Model save
Browse files- README.md +80 -0
- added_tokens.json +24 -0
- all_results.json +9 -0
- config.json +30 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +196 -0
- train_results.json +9 -0
- trainer_state.json +1219 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: hZzy/qwen2.5-0.5b-sft-news-IFT
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- expo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: qwen2.5-0.5b-expo-DPO-EXPERIMENT-10-5e6
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhiyuzha-university-of-florida/huggingface/runs/5jlf70he)
|
| 17 |
+
# qwen2.5-0.5b-expo-DPO-EXPERIMENT-10-5e6
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-news-IFT](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-news-IFT) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 15.2566
|
| 22 |
+
- Logps: -80.3981
|
| 23 |
+
- Logits: -1.0046
|
| 24 |
+
- Objective: 15.1445
|
| 25 |
+
- Dpo Loss: 15.1445
|
| 26 |
+
- Regularize: 15.1445
|
| 27 |
+
- Ranking Simple: 0.5134
|
| 28 |
+
- Ranking Idealized: 0.5093
|
| 29 |
+
- Ranking Idealized Expo: 0.5093
|
| 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: 4
|
| 50 |
+
- eval_batch_size: 4
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- num_devices: 6
|
| 54 |
+
- gradient_accumulation_steps: 12
|
| 55 |
+
- total_train_batch_size: 288
|
| 56 |
+
- total_eval_batch_size: 24
|
| 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: 2
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Logps | Logits | Objective | Dpo Loss | Regularize | Ranking Simple | Ranking Idealized | Ranking Idealized Expo |
|
| 65 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------:|:---------:|:--------:|:----------:|:--------------:|:-----------------:|:----------------------:|
|
| 66 |
+
| 9.5723 | 0.2834 | 50 | 9.2586 | -89.6862 | -1.4979 | 9.6501 | 9.6501 | 9.6501 | 0.5134 | 0.5093 | 0.5093 |
|
| 67 |
+
| 9.8364 | 0.5668 | 100 | 15.5453 | -79.4201 | -1.3475 | 15.5409 | 15.5409 | 15.5409 | 0.5176 | 0.5093 | 0.5093 |
|
| 68 |
+
| 8.8451 | 0.8503 | 150 | 16.6626 | -82.1459 | -1.1122 | 16.5626 | 16.5626 | 16.5626 | 0.5145 | 0.5093 | 0.5093 |
|
| 69 |
+
| 3.8083 | 1.1337 | 200 | 16.0519 | -81.6751 | -1.0874 | 16.3240 | 16.3240 | 16.3240 | 0.5186 | 0.5093 | 0.5093 |
|
| 70 |
+
| 3.6019 | 1.4171 | 250 | 15.8144 | -81.5609 | -0.9933 | 15.7679 | 15.7679 | 15.7679 | 0.5176 | 0.5093 | 0.5093 |
|
| 71 |
+
| 2.1682 | 1.7005 | 300 | 15.3824 | -80.3329 | -1.0036 | 15.2004 | 15.2004 | 15.2004 | 0.5114 | 0.5093 | 0.5093 |
|
| 72 |
+
| 2.703 | 1.9839 | 350 | 15.2566 | -80.3981 | -1.0046 | 15.1445 | 15.1445 | 15.1445 | 0.5134 | 0.5093 | 0.5093 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.42.0
|
| 78 |
+
- Pytorch 2.3.0+cu121
|
| 79 |
+
- Datasets 2.19.1
|
| 80 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.995276334435522,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 5.737799351865595,
|
| 5 |
+
"train_runtime": 14206.9508,
|
| 6 |
+
"train_samples": 50802,
|
| 7 |
+
"train_samples_per_second": 7.152,
|
| 8 |
+
"train_steps_per_second": 0.025
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hZzy/qwen2.5-0.5b-sft-news-IFT",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151644,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 24,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 14,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151645,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": 32768,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.42.0",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"use_mrope": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151665
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151644,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"pad_token_id": 151645,
|
| 6 |
+
"transformers_version": "4.42.0"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb46901fcf1645e4ee581240f2e3820878507a638bd3eebe414773faa0fc90f5
|
| 3 |
+
size 1975192208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>"
|
| 185 |
+
],
|
| 186 |
+
"bos_token": "<|im_start|>",
|
| 187 |
+
"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 %}",
|
| 188 |
+
"clean_up_tokenization_spaces": false,
|
| 189 |
+
"eos_token": "<|im_end|>",
|
| 190 |
+
"errors": "replace",
|
| 191 |
+
"model_max_length": 2048,
|
| 192 |
+
"pad_token": "<|im_end|>",
|
| 193 |
+
"split_special_tokens": false,
|
| 194 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 195 |
+
"unk_token": null
|
| 196 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.995276334435522,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 5.737799351865595,
|
| 5 |
+
"train_runtime": 14206.9508,
|
| 6 |
+
"train_samples": 50802,
|
| 7 |
+
"train_samples_per_second": 7.152,
|
| 8 |
+
"train_steps_per_second": 0.025
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.995276334435522,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 352,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"dpo_loss": 0.6931471824645996,
|
| 13 |
+
"epoch": 0.005668398677373642,
|
| 14 |
+
"grad_norm": 1341.3687944189992,
|
| 15 |
+
"learning_rate": 1.3888888888888888e-07,
|
| 16 |
+
"logits": -1.3147305250167847,
|
| 17 |
+
"logps": -88.0877456665039,
|
| 18 |
+
"loss": 0.6931,
|
| 19 |
+
"objective": 0.6931471824645996,
|
| 20 |
+
"ranking_idealized": 0.5208333134651184,
|
| 21 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 22 |
+
"ranking_simple": 0.5208333134651184,
|
| 23 |
+
"regularize": 0.6931471824645996,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"dpo_loss": 1.0099722146987915,
|
| 28 |
+
"epoch": 0.02834199338686821,
|
| 29 |
+
"grad_norm": 2182.754930022205,
|
| 30 |
+
"learning_rate": 6.944444444444446e-07,
|
| 31 |
+
"logits": -1.367998719215393,
|
| 32 |
+
"logps": -84.27975463867188,
|
| 33 |
+
"loss": 0.9543,
|
| 34 |
+
"objective": 1.0099722146987915,
|
| 35 |
+
"ranking_idealized": 0.546875,
|
| 36 |
+
"ranking_idealized_expo": 0.546875,
|
| 37 |
+
"ranking_simple": 0.546875,
|
| 38 |
+
"regularize": 1.0099722146987915,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"dpo_loss": 1.232261061668396,
|
| 43 |
+
"epoch": 0.05668398677373642,
|
| 44 |
+
"grad_norm": 1955.6998628854572,
|
| 45 |
+
"learning_rate": 1.3888888888888892e-06,
|
| 46 |
+
"logits": -1.4522252082824707,
|
| 47 |
+
"logps": -83.40966796875,
|
| 48 |
+
"loss": 1.4248,
|
| 49 |
+
"objective": 1.232261061668396,
|
| 50 |
+
"ranking_idealized": 0.512499988079071,
|
| 51 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 52 |
+
"ranking_simple": 0.512499988079071,
|
| 53 |
+
"regularize": 1.232261061668396,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"dpo_loss": 3.4686033725738525,
|
| 58 |
+
"epoch": 0.08502598016060463,
