Model save
Browse files- README.md +85 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- train_results.json +7 -0
- trainer_state.json +553 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: zephyr-7b-lora-dpo-dibt-v0
|
| 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 |
+
# zephyr-7b-lora-dpo-dibt-v0
|
| 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 an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6880
|
| 22 |
+
- Rewards/chosen: 0.0206
|
| 23 |
+
- Rewards/rejected: 0.0095
|
| 24 |
+
- Rewards/accuracies: 0.5543
|
| 25 |
+
- Rewards/margins: 0.0111
|
| 26 |
+
- Logps/rejected: -302.0764
|
| 27 |
+
- Logps/chosen: -309.3295
|
| 28 |
+
- Logits/rejected: -2.7006
|
| 29 |
+
- Logits/chosen: -2.7426
|
| 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-07
|
| 49 |
+
- train_batch_size: 8
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- gradient_accumulation_steps: 2
|
| 54 |
+
- total_train_batch_size: 16
|
| 55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 56 |
+
- lr_scheduler_type: cosine
|
| 57 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 58 |
+
- num_epochs: 2
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 64 |
+
| 0.692 | 0.15 | 15 | 0.6941 | 0.0033 | 0.0045 | 0.4293 | -0.0012 | -302.1268 | -309.5031 | -2.7013 | -2.7433 |
|
| 65 |
+
| 0.6928 | 0.29 | 30 | 0.6947 | 0.0052 | 0.0076 | 0.4674 | -0.0024 | -302.0954 | -309.4838 | -2.7012 | -2.7431 |
|
| 66 |
+
| 0.6917 | 0.44 | 45 | 0.6915 | 0.0061 | 0.0022 | 0.4891 | 0.0039 | -302.1492 | -309.4744 | -2.7012 | -2.7431 |
|
| 67 |
+
| 0.6924 | 0.58 | 60 | 0.6938 | 0.0076 | 0.0083 | 0.4837 | -0.0007 | -302.0891 | -309.4600 | -2.7012 | -2.7432 |
|
| 68 |
+
| 0.6907 | 0.73 | 75 | 0.6897 | 0.0137 | 0.0061 | 0.5489 | 0.0076 | -302.1107 | -309.3987 | -2.7009 | -2.7428 |
|
| 69 |
+
| 0.6921 | 0.87 | 90 | 0.6930 | 0.0096 | 0.0086 | 0.5163 | 0.0011 | -302.0862 | -309.4397 | -2.7008 | -2.7429 |
|
| 70 |
+
| 0.6935 | 1.02 | 105 | 0.6894 | 0.0165 | 0.0080 | 0.5272 | 0.0085 | -302.0916 | -309.3708 | -2.7007 | -2.7427 |
|
| 71 |
+
| 0.6873 | 1.17 | 120 | 0.6895 | 0.0192 | 0.0110 | 0.5435 | 0.0082 | -302.0618 | -309.3437 | -2.7005 | -2.7424 |
|
| 72 |
+
| 0.6869 | 1.31 | 135 | 0.6874 | 0.0181 | 0.0059 | 0.5489 | 0.0122 | -302.1123 | -309.3547 | -2.7006 | -2.7426 |
|
| 73 |
+
| 0.6842 | 1.46 | 150 | 0.6894 | 0.0179 | 0.0094 | 0.5543 | 0.0085 | -302.0776 | -309.3570 | -2.7005 | -2.7424 |
|
| 74 |
+
| 0.6848 | 1.6 | 165 | 0.6885 | 0.0171 | 0.0069 | 0.5924 | 0.0102 | -302.1031 | -309.3650 | -2.7007 | -2.7426 |
|
| 75 |
+
| 0.6906 | 1.75 | 180 | 0.6897 | 0.0183 | 0.0107 | 0.5652 | 0.0077 | -302.0652 | -309.3525 | -2.7007 | -2.7426 |
|
| 76 |
+
| 0.6878 | 1.89 | 195 | 0.6880 | 0.0206 | 0.0095 | 0.5543 | 0.0111 | -302.0764 | -309.3295 | -2.7006 | -2.7426 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- PEFT 0.8.2
|
| 82 |
+
- Transformers 4.38.0
|
| 83 |
+
- Pytorch 2.1.1+cu121
|
| 84 |
+
- Datasets 2.16.1
|
| 85 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"down_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_rslora": false
|
| 32 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40cc3fb10b4112d1d13d36de34f753a35d649edadff1464d61a9fa981dc2b240
|
| 3 |
+
size 83945744
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.6897733697613466,
