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 +428 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-v0.3
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: mistral-7b-0.3-gpt4o_100k_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 |
+
# mistral-7b-0.3-gpt4o_100k_classification-fft
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 5.3380
|
| 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: 0.0002
|
| 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 |
+
| 4.2827 | 1.0 | 268 | 5.3380 |
|
| 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": 1.0,
|
| 3 |
+
"total_flos": 14002264473600.0,
|
| 4 |
+
"train_loss": 6.666975224196022,
|
| 5 |
+
"train_runtime": 4378.2382,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 1.956,
|
| 8 |
+
"train_steps_per_second": 0.061
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 32768,
|
| 4 |
+
"eos_token_id": 32769,
|
| 5 |
+
"pad_token_id": 32769,
|
| 6 |
+
"transformers_version": "4.45.1"
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 14002264473600.0,
|
| 4 |
+
"train_loss": 6.666975224196022,
|
| 5 |
+
"train_runtime": 4378.2382,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 1.956,
|
| 8 |
+
"train_steps_per_second": 0.061
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 268,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0037313432835820895,
|
| 13 |
+
"grad_norm": 267.42432987632304,
|
| 14 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 15 |
+
"loss": 2.0376,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.018656716417910446,
|
| 20 |
+
"grad_norm": 497.8829601573007,
|
| 21 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 22 |
+
"loss": 5.6478,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03731343283582089,
|
| 27 |
+
"grad_norm": 454.2837874993471,
|
| 28 |
+
"learning_rate": 7.407407407407407e-05,
|
| 29 |
+
"loss": 9.0654,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.055970149253731345,
|
| 34 |
+
"grad_norm": 172.70761646653747,
|
| 35 |
+
"learning_rate": 0.00011111111111111112,
|
| 36 |
+
"loss": 11.6263,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07462686567164178,
|
| 41 |
+
"grad_norm": 431.0320152584827,
|
| 42 |
+
"learning_rate": 0.00014814814814814815,
|
| 43 |
+
"loss": 12.0175,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09328358208955224,
|
| 48 |
+
"grad_norm": 57.24075920715652,
|
| 49 |
+
"learning_rate": 0.0001851851851851852,
|
| 50 |
+
"loss": 10.5566,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11194029850746269,
|
| 55 |
+
"grad_norm": 207.16475278732815,
|
| 56 |
+
"learning_rate": 0.00019992354201925428,
|
| 57 |
+
"loss": 22.4578,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13059701492537312,
|
| 62 |
+
"grad_norm": 39.84010000225324,
|
| 63 |
+
"learning_rate": 0.0001994567221375987,
|
| 64 |
+
"loss": 13.0098,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14925373134328357,
|
| 69 |
+
"grad_norm": 421.8360841321533,
|
| 70 |
+
"learning_rate": 0.00019856753906964686,
|
| 71 |
+
"loss": 17.1304,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16791044776119404,
|
| 76 |
+
"grad_norm": 32.18021173317482,
|
| 77 |
+
"learning_rate": 0.00019725976891203376,
|
| 78 |
+
"loss": 9.8365,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1865671641791045,
|
| 83 |
+
"grad_norm": 17.663716447972774,
|
| 84 |
+
"learning_rate": 0.00019553896537655318,
|
| 85 |
+
"loss": 7.5461,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.20522388059701493,
|
| 90 |
+
"grad_norm": 15.828267774314414,
|
| 91 |
+
"learning_rate": 0.0001934124362051919,
|
| 92 |
+
"loss": 6.9658,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22388059701492538,
|
| 97 |
+
"grad_norm": 307.89143980814515,
|
| 98 |
+
"learning_rate": 0.000190889212136318,
|
| 99 |
+
"loss": 7.6309,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.24253731343283583,
|
| 104 |
+
"grad_norm": 17.3100107773664,
|
| 105 |
+
"learning_rate": 0.0001879800085538147,
|
| 106 |
+
"loss": 6.9331,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26119402985074625,
|
| 111 |
+
"grad_norm": 42.588666065454795,
|
| 112 |
+
"learning_rate": 0.00018469717998202462,
|
| 113 |
+
"loss": 6.9227,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2798507462686567,
|
| 118 |
+
"grad_norm": 10.804006051624885,
|
| 119 |
+