|
| 59 |
+
"grad_norm": 2014.579294209837,
|
| 60 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 61 |
+
"logits": -1.4239295721054077,
|
| 62 |
+
"logps": -83.23849487304688,
|
| 63 |
+
"loss": 2.5533,
|
| 64 |
+
"objective": 3.4686033725738525,
|
| 65 |
+
"ranking_idealized": 0.5041666626930237,
|
| 66 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 67 |
+
"ranking_simple": 0.5083333253860474,
|
| 68 |
+
"regularize": 3.4686033725738525,
|
| 69 |
+
"step": 15
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"dpo_loss": 4.306813716888428,
|
| 73 |
+
"epoch": 0.11336797354747284,
|
| 74 |
+
"grad_norm": 1483.6608319475595,
|
| 75 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 76 |
+
"logits": -1.3964630365371704,
|
| 77 |
+
"logps": -84.55473327636719,
|
| 78 |
+
"loss": 3.9251,
|
| 79 |
+
"objective": 4.306813716888428,
|
| 80 |
+
"ranking_idealized": 0.5375000238418579,
|
| 81 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 82 |
+
"ranking_simple": 0.550000011920929,
|
| 83 |
+
"regularize": 4.306813716888428,
|
| 84 |
+
"step": 20
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"dpo_loss": 4.465227127075195,
|
| 88 |
+
"epoch": 0.14170996693434104,
|
| 89 |
+
"grad_norm": 1726.5319247739817,
|
| 90 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 91 |
+
"logits": -1.406508207321167,
|
| 92 |
+
"logps": -83.8473129272461,
|
| 93 |
+
"loss": 5.3642,
|
| 94 |
+
"objective": 4.465227127075195,
|
| 95 |
+
"ranking_idealized": 0.4958333373069763,
|
| 96 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 97 |
+
"ranking_simple": 0.5083333253860474,
|
| 98 |
+
"regularize": 4.465227127075195,
|
| 99 |
+
"step": 25
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"dpo_loss": 7.850214004516602,
|
| 103 |
+
"epoch": 0.17005196032120926,
|
| 104 |
+
"grad_norm": 1356.804024894421,
|
| 105 |
+
"learning_rate": 4.166666666666667e-06,
|
| 106 |
+
"logits": -1.386705756187439,
|
| 107 |
+
"logps": -84.02658081054688,
|
| 108 |
+
"loss": 6.5533,
|
| 109 |
+
"objective": 7.850214004516602,
|
| 110 |
+
"ranking_idealized": 0.5416666865348816,
|
| 111 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 112 |
+
"ranking_simple": 0.550000011920929,
|
| 113 |
+
"regularize": 7.850214004516602,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"dpo_loss": 7.777320384979248,
|
| 118 |
+
"epoch": 0.19839395370807747,
|
| 119 |
+
"grad_norm": 1260.3392527439414,
|
| 120 |
+
"learning_rate": 4.861111111111111e-06,
|
| 121 |
+
"logits": -1.3726133108139038,
|
| 122 |
+
"logps": -81.83206176757812,
|
| 123 |
+
"loss": 6.6118,
|
| 124 |
+
"objective": 7.777320384979248,
|
| 125 |
+
"ranking_idealized": 0.5041666626930237,
|
| 126 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 127 |
+
"ranking_simple": 0.5291666388511658,
|
| 128 |
+
"regularize": 7.777320384979248,
|
| 129 |
+
"step": 35
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"dpo_loss": 6.831168174743652,
|
| 133 |
+
"epoch": 0.22673594709494568,
|
| 134 |
+
"grad_norm": 1252.0799000439422,
|
| 135 |
+
"learning_rate": 4.998023493068255e-06,
|
| 136 |
+
"logits": -1.359412431716919,
|
| 137 |
+
"logps": -81.25328826904297,
|
| 138 |
+
"loss": 7.7682,
|
| 139 |
+
"objective": 6.831168174743652,
|
| 140 |
+
"ranking_idealized": 0.5208333134651184,
|
| 141 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 142 |
+
"ranking_simple": 0.5625,
|
| 143 |
+
"regularize": 6.831168174743652,
|
| 144 |
+
"step": 40
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"dpo_loss": 8.811128616333008,
|
| 148 |
+
"epoch": 0.25507794048181387,
|
| 149 |
+
"grad_norm": 1307.005375082768,
|
| 150 |
+
"learning_rate": 4.989999289644993e-06,
|
| 151 |
+
"logits": -1.483437418937683,
|
| 152 |
+
"logps": -85.30819702148438,
|
| 153 |
+
"loss": 8.3899,
|
| 154 |
+
"objective": 8.811128616333008,
|
| 155 |
+
"ranking_idealized": 0.5375000238418579,
|
| 156 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 157 |
+
"ranking_simple": 0.5666666626930237,
|
| 158 |
+
"regularize": 8.811128616333008,
|
| 159 |
+
"step": 45
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"dpo_loss": 8.527603149414062,
|
| 163 |
+
"epoch": 0.2834199338686821,
|
| 164 |
+
"grad_norm": 1144.3338187353374,
|
| 165 |
+
"learning_rate": 4.975823666181256e-06,
|
| 166 |
+
"logits": -1.4239095449447632,
|
| 167 |
+
"logps": -83.47504425048828,
|
| 168 |
+
"loss": 9.5723,
|
| 169 |
+
"objective": 8.527603149414062,
|
| 170 |
+
"ranking_idealized": 0.42500001192092896,
|
| 171 |
+
"ranking_idealized_expo": 0.42500001192092896,
|
| 172 |
+
"ranking_simple": 0.5041666626930237,
|
| 173 |
+
"regularize": 8.527603149414062,
|
| 174 |
+
"step": 50
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.2834199338686821,
|
| 178 |
+
"eval_dpo_loss": 9.650106430053711,
|
| 179 |
+
"eval_logits": -1.4979068040847778,
|
| 180 |
+
"eval_logps": -89.68624114990234,
|
| 181 |
+
"eval_loss": 9.258649826049805,
|
| 182 |
+
"eval_objective": 9.650106430053711,
|
| 183 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 184 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 185 |
+
"eval_ranking_simple": 0.5134297609329224,
|
| 186 |
+
"eval_regularize": 9.650106430053711,
|
| 187 |
+
"eval_runtime": 260.9367,
|
| 188 |
+
"eval_samples_per_second": 22.189,
|
| 189 |
+
"eval_steps_per_second": 0.927,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"dpo_loss": 13.282089233398438,
|
| 194 |
+
"epoch": 0.3117619272555503,
|
| 195 |
+
"grad_norm": 1044.8496740930686,
|
| 196 |
+
"learning_rate": 4.955531642853404e-06,
|
| 197 |
+
"logits": -1.527586579322815,
|
| 198 |
+
"logps": -82.80742645263672,
|
| 199 |
+
"loss": 10.597,
|
| 200 |
+
"objective": 13.282089233398438,
|
| 201 |
+
"ranking_idealized": 0.5416666865348816,
|
| 202 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 203 |
+
"ranking_simple": 0.5625,
|
| 204 |
+
"regularize": 13.282089233398438,
|
| 205 |
+
"step": 55
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"dpo_loss": 10.371745109558105,
|
| 209 |
+
"epoch": 0.3401039206424185,
|
| 210 |
+
"grad_norm": 1331.4227369121395,
|
| 211 |
+
"learning_rate": 4.929173350101025e-06,
|
| 212 |
+
"logits": -1.4083276987075806,
|
| 213 |
+
"logps": -79.24844360351562,
|
| 214 |
+
"loss": 10.3404,
|
| 215 |
+
"objective": 10.371745109558105,
|
| 216 |
+
"ranking_idealized": 0.5166666507720947,
|
| 217 |
+
"ranking_idealized_expo": 0.512499988079071,
|
| 218 |
+
"ranking_simple": 0.5625,
|
| 219 |
+
"regularize": 10.371745109558105,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"dpo_loss": 10.49330997467041,
|
| 224 |
+
"epoch": 0.3684459140292867,
|
| 225 |
+
"grad_norm": 1137.902525031776,
|
| 226 |
+
