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-100-5e6
|
| 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/ptp2yd12)
|
| 17 |
+
# qwen2.5-0.5b-expo-DPO-EXPERIMENT-100-5e6
|
| 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: 153.9577
|
| 22 |
+
- Logps: -79.3234
|
| 23 |
+
- Logits: -1.1891
|
| 24 |
+
- Objective: 152.3116
|
| 25 |
+
- Dpo Loss: 152.3116
|
| 26 |
+
- Regularize: 152.3116
|
| 27 |
+
- Ranking Simple: 0.5227
|
| 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 |
+
| 89.5677 | 0.2834 | 50 | 97.0098 | -93.4757 | -1.4670 | 103.5481 | 103.5481 | 103.5481 | 0.5072 | 0.5093 | 0.5093 |
|
| 67 |
+
| 102.7372 | 0.5668 | 100 | 164.4481 | -79.3850 | -1.4159 | 169.0837 | 169.0837 | 169.0837 | 0.5238 | 0.5093 | 0.5093 |
|
| 68 |
+
| 86.6457 | 0.8503 | 150 | 159.7297 | -80.3621 | -1.2164 | 155.2103 | 155.2103 | 155.2103 | 0.5279 | 0.5093 | 0.5093 |
|
| 69 |
+
| 40.1205 | 1.1337 | 200 | 164.8019 | -78.8446 | -1.1758 | 161.0171 | 161.0171 | 161.0171 | 0.5248 | 0.5093 | 0.5093 |
|
| 70 |
+
| 40.2475 | 1.4171 | 250 | 156.8958 | -80.0693 | -1.2420 | 156.9776 | 156.9776 | 156.9776 | 0.5279 | 0.5093 | 0.5093 |
|
| 71 |
+
| 24.0056 | 1.7005 | 300 | 154.3221 | -79.4678 | -1.1971 | 153.7111 | 153.7111 | 153.7111 | 0.5238 | 0.5093 | 0.5093 |
|
| 72 |
+
| 25.1496 | 1.9839 | 350 | 153.9577 | -79.3234 | -1.1891 | 152.3116 | 152.3116 | 152.3116 | 0.5227 | 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": 58.09165079349821,
|
| 5 |
+
"train_runtime": 14332.9867,
|
| 6 |
+
"train_samples": 50802,
|
| 7 |
+
"train_samples_per_second": 7.089,
|
| 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 sha256:659488ac121e77894fb3e87b49bb7b10f8522c87566fe35ec3f3bee874de4110
|
| 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": 58.09165079349821,
|
| 5 |
+
"train_runtime": 14332.9867,
|
| 6 |
+
"train_samples": 50802,
|
| 7 |
+
"train_samples_per_second": 7.089,
|
| 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": 13413.646860161565,
|
| 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": 6.691188812255859,
|
| 28 |
+
"epoch": 0.02834199338686821,
|
| 29 |
+
"grad_norm": 25871.0368186516,
|
| 30 |
+
"learning_rate": 6.944444444444446e-07,
|
| 31 |
+
"logits": -1.3677693605422974,
|
| 32 |
+
"logps": -84.30184173583984,
|
| 33 |
+
"loss": 5.8145,
|
| 34 |
+
"objective": 6.691188812255859,
|
| 35 |
+
"ranking_idealized": 0.546875,
|
| 36 |
+
"ranking_idealized_expo": 0.546875,
|
| 37 |
+
"ranking_simple": 0.546875,
|
| 38 |
+
"regularize": 6.691188812255859,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"dpo_loss": 10.607693672180176,
|
| 43 |
+
"epoch": 0.05668398677373642,
|
| 44 |
+
"grad_norm": 23078.123366524644,
|
| 45 |
+
"learning_rate": 1.3888888888888892e-06,
|
| 46 |
+
"logits": -1.4513399600982666,
|
| 47 |
+
"logps": -83.46287536621094,
|
| 48 |
+
"loss": 12.4676,
|
| 49 |
+
"objective": 10.607693672180176,
|
| 50 |
+
"ranking_idealized": 0.5083333253860474,
|
| 51 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 52 |
+
"ranking_simple": 0.512499988079071,
|
| 53 |
+
"regularize": 10.607693672180176,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"dpo_loss": 32.00202941894531,
|
| 58 |
+
"epoch": 0.08502598016060463,
|
| 59 |
+
"grad_norm": 18694.454058265223,
|
| 60 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 61 |
+
"logits": -1.4168579578399658,
|
| 62 |
+
"logps": -83.43496704101562,
|
| 63 |
+
"loss": 22.9959,
|
| 64 |
+
"objective": 32.00202941894531,
|
| 65 |
+
"ranking_idealized": 0.5041666626930237,
|
| 66 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 67 |
+
"ranking_simple": 0.5083333253860474,
|
| 68 |
+
"regularize": 32.00202941894531,
|
| 69 |
+
"step": 15
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"dpo_loss": 45.9811897277832,
|
| 73 |
+
"epoch": 0.11336797354747284,
|
| 74 |
+
"grad_norm": 15943.429295919892,
|
| 75 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 76 |
+
"logits": -1.3946782350540161,
|
| 77 |
+
"logps": -84.17158508300781,
|
| 78 |
+
"loss": 40.0365,
|
| 79 |
+
"objective": 45.9811897277832,
|
| 80 |
+
"ranking_idealized": 0.5375000238418579,
|
| 81 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 82 |
+
"ranking_simple": 0.550000011920929,
|
| 83 |
+
"regularize": 45.9811897277832,
|
| 84 |
+
"step": 20
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"dpo_loss": 47.39955520629883,
|
| 88 |
+
"epoch": 0.14170996693434104,
|
| 89 |
+
"grad_norm": 18118.727737282403,
|
| 90 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 91 |
+
"logits": -1.4082823991775513,
|
| 92 |
+
"logps": -83.22772979736328,
|
| 93 |
+
"loss": 54.5353,
|
| 94 |
+
"objective": 47.39955520629883,
|
| 95 |
+
"ranking_idealized": 0.4958333373069763,
|
| 96 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 97 |
+
"ranking_simple": 0.512499988079071,
|
| 98 |
+
"regularize": 47.39955520629883,
|
| 99 |
+
"step": 25
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"dpo_loss": 78.01228332519531,
|
| 103 |
+
"epoch": 0.17005196032120926,
|
| 104 |
+
"grad_norm": 15166.879840931451,
|
| 105 |
+
"learning_rate": 4.166666666666667e-06,
|
| 106 |
+
"logits": -1.3809435367584229,
|
| 107 |
+
"logps": -83.88168334960938,
|
| 108 |
+
"loss": 66.4783,
|
| 109 |
+
"objective": 78.01228332519531,
|
| 110 |
+
"ranking_idealized": 0.5416666865348816,
|
| 111 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 112 |
+
"ranking_simple": 0.5375000238418579,
|
| 113 |
+
"regularize": 78.01228332519531,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"dpo_loss": 79.99754333496094,
|
| 118 |
+
"epoch": 0.19839395370807747,
|
| 119 |
+
"grad_norm": 16063.368260477022,
|
| 120 |
+
"learning_rate": 4.861111111111111e-06,
|
| 121 |
+
"logits": -1.3859208822250366,
|
| 122 |
+
"logps": -82.78713989257812,
|
| 123 |
+
"loss": 66.6027,
|
| 124 |
+
"objective": 79.99754333496094,
|
| 125 |
+
"ranking_idealized": 0.5041666626930237,
|
| 126 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 127 |
+
"ranking_simple": 0.5166666507720947,
|
| 128 |
+
"regularize": 79.99754333496094,
|
| 129 |
+
"step": 35
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"dpo_loss": 67.1819076538086,
|
| 133 |
+
"epoch": 0.22673594709494568,