"learning_rate": 0.00018105466761975109,
|
| 120 |
+
"loss": 6.5832,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.29850746268656714,
|
| 125 |
+
"grad_norm": 43.74337828897061,
|
| 126 |
+
"learning_rate": 0.00017706794013612364,
|
| 127 |
+
"loss": 6.8176,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.31716417910447764,
|
| 132 |
+
"grad_norm": 64.2085843780536,
|
| 133 |
+
"learning_rate": 0.00017275392797975032,
|
| 134 |
+
"loss": 6.7523,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3358208955223881,
|
| 139 |
+
"grad_norm": 16.593450775671112,
|
| 140 |
+
"learning_rate": 0.0001681309514801265,
|
| 141 |
+
"loss": 6.5873,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35447761194029853,
|
| 146 |
+
"grad_norm": 44.277670283010906,
|
| 147 |
+
"learning_rate": 0.00016321864304663173,
|
| 148 |
+
"loss": 6.5937,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.373134328358209,
|
| 153 |
+
"grad_norm": 10.997588847093564,
|
| 154 |
+
"learning_rate": 0.0001580378637955128,
|
| 155 |
+
"loss": 6.4452,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3917910447761194,
|
| 160 |
+
"grad_norm": 12.654122748772814,
|
| 161 |
+
"learning_rate": 0.00015261061495891345,
|
| 162 |
+
"loss": 6.3491,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.41044776119402987,
|
| 167 |
+
"grad_norm": 26.609938261473722,
|
| 168 |
+
"learning_rate": 0.00014695994445216985,
|
| 169 |
+
"loss": 6.4977,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4291044776119403,
|
| 174 |
+
"grad_norm": 29.405974371105227,
|
| 175 |
+
"learning_rate": 0.00014110984899615367,
|
| 176 |
+
"loss": 6.3102,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.44776119402985076,
|
| 181 |
+
"grad_norm": 14.382835497900352,
|
| 182 |
+
"learning_rate": 0.000135085172210319,
|
| 183 |
+
"loss": 6.2751,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4664179104477612,
|
| 188 |
+
"grad_norm": 27.156229733294634,
|
| 189 |
+
"learning_rate": 0.00012891149910922267,
|
| 190 |
+
"loss": 6.148,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.48507462686567165,
|
| 195 |
+
"grad_norm": 14.830451492836382,
|
| 196 |
+
"learning_rate": 0.00012261504745055964,
|
| 197 |
+
"loss": 5.9625,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.503731343283582,
|
| 202 |
+
"grad_norm": 16.181539488534295,
|
| 203 |
+
"learning_rate": 0.00011622255639612554,
|
| 204 |
+
"loss": 5.8024,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5223880597014925,
|
| 209 |
+
"grad_norm": 7.100118045807948,
|
| 210 |
+
"learning_rate": 0.00010976117295853154,
|
| 211 |
+
"loss": 5.7823,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5410447761194029,
|
| 216 |
+
"grad_norm": 6.078519973242612,
|
| 217 |
+
"learning_rate": 0.00010325833671589687,
|
| 218 |
+
"loss": 5.6857,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5597014925373134,
|
| 223 |
+
"grad_norm": 10.507318938395432,
|
| 224 |
+
"learning_rate": 9.674166328410318e-05,
|
| 225 |
+
"loss": 5.5985,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5783582089552238,
|
| 230 |
+
"grad_norm": 7.511601189522553,
|
| 231 |
+
"learning_rate": 9.023882704146848e-05,
|
| 232 |
+
"loss": 5.5306,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5970149253731343,
|
| 237 |
+
"grad_norm": 9.098000461581764,
|
| 238 |
+
"learning_rate": 8.377744360387447e-05,
|
| 239 |
+
"loss": 5.4113,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6156716417910447,
|
| 244 |
+
"grad_norm": 11.04848131475541,
|
| 245 |
+
"learning_rate": 7.738495254944042e-05,
|
| 246 |
+
"loss": 5.3399,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6343283582089553,
|
| 251 |
+
"grad_norm": 4.899181488882252,
|
| 252 |
+
"learning_rate": 7.108850089077735e-05,
|
| 253 |
+
"loss": 5.2061,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6529850746268657,
|
| 258 |
+
"grad_norm": 8.571361713934442,
|
| 259 |
+
"learning_rate": 6.491482778968104e-05,
|
| 260 |
+
"loss": 5.1067,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6716417910447762,
|
| 265 |
+
"grad_norm": 6.366810352482946,
|
| 266 |
+
"learning_rate": 5.889015100384636e-05,
|
| 267 |
+
"loss": 4.9611,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6902985074626866,
|
| 272 |
+
"grad_norm": 7.987975314659695,
|
| 273 |
+
"learning_rate": 5.304005554783015e-05,
|
| 274 |
+
