Upload folder using huggingface_hub
Browse files- checkpoint-120/README.md +218 -0
- checkpoint-120/adapter_config.json +31 -0
- checkpoint-120/adapter_model.safetensors +3 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/special_tokens_map.json +29 -0
- checkpoint-120/tokenizer.json +0 -0
- checkpoint-120/tokenizer.model +3 -0
- checkpoint-120/tokenizer_config.json +46 -0
- checkpoint-120/trainer_state.json +1699 -0
- checkpoint-120/training_args.bin +3 -0
checkpoint-120/README.md
ADDED
|
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: fblgit/una-cybertron-7b-v2-bf16
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
## Training procedure
|
| 203 |
+
|
| 204 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
+
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: False
|
| 207 |
+
- load_in_4bit: True
|
| 208 |
+
- llm_int8_threshold: 6.0
|
| 209 |
+
- llm_int8_skip_modules: None
|
| 210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
+
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: fp4
|
| 213 |
+
- bnb_4bit_use_double_quant: False
|
| 214 |
+
- bnb_4bit_compute_dtype: float32
|
| 215 |
+
|
| 216 |
+
### Framework versions
|
| 217 |
+
|
| 218 |
+
- PEFT 0.7.0
|
checkpoint-120/adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "fblgit/una-cybertron-7b-v2-bf16",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"up_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
checkpoint-120/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6500deb9e1d0356e19deeca1e1842b36579adeabdc01fd11c8580cdef7062240
|
| 3 |
+
size 167832240
|
checkpoint-120/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28b6ff0aa244073338cff6fe63df90a9c33c8eaa1313731530c92aaaa176cc7a
|
| 3 |
+
size 335812858
|
checkpoint-120/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-120/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27006f13e145c1f43befd56dd6520d4d5b21c6543a3e0facc601b4fc42bbb3e5
|
| 3 |
+
size 1064
|
checkpoint-120/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-120/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-120/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"pad_token": "</s>",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-120/trainer_state.json
ADDED
|
@@ -0,0 +1,1699 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.14930015552099535,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.000000000000001e-07,
|
| 14 |
+
"logits/chosen": -2.0463106632232666,
|
| 15 |
+
"logits/rejected": -1.8486888408660889,
|
| 16 |
+
"logps/chosen": -311.57489013671875,
|
| 17 |
+
"logps/rejected": -415.468505859375,
|
| 18 |
+
"loss": 0.671,
|
| 19 |
+
"rewards/accuracies": 0.75,
|
| 20 |
+
"rewards/chosen": -0.021808436140418053,
|
| 21 |
+
"rewards/margins": 0.04626159369945526,
|
| 22 |
+
"rewards/rejected": -0.06807002425193787,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 28 |
+
"logits/chosen": -2.060105562210083,
|
| 29 |
+
"logits/rejected": -2.106396198272705,
|
| 30 |
+
"logps/chosen": -220.380615234375,
|
| 31 |
+
"logps/rejected": -404.501220703125,
|
| 32 |
+
"loss": 0.6745,
|
| 33 |
+
