Model save
Browse files- README.md +75 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +284 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 9 |
+
model-index:
|
| 10 |
+
- name: nash_ave_pi_iter_3
|
| 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 |
+
# nash_ave_pi_iter_3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6740
|
| 22 |
+
- Rewards/chosen: 0.0085
|
| 23 |
+
- Rewards/rejected: -0.0290
|
| 24 |
+
- Rewards/accuracies: 0.6360
|
| 25 |
+
- Rewards/margins: 0.0375
|
| 26 |
+
- Logps/rejected: -263.6366
|
| 27 |
+
- Logps/chosen: -286.1499
|
| 28 |
+
- Logits/rejected: -2.6278
|
| 29 |
+
- Logits/chosen: -2.7115
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 5e-06
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 2
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- num_devices: 4
|
| 54 |
+
- gradient_accumulation_steps: 16
|
| 55 |
+
- total_train_batch_size: 128
|
| 56 |
+
- total_eval_batch_size: 8
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: cosine
|
| 59 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 60 |
+
- num_epochs: 1
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 66 |
+
| 0.6837 | 0.61 | 100 | 0.6740 | 0.0085 | -0.0290 | 0.6360 | 0.0375 | -263.6366 | -286.1499 | -2.6278 | -2.7115 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.7.1
|
| 72 |
+
- Transformers 4.36.2
|
| 73 |
+
- Pytorch 2.3.0+cu121
|
| 74 |
+
- Datasets 2.14.6
|
| 75 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.685761218359976,
|
| 4 |
+
"train_runtime": 6660.773,
|
| 5 |
+
"train_samples": 21135,
|
| 6 |
+
"train_samples_per_second": 3.173,
|
| 7 |
+
"train_steps_per_second": 0.025
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.685761218359976,
|
| 4 |
+
"train_runtime": 6660.773,
|
| 5 |
+
"train_samples": 21135,
|
| 6 |
+
"train_samples_per_second": 3.173,
|
| 7 |
+
"train_steps_per_second": 0.025
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,284 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9992429977289932,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 165,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 14 |
+
"logits/chosen": -2.737081289291382,
|
| 15 |
+
"logits/rejected": -2.680964708328247,
|
| 16 |
+
"logps/chosen": -126.38134765625,
|
| 17 |
+
"logps/rejected": -136.25076293945312,
|
| 18 |
+
"loss": 0.6931,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 28 |
+
"logits/chosen": -2.731968879699707,
|
| 29 |
+
"logits/rejected": -2.708989143371582,
|
| 30 |
+
"logps/chosen": -118.21139526367188,
|
| 31 |
+
"logps/rejected": -111.94728088378906,
|
| 32 |
+
"loss": 0.6932,
|
| 33 |
+
"rewards/accuracies": 0.4583333432674408,
|
| 34 |
+
"rewards/chosen": -1.655664891586639e-05,
|
| 35 |
+
"rewards/margins": -7.096579793142155e-05,
|
| 36 |
+
"rewards/rejected": 5.4409170843428e-05,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12,
|
| 41 |
+
"learning_rate": 4.994932636402032e-06,
|
| 42 |
+
"logits/chosen": -2.744499683380127,
|
| 43 |
+
"logits/rejected": -2.7339892387390137,
|
| 44 |
+
"logps/chosen": -113.14430236816406,
|
| 45 |
+
"logps/rejected": -123.68851470947266,
|
| 46 |
