Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- train_results.json +9 -0
- trainer_state.json +337 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: prometheus-7b-down-p0.1_seed42level1
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# prometheus-7b-down-p0.1_seed42level1
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.9914
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 4
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 1
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 59 |
+
| 0.7208 | 0.9988 | 204 | 0.9914 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.43.4
|
| 65 |
+
- Pytorch 2.3.1+cu121
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9987760097919217,
|
| 3 |
+
"total_flos": 42661104844800.0,
|
| 4 |
+
"train_loss": 0.8604376099857629,
|
| 5 |
+
"train_runtime": 5992.0788,
|
| 6 |
+
"train_samples": 19747,
|
| 7 |
+
"train_samples_per_second": 1.091,
|
| 8 |
+
"train_steps_per_second": 0.034
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.43.4"
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9987760097919217,
|
| 3 |
+
"total_flos": 42661104844800.0,
|
| 4 |
+
"train_loss": 0.8604376099857629,
|
| 5 |
+
"train_runtime": 5992.0788,
|
| 6 |
+
"train_samples": 19747,
|
| 7 |
+
"train_samples_per_second": 1.091,
|
| 8 |
+
"train_steps_per_second": 0.034
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9987760097919217,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 204,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004895960832313341,
|
| 13 |
+
"grad_norm": 31.803168810817947,
|
| 14 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 15 |
+
"loss": 1.3104,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02447980416156671,
|
| 20 |
+
"grad_norm": 12.089208314037734,
|
| 21 |
+
"learning_rate": 2.380952380952381e-06,
|
| 22 |
+
"loss": 1.2864,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04895960832313342,
|
| 27 |
+
"grad_norm": 3.734128443782965,
|
| 28 |
+
"learning_rate": 4.761904761904762e-06,
|
| 29 |
+
"loss": 1.0964,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07343941248470012,
|
| 34 |
+
"grad_norm": 2.7685333081809613,
|
| 35 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 36 |
+
"loss": 0.9865,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09791921664626684,
|
| 41 |
+
"grad_norm": 2.6618393187338545,
|
| 42 |
+
"learning_rate": 9.523809523809525e-06,
|
| 43 |
+
"loss": 0.9754,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12239902080783353,
|
| 48 |
+
"grad_norm": 2.8219368109360556,
|
| 49 |
+
"learning_rate": 9.988216158430033e-06,
|
| 50 |
+
"loss": 0.9828,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14687882496940025,
|
| 55 |
+
"grad_norm": 2.5325872032864996,
|
| 56 |
+
"learning_rate": 9.940439480455386e-06,
|
| 57 |
+
"loss": 0.9463,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.17135862913096694,
|
| 62 |
+
"grad_norm": 2.8908619331299925,
|
| 63 |
+
"learning_rate": 9.856284997329158e-06,
|
| 64 |
+
"loss": 0.9522,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.19583843329253367,
|
| 69 |
+
"grad_norm": 3.513186055584603,
|
| 70 |
+
"learning_rate": 9.736372361493584e-06,
|
| 71 |
+
"loss": 0.9812,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22031823745410037,
|
| 76 |
+
"grad_norm": 2.425130546395649,
|
| 77 |
+
"learning_rate": 9.581584522435025e-06,
|
| 78 |
+
"loss": 0.97,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.24479804161566707,
|
| 83 |
+
"grad_norm": 2.7085014552252793,
|
| 84 |
+
"learning_rate": 9.393061225285743e-06,
