm": 6.554897296239256e-05,
|
| 309 |
+
"learning_rate": 1.4614624674952842e-05,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3870967741935485,
|
| 315 |
+
"grad_norm": 8.946111691896196e-05,
|
| 316 |
+
"learning_rate": 1.3333316919358157e-05,
|
| 317 |
+
"loss": 0.0,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4193548387096775,
|
| 322 |
+
"grad_norm": 0.00021237835272870894,
|
| 323 |
+
"learning_rate": 1.2090063459025955e-05,
|
| 324 |
+
"loss": 0.0,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.4516129032258065,
|
| 329 |
+
"grad_norm": 8.780703503531893e-05,
|
| 330 |
+
"learning_rate": 1.0888919528330777e-05,
|
| 331 |
+
"loss": 0.0,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4838709677419355,
|
| 336 |
+
"grad_norm": 9.310185931359011e-05,
|
| 337 |
+
"learning_rate": 9.733803009114045e-06,
|
| 338 |
+
"loss": 0.0,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5161290322580645,
|
| 343 |
+
"grad_norm": 0.0022132919985140046,
|
| 344 |
+
"learning_rate": 8.628481651367876e-06,
|
| 345 |
+
"loss": 0.0002,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5483870967741935,
|
| 350 |
+
"grad_norm": 0.0001803834028245764,
|
| 351 |
+
"learning_rate": 7.576560783617668e-06,
|
| 352 |
+
"loss": 0.0,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5806451612903225,
|
| 357 |
+
"grad_norm": 0.0011069882126815845,
|
| 358 |
+
"learning_rate": 6.5814715530898745e-06,
|
| 359 |
+
"loss": 0.0001,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.6129032258064515,
|
| 364 |
+
"grad_norm": 0.00015904430381639932,
|
| 365 |
+
"learning_rate": 5.646459734022938e-06,
|
| 366 |
+
"loss": 0.0,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.6451612903225805,
|
| 371 |
+
"grad_norm": 0.00023196882598516344,
|
| 372 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 373 |
+
"loss": 0.0,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6774193548387095,
|
| 378 |
+
"grad_norm": 8.494839968665877e-05,
|
| 379 |
+
"learning_rate": 3.968661679220468e-06,
|
| 380 |
+
"loss": 0.0,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.7096774193548387,
|
| 385 |
+
"grad_norm": 7.495013324600562e-05,
|
| 386 |
+
"learning_rate": 3.2313480720055745e-06,
|
| 387 |
+
"loss": 0.0,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.7419354838709677,
|
| 392 |
+
"grad_norm": 0.00011153696481041336,
|
| 393 |
+
"learning_rate": 2.565039282716045e-06,
|
| 394 |
+
"loss": 0.0,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.7741935483870968,
|
| 399 |
+
"grad_norm": 9.790228118890396e-05,
|
| 400 |
+
"learning_rate": 1.97190867212875e-06,
|
| 401 |
+
"loss": 0.0,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.8064516129032258,
|
| 406 |
+
"grad_norm": 0.0005323293049174912,
|
| 407 |
+
"learning_rate": 1.4538909090118846e-06,
|
| 408 |
+
"loss": 0.0,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.838709677419355,
|
| 413 |
+
"grad_norm": 7.75389691903468e-05,
|
| 414 |
+
"learning_rate": 1.0126756596375686e-06,
|
| 415 |
+
"loss": 0.0,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.870967741935484,
|
| 420 |
+
"grad_norm": 9.419564261080586e-05,
|
| 421 |
+
"learning_rate": 6.497020764416633e-07,
|
| 422 |
+
"loss": 0.0,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.903225806451613,
|
| 427 |
+
"grad_norm": 1.6085484123530773e-05,
|
| 428 |
+
"learning_rate": 3.6615410380767544e-07,
|
| 429 |
+
"loss": 0.0,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.935483870967742,
|
| 434 |
+
"grad_norm": 0.0005223311340339994,
|
| 435 |
+
"learning_rate": 1.6295661628624447e-07,
|
| 436 |
+
"loss": 0.0001,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.967741935483871,
|
| 441 |
+
"grad_norm": 9.50629744971249e-05,
|
| 442 |
+
"learning_rate": 4.07724018466088e-08,
|
| 443 |
+
"loss": 0.0,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"grad_norm": 0.0005980841644283981,
|
| 449 |
+
"learning_rate": 0.0,
|
| 450 |
+
"loss": 0.0001,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.0,
|
| 455 |
+
"eval_loss": 0.0029119281098246574,
|
| 456 |
+
"eval_runtime": 1.4832,
|
| 457 |
+
"eval_samples_per_second": 0.674,
|
| 458 |
+
"eval_steps_per_second": 0.674,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.0,
|
| 463 |
+
"step": 62,
|
| 464 |
+
"total_flos": 1144521031680.0,
|
| 465 |
+
"train_loss": 0.0004356121934755896,
|
| 466 |
+
"train_runtime": 331.8626,
|
| 467 |
+
"train_samples_per_second": 0.374,
|
| 468 |
+
"train_steps_per_second": 0.187
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 1,
|
| 472 |
+
"max_steps": 62,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 2,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"stateful_callbacks": {
|
| 477 |
+
"TrainerControl": {
|
| 478 |
+
"args": {
|
| 479 |
+
"should_epoch_stop": false,
|
| 480 |
+
"should_evaluate": false,
|
| 481 |
+
"should_log": false,
|
| 482 |
+
"should_save": true,
|
| 483 |
+
"should_training_stop": true
|
| 484 |
+
},
|
| 485 |
+
"attributes": {}
|
| 486 |
+
}
|
| 487 |
+
},
|
| 488 |
+
"total_flos": 1144521031680.0,
|
| 489 |
+
"train_batch_size": 2,
|
| 490 |
+
"trial_name": null,
|
| 491 |
+
"trial_params": null
|
| 492 |
+
}
|