|
| 4 |
+
"train_runtime": 4283.1211,
|
| 5 |
+
"train_samples_per_second": 0.77,
|
| 6 |
+
"train_steps_per_second": 0.048
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 2048,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.6897733697613466,
|
| 4 |
+
"train_runtime": 4283.1211,
|
| 5 |
+
"train_samples_per_second": 0.77,
|
| 6 |
+
"train_steps_per_second": 0.048
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 15,
|
| 6 |
+
"global_step": 206,
|
| 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 |
+
"grad_norm": 7.41796875,
|
| 14 |
+
"learning_rate": 2.3809523809523807e-08,
|
| 15 |
+
"logits/chosen": -2.756326198577881,
|
| 16 |
+
"logits/rejected": -2.847414255142212,
|
| 17 |
+
"logps/chosen": -339.47064208984375,
|
| 18 |
+
"logps/rejected": -420.81683349609375,
|
| 19 |
+
"loss": 0.6931,
|
| 20 |
+
"rewards/accuracies": 0.0,
|
| 21 |
+
"rewards/chosen": 0.0,
|
| 22 |
+
"rewards/margins": 0.0,
|
| 23 |
+
"rewards/rejected": 0.0,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1,
|
| 28 |
+
"grad_norm": 6.6015625,
|
| 29 |
+
"learning_rate": 2.3809523809523806e-07,
|
| 30 |
+
"logits/chosen": -2.7214999198913574,
|
| 31 |
+
"logits/rejected": -2.6868648529052734,
|
| 32 |
+
"logps/chosen": -312.2082214355469,
|
| 33 |
+
"logps/rejected": -288.3475646972656,
|
| 34 |
+
"loss": 0.692,
|
| 35 |
+
"rewards/accuracies": 0.4027777910232544,
|
| 36 |
+
"rewards/chosen": 0.004871072247624397,
|
| 37 |
+
"rewards/margins": 0.002507249591872096,
|
| 38 |
+
"rewards/rejected": 0.0023638224229216576,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.15,
|
| 43 |
+
"eval_logits/chosen": -2.7432966232299805,
|
| 44 |
+
"eval_logits/rejected": -2.7012619972229004,
|
| 45 |
+
"eval_logps/chosen": -309.50311279296875,
|
| 46 |
+
"eval_logps/rejected": -302.12677001953125,
|
| 47 |
+
"eval_loss": 0.6940569281578064,
|
| 48 |
+
"eval_rewards/accuracies": 0.42934781312942505,
|
| 49 |
+
"eval_rewards/chosen": 0.0032746284268796444,
|
| 50 |
+
"eval_rewards/margins": -0.0012154963333159685,
|
| 51 |
+
"eval_rewards/rejected": 0.004490124061703682,
|
| 52 |
+
"eval_runtime": 80.1148,
|
| 53 |
+
"eval_samples_per_second": 2.297,
|
| 54 |
+
"eval_steps_per_second": 0.287,
|
| 55 |
+
"step": 15
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.19,
|
| 59 |
+
"grad_norm": 6.4453125,
|
| 60 |
+
"learning_rate": 4.761904761904761e-07,
|
| 61 |
+
"logits/chosen": -2.7492623329162598,
|
| 62 |
+
"logits/rejected": -2.7453362941741943,
|
| 63 |
+
"logps/chosen": -308.85650634765625,
|
| 64 |
+
"logps/rejected": -305.1255798339844,
|
| 65 |
+
"loss": 0.695,
|
| 66 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 67 |
+
"rewards/chosen": -0.0020826407708227634,
|
| 68 |
+
"rewards/margins": -0.0031254838686436415,
|
| 69 |
+
"rewards/rejected": 0.001042843097820878,
|
| 70 |
+
"step": 20
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.29,
|
| 74 |
+
"grad_norm": 6.54296875,
|
| 75 |
+
"learning_rate": 4.97085891010373e-07,
|
| 76 |
+
"logits/chosen": -2.6984972953796387,
|
| 77 |
+
"logits/rejected": -2.6688642501831055,
|
| 78 |
+
"logps/chosen": -333.7822265625,
|
| 79 |
+
"logps/rejected": -332.2225036621094,
|
| 80 |
+
"loss": 0.6928,
|
| 81 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 82 |