|
| 134 |
+
"grad_norm": 12400.159237202879,
|
| 135 |
+
"learning_rate": 4.998023493068255e-06,
|
| 136 |
+
"logits": -1.3994922637939453,
|
| 137 |
+
"logps": -82.4559555053711,
|
| 138 |
+
"loss": 81.1307,
|
| 139 |
+
"objective": 67.1819076538086,
|
| 140 |
+
"ranking_idealized": 0.5208333134651184,
|
| 141 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 142 |
+
"ranking_simple": 0.5625,
|
| 143 |
+
"regularize": 67.1819076538086,
|
| 144 |
+
"step": 40
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"dpo_loss": 89.6316146850586,
|
| 148 |
+
"epoch": 0.25507794048181387,
|
| 149 |
+
"grad_norm": 13052.93003597411,
|
| 150 |
+
"learning_rate": 4.989999289644993e-06,
|
| 151 |
+
"logits": -1.5318328142166138,
|
| 152 |
+
"logps": -87.26154327392578,
|
| 153 |
+
"loss": 93.1317,
|
| 154 |
+
"objective": 89.6316146850586,
|
| 155 |
+
"ranking_idealized": 0.5375000238418579,
|
| 156 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 157 |
+
"ranking_simple": 0.5833333134651184,
|
| 158 |
+
"regularize": 89.6316146850586,
|
| 159 |
+
"step": 45
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"dpo_loss": 78.09004974365234,
|
| 163 |
+
"epoch": 0.2834199338686821,
|
| 164 |
+
"grad_norm": 11250.619998937018,
|
| 165 |
+
"learning_rate": 4.975823666181256e-06,
|
| 166 |
+
"logits": -1.4500072002410889,
|
| 167 |
+
"logps": -85.9083480834961,
|
| 168 |
+
"loss": 89.5677,
|
| 169 |
+
"objective": 78.09004974365234,
|
| 170 |
+
"ranking_idealized": 0.42500001192092896,
|
| 171 |
+
"ranking_idealized_expo": 0.42500001192092896,
|
| 172 |
+
"ranking_simple": 0.5041666626930237,
|
| 173 |
+
"regularize": 78.09004974365234,
|
| 174 |
+
"step": 50
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.2834199338686821,
|
| 178 |
+
"eval_dpo_loss": 103.5480728149414,
|
| 179 |
+
"eval_logits": -1.4669513702392578,
|
| 180 |
+
"eval_logps": -93.47566986083984,
|
| 181 |
+
"eval_loss": 97.00978088378906,
|
| 182 |
+
"eval_objective": 103.5480728149414,
|
| 183 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 184 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 185 |
+
"eval_ranking_simple": 0.5072314143180847,
|
| 186 |
+
"eval_regularize": 103.5480728149414,
|
| 187 |
+
"eval_runtime": 260.1107,
|
| 188 |
+
"eval_samples_per_second": 22.26,
|
| 189 |
+
"eval_steps_per_second": 0.93,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"dpo_loss": 119.75566101074219,
|
| 194 |
+
"epoch": 0.3117619272555503,
|
| 195 |
+
"grad_norm": 11967.354493984145,
|
| 196 |
+
"learning_rate": 4.955531642853404e-06,
|
| 197 |
+
"logits": -1.4773657321929932,
|
| 198 |
+
"logps": -87.53749084472656,
|
| 199 |
+
"loss": 103.6358,
|
| 200 |
+
"objective": 119.75566101074219,
|
| 201 |
+
"ranking_idealized": 0.5416666865348816,
|
| 202 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 203 |
+
"ranking_simple": 0.5625,
|
| 204 |
+
"regularize": 119.75566101074219,
|
| 205 |
+
"step": 55
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"dpo_loss": 103.13274383544922,
|
| 209 |
+
"epoch": 0.3401039206424185,
|
| 210 |
+
"grad_norm": 13660.537457669956,
|
| 211 |
+
"learning_rate": 4.929173350101025e-06,
|
| 212 |
+
"logits": -1.3649991750717163,
|
| 213 |
+
"logps": -84.92853546142578,
|
| 214 |
+
"loss": 108.801,
|
| 215 |
+
"objective": 103.13274383544922,
|
| 216 |
+
"ranking_idealized": 0.512499988079071,
|
| 217 |
+
"ranking_idealized_expo": 0.512499988079071,
|
| 218 |
+
"ranking_simple": 0.5625,
|
| 219 |
+
"regularize": 103.13274383544922,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"dpo_loss": 113.21337127685547,
|
| 224 |
+
"epoch": 0.3684459140292867,
|
| 225 |
+
"grad_norm": 11209.264550394939,
|
| 226 |
+
"learning_rate": 4.896813904782162e-06,
|
| 227 |
+
"logits": -1.261940836906433,
|
| 228 |
+
"logps": -87.40038299560547,
|
| 229 |
+
"loss": 120.3211,
|
| 230 |
+
"objective": 113.21337127685547,
|
| 231 |
+
"ranking_idealized": 0.5083333253860474,
|
| 232 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 233 |
+
"ranking_simple": 0.5583333373069763,
|
| 234 |
+
"regularize": 113.21337127685547,
|
| 235 |
+
"step": 65
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"dpo_loss": 95.49691009521484,
|
| 239 |
+
"epoch": 0.39678790741615494,
|
| 240 |
+
"grad_norm": 11680.213261821276,
|
| 241 |
+
"learning_rate": 4.858533249305337e-06,
|
| 242 |
+
"logits": -1.2914222478866577,
|
| 243 |
+
"logps": -89.73137664794922,
|
| 244 |
+
"loss": 116.7305,
|
| 245 |
+
"objective": 95.49691009521484,
|
| 246 |
+
"ranking_idealized": 0.5166666507720947,
|
| 247 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 248 |
+
"ranking_simple": 0.5291666388511658,
|
| 249 |
+
"regularize": 95.49691009521484,
|
| 250 |
+
"step": 70
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"dpo_loss": 102.52694702148438,
|
| 254 |
+
"epoch": 0.42512990080302315,
|
| 255 |
+
"grad_norm": 10698.837873548197,
|
| 256 |
+
"learning_rate": 4.814425954135786e-06,
|
| 257 |
+
"logits": -1.3049275875091553,
|
| 258 |
+
"logps": -86.52586364746094,
|
| 259 |
+
"loss": 118.3255,
|
| 260 |
+
"objective": 102.52694702148438,
|
| 261 |
+
"ranking_idealized": 0.5458333492279053,
|
| 262 |
+
"ranking_idealized_expo": 0.5458333492279053,
|
| 263 |
+
"ranking_simple": 0.5874999761581421,
|
| 264 |
+
"regularize": 102.52694702148438,
|
| 265 |
+
"step": 75
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"dpo_loss": 117.94725036621094,
|
| 269 |
+
"epoch": 0.45347189418989137,
|
| 270 |
+
"grad_norm": 11104.97125441522,
|
| 271 |
+
"learning_rate": 4.764600984163809e-06,
|
| 272 |
+
"logits": -1.389280080795288,
|
| 273 |
+
"logps": -79.9697036743164,
|
| 274 |
+
"loss": 116.8339,
|
| 275 |
+
"objective": 117.94725036621094,
|
| 276 |
+
"ranking_idealized": 0.5166666507720947,
|
| 277 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 278 |
+
"ranking_simple": 0.5791666507720947,
|
| 279 |
+
"regularize": 117.94725036621094,
|
| 280 |
+
"step": 80
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"dpo_loss": 81.52342987060547,
|
| 284 |
+
"epoch": 0.4818138875767596,
|
| 285 |
+
"grad_norm": 9437.095124097401,
|
| 286 |
+
"learning_rate": 4.709181429512391e-06,
|
| 287 |
+