"learning_rate": 4.896813904782162e-06,
|
| 227 |
+
"logits": -1.2618812322616577,
|
| 228 |
+
"logps": -80.0319595336914,
|
| 229 |
+
"loss": 11.0189,
|
| 230 |
+
"objective": 10.49330997467041,
|
| 231 |
+
"ranking_idealized": 0.5083333253860474,
|
| 232 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 233 |
+
"ranking_simple": 0.5541666746139526,
|
| 234 |
+
"regularize": 10.49330997467041,
|
| 235 |
+
"step": 65
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"dpo_loss": 9.181135177612305,
|
| 239 |
+
"epoch": 0.39678790741615494,
|
| 240 |
+
"grad_norm": 1088.944949936674,
|
| 241 |
+
"learning_rate": 4.858533249305337e-06,
|
| 242 |
+
"logits": -1.2879325151443481,
|
| 243 |
+
"logps": -80.44699096679688,
|
| 244 |
+
"loss": 11.3087,
|
| 245 |
+
"objective": 9.181135177612305,
|
| 246 |
+
"ranking_idealized": 0.5166666507720947,
|
| 247 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 248 |
+
"ranking_simple": 0.5416666865348816,
|
| 249 |
+
"regularize": 9.181135177612305,
|
| 250 |
+
"step": 70
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"dpo_loss": 10.468655586242676,
|
| 254 |
+
"epoch": 0.42512990080302315,
|
| 255 |
+
"grad_norm": 999.1732460095175,
|
| 256 |
+
"learning_rate": 4.814425954135786e-06,
|
| 257 |
+
"logits": -1.2509528398513794,
|
| 258 |
+
"logps": -79.77677154541016,
|
| 259 |
+
"loss": 11.3742,
|
| 260 |
+
"objective": 10.468655586242676,
|
| 261 |
+
"ranking_idealized": 0.5458333492279053,
|
| 262 |
+
"ranking_idealized_expo": 0.5458333492279053,
|
| 263 |
+
"ranking_simple": 0.5791666507720947,
|
| 264 |
+
"regularize": 10.468655586242676,
|
| 265 |
+
"step": 75
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"dpo_loss": 12.168583869934082,
|
| 269 |
+
"epoch": 0.45347189418989137,
|
| 270 |
+
"grad_norm": 1008.7380345506941,
|
| 271 |
+
"learning_rate": 4.764600984163809e-06,
|
| 272 |
+
"logits": -1.282080888748169,
|
| 273 |
+
"logps": -77.80094909667969,
|
| 274 |
+
"loss": 11.9338,
|
| 275 |
+
"objective": 12.168583869934082,
|
| 276 |
+
"ranking_idealized": 0.5166666507720947,
|
| 277 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 278 |
+
"ranking_simple": 0.6000000238418579,
|
| 279 |
+
"regularize": 12.168583869934082,
|
| 280 |
+
"step": 80
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"dpo_loss": 8.932952880859375,
|
| 284 |
+
"epoch": 0.4818138875767596,
|
| 285 |
+
"grad_norm": 1016.915697188663,
|
| 286 |
+
"learning_rate": 4.709181429512391e-06,
|
| 287 |
+
"logits": -1.2718119621276855,
|
| 288 |
+
"logps": -74.034912109375,
|
| 289 |
+
"loss": 11.049,
|
| 290 |
+
"objective": 8.932952880859375,
|
| 291 |
+
"ranking_idealized": 0.5249999761581421,
|
| 292 |
+
"ranking_idealized_expo": 0.5249999761581421,
|
| 293 |
+
"ranking_simple": 0.5791666507720947,
|
| 294 |
+
"regularize": 8.932952880859375,
|
| 295 |
+
"step": 85
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"dpo_loss": 13.262398719787598,
|
| 299 |
+
"epoch": 0.5101558809636277,
|
| 300 |
+
"grad_norm": 943.5896837416125,
|
| 301 |
+
"learning_rate": 4.648304201449153e-06,
|
| 302 |
+
"logits": -1.1908345222473145,
|
| 303 |
+
"logps": -76.21371459960938,
|
| 304 |
+
"loss": 11.6717,
|
| 305 |
+
"objective": 13.262398719787598,
|
| 306 |
+
"ranking_idealized": 0.4791666567325592,
|
| 307 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 308 |
+
"ranking_simple": 0.49166667461395264,
|
| 309 |
+
"regularize": 13.262398719787598,
|
| 310 |
+
"step": 90
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"dpo_loss": 8.800294876098633,
|
| 314 |
+
"epoch": 0.538497874350496,
|
| 315 |
+
"grad_norm": 1052.3099264342789,
|
| 316 |
+
"learning_rate": 4.582119694153834e-06,
|
| 317 |
+
"logits": -1.3108305931091309,
|
| 318 |
+
"logps": -74.5205078125,
|
| 319 |
+
"loss": 9.5719,
|
| 320 |
+
"objective": 8.800294876098633,
|
| 321 |
+
"ranking_idealized": 0.5416666865348816,
|
| 322 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 323 |
+
"ranking_simple": 0.612500011920929,
|
| 324 |
+
"regularize": 8.800294876098633,
|
| 325 |
+
"step": 95
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"dpo_loss": 7.865393161773682,
|
| 329 |
+
"epoch": 0.5668398677373642,
|
| 330 |
+
"grad_norm": 888.472953862153,
|
| 331 |
+
"learning_rate": 4.510791413176912e-06,
|
| 332 |
+
"logits": -1.3763591051101685,
|
| 333 |
+
"logps": -75.36319732666016,
|
| 334 |
+
"loss": 9.8364,
|
| 335 |
+
"objective": 7.865393161773682,
|
| 336 |
+
"ranking_idealized": 0.5416666865348816,
|
| 337 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 338 |
+
"ranking_simple": 0.5958333611488342,
|
| 339 |
+
"regularize": 7.865393161773682,
|
| 340 |
+
"step": 100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.5668398677373642,
|
| 344 |
+
"eval_dpo_loss": 15.540860176086426,
|
| 345 |
+
"eval_logits": -1.3475213050842285,
|
| 346 |
+
"eval_logps": -79.4201431274414,
|
| 347 |
+
"eval_loss": 15.545284271240234,
|
| 348 |
+
"eval_objective": 15.540860176086426,
|
| 349 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 350 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 351 |
+
"eval_ranking_simple": 0.5175619721412659,
|
| 352 |
+
"eval_regularize": 15.540860176086426,
|
| 353 |
+
"eval_runtime": 260.1572,
|
| 354 |
+
"eval_samples_per_second": 22.256,
|
| 355 |
+
"eval_steps_per_second": 0.93,
|
| 356 |
+
"step": 100
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"dpo_loss": 9.041933059692383,
|
| 360 |
+
"epoch": 0.5951818611242324,
|
| 361 |
+
"grad_norm": 887.351501300793,
|
| 362 |
+
"learning_rate": 4.4344955715072344e-06,
|
| 363 |
+
"logits": -1.1800312995910645,
|
| 364 |
+
"logps": -76.02098083496094,
|
| 365 |
+
"loss": 10.6979,
|
| 366 |
+
"objective": 9.041933059692383,
|
| 367 |
+
"ranking_idealized": 0.5375000238418579,
|
| 368 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 369 |
+
"ranking_simple": 0.6083333492279053,
|
| 370 |
+
"regularize": 9.041933059692383,
|
| 371 |
+
"step": 105
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"dpo_loss": 10.477563858032227,
|
| 375 |
+
"epoch": 0.6235238545111006,
|
| 376 |
+
"grad_norm": 852.2946697576,
|
| 377 |
+
"learning_rate": 4.353420654246546e-06,
|
| 378 |
+
"logits": -1.2490488290786743,
|
| 379 |
+
"logps": -74.80319213867188,
|
| 380 |
+
"loss": 9.0671,
|
| 381 |
+
"objective": 10.477563858032227,
|
| 382 |
+
"ranking_idealized": 0.44999998807907104,
|
| 383 |
+
"ranking_idealized_expo": 0.44999998807907104,
|
| 384 |
+
"ranking_simple": 0.5375000238418579,
|
| 385 |
+
"regularize": 10.477563858032227,
|
| 386 |
+
"step": 110
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"dpo_loss": 9.403600692749023,
|
| 390 |
+
"epoch": 0.6518658478979689,
|
| 391 |
+
"grad_norm": 841.5806761052793,