+
"rewards/chosen": 0.0055278996005654335,
|
| 83 |
+
"rewards/margins": 0.0012028769124299288,
|
| 84 |
+
"rewards/rejected": 0.004325023386627436,
|
| 85 |
+
"step": 30
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.29,
|
| 89 |
+
"eval_logits/chosen": -2.743105173110962,
|
| 90 |
+
"eval_logits/rejected": -2.7011570930480957,
|
| 91 |
+
"eval_logps/chosen": -309.48382568359375,
|
| 92 |
+
"eval_logps/rejected": -302.09539794921875,
|
| 93 |
+
"eval_loss": 0.6946766972541809,
|
| 94 |
+
"eval_rewards/accuracies": 0.46739131212234497,
|
| 95 |
+
"eval_rewards/chosen": 0.0051994770765304565,
|
| 96 |
+
"eval_rewards/margins": -0.0024300608783960342,
|
| 97 |
+
"eval_rewards/rejected": 0.007629538420587778,
|
| 98 |
+
"eval_runtime": 80.0093,
|
| 99 |
+
"eval_samples_per_second": 2.3,
|
| 100 |
+
"eval_steps_per_second": 0.287,
|
| 101 |
+
"step": 30
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.39,
|
| 105 |
+
"grad_norm": 7.19140625,
|
| 106 |
+
"learning_rate": 4.870996167038154e-07,
|
| 107 |
+
"logits/chosen": -2.738722562789917,
|
| 108 |
+
"logits/rejected": -2.699627161026001,
|
| 109 |
+
"logps/chosen": -332.95074462890625,
|
| 110 |
+
"logps/rejected": -322.2561950683594,
|
| 111 |
+
"loss": 0.6917,
|
| 112 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 113 |
+
"rewards/chosen": 0.0022713630460202694,
|
| 114 |
+
"rewards/margins": 0.003374040825292468,
|
| 115 |
+
"rewards/rejected": -0.001102677546441555,
|
| 116 |
+
"step": 40
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.44,
|
| 120 |
+
"eval_logits/chosen": -2.7431130409240723,
|
| 121 |
+
"eval_logits/rejected": -2.701150417327881,
|
| 122 |
+
"eval_logps/chosen": -309.474365234375,
|
| 123 |
+
"eval_logps/rejected": -302.14923095703125,
|
| 124 |
+
"eval_loss": 0.6914945244789124,
|
| 125 |
+
"eval_rewards/accuracies": 0.489130437374115,
|
| 126 |
+
"eval_rewards/chosen": 0.006148318760097027,
|
| 127 |
+
"eval_rewards/margins": 0.0038983491249382496,
|
| 128 |
+
"eval_rewards/rejected": 0.0022499696351587772,
|
| 129 |
+
"eval_runtime": 80.0833,
|
| 130 |
+
"eval_samples_per_second": 2.298,
|
| 131 |
+
"eval_steps_per_second": 0.287,
|
| 132 |
+
"step": 45
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.49,
|
| 136 |
+
"grad_norm": 6.23828125,
|
| 137 |
+
"learning_rate": 4.702924181108745e-07,
|
| 138 |
+
"logits/chosen": -2.7548866271972656,
|
| 139 |
+
"logits/rejected": -2.7012178897857666,
|
| 140 |
+
"logps/chosen": -347.8164367675781,
|
| 141 |
+
"logps/rejected": -330.61187744140625,
|
| 142 |
+
"loss": 0.6938,
|
| 143 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 144 |
+
"rewards/chosen": 0.004203121177852154,
|
| 145 |
+
"rewards/margins": -0.0008790730498731136,
|
| 146 |
+
"rewards/rejected": 0.005082194693386555,
|
| 147 |
+
"step": 50
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.58,
|
| 151 |
+
"grad_norm": 6.83984375,
|
| 152 |
+
"learning_rate": 4.4714780773427975e-07,
|
| 153 |
+
"logits/chosen": -2.7282495498657227,
|
| 154 |
+
"logits/rejected": -2.695693254470825,
|
| 155 |
+
"logps/chosen": -320.3782653808594,
|
| 156 |
+
"logps/rejected": -316.97576904296875,
|
| 157 |
+
"loss": 0.6924,
|
| 158 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 159 |
+
"rewards/chosen": 0.00440209498628974,