"logits": -1.402341365814209,
|
| 288 |
+
"logps": -74.89615631103516,
|
| 289 |
+
"loss": 96.3803,
|
| 290 |
+
"objective": 81.52342987060547,
|
| 291 |
+
"ranking_idealized": 0.5249999761581421,
|
| 292 |
+
"ranking_idealized_expo": 0.5249999761581421,
|
| 293 |
+
"ranking_simple": 0.5833333134651184,
|
| 294 |
+
"regularize": 81.52342987060547,
|
| 295 |
+
"step": 85
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"dpo_loss": 123.97755432128906,
|
| 299 |
+
"epoch": 0.5101558809636277,
|
| 300 |
+
"grad_norm": 10670.5277421999,
|
| 301 |
+
"learning_rate": 4.648304201449153e-06,
|
| 302 |
+
"logits": -1.3095799684524536,
|
| 303 |
+
"logps": -75.67063903808594,
|
| 304 |
+
"loss": 113.352,
|
| 305 |
+
"objective": 123.97755432128906,
|
| 306 |
+
"ranking_idealized": 0.4791666567325592,
|
| 307 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 308 |
+
"ranking_simple": 0.48750001192092896,
|
| 309 |
+
"regularize": 123.97755432128906,
|
| 310 |
+
"step": 90
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"dpo_loss": 99.67278289794922,
|
| 314 |
+
"epoch": 0.538497874350496,
|
| 315 |
+
"grad_norm": 10466.418227348957,
|
| 316 |
+
"learning_rate": 4.582119694153834e-06,
|
| 317 |
+
"logits": -1.3693902492523193,
|
| 318 |
+
"logps": -73.55167388916016,
|
| 319 |
+
"loss": 100.734,
|
| 320 |
+
"objective": 99.67278289794922,
|
| 321 |
+
"ranking_idealized": 0.5416666865348816,
|
| 322 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 323 |
+
"ranking_simple": 0.612500011920929,
|
| 324 |
+
"regularize": 99.67278289794922,
|
| 325 |
+
"step": 95
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"dpo_loss": 81.45591735839844,
|
| 329 |
+
"epoch": 0.5668398677373642,
|
| 330 |
+
"grad_norm": 9021.660348254312,
|
| 331 |
+
"learning_rate": 4.510791413176912e-06,
|
| 332 |
+
"logits": -1.430596947669983,
|
| 333 |
+
"logps": -75.68968200683594,
|
| 334 |
+
"loss": 102.7372,
|
| 335 |
+
"objective": 81.45591735839844,
|
| 336 |
+
"ranking_idealized": 0.5416666865348816,
|
| 337 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 338 |
+
"ranking_simple": 0.6041666865348816,
|
| 339 |
+
"regularize": 81.45591735839844,
|
| 340 |
+
"step": 100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.5668398677373642,
|
| 344 |
+
"eval_dpo_loss": 169.08367919921875,
|
| 345 |
+
"eval_logits": -1.415890097618103,
|
| 346 |
+
"eval_logps": -79.38496398925781,
|
| 347 |
+
"eval_loss": 164.44805908203125,
|
| 348 |
+
"eval_objective": 169.08367919921875,
|
| 349 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 350 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 351 |
+
"eval_ranking_simple": 0.5237603187561035,
|
| 352 |
+
"eval_regularize": 169.08367919921875,
|
| 353 |
+
"eval_runtime": 259.898,
|
| 354 |
+
"eval_samples_per_second": 22.278,
|
| 355 |
+
"eval_steps_per_second": 0.931,
|
| 356 |
+
"step": 100
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"dpo_loss": 73.47309875488281,
|
| 360 |
+
"epoch": 0.5951818611242324,
|
| 361 |
+
"grad_norm": 8300.394502250436,
|
| 362 |
+
"learning_rate": 4.4344955715072344e-06,
|
| 363 |
+
"logits": -1.2836483716964722,
|
| 364 |
+
"logps": -74.31696319580078,
|
| 365 |
+
"loss": 98.1306,
|
| 366 |
+
"objective": 73.47309875488281,
|
| 367 |
+
"ranking_idealized": 0.5333333611488342,
|
| 368 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 369 |
+
"ranking_simple": 0.6208333373069763,
|
| 370 |
+
"regularize": 73.47309875488281,
|
| 371 |
+
"step": 105
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"dpo_loss": 113.51387023925781,
|
| 375 |
+
"epoch": 0.6235238545111006,
|
| 376 |
+
"grad_norm": 9297.62702465533,
|
| 377 |
+
"learning_rate": 4.353420654246546e-06,
|
| 378 |
+
"logits": -1.3452988862991333,
|
| 379 |
+
"logps": -70.39832305908203,
|
| 380 |
+
"loss": 101.6881,
|
| 381 |
+
"objective": 113.51387023925781,
|
| 382 |
+
"ranking_idealized": 0.44999998807907104,
|
| 383 |
+
"ranking_idealized_expo": 0.44999998807907104,
|
| 384 |
+
"ranking_simple": 0.5458333492279053,
|
| 385 |
+
"regularize": 113.51387023925781,
|
| 386 |
+
"step": 110
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"dpo_loss": 100.13522338867188,
|
| 390 |
+
"epoch": 0.6518658478979689,
|
| 391 |
+
"grad_norm": 8180.786427844167,
|
| 392 |
+
"learning_rate": 4.267766952966369e-06,
|
| 393 |
+
"logits": -1.3274390697479248,
|
| 394 |
+
"logps": -69.5139389038086,
|
| 395 |
+
"loss": 95.7434,
|
| 396 |
+
"objective": 100.13522338867188,
|
| 397 |
+
"ranking_idealized": 0.4833333194255829,
|
| 398 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 399 |
+
"ranking_simple": 0.5458333492279053,
|
| 400 |
+
"regularize": 100.13522338867188,
|
| 401 |
+
"step": 115
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"dpo_loss": 135.6210174560547,
|
| 405 |
+
"epoch": 0.680207841284837,
|
| 406 |
+
"grad_norm": 8871.326596420884,
|
| 407 |
+
"learning_rate": 4.177746070897593e-06,
|
| 408 |
+
"logits": -1.2849870920181274,
|
| 409 |
+
"logps": -69.76378631591797,
|
| 410 |
+
"loss": 95.0051,
|
| 411 |
+
"objective": 135.6210174560547,
|
| 412 |
+
"ranking_idealized": 0.5333333611488342,
|
| 413 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 414 |
+
"ranking_simple": 0.6000000238418579,
|
| 415 |
+
"regularize": 135.6210174560547,
|
| 416 |
+
"step": 120
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"dpo_loss": 112.95771789550781,
|
| 420 |
+
"epoch": 0.7085498346717053,
|
| 421 |
+
"grad_norm": 8888.276865587854,
|
| 422 |
+
"learning_rate": 4.083580400175153e-06,
|
| 423 |
+
"logits": -1.2603411674499512,
|
| 424 |
+
"logps": -68.24909210205078,
|
| 425 |
+
"loss": 104.944,
|
| 426 |
+
"objective": 112.95771789550781,
|
| 427 |
+
"ranking_idealized": 0.550000011920929,
|
| 428 |
+
"ranking_idealized_expo": 0.550000011920929,
|
| 429 |
+
"ranking_simple": 0.6166666746139526,
|
| 430 |
+
"regularize": 112.95771789550781,
|
| 431 |
+
"step": 125
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"dpo_loss": 91.826171875,
|
| 435 |
+
"epoch": 0.7368918280585735,
|
| 436 |
+
"grad_norm": 8626.309200082072,
|
| 437 |
+
"learning_rate": 3.985502572429277e-06,
|
| 438 |
+
"logits": -1.3430557250976562,
|
| 439 |
+
"logps": -67.98188018798828,