"rewards/accuracies": 0.6875,
|
| 34 |
+
"rewards/chosen": -0.02021012455224991,
|
| 35 |
+
"rewards/margins": 0.03883519023656845,
|
| 36 |
+
"rewards/rejected": -0.05904531478881836,
|
| 37 |
+
"step": 2
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0,
|
| 41 |
+
"learning_rate": 1.5e-06,
|
| 42 |
+
"logits/chosen": -2.239086151123047,
|
| 43 |
+
"logits/rejected": -2.0575525760650635,
|
| 44 |
+
"logps/chosen": -163.8677978515625,
|
| 45 |
+
"logps/rejected": -446.79180908203125,
|
| 46 |
+
"loss": 0.67,
|
| 47 |
+
"rewards/accuracies": 0.6875,
|
| 48 |
+
"rewards/chosen": -0.024322081357240677,
|
| 49 |
+
"rewards/margins": 0.04956565052270889,
|
| 50 |
+
"rewards/rejected": -0.07388772815465927,
|
| 51 |
+
"step": 3
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0,
|
| 55 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 56 |
+
"logits/chosen": -2.1058502197265625,
|
| 57 |
+
"logits/rejected": -2.344322681427002,
|
| 58 |
+
"logps/chosen": -318.9349670410156,
|
| 59 |
+
"logps/rejected": -378.9231262207031,
|
| 60 |
+
"loss": 0.6576,
|
| 61 |
+
"rewards/accuracies": 0.9375,
|
| 62 |
+
"rewards/chosen": -0.027724243700504303,
|
| 63 |
+
"rewards/margins": 0.07309143990278244,
|
| 64 |
+
"rewards/rejected": -0.10081568360328674,
|
| 65 |
+
"step": 4
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01,
|
| 69 |
+
"learning_rate": 2.5e-06,
|
| 70 |
+
"logits/chosen": -2.287339687347412,
|
| 71 |
+
"logits/rejected": -2.3221607208251953,
|
| 72 |
+
"logps/chosen": -221.33163452148438,
|
| 73 |
+
"logps/rejected": -388.6357421875,
|
| 74 |
+
"loss": 0.6498,
|
| 75 |
+
"rewards/accuracies": 0.8125,
|
| 76 |
+
"rewards/chosen": -0.03215093910694122,
|
| 77 |
+
"rewards/margins": 0.09096165001392365,
|
| 78 |
+
"rewards/rejected": -0.12311258912086487,
|
| 79 |
+
"step": 5
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.01,
|
| 83 |
+
"learning_rate": 3e-06,
|
| 84 |
+
"logits/chosen": -1.98830246925354,
|
| 85 |
+
"logits/rejected": -1.9178718328475952,
|
| 86 |
+
"logps/chosen": -244.0532684326172,
|
| 87 |
+
"logps/rejected": -373.9111328125,
|
| 88 |
+
"loss": 0.6395,
|
| 89 |
+
"rewards/accuracies": 0.8125,
|
| 90 |
+
"rewards/chosen": -0.0789945125579834,
|
| 91 |
+
"rewards/margins": 0.11430712044239044,
|
| 92 |
+
"rewards/rejected": -0.19330161809921265,
|
| 93 |
+
"step": 6
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 98 |
+
"logits/chosen": -2.0385985374450684,
|
| 99 |
+
"logits/rejected": -1.9476547241210938,
|
| 100 |
+
"logps/chosen": -347.14227294921875,
|
| 101 |
+
"logps/rejected": -426.24603271484375,
|
| 102 |
+
"loss": 0.6148,
|
| 103 |
+
"rewards/accuracies": 0.9375,
|
| 104 |
+
"rewards/chosen": -0.0816906988620758,
|
| 105 |
+
"rewards/margins": 0.1658005714416504,
|
| 106 |
+
"rewards/rejected": -0.2474912703037262,
|
| 107 |
+
"step": 7
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.01,
|
| 111 |
+
"learning_rate": 4.000000000000001e-06,
|
| 112 |
+
"logits/chosen": -1.695872187614441,
|
| 113 |
+
"logits/rejected": -1.7980302572250366,
|
| 114 |
+
"logps/chosen": -287.9168395996094,
|
| 115 |
+