|
| 160 |
+
"rewards/margins": 0.0020671573001891375,
|
| 161 |
+
"rewards/rejected": 0.002334937918931246,
|
| 162 |
+
"step": 60
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.58,
|
| 166 |
+
"eval_logits/chosen": -2.7431647777557373,
|
| 167 |
+
"eval_logits/rejected": -2.7012221813201904,
|
| 168 |
+
"eval_logps/chosen": -309.4599914550781,
|
| 169 |
+
"eval_logps/rejected": -302.0891418457031,
|
| 170 |
+
"eval_loss": 0.6937867999076843,
|
| 171 |
+
"eval_rewards/accuracies": 0.4836956560611725,
|
| 172 |
+
"eval_rewards/chosen": 0.007588263601064682,
|
| 173 |
+
"eval_rewards/margins": -0.0006714080809615552,
|
| 174 |
+
"eval_rewards/rejected": 0.008259671740233898,
|
| 175 |
+
"eval_runtime": 80.0947,
|
| 176 |
+
"eval_samples_per_second": 2.297,
|
| 177 |
+
"eval_steps_per_second": 0.287,
|
| 178 |
+
"step": 60
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.68,
|
| 182 |
+
"grad_norm": 7.26953125,
|
| 183 |
+
"learning_rate": 4.1833161387527984e-07,
|
| 184 |
+
"logits/chosen": -2.7414700984954834,
|
| 185 |
+
"logits/rejected": -2.7190544605255127,
|
| 186 |
+
"logps/chosen": -344.57464599609375,
|
| 187 |
+
"logps/rejected": -304.53741455078125,
|
| 188 |
+
"loss": 0.6907,
|
| 189 |
+
"rewards/accuracies": 0.48124998807907104,
|
| 190 |
+
"rewards/chosen": 0.006406247615814209,
|
| 191 |
+
"rewards/margins": 0.0055833784863352776,
|
| 192 |
+
"rewards/rejected": 0.0008228697115555406,
|
| 193 |
+
"step": 70
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.73,
|
| 197 |
+
"eval_logits/chosen": -2.742759943008423,
|
| 198 |
+
"eval_logits/rejected": -2.700887680053711,
|
| 199 |
+
"eval_logps/chosen": -309.398681640625,
|
| 200 |
+
"eval_logps/rejected": -302.1106872558594,
|
| 201 |
+
"eval_loss": 0.6897082328796387,
|
| 202 |
+
"eval_rewards/accuracies": 0.5489130616188049,
|
| 203 |
+
"eval_rewards/chosen": 0.01371287927031517,
|
| 204 |
+
"eval_rewards/margins": 0.0076101175509393215,
|
| 205 |
+
"eval_rewards/rejected": 0.006102761719375849,
|
| 206 |
+
"eval_runtime": 80.0628,
|
| 207 |
+
"eval_samples_per_second": 2.298,
|
| 208 |
+
"eval_steps_per_second": 0.287,
|
| 209 |
+
"step": 75
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"grad_norm": 6.1953125,
|
| 214 |
+
"learning_rate": 3.8467282596568595e-07,
|
| 215 |
+
"logits/chosen": -2.7366466522216797,
|
| 216 |
+
"logits/rejected": -2.691721200942993,
|
| 217 |
+
"logps/chosen": -328.6690368652344,
|
| 218 |
+
"logps/rejected": -300.95269775390625,
|
| 219 |
+
"loss": 0.6903,
|
| 220 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 221 |
+
"rewards/chosen": 0.010947758331894875,
|
| 222 |
+
"rewards/margins": 0.0062617165967822075,
|
| 223 |
+
"rewards/rejected": 0.004686042666435242,
|
| 224 |
+
"step": 80
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.87,
|
| 228 |
+
"grad_norm": 6.53125,
|
| 229 |
+
"learning_rate": 3.471397460512563e-07,
|
| 230 |
+
"logits/chosen": -2.743464946746826,
|
| 231 |
+
"logits/rejected": -2.73685359954834,
|
| 232 |
+
"logps/chosen": -333.5211486816406,
|
| 233 |
+
"logps/rejected": -327.77923583984375,
|
| 234 |
+
"loss": 0.6921,
|
| 235 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 236 |
+
"rewards/chosen": 0.012939219363033772,
|
| 237 |
+
"rewards/margins": 0.002580250846222043,