|
| 440 |
+
"loss": 94.7868,
|
| 441 |
+
"objective": 91.826171875,
|
| 442 |
+
"ranking_idealized": 0.44999998807907104,
|
| 443 |
+
"ranking_idealized_expo": 0.44999998807907104,
|
| 444 |
+
"ranking_simple": 0.5416666865348816,
|
| 445 |
+
"regularize": 91.826171875,
|
| 446 |
+
"step": 130
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"dpo_loss": 79.87511444091797,
|
| 450 |
+
"epoch": 0.7652338214454416,
|
| 451 |
+
"grad_norm": 9413.731102456015,
|
| 452 |
+
"learning_rate": 3.8837548840805395e-06,
|
| 453 |
+
"logits": -1.2686209678649902,
|
| 454 |
+
"logps": -72.34845733642578,
|
| 455 |
+
"loss": 86.2141,
|
| 456 |
+
"objective": 79.87511444091797,
|
| 457 |
+
"ranking_idealized": 0.5291666388511658,
|
| 458 |
+
"ranking_idealized_expo": 0.5291666388511658,
|
| 459 |
+
"ranking_simple": 0.5791666507720947,
|
| 460 |
+
"regularize": 79.87511444091797,
|
| 461 |
+
"step": 135
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"dpo_loss": 84.28844451904297,
|
| 465 |
+
"epoch": 0.7935758148323099,
|
| 466 |
+
"grad_norm": 7250.694243922807,
|
| 467 |
+
"learning_rate": 3.7785886977585562e-06,
|
| 468 |
+
"logits": -1.1709845066070557,
|
| 469 |
+
"logps": -72.76610565185547,
|
| 470 |
+
"loss": 82.4447,
|
| 471 |
+
"objective": 84.28844451904297,
|
| 472 |
+
"ranking_idealized": 0.5041666626930237,
|
| 473 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 474 |
+
"ranking_simple": 0.574999988079071,
|
| 475 |
+
"regularize": 84.28844451904297,
|
| 476 |
+
"step": 140
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"dpo_loss": 59.73074722290039,
|
| 480 |
+
"epoch": 0.821917808219178,
|
| 481 |
+
"grad_norm": 8021.4859376597515,
|
| 482 |
+
"learning_rate": 3.6702638213230344e-06,
|
| 483 |
+
"logits": -1.2125686407089233,
|
| 484 |
+
"logps": -73.49073791503906,
|
| 485 |
+
"loss": 76.9856,
|
| 486 |
+
"objective": 59.73074722290039,
|
| 487 |
+
"ranking_idealized": 0.4833333194255829,
|
| 488 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 489 |
+
"ranking_simple": 0.550000011920929,
|
| 490 |
+
"regularize": 59.73074722290039,
|
| 491 |
+
"step": 145
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"dpo_loss": 85.42176818847656,
|
| 495 |
+
"epoch": 0.8502598016060463,
|
| 496 |
+
"grad_norm": 7404.685943657088,
|
| 497 |
+
"learning_rate": 3.5590478660213214e-06,
|
| 498 |
+
"logits": -1.2063896656036377,
|
| 499 |
+
"logps": -72.71475982666016,
|
| 500 |
+
"loss": 86.6457,
|
| 501 |
+
"objective": 85.42176818847656,
|
| 502 |
+
"ranking_idealized": 0.5375000238418579,
|
| 503 |
+
"ranking_idealized_expo": 0.5375000238418579,
|
| 504 |
+
"ranking_simple": 0.5791666507720947,
|
| 505 |
+
"regularize": 85.42176818847656,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8502598016060463,
|
| 510 |
+
"eval_dpo_loss": 155.21026611328125,
|
| 511 |
+
"eval_logits": -1.2164032459259033,
|
| 512 |
+
"eval_logps": -80.36211395263672,
|
| 513 |
+
"eval_loss": 159.7296905517578,
|
| 514 |
+
"eval_objective": 155.21026611328125,
|
| 515 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 516 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 517 |
+
"eval_ranking_simple": 0.5278925895690918,
|
| 518 |
+
"eval_regularize": 155.21026611328125,
|
| 519 |
+
"eval_runtime": 259.4907,
|
| 520 |
+
"eval_samples_per_second": 22.313,
|
| 521 |
+
"eval_steps_per_second": 0.933,
|
| 522 |
+
"step": 150
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"dpo_loss": 90.06107330322266,
|
| 526 |
+
"epoch": 0.8786017949929145,
|
| 527 |
+
"grad_norm": 7592.300325394891,
|
| 528 |
+
"learning_rate": 3.4452155853680457e-06,
|
| 529 |
+
"logits": -1.129014253616333,
|
| 530 |
+
"logps": -74.393798828125,
|
| 531 |
+
"loss": 74.8455,
|
| 532 |
+
"objective": 90.06107330322266,
|
| 533 |
+
"ranking_idealized": 0.512499988079071,
|
| 534 |
+
"ranking_idealized_expo": 0.512499988079071,
|
| 535 |
+
"ranking_simple": 0.612500011920929,
|
| 536 |
+
"regularize": 90.06107330322266,
|
| 537 |
+
"step": 155
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"dpo_loss": 80.76229095458984,
|
| 541 |
+
"epoch": 0.9069437883797827,
|
| 542 |
+
"grad_norm": 8007.48855908563,
|
| 543 |
+
"learning_rate": 3.32904819638017e-06,
|
| 544 |
+
"logits": -0.9675666093826294,
|
| 545 |
+
"logps": -77.41276550292969,
|
| 546 |
+
"loss": 83.7281,
|
| 547 |
+
"objective": 80.76229095458984,
|
| 548 |
+
"ranking_idealized": 0.4958333373069763,
|
| 549 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 550 |
+
"ranking_simple": 0.5958333611488342,
|
| 551 |
+
"regularize": 80.76229095458984,
|
| 552 |
+
"step": 160
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"dpo_loss": 66.69430541992188,
|
| 556 |
+
"epoch": 0.9352857817666509,
|
| 557 |
+
"grad_norm": 6958.931367168085,
|
| 558 |
+
"learning_rate": 3.2108326848442507e-06,
|
| 559 |
+
"logits": -1.0013041496276855,
|
| 560 |
+
"logps": -77.83885192871094,
|
| 561 |
+
"loss": 79.6961,
|
| 562 |
+
"objective": 66.69430541992188,
|
| 563 |
+
"ranking_idealized": 0.5208333134651184,
|
| 564 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 565 |
+
"ranking_simple": 0.6000000238418579,
|
| 566 |
+
"regularize": 66.69430541992188,
|
| 567 |
+
"step": 165
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"dpo_loss": 88.68855285644531,
|
| 571 |
+
"epoch": 0.9636277751535192,
|
| 572 |
+
"grad_norm": 7579.2896683801755,
|
| 573 |
+
"learning_rate": 3.090861096332263e-06,
|
| 574 |
+
"logits": -1.0412068367004395,
|
| 575 |
+
"logps": -77.83744812011719,
|
| 576 |
+
"loss": 81.023,
|
| 577 |
+
"objective": 88.68855285644531,
|
| 578 |
+
"ranking_idealized": 0.5083333253860474,
|
| 579 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 580 |
+
"ranking_simple": 0.5791666507720947,
|
| 581 |
+
"regularize": 88.68855285644531,
|
| 582 |
+
"step": 170
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"dpo_loss": 71.89635467529297,
|
| 586 |
+
"epoch": 0.9919697685403873,
|
| 587 |
+
"grad_norm": 7064.218511171905,
|
| 588 |
+
"learning_rate": 2.9694298147174566e-06,
|
| 589 |
+
"logits": -1.030120849609375,
|
| 590 |
+
"logps": -77.39608001708984,
|
| 591 |
+
"loss": 67.6747,
|
| 592 |
+
"objective": 71.89635467529297,
|
| 593 |
+