|
| 392 |
+
"learning_rate": 4.267766952966369e-06,
|
| 393 |
+
"logits": -1.2325801849365234,
|
| 394 |
+
"logps": -73.80712127685547,
|
| 395 |
+
"loss": 9.6957,
|
| 396 |
+
"objective": 9.403600692749023,
|
| 397 |
+
"ranking_idealized": 0.4833333194255829,
|
| 398 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 399 |
+
"ranking_simple": 0.5625,
|
| 400 |
+
"regularize": 9.403600692749023,
|
| 401 |
+
"step": 115
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"dpo_loss": 12.634725570678711,
|
| 405 |
+
"epoch": 0.680207841284837,
|
| 406 |
+
"grad_norm": 843.1072296477777,
|
| 407 |
+
"learning_rate": 4.177746070897593e-06,
|
| 408 |
+
"logits": -1.159250259399414,
|
| 409 |
+
"logps": -74.65933990478516,
|
| 410 |
+
"loss": 10.2588,
|
| 411 |
+
"objective": 12.634725570678711,
|
| 412 |
+
"ranking_idealized": 0.5333333611488342,
|
| 413 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 414 |
+
"ranking_simple": 0.5958333611488342,
|
| 415 |
+
"regularize": 12.634725570678711,
|
| 416 |
+
"step": 120
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"dpo_loss": 13.12292766571045,
|
| 420 |
+
"epoch": 0.7085498346717053,
|
| 421 |
+
"grad_norm": 839.6378874859962,
|
| 422 |
+
"learning_rate": 4.083580400175153e-06,
|
| 423 |
+
"logits": -1.1041706800460815,
|
| 424 |
+
"logps": -73.04627990722656,
|
| 425 |
+
"loss": 9.9023,
|
| 426 |
+
"objective": 13.12292766571045,
|
| 427 |
+
"ranking_idealized": 0.550000011920929,
|
| 428 |
+
"ranking_idealized_expo": 0.550000011920929,
|
| 429 |
+
"ranking_simple": 0.6041666865348816,
|
| 430 |
+
"regularize": 13.12292766571045,
|
| 431 |
+
"step": 125
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"dpo_loss": 9.77008056640625,
|
| 435 |
+
"epoch": 0.7368918280585735,
|
| 436 |
+
"grad_norm": 932.0089885121237,
|
| 437 |
+
"learning_rate": 3.985502572429277e-06,
|
| 438 |
+
"logits": -1.1575837135314941,
|
| 439 |
+
"logps": -72.78858184814453,
|
| 440 |
+
"loss": 9.9485,
|
| 441 |
+
"objective": 9.77008056640625,
|
| 442 |
+
"ranking_idealized": 0.44999998807907104,
|
| 443 |
+
"ranking_idealized_expo": 0.44999998807907104,
|
| 444 |
+
"ranking_simple": 0.5249999761581421,
|
| 445 |
+
"regularize": 9.77008056640625,
|
| 446 |
+
"step": 130
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"dpo_loss": 9.381123542785645,
|
| 450 |
+
"epoch": 0.7652338214454416,
|
| 451 |
+
"grad_norm": 845.3231606025312,
|
| 452 |
+
"learning_rate": 3.8837548840805395e-06,
|
| 453 |
+
"logits": -1.137967824935913,
|
| 454 |
+
"logps": -75.26256561279297,
|
| 455 |
+
"loss": 9.4092,
|
| 456 |
+
"objective": 9.381123542785645,
|
| 457 |
+
"ranking_idealized": 0.5291666388511658,
|
| 458 |
+
"ranking_idealized_expo": 0.5291666388511658,
|
| 459 |
+
"ranking_simple": 0.5791666507720947,
|
| 460 |
+
"regularize": 9.381123542785645,
|
| 461 |
+
"step": 135
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"dpo_loss": 8.004253387451172,
|
| 465 |
+
"epoch": 0.7935758148323099,
|
| 466 |
+
"grad_norm": 733.7736305772362,
|
| 467 |
+
"learning_rate": 3.7785886977585562e-06,
|
| 468 |
+
"logits": -1.0919610261917114,
|
| 469 |
+
"logps": -74.39104461669922,
|
| 470 |
+
"loss": 8.376,
|
| 471 |
+
"objective": 8.004253387451172,
|
| 472 |
+
"ranking_idealized": 0.5041666626930237,
|
| 473 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 474 |
+
"ranking_simple": 0.5625,
|
| 475 |
+
"regularize": 8.004253387451172,
|
| 476 |
+
"step": 140
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"dpo_loss": 6.367016315460205,
|
| 480 |
+
"epoch": 0.821917808219178,
|
| 481 |
+
"grad_norm": 796.4959704194974,
|
| 482 |
+
"learning_rate": 3.6702638213230344e-06,
|
| 483 |
+
"logits": -1.115335464477539,
|
| 484 |
+
"logps": -75.12439727783203,
|
| 485 |
+
"loss": 7.6587,
|
| 486 |
+
"objective": 6.367016315460205,
|
| 487 |
+
"ranking_idealized": 0.4833333194255829,
|
| 488 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 489 |
+
"ranking_simple": 0.5541666746139526,
|
| 490 |
+
"regularize": 6.367016315460205,
|
| 491 |
+
"step": 145
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"dpo_loss": 8.81261920928955,
|
| 495 |
+
"epoch": 0.8502598016060463,
|
| 496 |
+
"grad_norm": 773.8278413807583,
|
| 497 |
+
"learning_rate": 3.5590478660213214e-06,
|
| 498 |
+
"logits": -1.0867894887924194,
|
| 499 |
+
"logps": -74.4196548461914,
|
| 500 |
+
"loss": 8.8451,
|
| 501 |
+
"objective": 8.81261920928955,
|
| 502 |
+
"ranking_idealized": 0.5416666865348816,
|
| 503 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 504 |
+
"ranking_simple": 0.5791666507720947,
|
| 505 |
+
"regularize": 8.81261920928955,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8502598016060463,
|
| 510 |
+
"eval_dpo_loss": 16.562625885009766,
|
| 511 |
+
"eval_logits": -1.1121788024902344,
|
| 512 |
+
"eval_logps": -82.14590454101562,
|
| 513 |
+
"eval_loss": 16.66257095336914,
|
| 514 |
+
"eval_objective": 16.562625885009766,
|
| 515 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 516 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 517 |
+
"eval_ranking_simple": 0.5144628286361694,
|
| 518 |
+
"eval_regularize": 16.562625885009766,
|
| 519 |
+
"eval_runtime": 259.9617,
|
| 520 |
+
"eval_samples_per_second": 22.273,
|
| 521 |
+
"eval_steps_per_second": 0.931,
|
| 522 |
+
"step": 150
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"dpo_loss": 7.545068264007568,
|
| 526 |
+
"epoch": 0.8786017949929145,
|
| 527 |
+
"grad_norm": 757.3947735379465,
|
| 528 |
+
"learning_rate": 3.4452155853680457e-06,
|
| 529 |
+
"logits": -1.0470577478408813,
|
| 530 |
+
"logps": -75.96894836425781,
|
| 531 |
+
"loss": 7.0262,
|
| 532 |
+
"objective": 7.545068264007568,
|
| 533 |
+
"ranking_idealized": 0.512499988079071,
|
| 534 |
+
"ranking_idealized_expo": 0.512499988079071,
|
| 535 |
+
"ranking_simple": 0.6208333373069763,
|
| 536 |
+
"regularize": 7.545068264007568,
|
| 537 |
+
"step": 155
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"dpo_loss": 6.935917854309082,
|
| 541 |
+
"epoch": 0.9069437883797827,
|
| 542 |
+
"grad_norm": 751.9625745316074,
|
| 543 |
+
"learning_rate": 3.32904819638017e-06,
|
| 544 |
+
"logits": -0.919123113155365,
|
| 545 |
+
"logps": -78.4984359741211,
|
| 546 |
+
"loss": 7.8293,
|
| 547 |
+
"objective": 6.935917854309082,
|
| 548 |
+
"ranking_idealized": 0.4958333373069763,
|
| 549 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 550 |
+
"ranking_simple": 0.5916666388511658,
|
| 551 |
+
"regularize": 6.935917854309082,
|
| 552 |
+
"step": 160
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"dpo_loss": 7.154492378234863,
|
| 556 |
+
"epoch": 0.9352857817666509,
|
| 557 |
+
"grad_norm": 658.8620194691712,
|
| 558 |