"logps/rejected": -355.14129638671875,
|
| 116 |
+
"loss": 0.5785,
|
| 117 |
+
"rewards/accuracies": 1.0,
|
| 118 |
+
"rewards/chosen": -0.07900090515613556,
|
| 119 |
+
"rewards/margins": 0.25094836950302124,
|
| 120 |
+
"rewards/rejected": -0.329949289560318,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.01,
|
| 125 |
+
"learning_rate": 4.5e-06,
|
| 126 |
+
"logits/chosen": -1.9222339391708374,
|
| 127 |
+
"logits/rejected": -1.8972643613815308,
|
| 128 |
+
"logps/chosen": -211.97979736328125,
|
| 129 |
+
"logps/rejected": -405.848388671875,
|
| 130 |
+
"loss": 0.5229,
|
| 131 |
+
"rewards/accuracies": 1.0,
|
| 132 |
+
"rewards/chosen": -0.09827227890491486,
|
| 133 |
+
"rewards/margins": 0.3891267478466034,
|
| 134 |
+
"rewards/rejected": -0.48739901185035706,
|
| 135 |
+
"step": 9
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.01,
|
| 139 |
+
"learning_rate": 5e-06,
|
| 140 |
+
"logits/chosen": -1.9703621864318848,
|
| 141 |
+
"logits/rejected": -1.7560880184173584,
|
| 142 |
+
"logps/chosen": -277.2589416503906,
|
| 143 |
+
"logps/rejected": -445.6544494628906,
|
| 144 |
+
"loss": 0.4853,
|
| 145 |
+
"rewards/accuracies": 1.0,
|
| 146 |
+
"rewards/chosen": -0.1426083892583847,
|
| 147 |
+
"rewards/margins": 0.4861423373222351,
|
| 148 |
+
"rewards/rejected": -0.628750741481781,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.01,
|
| 153 |
+
"learning_rate": 5.500000000000001e-06,
|
| 154 |
+
"logits/chosen": -2.0542986392974854,
|
| 155 |
+
"logits/rejected": -2.110658884048462,
|
| 156 |
+
"logps/chosen": -283.9775390625,
|
| 157 |
+
"logps/rejected": -394.361572265625,
|
| 158 |
+
"loss": 0.4476,
|
| 159 |
+
"rewards/accuracies": 1.0,
|
| 160 |
+
"rewards/chosen": -0.14311671257019043,
|
| 161 |
+
"rewards/margins": 0.6046640872955322,
|
| 162 |
+
"rewards/rejected": -0.7477807998657227,
|
| 163 |
+
"step": 11
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.01,
|
| 167 |
+
"learning_rate": 6e-06,
|
| 168 |
+
"logits/chosen": -2.0650949478149414,
|
| 169 |
+
"logits/rejected": -2.0736098289489746,
|
| 170 |
+
"logps/chosen": -235.07675170898438,
|
| 171 |
+
"logps/rejected": -448.17919921875,
|
| 172 |
+
"loss": 0.3701,
|
| 173 |
+
"rewards/accuracies": 1.0,
|
| 174 |
+
"rewards/chosen": -0.23901399970054626,
|
| 175 |
+
"rewards/margins": 0.9068580269813538,
|
| 176 |
+
"rewards/rejected": -1.1458721160888672,
|
| 177 |
+
"step": 12
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.02,
|
| 181 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 182 |
+
"logits/chosen": -2.011099100112915,
|
| 183 |
+
"logits/rejected": -2.106595754623413,
|
| 184 |
+
"logps/chosen": -289.19970703125,
|
| 185 |
+
"logps/rejected": -417.64208984375,
|
| 186 |
+
"loss": 0.3675,
|
| 187 |
+
"rewards/accuracies": 1.0,
|
| 188 |
+
"rewards/chosen": -0.26357388496398926,
|
| 189 |
+
"rewards/margins": 0.8955046534538269,
|
| 190 |
+
"rewards/rejected": -1.159078598022461,
|
| 191 |
+
"step": 13
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.02,
|
| 195 |
+
"learning_rate": 7.000000000000001e-06,
|
| 196 |
+
"logits/chosen": -2.1066994667053223,
|
| 197 |