|
| 85 |
+
"loss": 0.9428,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2692778457772338,
|
| 90 |
+
"grad_norm": 2.5282305939205645,
|
| 91 |
+
"learning_rate": 9.172190618569236e-06,
|
| 92 |
+
"loss": 0.9455,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2937576499388005,
|
| 97 |
+
"grad_norm": 2.6167693326627406,
|
| 98 |
+
"learning_rate": 8.920599032883553e-06,
|
| 99 |
+
"loss": 0.9291,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3182374541003672,
|
| 104 |
+
"grad_norm": 2.4397467891197953,
|
| 105 |
+
"learning_rate": 8.640139005784924e-06,
|
| 106 |
+
"loss": 0.897,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3427172582619339,
|
| 111 |
+
"grad_norm": 2.687082572276412,
|
| 112 |
+
"learning_rate": 8.332875641047817e-06,
|
| 113 |
+
"loss": 0.8971,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3671970624235006,
|
| 118 |
+
"grad_norm": 2.464301621801395,
|
| 119 |
+
"learning_rate": 8.001071402741843e-06,
|
| 120 |
+
"loss": 0.9071,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.39167686658506734,
|
| 125 |
+
"grad_norm": 2.3157277119472557,
|
| 126 |
+
"learning_rate": 7.647169456090925e-06,
|
| 127 |
+
"loss": 0.8622,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.41615667074663404,
|
| 132 |
+
"grad_norm": 2.340548302385909,
|
| 133 |
+
"learning_rate": 7.27377567778053e-06,
|
| 134 |
+
"loss": 0.8368,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.44063647490820074,
|
| 139 |
+
"grad_norm": 2.434317748871704,
|
| 140 |
+
"learning_rate": 6.883639468175926e-06,
|
| 141 |
+
"loss": 0.871,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.46511627906976744,
|
| 146 |
+
"grad_norm": 2.9663953802110443,
|
| 147 |
+
"learning_rate": 6.479633506736447e-06,
|
| 148 |
+
"loss": 0.8407,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.48959608323133413,
|
| 153 |
+
"grad_norm": 2.5695792323184006,
|
| 154 |
+
"learning_rate": 6.064732599692079e-06,
|
| 155 |
+
"loss": 0.826,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5140758873929009,
|
| 160 |
+
"grad_norm": 2.999056757416413,
|
| 161 |
+
"learning_rate": 5.641991775732756e-06,
|
| 162 |
+
"loss": 0.8457,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5385556915544676,
|
| 167 |
+
"grad_norm": 2.9168664674153466,
|
| 168 |
+
"learning_rate": 5.214523790997773e-06,
|
| 169 |
+
"loss": 0.8173,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5630354957160343,
|
| 174 |
+
"grad_norm": 2.418710961036661,
|
| 175 |
+
"learning_rate": 4.7854762090022274e-06,
|
| 176 |
+
"loss": 0.8217,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.587515299877601,
|
| 181 |
+
"grad_norm": 2.324625674148865,
|
| 182 |
+
"learning_rate": 4.358008224267245e-06,
|
| 183 |
+
"loss": 0.8186,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6119951040391677,
|
| 188 |
+
"grad_norm": 2.354640178196254,
|
| 189 |
+
"learning_rate": 3.9352674003079225e-06,
|
| 190 |
+
"loss": 0.7969,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6364749082007344,
|
| 195 |
+
"grad_norm": 2.4349410812593524,
|
| 196 |
+
"learning_rate": 3.520366493263554e-06,
|
| 197 |
+
"loss": 0.7996,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6609547123623011,
|
| 202 |
+
"grad_norm": 2.415118649892107,
|
| 203 |
+
"learning_rate": 3.116360531824074e-06,
|
| 204 |
+
"loss": 0.8086,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6854345165238678,
|
| 209 |
+
"grad_norm": 2.369315986332015,
|
| 210 |
+
"learning_rate": 2.7262243222194728e-06,
|
| 211 |
+
"loss": 0.7904,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7099143206854345,