+
"learning_rate": 3.2108326848442507e-06,
|
| 559 |
+
"logits": -0.9658632278442383,
|
| 560 |
+
"logps": -79.98240661621094,
|
| 561 |
+
"loss": 7.7063,
|
| 562 |
+
"objective": 7.154492378234863,
|
| 563 |
+
"ranking_idealized": 0.5208333134651184,
|
| 564 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 565 |
+
"ranking_simple": 0.5958333611488342,
|
| 566 |
+
"regularize": 7.154492378234863,
|
| 567 |
+
"step": 165
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"dpo_loss": 7.305918216705322,
|
| 571 |
+
"epoch": 0.9636277751535192,
|
| 572 |
+
"grad_norm": 788.1879535129325,
|
| 573 |
+
"learning_rate": 3.090861096332263e-06,
|
| 574 |
+
"logits": -1.0152103900909424,
|
| 575 |
+
"logps": -79.22311401367188,
|
| 576 |
+
"loss": 7.4405,
|
| 577 |
+
"objective": 7.305918216705322,
|
| 578 |
+
"ranking_idealized": 0.512499988079071,
|
| 579 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 580 |
+
"ranking_simple": 0.5708333253860474,
|
| 581 |
+
"regularize": 7.305918216705322,
|
| 582 |
+
"step": 170
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"dpo_loss": 7.161056995391846,
|
| 586 |
+
"epoch": 0.9919697685403873,
|
| 587 |
+
"grad_norm": 703.4556255689452,
|
| 588 |
+
"learning_rate": 2.9694298147174566e-06,
|
| 589 |
+
"logits": -1.0000672340393066,
|
| 590 |
+
"logps": -78.11359405517578,
|
| 591 |
+
"loss": 6.5526,
|
| 592 |
+
"objective": 7.161056995391846,
|
| 593 |
+
"ranking_idealized": 0.574999988079071,
|
| 594 |
+
"ranking_idealized_expo": 0.574999988079071,
|
| 595 |
+
"ranking_simple": 0.6791666746139526,
|
| 596 |
+
"regularize": 7.161056995391846,
|
| 597 |
+
"step": 175
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"dpo_loss": 5.952729225158691,
|
| 601 |
+
"epoch": 1.0203117619272555,
|
| 602 |
+
"grad_norm": 665.4146360676681,
|
| 603 |
+
"learning_rate": 2.8468388299726714e-06,
|
| 604 |
+
"logits": -1.1097006797790527,
|
| 605 |
+
"logps": -78.40138244628906,
|
| 606 |
+
"loss": 4.6537,
|
| 607 |
+
"objective": 5.952729225158691,
|
| 608 |
+
"ranking_idealized": 0.5416666865348816,
|
| 609 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 610 |
+
"ranking_simple": 0.637499988079071,
|
| 611 |
+
"regularize": 5.952729225158691,
|
| 612 |
+
"step": 180
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"dpo_loss": 4.262913703918457,
|
| 616 |
+
"epoch": 1.0486537553141237,
|
| 617 |
+
"grad_norm": 584.0991136785685,
|
| 618 |
+
"learning_rate": 2.723390997059943e-06,
|
| 619 |
+
"logits": -1.034575343132019,
|
| 620 |
+
"logps": -76.80313110351562,
|
| 621 |
+
"loss": 3.7788,
|
| 622 |
+
"objective": 4.262913703918457,
|
| 623 |
+
"ranking_idealized": 0.4833333194255829,
|
| 624 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 625 |
+
"ranking_simple": 0.5791666507720947,
|
| 626 |
+
"regularize": 4.262913703918457,
|
| 627 |
+
"step": 185
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"dpo_loss": 3.1785500049591064,
|
| 631 |
+
"epoch": 1.076995748700992,
|
| 632 |
+
"grad_norm": 544.0621151708413,
|
| 633 |
+
"learning_rate": 2.599391287742315e-06,
|
| 634 |
+
"logits": -1.0769795179367065,
|
| 635 |
+
"logps": -77.34581756591797,
|
| 636 |
+
"loss": 3.5653,
|
| 637 |
+
"objective": 3.1785500049591064,
|
| 638 |
+
"ranking_idealized": 0.5541666746139526,
|
| 639 |
+
"ranking_idealized_expo": 0.550000011920929,
|
| 640 |
+
"ranking_simple": 0.6458333134651184,
|
| 641 |
+
"regularize": 3.1785500049591064,
|
| 642 |
+
"step": 190
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"dpo_loss": 2.1757826805114746,
|
| 646 |
+
"epoch": 1.10533774208786,
|
| 647 |
+
"grad_norm": 485.2987165965692,
|
| 648 |
+
"learning_rate": 2.4751460371661763e-06,
|
| 649 |
+
"logits": -1.0281838178634644,
|
| 650 |
+
"logps": -76.58784484863281,
|
| 651 |
+
"loss": 3.4138,
|
| 652 |
+
"objective": 2.1757826805114746,
|
| 653 |
+
"ranking_idealized": 0.5666666626930237,
|
| 654 |
+
"ranking_idealized_expo": 0.5666666626930237,
|
| 655 |
+
"ranking_simple": 0.6666666865348816,
|
| 656 |
+
"regularize": 2.1757826805114746,
|
| 657 |
+
"step": 195
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"dpo_loss": 2.5434367656707764,
|
| 661 |
+
"epoch": 1.1336797354747283,
|
| 662 |
+
"grad_norm": 579.2034510566444,
|
| 663 |
+
"learning_rate": 2.3509621870754505e-06,
|
| 664 |
+
"logits": -1.0624656677246094,
|
| 665 |
+
"logps": -76.0323715209961,
|
| 666 |
+
"loss": 3.8083,
|
| 667 |
+
"objective": 2.5434367656707764,
|
| 668 |
+
"ranking_idealized": 0.5083333253860474,
|
| 669 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 670 |
+
"ranking_simple": 0.6208333373069763,
|
| 671 |
+
"regularize": 2.5434367656707764,
|
| 672 |
+
"step": 200
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.1336797354747283,
|
| 676 |
+
"eval_dpo_loss": 16.32398223876953,
|
| 677 |
+
"eval_logits": -1.0874205827713013,
|
| 678 |
+
"eval_logps": -81.67513275146484,
|
| 679 |
+
"eval_loss": 16.051929473876953,
|
| 680 |
+
"eval_objective": 16.32398223876953,
|
| 681 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 682 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 683 |
+
"eval_ranking_simple": 0.5185950398445129,
|
| 684 |
+
"eval_regularize": 16.32398223876953,
|
| 685 |
+
"eval_runtime": 260.3079,
|
| 686 |
+
"eval_samples_per_second": 22.243,
|
| 687 |
+
"eval_steps_per_second": 0.93,
|
| 688 |
+
"step": 200
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"dpo_loss": 4.850390434265137,
|
| 692 |
+
"epoch": 1.1620217288615966,
|
| 693 |
+
"grad_norm": 492.7125988147346,
|
| 694 |
+
"learning_rate": 2.2271465275271985e-06,
|
| 695 |
+
"logits": -1.0401540994644165,
|
| 696 |
+
"logps": -76.98418426513672,
|
| 697 |
+
"loss": 3.4645,
|
| 698 |
+
"objective": 4.850390434265137,
|
| 699 |
+
"ranking_idealized": 0.48750001192092896,
|
| 700 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 701 |
+
"ranking_simple": 0.6041666865348816,
|
| 702 |
+
"regularize": 4.850390434265137,
|
| 703 |
+
"step": 205
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"dpo_loss": 3.4442708492279053,
|
| 707 |
+
"epoch": 1.1903637222484649,
|
| 708 |
+
"grad_norm": 560.4210922655933,
|
| 709 |
+
"learning_rate": 2.1040049389819628e-06,
|
| 710 |
+
"logits": -1.0271131992340088,
|
| 711 |
+
"logps": -76.39945220947266,
|
| 712 |
+
"loss": 3.425,
|
| 713 |
+
"objective": 3.4442708492279053,
|
| 714 |
+
"ranking_idealized": 0.5,
|
| 715 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 716 |
+
"ranking_simple": 0.5874999761581421,
|
| 717 |
+
"regularize": 3.4442708492279053,
|
| 718 |
+
"step": 210
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"dpo_loss": 4.348363399505615,
|
| 722 |
+
"epoch": 1.2187057156353331,
|
| 723 |
+