+
"logits/rejected": -1.7827305793762207,
|
| 198 |
+
"logps/chosen": -169.27044677734375,
|
| 199 |
+
"logps/rejected": -446.7305908203125,
|
| 200 |
+
"loss": 0.254,
|
| 201 |
+
"rewards/accuracies": 1.0,
|
| 202 |
+
"rewards/chosen": -0.2715146541595459,
|
| 203 |
+
"rewards/margins": 1.3259609937667847,
|
| 204 |
+
"rewards/rejected": -1.5974756479263306,
|
| 205 |
+
"step": 14
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.02,
|
| 209 |
+
"learning_rate": 7.5e-06,
|
| 210 |
+
"logits/chosen": -1.9394950866699219,
|
| 211 |
+
"logits/rejected": -1.9831421375274658,
|
| 212 |
+
"logps/chosen": -194.98016357421875,
|
| 213 |
+
"logps/rejected": -470.9692687988281,
|
| 214 |
+
"loss": 0.2298,
|
| 215 |
+
"rewards/accuracies": 1.0,
|
| 216 |
+
"rewards/chosen": -0.4095136225223541,
|
| 217 |
+
"rewards/margins": 1.628616452217102,
|
| 218 |
+
"rewards/rejected": -2.038130044937134,
|
| 219 |
+
"step": 15
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.02,
|
| 223 |
+
"learning_rate": 8.000000000000001e-06,
|
| 224 |
+
"logits/chosen": -1.7606948614120483,
|
| 225 |
+
"logits/rejected": -2.0152878761291504,
|
| 226 |
+
"logps/chosen": -253.0347900390625,
|
| 227 |
+
"logps/rejected": -428.3993835449219,
|
| 228 |
+
"loss": 0.2528,
|
| 229 |
+
"rewards/accuracies": 1.0,
|
| 230 |
+
"rewards/chosen": -0.581798255443573,
|
| 231 |
+
"rewards/margins": 1.3869069814682007,
|
| 232 |
+
"rewards/rejected": -1.968705177307129,
|
| 233 |
+
"step": 16
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.02,
|
| 237 |
+
"learning_rate": 8.500000000000002e-06,
|
| 238 |
+
"logits/chosen": -2.0609982013702393,
|
| 239 |
+
"logits/rejected": -1.9835376739501953,
|
| 240 |
+
"logps/chosen": -265.3518371582031,
|
| 241 |
+
"logps/rejected": -501.8542785644531,
|
| 242 |
+
"loss": 0.1997,
|
| 243 |
+
"rewards/accuracies": 1.0,
|
| 244 |
+
"rewards/chosen": -0.681609570980072,
|
| 245 |
+
"rewards/margins": 2.0102298259735107,
|
| 246 |
+
"rewards/rejected": -2.6918392181396484,
|
| 247 |
+
"step": 17
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.02,
|
| 251 |
+
"learning_rate": 9e-06,
|
| 252 |
+
"logits/chosen": -2.117746114730835,
|
| 253 |
+
"logits/rejected": -2.218081474304199,
|
| 254 |
+
"logps/chosen": -202.6907501220703,
|
| 255 |
+
"logps/rejected": -413.13604736328125,
|
| 256 |
+
"loss": 0.1582,
|
| 257 |
+
"rewards/accuracies": 1.0,
|
| 258 |
+
"rewards/chosen": -0.6984068751335144,
|
| 259 |
+
"rewards/margins": 1.8970444202423096,
|
| 260 |
+
"rewards/rejected": -2.5954513549804688,
|
| 261 |
+
"step": 18
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.02,
|
| 265 |
+
"learning_rate": 9.5e-06,
|
| 266 |
+
"logits/chosen": -2.385519504547119,
|
| 267 |
+
"logits/rejected": -1.8222811222076416,
|
| 268 |
+
"logps/chosen": -175.93809509277344,
|
| 269 |
+
"logps/rejected": -469.17657470703125,
|
| 270 |
+
"loss": 0.0951,
|
| 271 |
+
"rewards/accuracies": 1.0,
|
| 272 |
+
"rewards/chosen": -0.7677481174468994,
|
| 273 |
+
"rewards/margins": 2.7113454341888428,
|
| 274 |
+
"rewards/rejected": -3.479093551635742,
|
| 275 |
+
"step": 19