|
| 238 |
+
"rewards/rejected": 0.010358968749642372,
|
| 239 |
+
"step": 90
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.87,
|
| 243 |
+
"eval_logits/chosen": -2.742880344390869,
|
| 244 |
+
"eval_logits/rejected": -2.700843095779419,
|
| 245 |
+
"eval_logps/chosen": -309.439697265625,
|
| 246 |
+
"eval_logps/rejected": -302.086181640625,
|
| 247 |
+
"eval_loss": 0.6929823160171509,
|
| 248 |
+
"eval_rewards/accuracies": 0.5163043737411499,
|
| 249 |
+
"eval_rewards/chosen": 0.009615669958293438,
|
| 250 |
+
"eval_rewards/margins": 0.0010632658377289772,
|
| 251 |
+
"eval_rewards/rejected": 0.008552403189241886,
|
| 252 |
+
"eval_runtime": 80.0648,
|
| 253 |
+
"eval_samples_per_second": 2.298,
|
| 254 |
+
"eval_steps_per_second": 0.287,
|
| 255 |
+
"step": 90
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.97,
|
| 259 |
+
"grad_norm": 6.62109375,
|
| 260 |
+
"learning_rate": 3.068121325048225e-07,
|
| 261 |
+
"logits/chosen": -2.6984450817108154,
|
| 262 |
+
"logits/rejected": -2.6824753284454346,
|
| 263 |
+
"logps/chosen": -305.10772705078125,
|
| 264 |
+
"logps/rejected": -307.2846374511719,
|
| 265 |
+
"loss": 0.6935,
|
| 266 |
+
"rewards/accuracies": 0.4937500059604645,
|
| 267 |
+
"rewards/chosen": 0.007278606295585632,
|
| 268 |
+
"rewards/margins": -0.0001863084762590006,
|
| 269 |
+
"rewards/rejected": 0.00746491551399231,
|
| 270 |
+
"step": 100
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.02,
|
| 274 |
+
"eval_logits/chosen": -2.742656946182251,
|
| 275 |
+
"eval_logits/rejected": -2.700707197189331,
|
| 276 |
+
"eval_logps/chosen": -309.3708190917969,
|
| 277 |
+
"eval_logps/rejected": -302.0916442871094,
|
| 278 |
+
"eval_loss": 0.6893685460090637,
|
| 279 |
+
"eval_rewards/accuracies": 0.5271739363670349,
|
| 280 |
+
"eval_rewards/chosen": 0.016502486541867256,
|
| 281 |
+
"eval_rewards/margins": 0.008497907780110836,
|
| 282 |
+
"eval_rewards/rejected": 0.00800458062440157,
|
| 283 |
+
"eval_runtime": 80.0666,
|
| 284 |
+
"eval_samples_per_second": 2.298,
|
| 285 |
+
"eval_steps_per_second": 0.287,
|
| 286 |
+
"step": 105
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.07,
|
| 290 |
+
"grad_norm": 7.98046875,
|
| 291 |
+
"learning_rate": 2.648501373438142e-07,
|
| 292 |
+
"logits/chosen": -2.717855215072632,
|
| 293 |
+
"logits/rejected": -2.7231907844543457,
|
| 294 |
+
"logps/chosen": -324.5370788574219,
|
| 295 |
+
"logps/rejected": -332.6354675292969,
|
| 296 |
+
"loss": 0.6863,
|
| 297 |
+
"rewards/accuracies": 0.612500011920929,
|
| 298 |
+
"rewards/chosen": 0.015826944261789322,
|
| 299 |
+
"rewards/margins": 0.01423991471529007,
|
| 300 |
+
"rewards/rejected": 0.0015870295464992523,
|
| 301 |
+
"step": 110
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.17,
|
| 305 |
+
"grad_norm": 7.64453125,
|
| 306 |
+
"learning_rate": 2.2246093076900142e-07,
|
| 307 |
+
"logits/chosen": -2.7776942253112793,
|
| 308 |
+
"logits/rejected": -2.7235989570617676,
|
| 309 |
+
"logps/chosen": -353.61517333984375,
|
| 310 |
+
"logps/rejected": -319.27044677734375,
|
| 311 |
+
"loss": 0.6873,
|
| 312 |
+
"rewards/accuracies": 0.5687500238418579,
|
| 313 |
+
"rewards/chosen": 0.017044033855199814,
|
| 314 |
+
"rewards/margins": 0.012399711646139622,
|
| 315 |
+
"rewards/rejected": 0.004644324071705341,