"grad_norm": 570.4040655884006,
|
| 724 |
+
"learning_rate": 1.9818416366412277e-06,
|
| 725 |
+
"logits": -0.9843409657478333,
|
| 726 |
+
"logps": -75.80220031738281,
|
| 727 |
+
"loss": 3.8326,
|
| 728 |
+
"objective": 4.348363399505615,
|
| 729 |
+
"ranking_idealized": 0.4833333194255829,
|
| 730 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 731 |
+
"ranking_simple": 0.612500011920929,
|
| 732 |
+
"regularize": 4.348363399505615,
|
| 733 |
+
"step": 215
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"dpo_loss": 3.9427292346954346,
|
| 737 |
+
"epoch": 1.2470477090222012,
|
| 738 |
+
"grad_norm": 674.1094626776156,
|
| 739 |
+
"learning_rate": 1.8609584188988135e-06,
|
| 740 |
+
"logits": -0.8341898322105408,
|
| 741 |
+
"logps": -75.6758804321289,
|
| 742 |
+
"loss": 3.8234,
|
| 743 |
+
"objective": 3.9427292346954346,
|
| 744 |
+
"ranking_idealized": 0.6000000238418579,
|
| 745 |
+
"ranking_idealized_expo": 0.6000000238418579,
|
| 746 |
+
"ranking_simple": 0.675000011920929,
|
| 747 |
+
"regularize": 3.9427292346954346,
|
| 748 |
+
"step": 220
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"dpo_loss": 3.127484083175659,
|
| 752 |
+
"epoch": 1.2753897024090695,
|
| 753 |
+
"grad_norm": 586.9637333254279,
|
| 754 |
+
"learning_rate": 1.7416539217628792e-06,
|
| 755 |
+
"logits": -0.8649470806121826,
|
| 756 |
+
"logps": -77.80410766601562,
|
| 757 |
+
"loss": 3.7703,
|
| 758 |
+
"objective": 3.127484083175659,
|
| 759 |
+
"ranking_idealized": 0.5291666388511658,
|
| 760 |
+
"ranking_idealized_expo": 0.5291666388511658,
|
| 761 |
+
"ranking_simple": 0.6541666388511658,
|
| 762 |
+
"regularize": 3.127484083175659,
|
| 763 |
+
"step": 225
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"dpo_loss": 3.9277312755584717,
|
| 767 |
+
"epoch": 1.3037316957959377,
|
| 768 |
+
"grad_norm": 500.9237074632472,
|
| 769 |
+
"learning_rate": 1.6242228810904393e-06,
|
| 770 |
+
"logits": -0.806861162185669,
|
| 771 |
+
"logps": -77.2365951538086,
|
| 772 |
+
"loss": 3.2759,
|
| 773 |
+
"objective": 3.9277312755584717,
|
| 774 |
+
"ranking_idealized": 0.5083333253860474,
|
| 775 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 776 |
+
"ranking_simple": 0.5833333134651184,
|
| 777 |
+
"regularize": 3.9277312755584717,
|
| 778 |
+
"step": 230
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"dpo_loss": 2.1227903366088867,
|
| 782 |
+
"epoch": 1.3320736891828058,
|
| 783 |
+
"grad_norm": 529.1823240184154,
|
| 784 |
+
"learning_rate": 1.508955404457015e-06,
|
| 785 |
+
"logits": -0.8957360982894897,
|
| 786 |
+
"logps": -74.15618133544922,
|
| 787 |
+
"loss": 3.8217,
|
| 788 |
+
"objective": 2.1227903366088867,
|
| 789 |
+
"ranking_idealized": 0.4833333194255829,
|
| 790 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 791 |
+
"ranking_simple": 0.6416666507720947,
|
| 792 |
+
"regularize": 2.1227903366088867,
|
| 793 |
+
"step": 235
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"dpo_loss": 3.4101717472076416,
|
| 797 |
+
"epoch": 1.360415682569674,
|
| 798 |
+
"grad_norm": 527.5490363089041,
|
| 799 |
+
"learning_rate": 1.3961362544602215e-06,
|
| 800 |
+
"logits": -0.8434502482414246,
|
| 801 |
+
"logps": -76.20458221435547,
|
| 802 |
+
"loss": 3.1011,
|
| 803 |
+
"objective": 3.4101717472076416,
|
| 804 |
+
"ranking_idealized": 0.4791666567325592,
|
| 805 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 806 |
+
"ranking_simple": 0.625,
|
| 807 |
+
"regularize": 3.4101717472076416,
|
| 808 |
+
"step": 240
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"dpo_loss": 3.476386070251465,
|
| 812 |
+
"epoch": 1.3887576759565423,
|
| 813 |
+
"grad_norm": 571.2307522066004,
|
| 814 |
+
"learning_rate": 1.2860441452278578e-06,
|
| 815 |
+
"logits": -0.8681662082672119,
|
| 816 |
+
"logps": -76.64582061767578,
|
| 817 |
+
"loss": 3.8625,
|
| 818 |
+
"objective": 3.476386070251465,
|
| 819 |
+
"ranking_idealized": 0.5208333134651184,
|
| 820 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 821 |
+
"ranking_simple": 0.612500011920929,
|
| 822 |
+
"regularize": 3.476386070251465,
|
| 823 |
+
"step": 245
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"dpo_loss": 1.8152854442596436,
|
| 827 |
+
"epoch": 1.4170996693434104,
|
| 828 |
+
"grad_norm": 506.7476965423747,
|
| 829 |
+
"learning_rate": 1.1789510538684524e-06,
|
| 830 |
+
"logits": -0.8697729110717773,
|
| 831 |
+
"logps": -76.35972595214844,
|
| 832 |
+
"loss": 3.6019,
|
| 833 |
+
"objective": 1.8152854442596436,
|
| 834 |
+
"ranking_idealized": 0.47083333134651184,
|
| 835 |
+
"ranking_idealized_expo": 0.47083333134651184,
|
| 836 |
+
"ranking_simple": 0.612500011920929,
|
| 837 |
+
"regularize": 1.8152854442596436,
|
| 838 |
+
"step": 250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.4170996693434104,
|
| 842 |
+
"eval_dpo_loss": 15.767914772033691,
|
| 843 |
+
"eval_logits": -0.993295431137085,
|
| 844 |
+
"eval_logps": -81.56088256835938,
|
| 845 |
+
"eval_loss": 15.814361572265625,
|
| 846 |
+
"eval_objective": 15.767914772033691,
|
| 847 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 848 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 849 |
+
"eval_ranking_simple": 0.5175619721412659,
|
| 850 |
+
"eval_regularize": 15.767914772033691,
|
| 851 |
+
"eval_runtime": 259.6498,
|
| 852 |
+
"eval_samples_per_second": 22.299,
|
| 853 |
+
"eval_steps_per_second": 0.932,
|
| 854 |
+
"step": 250
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"dpo_loss": 3.3358986377716064,
|
| 858 |
+
"epoch": 1.4454416627302786,
|
| 859 |
+
"grad_norm": 563.3612521264971,
|
| 860 |
+
"learning_rate": 1.0751215485652644e-06,
|
| 861 |
+
"logits": -0.891727089881897,
|
| 862 |
+
"logps": -76.76223754882812,
|
| 863 |
+
"loss": 3.0719,
|
| 864 |
+
"objective": 3.3358986377716064,
|
| 865 |
+
"ranking_idealized": 0.5458333492279053,
|
| 866 |
+
"ranking_idealized_expo": 0.5458333492279053,
|
| 867 |
+
"ranking_simple": 0.637499988079071,
|
| 868 |
+
"regularize": 3.3358986377716064,
|
| 869 |
+
"step": 255
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"dpo_loss": 2.244086265563965,
|
| 873 |
+
"epoch": 1.473783656117147,
|
| 874 |
+
"grad_norm": 518.9208628864491,
|
| 875 |
+
"learning_rate": 9.74812134973689e-07,
|
| 876 |
+
"logits": -0.9449579119682312,
|
| 877 |
+
"logps": -76.72704315185547,
|
| 878 |
+
"loss": 2.8837,
|
| 879 |
+
"objective": 2.244086265563965,
|
| 880 |
+
"ranking_idealized": 0.48750001192092896,
|
| 881 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 882 |
+
"ranking_simple": 0.6041666865348816,
|
| 883 |
+
"regularize": 2.244086265563965,
|
| 884 |
+
"step": 260
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"dpo_loss": 3.1619741916656494,
|
| 888 |
+
"epoch": 1.5021256495040152,