+
"loss": 0.6929,
|
| 47 |
+
"rewards/accuracies": 0.5218750238418579,
|
| 48 |
+
"rewards/chosen": 0.007225497625768185,
|
| 49 |
+
"rewards/margins": 0.0004294503596611321,
|
| 50 |
+
"rewards/rejected": 0.0067960480228066444,
|
| 51 |
+
"step": 20
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"learning_rate": 4.905416503522124e-06,
|
| 56 |
+
"logits/chosen": -2.772244930267334,
|
| 57 |
+
"logits/rejected": -2.7886576652526855,
|
| 58 |
+
"logps/chosen": -115.32562255859375,
|
| 59 |
+
"logps/rejected": -122.47587585449219,
|
| 60 |
+
"loss": 0.6925,
|
| 61 |
+
"rewards/accuracies": 0.518750011920929,
|
| 62 |
+
"rewards/chosen": 0.024915488436818123,
|
| 63 |
+
"rewards/margins": 0.00023288575175683945,
|
| 64 |
+
"rewards/rejected": 0.024682600051164627,
|
| 65 |
+
"step": 30
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.24,
|
| 69 |
+
"learning_rate": 4.707922373336524e-06,
|
| 70 |
+
"logits/chosen": -2.740614175796509,
|
| 71 |
+
"logits/rejected": -2.727870464324951,
|
| 72 |
+
"logps/chosen": -111.22251892089844,
|
| 73 |
+
"logps/rejected": -113.79164123535156,
|
| 74 |
+
"loss": 0.691,
|
| 75 |
+
"rewards/accuracies": 0.596875011920929,
|
| 76 |
+
"rewards/chosen": 0.052265096455812454,
|
| 77 |
+
"rewards/margins": 0.003552838694304228,
|
| 78 |
+
"rewards/rejected": 0.04871225729584694,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3,
|
| 83 |
+
"learning_rate": 4.411315662967732e-06,
|
| 84 |
+
"logits/chosen": -2.775801181793213,
|
| 85 |
+
"logits/rejected": -2.7031962871551514,
|
| 86 |
+
"logps/chosen": -109.81254577636719,
|
| 87 |
+
"logps/rejected": -113.3335952758789,
|
| 88 |
+
"loss": 0.6897,
|
| 89 |
+
"rewards/accuracies": 0.550000011920929,
|
| 90 |
+
"rewards/chosen": 0.0849301889538765,
|
| 91 |
+
"rewards/margins": 0.006556935608386993,
|
| 92 |
+
"rewards/rejected": 0.0783732533454895,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.36,
|
| 97 |
+
"learning_rate": 4.028910905897229e-06,
|
| 98 |
+
"logits/chosen": -2.756106376647949,
|
| 99 |
+
"logits/rejected": -2.7039153575897217,
|
| 100 |
+
"logps/chosen": -110.66825103759766,
|
| 101 |
+
"logps/rejected": -110.25054931640625,
|
| 102 |
+
"loss": 0.689,
|
| 103 |
+
"rewards/accuracies": 0.596875011920929,
|
| 104 |
+
"rewards/chosen": 0.09365645796060562,
|
| 105 |
+
"rewards/margins": 0.008471069857478142,
|
| 106 |
+
"rewards/rejected": 0.08518538624048233,
|
| 107 |
+
"step": 60
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.42,
|
| 111 |
+
"learning_rate": 3.577874068920446e-06,
|
| 112 |
+
"logits/chosen": -2.7151947021484375,
|
| 113 |
+
"logits/rejected": -2.706727981567383,
|
| 114 |
+
"logps/chosen": -109.93450927734375,
|
| 115 |
+
"logps/rejected": -113.0154800415039,
|
| 116 |
+
"loss": 0.6885,
|
| 117 |
+
"rewards/accuracies": 0.546875,
|
| 118 |
+
"rewards/chosen": 0.07744868099689484,
|
| 119 |
+
"rewards/margins": 0.004513105843216181,
|
| 120 |
+
"rewards/rejected": 0.0729355737566948,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.48,
|
| 125 |
+
"learning_rate": 3.0784519801008546e-06,
|
| 126 |
+
"logits/chosen": -2.692235231399536,
|
| 127 |
+