"ranking_idealized": 0.574999988079071,
|
| 594 |
+
"ranking_idealized_expo": 0.574999988079071,
|
| 595 |
+
"ranking_simple": 0.6458333134651184,
|
| 596 |
+
"regularize": 71.89635467529297,
|
| 597 |
+
"step": 175
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"dpo_loss": 47.506874084472656,
|
| 601 |
+
"epoch": 1.0203117619272555,
|
| 602 |
+
"grad_norm": 5387.152679525541,
|
| 603 |
+
"learning_rate": 2.8468388299726714e-06,
|
| 604 |
+
"logits": -1.1444560289382935,
|
| 605 |
+
"logps": -77.81489562988281,
|
| 606 |
+
"loss": 45.6813,
|
| 607 |
+
"objective": 47.506874084472656,
|
| 608 |
+
"ranking_idealized": 0.5416666865348816,
|
| 609 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 610 |
+
"ranking_simple": 0.625,
|
| 611 |
+
"regularize": 47.506874084472656,
|
| 612 |
+
"step": 180
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"dpo_loss": 31.202707290649414,
|
| 616 |
+
"epoch": 1.0486537553141237,
|
| 617 |
+
"grad_norm": 6114.056834531026,
|
| 618 |
+
"learning_rate": 2.723390997059943e-06,
|
| 619 |
+
"logits": -1.0663727521896362,
|
| 620 |
+
"logps": -76.52796936035156,
|
| 621 |
+
"loss": 39.8195,
|
| 622 |
+
"objective": 31.202707290649414,
|
| 623 |
+
"ranking_idealized": 0.4833333194255829,
|
| 624 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 625 |
+
"ranking_simple": 0.5791666507720947,
|
| 626 |
+
"regularize": 31.202707290649414,
|
| 627 |
+
"step": 185
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"dpo_loss": 44.269371032714844,
|
| 631 |
+
"epoch": 1.076995748700992,
|
| 632 |
+
"grad_norm": 5270.211981458209,
|
| 633 |
+
"learning_rate": 2.599391287742315e-06,
|
| 634 |
+
"logits": -1.1319305896759033,
|
| 635 |
+
"logps": -76.61626434326172,
|
| 636 |
+
"loss": 40.779,
|
| 637 |
+
"objective": 44.269371032714844,
|
| 638 |
+
"ranking_idealized": 0.550000011920929,
|
| 639 |
+
"ranking_idealized_expo": 0.550000011920929,
|
| 640 |
+
"ranking_simple": 0.6583333611488342,
|
| 641 |
+
"regularize": 44.269371032714844,
|
| 642 |
+
"step": 190
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"dpo_loss": 26.442119598388672,
|
| 646 |
+
"epoch": 1.10533774208786,
|
| 647 |
+
"grad_norm": 5494.940123258311,
|
| 648 |
+
"learning_rate": 2.4751460371661763e-06,
|
| 649 |
+
"logits": -1.1119343042373657,
|
| 650 |
+
"logps": -75.08609771728516,
|
| 651 |
+
"loss": 34.1025,
|
| 652 |
+
"objective": 26.442119598388672,
|
| 653 |
+
"ranking_idealized": 0.5666666626930237,
|
| 654 |
+
"ranking_idealized_expo": 0.5666666626930237,
|
| 655 |
+
"ranking_simple": 0.6625000238418579,
|
| 656 |
+
"regularize": 26.442119598388672,
|
| 657 |
+
"step": 195
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"dpo_loss": 38.491580963134766,
|
| 661 |
+
"epoch": 1.1336797354747283,
|
| 662 |
+
"grad_norm": 5360.53985158099,
|
| 663 |
+
"learning_rate": 2.3509621870754505e-06,
|
| 664 |
+
"logits": -1.1571154594421387,
|
| 665 |
+
"logps": -74.1915283203125,
|
| 666 |
+
"loss": 40.1205,
|
| 667 |
+
"objective": 38.491580963134766,
|
| 668 |
+
"ranking_idealized": 0.5083333253860474,
|
| 669 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 670 |
+
"ranking_simple": 0.6041666865348816,
|
| 671 |
+
"regularize": 38.491580963134766,
|
| 672 |
+
"step": 200
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.1336797354747283,
|
| 676 |
+
"eval_dpo_loss": 161.01707458496094,
|
| 677 |
+
"eval_logits": -1.175844430923462,
|
| 678 |
+
"eval_logps": -78.84459686279297,
|
| 679 |
+
"eval_loss": 164.80186462402344,
|
| 680 |
+
"eval_objective": 161.01707458496094,
|
| 681 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 682 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 683 |
+
"eval_ranking_simple": 0.5247933864593506,
|
| 684 |
+
"eval_regularize": 161.01707458496094,
|
| 685 |
+
"eval_runtime": 263.5743,
|
| 686 |
+
"eval_samples_per_second": 21.967,
|
| 687 |
+
"eval_steps_per_second": 0.918,
|
| 688 |
+
"step": 200
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"dpo_loss": 40.98146057128906,
|
| 692 |
+
"epoch": 1.1620217288615966,
|
| 693 |
+
"grad_norm": 4948.541109752384,
|
| 694 |
+
"learning_rate": 2.2271465275271985e-06,
|
| 695 |
+
"logits": -1.1139543056488037,
|
| 696 |
+
"logps": -74.31828308105469,
|
| 697 |
+
"loss": 36.4184,
|
| 698 |
+
"objective": 40.98146057128906,
|
| 699 |
+
"ranking_idealized": 0.48750001192092896,
|
| 700 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 701 |
+
"ranking_simple": 0.5583333373069763,
|
| 702 |
+
"regularize": 40.98146057128906,
|
| 703 |
+
"step": 205
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"dpo_loss": 33.11323165893555,
|
| 707 |
+
"epoch": 1.1903637222484649,
|
| 708 |
+
"grad_norm": 5703.102811198386,
|
| 709 |
+
"learning_rate": 2.1040049389819628e-06,
|
| 710 |
+
"logits": -1.088984727859497,
|
| 711 |
+
"logps": -74.35527038574219,
|
| 712 |
+
"loss": 37.3029,
|
| 713 |
+
"objective": 33.11323165893555,
|
| 714 |
+
"ranking_idealized": 0.4958333373069763,
|
| 715 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 716 |
+
"ranking_simple": 0.5833333134651184,
|
| 717 |
+
"regularize": 33.11323165893555,
|
| 718 |
+
"step": 210
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"dpo_loss": 39.365211486816406,
|
| 722 |
+
"epoch": 1.2187057156353331,
|
| 723 |
+
"grad_norm": 6043.230876979848,
|
| 724 |
+
"learning_rate": 1.9818416366412277e-06,
|
| 725 |
+
"logits": -1.0735052824020386,
|
| 726 |
+
"logps": -74.10447692871094,
|
| 727 |
+
"loss": 37.505,
|
| 728 |
+
"objective": 39.365211486816406,
|
| 729 |
+
"ranking_idealized": 0.4833333194255829,
|
| 730 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 731 |
+
"ranking_simple": 0.612500011920929,
|
| 732 |
+
"regularize": 39.365211486816406,
|
| 733 |
+
"step": 215
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"dpo_loss": 31.49414825439453,
|
| 737 |
+
"epoch": 1.2470477090222012,
|
| 738 |
+
"grad_norm": 5895.953296177759,
|
| 739 |
+
"learning_rate": 1.8609584188988135e-06,
|
| 740 |
+
"logits": -0.9674416780471802,
|
| 741 |
+
"logps": -74.39078521728516,
|
| 742 |
+
"loss": 39.9075,
|
| 743 |
+
"objective": 31.49414825439453,
|
| 744 |
+
"ranking_idealized": 0.6000000238418579,
|
| 745 |
+