|
| 889 |
+
"grad_norm": 583.760652002654,
|
| 890 |
+
"learning_rate": 8.78270622536716e-07,
|
| 891 |
+
"logits": -0.953507125377655,
|
| 892 |
+
"logps": -75.11036682128906,
|
| 893 |
+
"loss": 2.925,
|
| 894 |
+
"objective": 3.1619741916656494,
|
| 895 |
+
"ranking_idealized": 0.5041666626930237,
|
| 896 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 897 |
+
"ranking_simple": 0.6083333492279053,
|
| 898 |
+
"regularize": 3.1619741916656494,
|
| 899 |
+
"step": 265
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"dpo_loss": 2.98382830619812,
|
| 903 |
+
"epoch": 1.5304676428908834,
|
| 904 |
+
"grad_norm": 520.7932622156393,
|
| 905 |
+
"learning_rate": 7.857355122839674e-07,
|
| 906 |
+
"logits": -0.9570529460906982,
|
| 907 |
+
"logps": -76.34257507324219,
|
| 908 |
+
"loss": 2.3431,
|
| 909 |
+
"objective": 2.98382830619812,
|
| 910 |
+
"ranking_idealized": 0.5083333253860474,
|
| 911 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 912 |
+
"ranking_simple": 0.6041666865348816,
|
| 913 |
+
"regularize": 2.98382830619812,
|
| 914 |
+
"step": 270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"dpo_loss": 2.821234941482544,
|
| 918 |
+
"epoch": 1.5588096362777515,
|
| 919 |
+
"grad_norm": 536.6516299894466,
|
| 920 |
+
"learning_rate": 6.974354076267081e-07,
|
| 921 |
+
"logits": -0.9497679471969604,
|
| 922 |
+
"logps": -76.84500122070312,
|
| 923 |
+
"loss": 3.0543,
|
| 924 |
+
"objective": 2.821234941482544,
|
| 925 |
+
"ranking_idealized": 0.5249999761581421,
|
| 926 |
+
"ranking_idealized_expo": 0.5249999761581421,
|
| 927 |
+
"ranking_simple": 0.6625000238418579,
|
| 928 |
+
"regularize": 2.821234941482544,
|
| 929 |
+
"step": 275
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"dpo_loss": 1.6416581869125366,
|
| 933 |
+
"epoch": 1.5871516296646198,
|
| 934 |
+
"grad_norm": 473.79557869240267,
|
| 935 |
+
"learning_rate": 6.135884496044245e-07,
|
| 936 |
+
"logits": -0.8786503076553345,
|
| 937 |
+
"logps": -75.35763549804688,
|
| 938 |
+
"loss": 2.5903,
|
| 939 |
+
"objective": 1.6416581869125366,
|
| 940 |
+
"ranking_idealized": 0.5041666626930237,
|
| 941 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 942 |
+
"ranking_simple": 0.6000000238418579,
|
| 943 |
+
"regularize": 1.6416581869125366,
|
| 944 |
+
"step": 280
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"dpo_loss": 2.1852915287017822,
|
| 948 |
+
"epoch": 1.615493623051488,
|
| 949 |
+
"grad_norm": 530.1117274697609,
|
| 950 |
+
"learning_rate": 5.344017779781835e-07,
|
| 951 |
+
"logits": -0.9772613048553467,
|
| 952 |
+
"logps": -76.81114196777344,
|
| 953 |
+
"loss": 2.5659,
|
| 954 |
+
"objective": 2.1852915287017822,
|
| 955 |
+
"ranking_idealized": 0.5166666507720947,
|
| 956 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 957 |
+
"ranking_simple": 0.6166666746139526,
|
| 958 |
+
"regularize": 2.1852915287017822,
|
| 959 |
+
"step": 285
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"dpo_loss": 3.540595769882202,
|
| 963 |
+
"epoch": 1.643835616438356,
|
| 964 |
+
"grad_norm": 543.628954255078,
|
| 965 |
+
"learning_rate": 4.6007101950209827e-07,
|
| 966 |
+
"logits": -0.9982803463935852,
|
| 967 |
+
"logps": -74.47586059570312,
|
| 968 |
+
"loss": 3.1645,
|
| 969 |
+
"objective": 3.540595769882202,
|
| 970 |
+
"ranking_idealized": 0.5625,
|
| 971 |
+
"ranking_idealized_expo": 0.5625,
|
| 972 |
+
"ranking_simple": 0.625,
|
| 973 |
+
"regularize": 3.540595769882202,
|
| 974 |
+
"step": 290
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"dpo_loss": 1.856958031654358,
|
| 978 |
+
"epoch": 1.6721776098252243,
|
| 979 |
+
"grad_norm": 523.9882241509144,
|
| 980 |
+
"learning_rate": 3.907798046371139e-07,
|
| 981 |
+
"logits": -0.9143877029418945,
|
| 982 |
+
"logps": -73.36082458496094,
|
| 983 |
+
"loss": 2.4952,
|
| 984 |
+
"objective": 1.856958031654358,
|
| 985 |
+
"ranking_idealized": 0.4791666567325592,
|
| 986 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 987 |
+
"ranking_simple": 0.612500011920929,
|
| 988 |
+
"regularize": 1.856958031654358,
|
| 989 |
+
"step": 295
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"dpo_loss": 1.6541905403137207,
|
| 993 |
+
"epoch": 1.7005196032120926,
|
| 994 |
+
"grad_norm": 474.76333707639907,
|
| 995 |
+
"learning_rate": 3.266993139010438e-07,
|
| 996 |
+
"logits": -0.9617911577224731,
|
| 997 |
+
"logps": -74.96733093261719,
|
| 998 |
+
"loss": 2.1682,
|
| 999 |
+
"objective": 1.6541905403137207,
|
| 1000 |
+
"ranking_idealized": 0.574999988079071,
|
| 1001 |
+
"ranking_idealized_expo": 0.574999988079071,
|
| 1002 |
+
"ranking_simple": 0.6708333492279053,
|
| 1003 |
+
"regularize": 1.6541905403137207,
|
| 1004 |
+
"step": 300
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7005196032120926,
|
| 1008 |
+
"eval_dpo_loss": 15.200382232666016,
|
| 1009 |
+
"eval_logits": -1.0035560131072998,
|
| 1010 |
+
"eval_logps": -80.33287811279297,
|
| 1011 |
+
"eval_loss": 15.382392883300781,
|
| 1012 |
+
"eval_objective": 15.200382232666016,
|
| 1013 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 1014 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 1015 |
+
"eval_ranking_simple": 0.5113636255264282,
|
| 1016 |
+
"eval_regularize": 15.200382232666016,
|
| 1017 |
+
"eval_runtime": 264.8415,
|
| 1018 |
+
"eval_samples_per_second": 21.862,
|
| 1019 |
+
"eval_steps_per_second": 0.914,
|
| 1020 |
+
"step": 300
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"dpo_loss": 2.5656979084014893,
|
| 1024 |
+
"epoch": 1.7288615965989607,
|
| 1025 |
+
"grad_norm": 503.0202503507287,
|
| 1026 |
+
"learning_rate": 2.6798785497556184e-07,
|
| 1027 |
+
"logits": -0.933074414730072,
|
| 1028 |
+
"logps": -76.0098876953125,
|
| 1029 |
+
"loss": 2.728,
|
| 1030 |
+
"objective": 2.5656979084014893,
|
| 1031 |
+
"ranking_idealized": 0.5083333253860474,
|
| 1032 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 1033 |
+
"ranking_simple": 0.6166666746139526,
|
| 1034 |
+
"regularize": 2.5656979084014893,
|
| 1035 |
+
"step": 305
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"dpo_loss": 2.7561254501342773,
|
| 1039 |
+
"epoch": 1.7572035899858292,
|
| 1040 |
+
"grad_norm": 551.8103525795702,
|
| 1041 |
+
"learning_rate": 2.1479047161491351e-07,
|
| 1042 |
+
"logits": -0.9786698222160339,
|
| 1043 |
+
"logps": -73.98075103759766,
|
| 1044 |
+
"loss": 3.2082,
|
| 1045 |
+
"objective": 2.7561254501342773,
|
| 1046 |
+
"ranking_idealized": 0.5208333134651184,
|
| 1047 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 1048 |
+
"ranking_simple": 0.625,
|
| 1049 |
+
"regularize": 2.7561254501342773,
|
| 1050 |
+
"step": 310
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"dpo_loss": 2.8616750240325928,