"logits/rejected": -2.6538617610931396,
|
| 128 |
+
"logps/chosen": -111.87430572509766,
|
| 129 |
+
"logps/rejected": -115.57984924316406,
|
| 130 |
+
"loss": 0.6867,
|
| 131 |
+
"rewards/accuracies": 0.596875011920929,
|
| 132 |
+
"rewards/chosen": 0.07563529908657074,
|
| 133 |
+
"rewards/margins": 0.015832457691431046,
|
| 134 |
+
"rewards/rejected": 0.059802841395139694,
|
| 135 |
+
"step": 80
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.55,
|
| 139 |
+
"learning_rate": 2.553063458334059e-06,
|
| 140 |
+
"logits/chosen": -2.738804340362549,
|
| 141 |
+
"logits/rejected": -2.690701723098755,
|
| 142 |
+
"logps/chosen": -120.409423828125,
|
| 143 |
+
"logps/rejected": -118.25407409667969,
|
| 144 |
+
"loss": 0.6841,
|
| 145 |
+
"rewards/accuracies": 0.574999988079071,
|
| 146 |
+
"rewards/chosen": 0.05362895876169205,
|
| 147 |
+
"rewards/margins": 0.01961613819003105,
|
| 148 |
+
"rewards/rejected": 0.034012824296951294,
|
| 149 |
+
"step": 90
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.61,
|
| 153 |
+
"learning_rate": 2.025292943281429e-06,
|
| 154 |
+
"logits/chosen": -2.718660593032837,
|
| 155 |
+
"logits/rejected": -2.7189323902130127,
|
| 156 |
+
"logps/chosen": -108.1891098022461,
|
| 157 |
+
"logps/rejected": -112.934814453125,
|
| 158 |
+
"loss": 0.6837,
|
| 159 |
+
"rewards/accuracies": 0.590624988079071,
|
| 160 |
+
"rewards/chosen": 0.06428461521863937,
|
| 161 |
+
"rewards/margins": 0.0179769154638052,
|
| 162 |
+
"rewards/rejected": 0.04630769044160843,
|
| 163 |
+
"step": 100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.61,
|
| 167 |
+
"eval_logits/chosen": -2.7115368843078613,
|
| 168 |
+
"eval_logits/rejected": -2.6278061866760254,
|
| 169 |
+
"eval_logps/chosen": -286.1498718261719,
|
| 170 |
+
"eval_logps/rejected": -263.6365966796875,
|
| 171 |
+
"eval_loss": 0.6740216016769409,
|
| 172 |
+
"eval_rewards/accuracies": 0.6359999775886536,
|
| 173 |
+
"eval_rewards/chosen": 0.008544988930225372,
|
| 174 |
+
"eval_rewards/margins": 0.03750109300017357,
|
| 175 |
+
"eval_rewards/rejected": -0.028956104069948196,
|
| 176 |
+
"eval_runtime": 383.9881,
|
| 177 |
+
"eval_samples_per_second": 5.208,
|
| 178 |
+
"eval_steps_per_second": 0.651,
|
| 179 |
+
"step": 100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.67,
|
| 183 |
+
"learning_rate": 1.5188318011445907e-06,
|
| 184 |
+
"logits/chosen": -2.7399725914001465,
|
| 185 |
+
"logits/rejected": -2.710850954055786,
|
| 186 |
+
"logps/chosen": -123.49687194824219,
|
| 187 |
+
"logps/rejected": -121.06239318847656,
|
| 188 |
+
"loss": 0.6835,
|
| 189 |
+
"rewards/accuracies": 0.637499988079071,
|
| 190 |
+
"rewards/chosen": 0.031930722296237946,
|
| 191 |
+
"rewards/margins": 0.025511348620057106,
|
| 192 |
+
"rewards/rejected": 0.00641937181353569,
|
| 193 |
+
"step": 110
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.73,
|
| 197 |
+
"learning_rate": 1.0564148305586296e-06,
|
| 198 |
+
"logits/chosen": -2.733646869659424,
|
| 199 |
+
"logits/rejected": -2.7130093574523926,
|
| 200 |
+
"logps/chosen": -116.14371490478516,
|
| 201 |
+
"logps/rejected": -121.31622314453125,
|
| 202 |
+