|
| 216 |
+
"grad_norm": 2.8408105027248056,
|
| 217 |
+
"learning_rate": 2.3528305439090744e-06,
|
| 218 |
+
"loss": 0.7711,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7343941248470012,
|
| 223 |
+
"grad_norm": 2.277003258633081,
|
| 224 |
+
"learning_rate": 1.9989285972581595e-06,
|
| 225 |
+
"loss": 0.7928,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.758873929008568,
|
| 230 |
+
"grad_norm": 2.398404156603122,
|
| 231 |
+
"learning_rate": 1.667124358952184e-06,
|
| 232 |
+
"loss": 0.7668,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7833537331701347,
|
| 237 |
+
"grad_norm": 2.3139627873668664,
|
| 238 |
+
"learning_rate": 1.3598609942150765e-06,
|
| 239 |
+
"loss": 0.7646,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8078335373317014,
|
| 244 |
+
"grad_norm": 2.322258534353416,
|
| 245 |
+
"learning_rate": 1.0794009671164484e-06,
|
| 246 |
+
"loss": 0.7782,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8323133414932681,
|
| 251 |
+
"grad_norm": 2.253023482934021,
|
| 252 |
+
"learning_rate": 8.278093814307637e-07,
|
| 253 |
+
"loss": 0.7425,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8567931456548348,
|
| 258 |
+
"grad_norm": 2.2625430444178223,
|
| 259 |
+
"learning_rate": 6.069387747142591e-07,
|
| 260 |
+
"loss": 0.7393,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8812729498164015,
|
| 265 |
+
"grad_norm": 2.474019483415415,
|
| 266 |
+
"learning_rate": 4.184154775649768e-07,
|
| 267 |
+
"loss": 0.7243,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9057527539779682,
|
| 272 |
+
"grad_norm": 2.318789387417803,
|
| 273 |
+
"learning_rate": 2.636276385064157e-07,
|
| 274 |
+
"loss": 0.7528,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9302325581395349,
|
| 279 |
+
"grad_norm": 2.2755119405821054,
|
| 280 |
+
"learning_rate": 1.4371500267084337e-07,
|
| 281 |
+
"loss": 0.755,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9547123623011016,
|
| 286 |
+
"grad_norm": 2.1830710176964283,
|
| 287 |
+
"learning_rate": 5.9560519544614725e-08,
|
| 288 |
+
"loss": 0.7424,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9791921664626683,
|
| 293 |
+
"grad_norm": 2.437291192873111,
|
| 294 |
+
"learning_rate": 1.1783841569968368e-08,
|
| 295 |
+
"loss": 0.7208,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9987760097919217,
|
| 300 |
+
"eval_loss": 0.9913554787635803,
|
| 301 |
+
"eval_runtime": 1210.5452,
|
| 302 |
+
"eval_samples_per_second": 3.159,
|
| 303 |
+
"eval_steps_per_second": 0.79,
|
| 304 |
+
"step": 204
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9987760097919217,
|
| 308 |
+
"step": 204,
|
| 309 |
+
"total_flos": 42661104844800.0,
|
| 310 |
+
"train_loss": 0.8604376099857629,
|
| 311 |
+
"train_runtime": 5992.0788,
|
| 312 |
+
"train_samples_per_second": 1.091,
|
| 313 |
+
"train_steps_per_second": 0.034
|
| 314 |
+
}
|
| 315 |
+
],
|
| 316 |
+
"logging_steps": 5,
|
| 317 |
+
"max_steps": 204,
|
| 318 |
+
"num_input_tokens_seen": 0,
|
| 319 |
+
"num_train_epochs": 1,
|
| 320 |
+
"save_steps": 100,
|
| 321 |
+
"stateful_callbacks": {
|
| 322 |
+
"TrainerControl": {
|
| 323 |
+
"args": {
|
| 324 |
+
"should_epoch_stop": false,
|
| 325 |
+
"should_evaluate": false,
|
| 326 |
+
"should_log": false,
|
| 327 |
+
"should_save": true,
|
| 328 |
+
"should_training_stop": true
|
| 329 |
+
},
|
| 330 |
+
"attributes": {}
|
| 331 |
+
}
|
| 332 |
+
},
|
| 333 |
+
"total_flos": 42661104844800.0,
|
| 334 |
+
"train_batch_size": 2,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|