"loss": 4.9129,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7089552238805971,
|
| 279 |
+
"grad_norm": 4.106981286779299,
|
| 280 |
+
"learning_rate": 4.738938504108659e-05,
|
| 281 |
+
"loss": 4.8382,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7276119402985075,
|
| 286 |
+
"grad_norm": 3.7918439805690527,
|
| 287 |
+
"learning_rate": 4.196213620448723e-05,
|
| 288 |
+
"loss": 4.7711,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.746268656716418,
|
| 293 |
+
"grad_norm": 3.6468350915483128,
|
| 294 |
+
"learning_rate": 3.6781356953368284e-05,
|
| 295 |
+
"loss": 4.6595,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7649253731343284,
|
| 300 |
+
"grad_norm": 2.974947620754676,
|
| 301 |
+
"learning_rate": 3.186904851987351e-05,
|
| 302 |
+
"loss": 4.638,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7835820895522388,
|
| 307 |
+
"grad_norm": 2.355137193482797,
|
| 308 |
+
"learning_rate": 2.724607202024969e-05,
|
| 309 |
+
"loss": 4.5794,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8022388059701493,
|
| 314 |
+
"grad_norm": 3.096708977884932,
|
| 315 |
+
"learning_rate": 2.2932059863876365e-05,
|
| 316 |
+
"loss": 4.5585,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8208955223880597,
|
| 321 |
+
"grad_norm": 2.8473392855240984,
|
| 322 |
+
"learning_rate": 1.8945332380248913e-05,
|
| 323 |
+
"loss": 4.4602,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8395522388059702,
|
| 328 |
+
"grad_norm": 2.7970718450568692,
|
| 329 |
+
"learning_rate": 1.5302820017975394e-05,
|
| 330 |
+
"loss": 4.419,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8582089552238806,
|
| 335 |
+
"grad_norm": 3.5908637322056407,
|
| 336 |
+
"learning_rate": 1.2019991446185309e-05,
|
| 337 |
+
"loss": 4.394,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8768656716417911,
|
| 342 |
+
"grad_norm": 2.327431302717702,
|
| 343 |
+
"learning_rate": 9.110787863682002e-06,
|
| 344 |
+
"loss": 4.3572,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8955223880597015,
|
| 349 |
+
"grad_norm": 3.3167882122894534,
|
| 350 |
+
"learning_rate": 6.587563794808127e-06,
|
| 351 |
+
"loss": 4.3148,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.914179104477612,
|
| 356 |
+
"grad_norm": 3.128747890951307,
|
| 357 |
+
"learning_rate": 4.461034623446847e-06,
|
| 358 |
+
"loss": 4.3543,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9328358208955224,
|
| 363 |
+
"grad_norm": 2.4600560952322423,
|
| 364 |
+
"learning_rate": 2.7402310879662497e-06,
|
| 365 |
+
"loss": 4.301,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9514925373134329,
|
| 370 |
+
"grad_norm": 2.0585484791225954,
|
| 371 |
+
"learning_rate": 1.43246093035313e-06,
|
| 372 |
+
"loss": 4.2912,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9701492537313433,
|
| 377 |
+
"grad_norm": 1.864333596517171,
|
| 378 |
+
"learning_rate": 5.432778624013257e-07,
|
| 379 |
+
"loss": 4.281,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9888059701492538,
|
| 384 |
+
"grad_norm": 1.6036658756559803,
|
| 385 |
+
"learning_rate": 7.645798074572552e-08,
|
| 386 |
+
"loss": 4.2827,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.0,
|
| 391 |
+
"eval_loss": 5.337969779968262,
|
| 392 |
+
"eval_runtime": 2.3919,
|
| 393 |
+
"eval_samples_per_second": 0.836,
|
| 394 |
+
"eval_steps_per_second": 0.418,
|
| 395 |
+
"step": 268
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.0,
|
| 399 |
+
"step": 268,
|
| 400 |
+
"total_flos": 14002264473600.0,
|
| 401 |
+
"train_loss": 6.666975224196022,
|
| 402 |
+
"train_runtime": 4378.2382,
|
| 403 |
+
"train_samples_per_second": 1.956,
|
| 404 |
+
"train_steps_per_second": 0.061
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"logging_steps": 5,
|
| 408 |
+
"max_steps": 268,
|
| 409 |
+
"num_input_tokens_seen": 0,
|
| 410 |
+
"num_train_epochs": 1,
|
| 411 |
+
"save_steps": 100,
|
| 412 |
+
"stateful_callbacks": {
|
| 413 |
+
"TrainerControl": {
|
| 414 |
+
"args": {
|
| 415 |
+
"should_epoch_stop": false,
|
| 416 |
+
"should_evaluate": false,
|
| 417 |
+
"should_log": false,
|
| 418 |
+
"should_save": true,
|
| 419 |
+
"should_training_stop": true
|
| 420 |
+
},
|
| 421 |
+
"attributes": {}
|
| 422 |
+
}
|
| 423 |
+
},
|
| 424 |
+
"total_flos": 14002264473600.0,
|
| 425 |
+
"train_batch_size": 2,
|
| 426 |
+
"trial_name": null,
|
| 427 |
+
"trial_params": null
|
| 428 |
+
}
|