"loss": 0.6835,
|
| 203 |
+
"rewards/accuracies": 0.559374988079071,
|
| 204 |
+
"rewards/chosen": 0.04128889739513397,
|
| 205 |
+
"rewards/margins": 0.021482665091753006,
|
| 206 |
+
"rewards/rejected": 0.019806232303380966,
|
| 207 |
+
"step": 120
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.79,
|
| 211 |
+
"learning_rate": 6.587997083462197e-07,
|
| 212 |
+
"logits/chosen": -2.706106424331665,
|
| 213 |
+
"logits/rejected": -2.683042049407959,
|
| 214 |
+
"logps/chosen": -121.27201080322266,
|
| 215 |
+
"logps/rejected": -124.78038024902344,
|
| 216 |
+
"loss": 0.6784,
|
| 217 |
+
"rewards/accuracies": 0.621874988079071,
|
| 218 |
+
"rewards/chosen": 0.032023753970861435,
|
| 219 |
+
"rewards/margins": 0.03133785352110863,
|
| 220 |
+
"rewards/rejected": 0.0006858977722004056,
|
| 221 |
+
"step": 130
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.85,
|
| 225 |
+
"learning_rate": 3.438351873250492e-07,
|
| 226 |
+
"logits/chosen": -2.6774215698242188,
|
| 227 |
+
"logits/rejected": -2.66115140914917,
|
| 228 |
+
"logps/chosen": -111.2270736694336,
|
| 229 |
+
"logps/rejected": -116.47705078125,
|
| 230 |
+
"loss": 0.6774,
|
| 231 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 232 |
+
"rewards/chosen": 0.032939545810222626,
|
| 233 |
+
"rewards/margins": 0.04166686534881592,
|
| 234 |
+
"rewards/rejected": -0.008727315813302994,
|
| 235 |
+
"step": 140
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.91,
|
| 239 |
+
"learning_rate": 1.2565987432367032e-07,
|
| 240 |
+
"logits/chosen": -2.7032761573791504,
|
| 241 |
+
"logits/rejected": -2.6723108291625977,
|
| 242 |
+
"logps/chosen": -109.5132064819336,
|
| 243 |
+
"logps/rejected": -114.572509765625,
|
| 244 |
+
"loss": 0.6802,
|
| 245 |
+
"rewards/accuracies": 0.581250011920929,
|
| 246 |
+
"rewards/chosen": 0.037231095135211945,
|
| 247 |
+
"rewards/margins": 0.029751187190413475,
|
| 248 |
+
"rewards/rejected": 0.007479907013475895,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.97,
|
| 253 |
+
"learning_rate": 1.4067554877743861e-08,
|
| 254 |
+
"logits/chosen": -2.6688144207000732,
|
| 255 |
+
"logits/rejected": -2.6238021850585938,
|
| 256 |
+
"logps/chosen": -110.0870361328125,
|
| 257 |
+
"logps/rejected": -108.6930160522461,
|
| 258 |
+
"loss": 0.68,
|
| 259 |
+
"rewards/accuracies": 0.5843750238418579,
|
| 260 |
+
"rewards/chosen": 0.050410233438014984,
|
| 261 |
+
"rewards/margins": 0.03611644357442856,
|
| 262 |
+
"rewards/rejected": 0.014293788000941277,
|
| 263 |
+
"step": 160
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.0,
|
| 267 |
+
"step": 165,
|
| 268 |
+
"total_flos": 0.0,
|
| 269 |
+
"train_loss": 0.685761218359976,
|
| 270 |
+
"train_runtime": 6660.773,
|
| 271 |
+
"train_samples_per_second": 3.173,
|
| 272 |
+
"train_steps_per_second": 0.025
|
| 273 |
+
}
|
| 274 |
+
],
|
| 275 |
+
"logging_steps": 10,
|
| 276 |
+
"max_steps": 165,
|
| 277 |
+
"num_input_tokens_seen": 0,
|
| 278 |
+
"num_train_epochs": 1,
|
| 279 |
+
"save_steps": 100,
|
| 280 |
+
"total_flos": 0.0,
|
| 281 |
+
"train_batch_size": 2,
|
| 282 |
+
"trial_name": null,
|
| 283 |
+
"trial_params": null
|
| 284 |
+
}
|