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.02,
|
| 279 |
+
"learning_rate": 1e-05,
|
| 280 |
+
"logits/chosen": -2.187441349029541,
|
| 281 |
+
"logits/rejected": -2.1218032836914062,
|
| 282 |
+
"logps/chosen": -301.7166442871094,
|
| 283 |
+
"logps/rejected": -490.854736328125,
|
| 284 |
+
"loss": 0.0944,
|
| 285 |
+
"rewards/accuracies": 1.0,
|
| 286 |
+
"rewards/chosen": -1.2999629974365234,
|
| 287 |
+
"rewards/margins": 3.2447361946105957,
|
| 288 |
+
"rewards/rejected": -4.544699192047119,
|
| 289 |
+
"step": 20
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.03,
|
| 293 |
+
"learning_rate": 1.05e-05,
|
| 294 |
+
"logits/chosen": -1.967098355293274,
|
| 295 |
+
"logits/rejected": -1.9263262748718262,
|
| 296 |
+
"logps/chosen": -176.0479278564453,
|
| 297 |
+
"logps/rejected": -472.8221435546875,
|
| 298 |
+
"loss": 0.0459,
|
| 299 |
+
"rewards/accuracies": 1.0,
|
| 300 |
+
"rewards/chosen": -0.8402897119522095,
|
| 301 |
+
"rewards/margins": 4.1183624267578125,
|
| 302 |
+
"rewards/rejected": -4.958651542663574,
|
| 303 |
+
"step": 21
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.03,
|
| 307 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 308 |
+
"logits/chosen": -2.188459873199463,
|
| 309 |
+
"logits/rejected": -2.156071424484253,
|
| 310 |
+
"logps/chosen": -243.41683959960938,
|
| 311 |
+
"logps/rejected": -465.08685302734375,
|
| 312 |
+
"loss": 0.1389,
|
| 313 |
+
"rewards/accuracies": 0.9375,
|
| 314 |
+
"rewards/chosen": -1.5002142190933228,
|
| 315 |
+
"rewards/margins": 4.108778953552246,
|
| 316 |
+
"rewards/rejected": -5.608993053436279,
|
| 317 |
+
"step": 22
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.03,
|
| 321 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 322 |
+
"logits/chosen": -1.7361280918121338,
|
| 323 |
+
"logits/rejected": -1.8734406232833862,
|
| 324 |
+
"logps/chosen": -274.4007568359375,
|
| 325 |
+
"logps/rejected": -465.7174987792969,
|
| 326 |
+
"loss": 0.074,
|
| 327 |
+
"rewards/accuracies": 1.0,
|
| 328 |
+
"rewards/chosen": -1.6840157508850098,
|
| 329 |
+
"rewards/margins": 4.5255866050720215,
|
| 330 |
+
"rewards/rejected": -6.209602355957031,
|
| 331 |
+
"step": 23
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.03,
|
| 335 |
+
"learning_rate": 1.2e-05,
|
| 336 |
+
"logits/chosen": -1.8966342210769653,
|
| 337 |
+
"logits/rejected": -1.772972583770752,
|
| 338 |
+
"logps/chosen": -275.3910217285156,
|
| 339 |
+
"logps/rejected": -462.07720947265625,
|
| 340 |
+
"loss": 0.0381,
|
| 341 |
+
"rewards/accuracies": 1.0,
|
| 342 |
+
"rewards/chosen": -2.017077922821045,
|
| 343 |
+
"rewards/margins": 4.740576267242432,
|
| 344 |
+
"rewards/rejected": -6.757654666900635,
|
| 345 |
+
"step": 24
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.03,
|
| 349 |
+
"learning_rate": 1.25e-05,
|
| 350 |
+
"logits/chosen": -2.2573952674865723,
|
| 351 |
+
"logits/rejected": -1.9883058071136475,
|
| 352 |
+
"logps/chosen": -172.16043090820312,
|
| 353 |
+
"logps/rejected": -391.4390563964844,
|
| 354 |
+
"loss": 0.0666,
|
| 355 |
+
"rewards/accuracies": 1.0,
|
| 356 |
+