"ranking_idealized_expo": 0.6000000238418579,
|
| 746 |
+
"ranking_simple": 0.6833333373069763,
|
| 747 |
+
"regularize": 31.49414825439453,
|
| 748 |
+
"step": 220
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"dpo_loss": 44.06827926635742,
|
| 752 |
+
"epoch": 1.2753897024090695,
|
| 753 |
+
"grad_norm": 5452.729795480165,
|
| 754 |
+
"learning_rate": 1.7416539217628792e-06,
|
| 755 |
+
"logits": -1.0521718263626099,
|
| 756 |
+
"logps": -76.1507797241211,
|
| 757 |
+
"loss": 39.9429,
|
| 758 |
+
"objective": 44.06827926635742,
|
| 759 |
+
"ranking_idealized": 0.5291666388511658,
|
| 760 |
+
"ranking_idealized_expo": 0.5291666388511658,
|
| 761 |
+
"ranking_simple": 0.6583333611488342,
|
| 762 |
+
"regularize": 44.06827926635742,
|
| 763 |
+
"step": 225
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"dpo_loss": 37.31355285644531,
|
| 767 |
+
"epoch": 1.3037316957959377,
|
| 768 |
+
"grad_norm": 5721.574963742396,
|
| 769 |
+
"learning_rate": 1.6242228810904393e-06,
|
| 770 |
+
"logits": -1.0492419004440308,
|
| 771 |
+
"logps": -75.18516540527344,
|
| 772 |
+
"loss": 41.1066,
|
| 773 |
+
"objective": 37.31355285644531,
|
| 774 |
+
"ranking_idealized": 0.5083333253860474,
|
| 775 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 776 |
+
"ranking_simple": 0.5958333611488342,
|
| 777 |
+
"regularize": 37.31355285644531,
|
| 778 |
+
"step": 230
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"dpo_loss": 19.191679000854492,
|
| 782 |
+
"epoch": 1.3320736891828058,
|
| 783 |
+
"grad_norm": 5669.232860831048,
|
| 784 |
+
"learning_rate": 1.508955404457015e-06,
|
| 785 |
+
"logits": -1.1627520322799683,
|
| 786 |
+
"logps": -72.39102172851562,
|
| 787 |
+
"loss": 34.805,
|
| 788 |
+
"objective": 19.191679000854492,
|
| 789 |
+
"ranking_idealized": 0.4833333194255829,
|
| 790 |
+
"ranking_idealized_expo": 0.4833333194255829,
|
| 791 |
+
"ranking_simple": 0.6291666626930237,
|
| 792 |
+
"regularize": 19.191679000854492,
|
| 793 |
+
"step": 235
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"dpo_loss": 34.50796890258789,
|
| 797 |
+
"epoch": 1.360415682569674,
|
| 798 |
+
"grad_norm": 5948.081274276107,
|
| 799 |
+
"learning_rate": 1.3961362544602215e-06,
|
| 800 |
+
"logits": -1.1354502439498901,
|
| 801 |
+
"logps": -74.62174224853516,
|
| 802 |
+
"loss": 34.725,
|
| 803 |
+
"objective": 34.50796890258789,
|
| 804 |
+
"ranking_idealized": 0.4791666567325592,
|
| 805 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 806 |
+
"ranking_simple": 0.6041666865348816,
|
| 807 |
+
"regularize": 34.50796890258789,
|
| 808 |
+
"step": 240
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"dpo_loss": 40.89650344848633,
|
| 812 |
+
"epoch": 1.3887576759565423,
|
| 813 |
+
"grad_norm": 5428.624790806261,
|
| 814 |
+
"learning_rate": 1.2860441452278578e-06,
|
| 815 |
+
"logits": -1.1472022533416748,
|
| 816 |
+
"logps": -74.75707244873047,
|
| 817 |
+
"loss": 32.9306,
|
| 818 |
+
"objective": 40.89650344848633,
|
| 819 |
+
"ranking_idealized": 0.5166666507720947,
|
| 820 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 821 |
+
"ranking_simple": 0.6083333492279053,
|
| 822 |
+
"regularize": 40.89650344848633,
|
| 823 |
+
"step": 245
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"dpo_loss": 27.386281967163086,
|
| 827 |
+
"epoch": 1.4170996693434104,
|
| 828 |
+
"grad_norm": 5252.261360047395,
|
| 829 |
+
"learning_rate": 1.1789510538684524e-06,
|
| 830 |
+
"logits": -1.1399437189102173,
|
| 831 |
+
"logps": -74.77461242675781,
|
| 832 |
+
"loss": 40.2475,
|
| 833 |
+
"objective": 27.386281967163086,
|
| 834 |
+
"ranking_idealized": 0.47083333134651184,
|
| 835 |
+
"ranking_idealized_expo": 0.47083333134651184,
|
| 836 |
+
"ranking_simple": 0.6000000238418579,
|
| 837 |
+
"regularize": 27.386281967163086,
|
| 838 |
+
"step": 250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.4170996693434104,
|
| 842 |
+
"eval_dpo_loss": 156.97756958007812,
|
| 843 |
+
"eval_logits": -1.2420457601547241,
|
| 844 |
+
"eval_logps": -80.06932830810547,
|
| 845 |
+
"eval_loss": 156.89581298828125,
|
| 846 |
+
"eval_objective": 156.97756958007812,
|
| 847 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 848 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 849 |
+
"eval_ranking_simple": 0.5278925895690918,
|
| 850 |
+
"eval_regularize": 156.97756958007812,
|
| 851 |
+
"eval_runtime": 259.9252,
|
| 852 |
+
"eval_samples_per_second": 22.276,
|
| 853 |
+
"eval_steps_per_second": 0.931,
|
| 854 |
+
"step": 250
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"dpo_loss": 32.30294418334961,
|
| 858 |
+
"epoch": 1.4454416627302786,
|
| 859 |
+
"grad_norm": 5037.556682913565,
|
| 860 |
+
"learning_rate": 1.0751215485652644e-06,
|
| 861 |
+
"logits": -1.146283745765686,
|
| 862 |
+
"logps": -75.65272521972656,
|
| 863 |
+
"loss": 32.8874,
|
| 864 |
+
"objective": 32.30294418334961,
|
| 865 |
+
"ranking_idealized": 0.5458333492279053,
|
| 866 |
+
"ranking_idealized_expo": 0.5458333492279053,
|
| 867 |
+
"ranking_simple": 0.6458333134651184,
|
| 868 |
+
"regularize": 32.30294418334961,
|
| 869 |
+
"step": 255
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"dpo_loss": 31.96709632873535,
|
| 873 |
+
"epoch": 1.473783656117147,
|
| 874 |
+
"grad_norm": 5067.355799390521,
|
| 875 |
+
"learning_rate": 9.74812134973689e-07,
|
| 876 |
+
"logits": -1.1747548580169678,
|
| 877 |
+
"logps": -76.0610580444336,
|
| 878 |
+
"loss": 26.7271,
|
| 879 |
+
"objective": 31.96709632873535,
|
| 880 |
+
"ranking_idealized": 0.48750001192092896,
|
| 881 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 882 |
+
"ranking_simple": 0.6041666865348816,
|
| 883 |
+
"regularize": 31.96709632873535,
|
| 884 |
+
"step": 260
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"dpo_loss": 37.10657501220703,
|
| 888 |
+
"epoch": 1.5021256495040152,
|
| 889 |
+
"grad_norm": 6284.794884577889,
|
| 890 |
+
"learning_rate": 8.78270622536716e-07,
|
| 891 |
+
"logits": -1.1707472801208496,
|
| 892 |
+
"logps": -74.64857482910156,
|
| 893 |
+
"loss": 32.6747,
|
| 894 |
+
"objective": 37.10657501220703,
|
| 895 |
+
"ranking_idealized": 0.5041666626930237,
|
| 896 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 897 |