|
| 1054 |
+
"epoch": 1.7855455833726972,
|
| 1055 |
+
"grad_norm": 481.44311587523885,
|
| 1056 |
+
"learning_rate": 1.6723858532249783e-07,
|
| 1057 |
+
"logits": -0.9176926016807556,
|
| 1058 |
+
"logps": -74.52711486816406,
|
| 1059 |
+
"loss": 2.6534,
|
| 1060 |
+
"objective": 2.8616750240325928,
|
| 1061 |
+
"ranking_idealized": 0.5083333253860474,
|
| 1062 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 1063 |
+
"ranking_simple": 0.6208333373069763,
|
| 1064 |
+
"regularize": 2.8616750240325928,
|
| 1065 |
+
"step": 315
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"dpo_loss": 2.875875949859619,
|
| 1069 |
+
"epoch": 1.8138875767595655,
|
| 1070 |
+
"grad_norm": 473.64902583279064,
|
| 1071 |
+
"learning_rate": 1.2544967068054332e-07,
|
| 1072 |
+
"logits": -0.968319833278656,
|
| 1073 |
+
"logps": -76.5433120727539,
|
| 1074 |
+
"loss": 2.4726,
|
| 1075 |
+
"objective": 2.875875949859619,
|
| 1076 |
+
"ranking_idealized": 0.5041666626930237,
|
| 1077 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 1078 |
+
"ranking_simple": 0.6083333492279053,
|
| 1079 |
+
"regularize": 2.875875949859619,
|
| 1080 |
+
"step": 320
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"dpo_loss": 2.392838716506958,
|
| 1084 |
+
"epoch": 1.8422295701464337,
|
| 1085 |
+
"grad_norm": 598.6261084207288,
|
| 1086 |
+
"learning_rate": 8.952696513496756e-08,
|
| 1087 |
+
"logits": -1.005333662033081,
|
| 1088 |
+
"logps": -77.68478393554688,
|
| 1089 |
+
"loss": 2.8906,
|
| 1090 |
+
"objective": 2.392838716506958,
|
| 1091 |
+
"ranking_idealized": 0.5166666507720947,
|
| 1092 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 1093 |
+
"ranking_simple": 0.6541666388511658,
|
| 1094 |
+
"regularize": 2.392838716506958,
|
| 1095 |
+
"step": 325
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"dpo_loss": 2.538822889328003,
|
| 1099 |
+
"epoch": 1.8705715635333018,
|
| 1100 |
+
"grad_norm": 468.16090350396775,
|
| 1101 |
+
"learning_rate": 5.955921395237318e-08,
|
| 1102 |
+
"logits": -0.8062960505485535,
|
| 1103 |
+
"logps": -74.2054443359375,
|
| 1104 |
+
"loss": 2.6483,
|
| 1105 |
+
"objective": 2.538822889328003,
|
| 1106 |
+
"ranking_idealized": 0.4749999940395355,
|
| 1107 |
+
"ranking_idealized_expo": 0.47083333134651184,
|
| 1108 |
+
"ranking_simple": 0.5791666507720947,
|
| 1109 |
+
"regularize": 2.538822889328003,
|
| 1110 |
+
"step": 330
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"dpo_loss": 2.293182849884033,
|
| 1114 |
+
"epoch": 1.89891355692017,
|
| 1115 |
+
"grad_norm": 457.5310635009536,
|
| 1116 |
+
"learning_rate": 3.5620450979259034e-08,
|
| 1117 |
+
"logits": -0.9471557140350342,
|
| 1118 |
+
"logps": -74.38040161132812,
|
| 1119 |
+
"loss": 2.5969,
|
| 1120 |
+
"objective": 2.293182849884033,
|
| 1121 |
+
"ranking_idealized": 0.4958333373069763,
|
| 1122 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 1123 |
+
"ranking_simple": 0.6333333253860474,
|
| 1124 |
+
"regularize": 2.293182849884033,
|
| 1125 |
+
"step": 335
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"dpo_loss": 2.192481279373169,
|
| 1129 |
+
"epoch": 1.9272555503070383,
|
| 1130 |
+
"grad_norm": 536.3353914926571,
|
| 1131 |
+
"learning_rate": 1.7769815745066476e-08,
|
| 1132 |
+
"logits": -0.9198692440986633,
|
| 1133 |
+
"logps": -76.65982055664062,
|
| 1134 |
+
"loss": 2.8401,
|
| 1135 |
+
"objective": 2.192481279373169,
|
| 1136 |
+
"ranking_idealized": 0.5416666865348816,
|
| 1137 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 1138 |
+
"ranking_simple": 0.6625000238418579,
|
| 1139 |
+
"regularize": 2.192481279373169,
|
| 1140 |
+
"step": 340
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"dpo_loss": 1.9803303480148315,
|
| 1144 |
+
"epoch": 1.9555975436939064,
|
| 1145 |
+
"grad_norm": 445.05103819649605,
|
| 1146 |
+
"learning_rate": 6.051407360895822e-09,
|
| 1147 |
+
"logits": -0.9369055032730103,
|
| 1148 |
+
"logps": -75.275634765625,
|
| 1149 |
+
"loss": 2.7774,
|
| 1150 |
+
"objective": 1.9803303480148315,
|
| 1151 |
+
"ranking_idealized": 0.5333333611488342,
|
| 1152 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 1153 |
+
"ranking_simple": 0.6333333253860474,
|
| 1154 |
+
"regularize": 1.9803303480148315,
|
| 1155 |
+
"step": 345
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"dpo_loss": 2.6546401977539062,
|
| 1159 |
+
"epoch": 1.9839395370807746,
|
| 1160 |
+
"grad_norm": 571.7789309975336,
|
| 1161 |
+
"learning_rate": 4.941755748361088e-10,
|
| 1162 |
+
"logits": -0.8779342770576477,
|
| 1163 |
+
"logps": -76.04293060302734,
|
| 1164 |
+
"loss": 2.703,
|
| 1165 |
+
"objective": 2.6546401977539062,
|
| 1166 |
+
"ranking_idealized": 0.48750001192092896,
|
| 1167 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 1168 |
+
"ranking_simple": 0.5874999761581421,
|
| 1169 |
+
"regularize": 2.6546401977539062,
|
| 1170 |
+
"step": 350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.9839395370807746,
|
| 1174 |
+
"eval_dpo_loss": 15.144511222839355,
|
| 1175 |
+
"eval_logits": -1.0045602321624756,
|
| 1176 |
+
"eval_logps": -80.39806365966797,
|
| 1177 |
+
"eval_loss": 15.256567001342773,
|
| 1178 |
+
"eval_objective": 15.144511222839355,
|
| 1179 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 1180 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 1181 |
+
"eval_ranking_simple": 0.5134297609329224,
|
| 1182 |
+
"eval_regularize": 15.144511222839355,
|
| 1183 |
+
"eval_runtime": 259.6567,
|
| 1184 |
+
"eval_samples_per_second": 22.299,
|
| 1185 |
+
"eval_steps_per_second": 0.932,
|
| 1186 |
+
"step": 350
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.995276334435522,
|
| 1190 |
+
"step": 352,
|
| 1191 |
+
"total_flos": 0.0,
|
| 1192 |
+
"train_loss": 5.737799351865595,
|
| 1193 |
+
"train_runtime": 14206.9508,
|
| 1194 |
+
"train_samples_per_second": 7.152,
|
| 1195 |
+
"train_steps_per_second": 0.025
|
| 1196 |
+
}
|
| 1197 |
+
],
|
| 1198 |
+
"logging_steps": 5,
|
| 1199 |
+
"max_steps": 352,
|
| 1200 |
+
"num_input_tokens_seen": 0,
|
| 1201 |
+
"num_train_epochs": 2,
|
| 1202 |
+
"save_steps": 500,
|
| 1203 |
+
"stateful_callbacks": {
|
| 1204 |
+
"TrainerControl": {
|
| 1205 |
+
"args": {
|
| 1206 |
+
"should_epoch_stop": false,
|
| 1207 |
+
"should_evaluate": false,
|
| 1208 |
+
"should_log": false,
|
| 1209 |
+
"should_save": false,
|
| 1210 |
+
"should_training_stop": false
|
| 1211 |
+
},
|
| 1212 |
+
"attributes": {}
|
| 1213 |
+
}
|
| 1214 |
+
},
|
| 1215 |
+
"total_flos": 0.0,
|
| 1216 |
+
"train_batch_size": 4,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffc7e51c4765b66bb028d2f753d4960c926ab5c0c987f58ea0e0c4ca1b435b8c
|
| 3 |
+
size 8120
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|