|
| 316 |
+
"step": 120
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.17,
|
| 320 |
+
"eval_logits/chosen": -2.7423901557922363,
|
| 321 |
+
"eval_logits/rejected": -2.700549840927124,
|
| 322 |
+
"eval_logps/chosen": -309.3437194824219,
|
| 323 |
+
"eval_logps/rejected": -302.061767578125,
|
| 324 |
+
"eval_loss": 0.6894586086273193,
|
| 325 |
+
"eval_rewards/accuracies": 0.54347825050354,
|
| 326 |
+
"eval_rewards/chosen": 0.01921399123966694,
|
| 327 |
+
"eval_rewards/margins": 0.008224469609558582,
|
| 328 |
+
"eval_rewards/rejected": 0.010989520698785782,
|
| 329 |
+
"eval_runtime": 80.1067,
|
| 330 |
+
"eval_samples_per_second": 2.297,
|
| 331 |
+
"eval_steps_per_second": 0.287,
|
| 332 |
+
"step": 120
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.26,
|
| 336 |
+
"grad_norm": 6.19921875,
|
| 337 |
+
"learning_rate": 1.8086397307570723e-07,
|
| 338 |
+
"logits/chosen": -2.7408628463745117,
|
| 339 |
+
"logits/rejected": -2.710510730743408,
|
| 340 |
+
"logps/chosen": -310.96539306640625,
|
| 341 |
+
"logps/rejected": -304.93402099609375,
|
| 342 |
+
"loss": 0.6869,
|
| 343 |
+
"rewards/accuracies": 0.59375,
|
| 344 |
+
"rewards/chosen": 0.02044372819364071,
|
| 345 |
+
"rewards/margins": 0.013077561743557453,
|
| 346 |
+
"rewards/rejected": 0.007366166915744543,
|
| 347 |
+
"step": 130
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.31,
|
| 351 |
+
"eval_logits/chosen": -2.7425851821899414,
|
| 352 |
+
"eval_logits/rejected": -2.7006468772888184,
|
| 353 |
+
"eval_logps/chosen": -309.3547058105469,
|
| 354 |
+
"eval_logps/rejected": -302.1122741699219,
|
| 355 |
+
"eval_loss": 0.6874393820762634,
|
| 356 |
+
"eval_rewards/accuracies": 0.5489130616188049,
|
| 357 |
+
"eval_rewards/chosen": 0.018117737025022507,
|
| 358 |
+
"eval_rewards/margins": 0.012173162773251534,
|
| 359 |
+
"eval_rewards/rejected": 0.005944571923464537,
|
| 360 |
+
"eval_runtime": 80.1104,
|
| 361 |
+
"eval_samples_per_second": 2.297,
|
| 362 |
+
"eval_steps_per_second": 0.287,
|
| 363 |
+
"step": 135
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.36,
|
| 367 |
+
"grad_norm": 7.15625,
|
| 368 |
+
"learning_rate": 1.4125593300137765e-07,
|
| 369 |
+
"logits/chosen": -2.745990514755249,
|
| 370 |
+
"logits/rejected": -2.7245097160339355,
|
| 371 |
+
"logps/chosen": -329.66326904296875,
|
| 372 |
+
"logps/rejected": -323.501708984375,
|
| 373 |
+
"loss": 0.6861,
|
| 374 |
+
"rewards/accuracies": 0.625,
|
| 375 |
+
"rewards/chosen": 0.018962949514389038,
|
| 376 |
+
"rewards/margins": 0.014824052341282368,
|
| 377 |
+
"rewards/rejected": 0.004138897638767958,
|
| 378 |
+
"step": 140
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.46,
|
| 382 |
+
"grad_norm": 6.859375,
|
| 383 |
+
"learning_rate": 1.0477626174477403e-07,
|
| 384 |
+
"logits/chosen": -2.733142375946045,
|
| 385 |
+
"logits/rejected": -2.704571008682251,
|
| 386 |
+
"logps/chosen": -322.4414978027344,
|
| 387 |
+
"logps/rejected": -289.4591369628906,
|
| 388 |
+
"loss": 0.6842,
|
| 389 |
+
"rewards/accuracies": 0.637499988079071,
|
| 390 |
+
"rewards/chosen": 0.018724968656897545,
|
| 391 |
+
"rewards/margins": 0.01844913512468338,
|
| 392 |
+
"rewards/rejected": 0.0002758347836788744,
|
| 393 |
+
"step": 150
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.46,