+
"ranking_simple": 0.6208333373069763,
|
| 898 |
+
"regularize": 37.10657501220703,
|
| 899 |
+
"step": 265
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"dpo_loss": 23.847713470458984,
|
| 903 |
+
"epoch": 1.5304676428908834,
|
| 904 |
+
"grad_norm": 5807.154647298787,
|
| 905 |
+
"learning_rate": 7.857355122839674e-07,
|
| 906 |
+
"logits": -1.1641870737075806,
|
| 907 |
+
"logps": -75.7414321899414,
|
| 908 |
+
"loss": 26.4138,
|
| 909 |
+
"objective": 23.847713470458984,
|
| 910 |
+
"ranking_idealized": 0.5041666626930237,
|
| 911 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 912 |
+
"ranking_simple": 0.612500011920929,
|
| 913 |
+
"regularize": 23.847713470458984,
|
| 914 |
+
"step": 270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"dpo_loss": 44.59386444091797,
|
| 918 |
+
"epoch": 1.5588096362777515,
|
| 919 |
+
"grad_norm": 5794.329572664694,
|
| 920 |
+
"learning_rate": 6.974354076267081e-07,
|
| 921 |
+
"logits": -1.1526013612747192,
|
| 922 |
+
"logps": -75.73735046386719,
|
| 923 |
+
"loss": 29.7657,
|
| 924 |
+
"objective": 44.59386444091797,
|
| 925 |
+
"ranking_idealized": 0.5249999761581421,
|
| 926 |
+
"ranking_idealized_expo": 0.5249999761581421,
|
| 927 |
+
"ranking_simple": 0.6416666507720947,
|
| 928 |
+
"regularize": 44.59386444091797,
|
| 929 |
+
"step": 275
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"dpo_loss": 17.95917320251465,
|
| 933 |
+
"epoch": 1.5871516296646198,
|
| 934 |
+
"grad_norm": 5034.884137017343,
|
| 935 |
+
"learning_rate": 6.135884496044245e-07,
|
| 936 |
+
"logits": -1.077419400215149,
|
| 937 |
+
"logps": -74.3064956665039,
|
| 938 |
+
"loss": 30.0354,
|
| 939 |
+
"objective": 17.95917320251465,
|
| 940 |
+
"ranking_idealized": 0.5041666626930237,
|
| 941 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 942 |
+
"ranking_simple": 0.6041666865348816,
|
| 943 |
+
"regularize": 17.95917320251465,
|
| 944 |
+
"step": 280
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"dpo_loss": 24.92406463623047,
|
| 948 |
+
"epoch": 1.615493623051488,
|
| 949 |
+
"grad_norm": 5064.875903206014,
|
| 950 |
+
"learning_rate": 5.344017779781835e-07,
|
| 951 |
+
"logits": -1.1750729084014893,
|
| 952 |
+
"logps": -75.65376281738281,
|
| 953 |
+
"loss": 28.5295,
|
| 954 |
+
"objective": 24.92406463623047,
|
| 955 |
+
"ranking_idealized": 0.5166666507720947,
|
| 956 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 957 |
+
"ranking_simple": 0.6333333253860474,
|
| 958 |
+
"regularize": 24.92406463623047,
|
| 959 |
+
"step": 285
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"dpo_loss": 33.37800598144531,
|
| 963 |
+
"epoch": 1.643835616438356,
|
| 964 |
+
"grad_norm": 5057.655323901423,
|
| 965 |
+
"learning_rate": 4.6007101950209827e-07,
|
| 966 |
+
"logits": -1.1915957927703857,
|
| 967 |
+
"logps": -73.43339538574219,
|
| 968 |
+
"loss": 27.6645,
|
| 969 |
+
"objective": 33.37800598144531,
|
| 970 |
+
"ranking_idealized": 0.5625,
|
| 971 |
+
"ranking_idealized_expo": 0.5625,
|
| 972 |
+
"ranking_simple": 0.6291666626930237,
|
| 973 |
+
"regularize": 33.37800598144531,
|
| 974 |
+
"step": 290
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"dpo_loss": 17.80238151550293,
|
| 978 |
+
"epoch": 1.6721776098252243,
|
| 979 |
+
"grad_norm": 5184.197441213302,
|
| 980 |
+
"learning_rate": 3.907798046371139e-07,
|
| 981 |
+
"logits": -1.1149822473526,
|
| 982 |
+
"logps": -72.55225372314453,
|
| 983 |
+
"loss": 25.6518,
|
| 984 |
+
"objective": 17.80238151550293,
|
| 985 |
+
"ranking_idealized": 0.4791666567325592,
|
| 986 |
+
"ranking_idealized_expo": 0.4791666567325592,
|
| 987 |
+
"ranking_simple": 0.6041666865348816,
|
| 988 |
+
"regularize": 17.80238151550293,
|
| 989 |
+
"step": 295
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"dpo_loss": 16.620241165161133,
|
| 993 |
+
"epoch": 1.7005196032120926,
|
| 994 |
+
"grad_norm": 4977.226734001169,
|
| 995 |
+
"learning_rate": 3.266993139010438e-07,
|
| 996 |
+
"logits": -1.1575456857681274,
|
| 997 |
+
"logps": -74.20482635498047,
|
| 998 |
+
"loss": 24.0056,
|
| 999 |
+
"objective": 16.620241165161133,
|
| 1000 |
+
"ranking_idealized": 0.574999988079071,
|
| 1001 |
+
"ranking_idealized_expo": 0.574999988079071,
|
| 1002 |
+
"ranking_simple": 0.6791666746139526,
|
| 1003 |
+
"regularize": 16.620241165161133,
|
| 1004 |
+
"step": 300
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7005196032120926,
|
| 1008 |
+
"eval_dpo_loss": 153.7111358642578,
|
| 1009 |
+
"eval_logits": -1.1970975399017334,
|
| 1010 |
+
"eval_logps": -79.46780395507812,
|
| 1011 |
+
"eval_loss": 154.3220672607422,
|
| 1012 |
+
"eval_objective": 153.7111358642578,
|
| 1013 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 1014 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 1015 |
+
"eval_ranking_simple": 0.5237603187561035,
|
| 1016 |
+
"eval_regularize": 153.7111358642578,
|
| 1017 |
+
"eval_runtime": 260.0103,
|
| 1018 |
+
"eval_samples_per_second": 22.268,
|
| 1019 |
+
"eval_steps_per_second": 0.931,
|
| 1020 |
+
"step": 300
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"dpo_loss": 26.987300872802734,
|
| 1024 |
+
"epoch": 1.7288615965989607,
|
| 1025 |
+
"grad_norm": 5666.8865170633535,
|
| 1026 |
+
"learning_rate": 2.6798785497556184e-07,
|
| 1027 |
+
"logits": -1.1298245191574097,
|
| 1028 |
+
"logps": -75.2568588256836,
|
| 1029 |
+
"loss": 25.3362,
|
| 1030 |
+
"objective": 26.987300872802734,
|
| 1031 |
+
"ranking_idealized": 0.5041666626930237,
|
| 1032 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 1033 |
+
"ranking_simple": 0.6000000238418579,
|
| 1034 |
+
"regularize": 26.987300872802734,
|
| 1035 |
+
"step": 305
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"dpo_loss": 27.362499237060547,
|
| 1039 |
+
"epoch": 1.7572035899858292,
|
| 1040 |
+
"grad_norm": 6726.005866778725,
|
| 1041 |
+
"learning_rate": 2.1479047161491351e-07,
|
| 1042 |
+
"logits": -1.1657706499099731,
|
| 1043 |
+
"logps": -73.20048522949219,
|
| 1044 |
+
"loss": 34.4912,
|
| 1045 |
+
"objective": 27.362499237060547,
|
| 1046 |
+
"ranking_idealized": 0.5208333134651184,
|
| 1047 |
+
"ranking_idealized_expo": 0.5208333134651184,
|
| 1048 |
+
"ranking_simple": 0.6291666626930237,