|
| 397 |
+
"eval_logits/chosen": -2.7424399852752686,
|
| 398 |
+
"eval_logits/rejected": -2.700540542602539,
|
| 399 |
+
"eval_logps/chosen": -309.3570251464844,
|
| 400 |
+
"eval_logps/rejected": -302.0776062011719,
|
| 401 |
+
"eval_loss": 0.6893653273582458,
|
| 402 |
+
"eval_rewards/accuracies": 0.554347813129425,
|
| 403 |
+
"eval_rewards/chosen": 0.01788530871272087,
|
| 404 |
+
"eval_rewards/margins": 0.008479845710098743,
|
| 405 |
+
"eval_rewards/rejected": 0.009405463002622128,
|
| 406 |
+
"eval_runtime": 80.0859,
|
| 407 |
+
"eval_samples_per_second": 2.298,
|
| 408 |
+
"eval_steps_per_second": 0.287,
|
| 409 |
+
"step": 150
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.55,
|
| 413 |
+
"grad_norm": 5.984375,
|
| 414 |
+
"learning_rate": 7.247441302957857e-08,
|
| 415 |
+
"logits/chosen": -2.7013072967529297,
|
| 416 |
+
"logits/rejected": -2.6784555912017822,
|
| 417 |
+
"logps/chosen": -313.1523742675781,
|
| 418 |
+
"logps/rejected": -322.9856872558594,
|
| 419 |
+
"loss": 0.6848,
|
| 420 |
+
"rewards/accuracies": 0.643750011920929,
|
| 421 |
+
"rewards/chosen": 0.019991694018244743,
|
| 422 |
+
"rewards/margins": 0.01737087592482567,
|
| 423 |
+
"rewards/rejected": 0.0026208176277577877,
|
| 424 |
+
"step": 160
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.6,
|
| 428 |
+
"eval_logits/chosen": -2.742584466934204,
|
| 429 |
+
"eval_logits/rejected": -2.7006893157958984,
|
| 430 |
+
"eval_logps/chosen": -309.364990234375,
|
| 431 |
+
"eval_logps/rejected": -302.1031188964844,
|
| 432 |
+
"eval_loss": 0.688545823097229,
|
| 433 |
+
"eval_rewards/accuracies": 0.592391312122345,
|
| 434 |
+
"eval_rewards/chosen": 0.01708848401904106,
|
| 435 |
+
"eval_rewards/margins": 0.01023196056485176,
|
| 436 |
+
"eval_rewards/rejected": 0.006856524385511875,
|
| 437 |
+
"eval_runtime": 80.1654,
|
| 438 |
+
"eval_samples_per_second": 2.295,
|
| 439 |
+
"eval_steps_per_second": 0.287,
|
| 440 |
+
"step": 165
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.65,
|
| 444 |
+
"grad_norm": 7.17578125,
|
| 445 |
+
"learning_rate": 4.527965223149957e-08,
|
| 446 |
+
"logits/chosen": -2.7650394439697266,
|
| 447 |
+
"logits/rejected": -2.7313895225524902,
|
| 448 |
+
"logps/chosen": -362.62762451171875,
|
| 449 |
+
"logps/rejected": -352.7076416015625,
|
| 450 |
+
"loss": 0.6872,
|
| 451 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 452 |
+
"rewards/chosen": 0.01878621242940426,
|
| 453 |
+
"rewards/margins": 0.012676900252699852,
|
| 454 |
+
"rewards/rejected": 0.006109311245381832,
|
| 455 |
+
"step": 170
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.75,
|
| 459 |
+
"grad_norm": 7.046875,
|
| 460 |
+
"learning_rate": 2.3974323105321325e-08,
|
| 461 |
+
"logits/chosen": -2.7575607299804688,
|
| 462 |
+
"logits/rejected": -2.718557834625244,
|
| 463 |
+
"logps/chosen": -344.5066223144531,
|
| 464 |
+
"logps/rejected": -322.46087646484375,
|
| 465 |
+
"loss": 0.6906,
|
| 466 |
+
"rewards/accuracies": 0.5,
|
| 467 |
+
"rewards/chosen": 0.009926950559020042,
|
| 468 |
+
"rewards/margins": 0.005830779671669006,
|
| 469 |
+
"rewards/rejected": 0.004096170887351036,
|
| 470 |
+
"step": 180
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.75,
|
| 474 |
+
"eval_logits/chosen": -2.7426013946533203,
|
| 475 |
+
"eval_logits/rejected": -2.7006635665893555,
|
| 476 |
+
"eval_logps/chosen": -309.3525085449219,
|
| 477 |
+
"eval_logps/rejected": -302.065185546875,
|
| 478 |
+
"eval_loss": 0.6897236108779907,
|
| 479 |
+
"eval_rewards/accuracies": 0.5652173757553101,
|
| 480 |
+
"eval_rewards/chosen": 0.018333308398723602,
|
| 481 |
+
"eval_rewards/margins": 0.007681697141379118,
|
| 482 |
+
"eval_rewards/rejected": 0.010651610791683197,
|
| 483 |
+
"eval_runtime": 80.2374,
|
| 484 |
+
"eval_samples_per_second": 2.293,
|
| 485 |
+
"eval_steps_per_second": 0.287,
|
| 486 |
+
"step": 180
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.84,
|
| 490 |
+
"grad_norm": 6.7578125,
|
| 491 |
+
"learning_rate": 9.171341179489034e-09,
|
| 492 |
+
"logits/chosen": -2.7172653675079346,
|
| 493 |
+
"logits/rejected": -2.6811535358428955,
|
| 494 |
+
"logps/chosen": -313.10675048828125,
|
| 495 |
+
"logps/rejected": -291.1024169921875,
|
| 496 |
+
"loss": 0.6878,
|
| 497 |
+
"rewards/accuracies": 0.581250011920929,
|
| 498 |
+
"rewards/chosen": 0.013504253700375557,
|
| 499 |
+
"rewards/margins": 0.011249206960201263,
|
| 500 |
+
"rewards/rejected": 0.002255047671496868,
|
| 501 |
+
"step": 190
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.89,
|
| 505 |
+
"eval_logits/chosen": -2.7426187992095947,
|
| 506 |
+
"eval_logits/rejected": -2.7006161212921143,
|
| 507 |
+
"eval_logps/chosen": -309.3294982910156,
|
| 508 |
+
"eval_logps/rejected": -302.0763854980469,
|
| 509 |
+
"eval_loss": 0.6879727244377136,
|
| 510 |
+
"eval_rewards/accuracies": 0.554347813129425,
|
| 511 |
+
"eval_rewards/chosen": 0.020635133609175682,
|
| 512 |
+
"eval_rewards/margins": 0.011101042851805687,
|
| 513 |
+
"eval_rewards/rejected": 0.00953409168869257,
|
| 514 |
+
"eval_runtime": 80.1219,
|
| 515 |
+
"eval_samples_per_second": 2.297,
|
| 516 |
+
"eval_steps_per_second": 0.287,
|
| 517 |
+
"step": 195
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.94,
|
| 521 |
+
"grad_norm": 7.3515625,
|
| 522 |
+
"learning_rate": 1.2965612922874458e-09,
|
| 523 |
+
"logits/chosen": -2.7186667919158936,
|
| 524 |
+
"logits/rejected": -2.7049057483673096,
|
| 525 |
+
"logps/chosen": -299.2220153808594,
|
| 526 |
+
"logps/rejected": -286.4860534667969,
|
| 527 |
+
"loss": 0.6894,
|
| 528 |
+
"rewards/accuracies": 0.53125,
|
| 529 |
+
"rewards/chosen": 0.015637261793017387,
|
| 530 |
+
"rewards/margins": 0.008065862581133842,
|
| 531 |
+
"rewards/rejected": 0.007571399211883545,
|
| 532 |
+
"step": 200
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.0,
|
| 536 |
+
"step": 206,
|
| 537 |
+
"total_flos": 0.0,
|
| 538 |
+
"train_loss": 0.6897733697613466,
|
| 539 |
+
"train_runtime": 4283.1211,
|
| 540 |
+
"train_samples_per_second": 0.77,
|
| 541 |
+
"train_steps_per_second": 0.048
|
| 542 |
+
}
|
| 543 |
+
],
|
| 544 |
+
"logging_steps": 10,
|
| 545 |
+
"max_steps": 206,
|
| 546 |
+
"num_input_tokens_seen": 0,
|
| 547 |
+
"num_train_epochs": 2,
|
| 548 |
+
"save_steps": 500,
|
| 549 |
+
"total_flos": 0.0,
|
| 550 |
+
"train_batch_size": 8,
|
| 551 |
+
"trial_name": null,
|
| 552 |
+
"trial_params": null
|
| 553 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fd11e1b32f0c413ca79ac7fef8a2641762d362dbbbf3a708039e3abbfcb7e65
|
| 3 |
+
size 5112
|