|
| 1049 |
+
"regularize": 27.362499237060547,
|
| 1050 |
+
"step": 310
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"dpo_loss": 26.551549911499023,
|
| 1054 |
+
"epoch": 1.7855455833726972,
|
| 1055 |
+
"grad_norm": 4920.254333292925,
|
| 1056 |
+
"learning_rate": 1.6723858532249783e-07,
|
| 1057 |
+
"logits": -1.1162974834442139,
|
| 1058 |
+
"logps": -73.76349639892578,
|
| 1059 |
+
"loss": 28.333,
|
| 1060 |
+
"objective": 26.551549911499023,
|
| 1061 |
+
"ranking_idealized": 0.5083333253860474,
|
| 1062 |
+
"ranking_idealized_expo": 0.5083333253860474,
|
| 1063 |
+
"ranking_simple": 0.625,
|
| 1064 |
+
"regularize": 26.551549911499023,
|
| 1065 |
+
"step": 315
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"dpo_loss": 27.110830307006836,
|
| 1069 |
+
"epoch": 1.8138875767595655,
|
| 1070 |
+
"grad_norm": 5055.149103387853,
|
| 1071 |
+
"learning_rate": 1.2544967068054332e-07,
|
| 1072 |
+
"logits": -1.1586967706680298,
|
| 1073 |
+
"logps": -75.58198547363281,
|
| 1074 |
+
"loss": 29.2707,
|
| 1075 |
+
"objective": 27.110830307006836,
|
| 1076 |
+
"ranking_idealized": 0.5041666626930237,
|
| 1077 |
+
"ranking_idealized_expo": 0.5041666626930237,
|
| 1078 |
+
"ranking_simple": 0.6208333373069763,
|
| 1079 |
+
"regularize": 27.110830307006836,
|
| 1080 |
+
"step": 320
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"dpo_loss": 21.96232032775879,
|
| 1084 |
+
"epoch": 1.8422295701464337,
|
| 1085 |
+
"grad_norm": 5590.846808187711,
|
| 1086 |
+
"learning_rate": 8.952696513496756e-08,
|
| 1087 |
+
"logits": -1.190901279449463,
|
| 1088 |
+
"logps": -76.7601318359375,
|
| 1089 |
+
"loss": 31.3297,
|
| 1090 |
+
"objective": 21.96232032775879,
|
| 1091 |
+
"ranking_idealized": 0.5166666507720947,
|
| 1092 |
+
"ranking_idealized_expo": 0.5166666507720947,
|
| 1093 |
+
"ranking_simple": 0.6583333611488342,
|
| 1094 |
+
"regularize": 21.96232032775879,
|
| 1095 |
+
"step": 325
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"dpo_loss": 15.405153274536133,
|
| 1099 |
+
"epoch": 1.8705715635333018,
|
| 1100 |
+
"grad_norm": 4532.986973110623,
|
| 1101 |
+
"learning_rate": 5.955921395237318e-08,
|
| 1102 |
+
"logits": -1.0123432874679565,
|
| 1103 |
+
"logps": -73.34371948242188,
|
| 1104 |
+
"loss": 25.3935,
|
| 1105 |
+
"objective": 15.405153274536133,
|
| 1106 |
+
"ranking_idealized": 0.47083333134651184,
|
| 1107 |
+
"ranking_idealized_expo": 0.47083333134651184,
|
| 1108 |
+
"ranking_simple": 0.5833333134651184,
|
| 1109 |
+
"regularize": 15.405153274536133,
|
| 1110 |
+
"step": 330
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"dpo_loss": 27.14239501953125,
|
| 1114 |
+
"epoch": 1.89891355692017,
|
| 1115 |
+
"grad_norm": 4025.6636432059317,
|
| 1116 |
+
"learning_rate": 3.5620450979259034e-08,
|
| 1117 |
+
"logits": -1.1433656215667725,
|
| 1118 |
+
"logps": -73.34452056884766,
|
| 1119 |
+
"loss": 28.8551,
|
| 1120 |
+
"objective": 27.14239501953125,
|
| 1121 |
+
"ranking_idealized": 0.4958333373069763,
|
| 1122 |
+
"ranking_idealized_expo": 0.4958333373069763,
|
| 1123 |
+
"ranking_simple": 0.6333333253860474,
|
| 1124 |
+
"regularize": 27.14239501953125,
|
| 1125 |
+
"step": 335
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"dpo_loss": 27.192691802978516,
|
| 1129 |
+
"epoch": 1.9272555503070383,
|
| 1130 |
+
"grad_norm": 4979.044810332174,
|
| 1131 |
+
"learning_rate": 1.7769815745066476e-08,
|
| 1132 |
+
"logits": -1.1102468967437744,
|
| 1133 |
+
"logps": -75.71009063720703,
|
| 1134 |
+
"loss": 28.1441,
|
| 1135 |
+
"objective": 27.192691802978516,
|
| 1136 |
+
"ranking_idealized": 0.5416666865348816,
|
| 1137 |
+
"ranking_idealized_expo": 0.5416666865348816,
|
| 1138 |
+
"ranking_simple": 0.6625000238418579,
|
| 1139 |
+
"regularize": 27.192691802978516,
|
| 1140 |
+
"step": 340
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"dpo_loss": 20.978731155395508,
|
| 1144 |
+
"epoch": 1.9555975436939064,
|
| 1145 |
+
"grad_norm": 4629.432890304778,
|
| 1146 |
+
"learning_rate": 6.051407360895822e-09,
|
| 1147 |
+
"logits": -1.1233471632003784,
|
| 1148 |
+
"logps": -74.21357727050781,
|
| 1149 |
+
"loss": 26.2298,
|
| 1150 |
+
"objective": 20.978731155395508,
|
| 1151 |
+
"ranking_idealized": 0.5333333611488342,
|
| 1152 |
+
"ranking_idealized_expo": 0.5333333611488342,
|
| 1153 |
+
"ranking_simple": 0.6083333492279053,
|
| 1154 |
+
"regularize": 20.978731155395508,
|
| 1155 |
+
"step": 345
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"dpo_loss": 24.83169174194336,
|
| 1159 |
+
"epoch": 1.9839395370807746,
|
| 1160 |
+
"grad_norm": 5527.549670581212,
|
| 1161 |
+
"learning_rate": 4.941755748361088e-10,
|
| 1162 |
+
"logits": -1.0784180164337158,
|
| 1163 |
+
"logps": -74.90613555908203,
|
| 1164 |
+
"loss": 25.1496,
|
| 1165 |
+
"objective": 24.83169174194336,
|
| 1166 |
+
"ranking_idealized": 0.48750001192092896,
|
| 1167 |
+
"ranking_idealized_expo": 0.48750001192092896,
|
| 1168 |
+
"ranking_simple": 0.6041666865348816,
|
| 1169 |
+
"regularize": 24.83169174194336,
|
| 1170 |
+
"step": 350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.9839395370807746,
|
| 1174 |
+
"eval_dpo_loss": 152.31163024902344,
|
| 1175 |
+
"eval_logits": -1.1890522241592407,
|
| 1176 |
+
"eval_logps": -79.3233642578125,
|
| 1177 |
+
"eval_loss": 153.95770263671875,
|
| 1178 |
+
"eval_objective": 152.31163024902344,
|
| 1179 |
+
"eval_ranking_idealized": 0.5092975497245789,
|
| 1180 |
+
"eval_ranking_idealized_expo": 0.5092975497245789,
|
| 1181 |
+
"eval_ranking_simple": 0.5227272510528564,
|
| 1182 |
+
"eval_regularize": 152.31163024902344,
|
| 1183 |
+
"eval_runtime": 259.9659,
|
| 1184 |
+
"eval_samples_per_second": 22.272,
|
| 1185 |
+
"eval_steps_per_second": 0.931,
|
| 1186 |
+
"step": 350
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.995276334435522,
|
| 1190 |
+
"step": 352,
|
| 1191 |
+
"total_flos": 0.0,
|
| 1192 |
+
"train_loss": 58.09165079349821,
|
| 1193 |
+
"train_runtime": 14332.9867,
|
| 1194 |
+
"train_samples_per_second": 7.089,
|
| 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 sha256:654881f84e32d89646896e59a547511a288187527c99c25744f1cf541db4c529
|
| 3 |
+
size 8120
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|