"rewards/chosen": -1.9856681823730469,
|
| 357 |
+
"rewards/margins": 4.858271598815918,
|
| 358 |
+
"rewards/rejected": -6.843939781188965,
|
| 359 |
+
"step": 25
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.03,
|
| 363 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 364 |
+
"logits/chosen": -2.0475640296936035,
|
| 365 |
+
"logits/rejected": -1.8690011501312256,
|
| 366 |
+
"logps/chosen": -184.4323272705078,
|
| 367 |
+
"logps/rejected": -468.86175537109375,
|
| 368 |
+
"loss": 0.0805,
|
| 369 |
+
"rewards/accuracies": 0.9375,
|
| 370 |
+
"rewards/chosen": -2.08463716506958,
|
| 371 |
+
"rewards/margins": 6.207521438598633,
|
| 372 |
+
"rewards/rejected": -8.292158126831055,
|
| 373 |
+
"step": 26
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.03,
|
| 377 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 378 |
+
"logits/chosen": -1.9634509086608887,
|
| 379 |
+
"logits/rejected": -2.260413646697998,
|
| 380 |
+
"logps/chosen": -398.9476013183594,
|
| 381 |
+
"logps/rejected": -540.3334350585938,
|
| 382 |
+
"loss": 0.029,
|
| 383 |
+
"rewards/accuracies": 1.0,
|
| 384 |
+
"rewards/chosen": -3.3595480918884277,
|
| 385 |
+
"rewards/margins": 6.726611614227295,
|
| 386 |
+
"rewards/rejected": -10.086159706115723,
|
| 387 |
+
"step": 27
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.03,
|
| 391 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 392 |
+
"logits/chosen": -1.9712620973587036,
|
| 393 |
+
"logits/rejected": -1.827807068824768,
|
| 394 |
+
"logps/chosen": -221.26559448242188,
|
| 395 |
+
"logps/rejected": -483.7889709472656,
|
| 396 |
+
"loss": 0.0063,
|
| 397 |
+
"rewards/accuracies": 1.0,
|
| 398 |
+
"rewards/chosen": -2.3635034561157227,
|
| 399 |
+
"rewards/margins": 7.733745098114014,
|
| 400 |
+
"rewards/rejected": -10.097248077392578,
|
| 401 |
+
"step": 28
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.04,
|
| 405 |
+
"learning_rate": 1.45e-05,
|
| 406 |
+
"logits/chosen": -1.542866587638855,
|
| 407 |
+
"logits/rejected": -1.7318823337554932,
|
| 408 |
+
"logps/chosen": -267.33880615234375,
|
| 409 |
+
"logps/rejected": -558.8424072265625,
|
| 410 |
+
"loss": 0.0746,
|
| 411 |
+
"rewards/accuracies": 0.9375,
|
| 412 |
+
"rewards/chosen": -3.391514301300049,
|
| 413 |
+
"rewards/margins": 9.136863708496094,
|
| 414 |
+
"rewards/rejected": -12.528377532958984,
|
| 415 |
+
"step": 29
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.04,
|
| 419 |
+
"learning_rate": 1.5e-05,
|
| 420 |
+
"logits/chosen": -2.037372589111328,
|
| 421 |
+
"logits/rejected": -1.8312575817108154,
|
| 422 |
+
"logps/chosen": -288.1588134765625,
|
| 423 |
+
"logps/rejected": -670.7269287109375,
|
| 424 |
+
"loss": 0.0007,
|
| 425 |
+
"rewards/accuracies": 1.0,
|
| 426 |
+
"rewards/chosen": -3.795253276824951,
|
| 427 |
+
"rewards/margins": 11.858222961425781,
|
| 428 |
+
"rewards/rejected": -15.653478622436523,
|
| 429 |
+
"step": 30
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.04,
|
| 433 |
+
"learning_rate": 1.55e-05,
|
| 434 |
+
"logits/chosen": -1.5374680757522583,
|
| 435 |
+
"logits/rejected": -1.8392678499221802,
|
| 436 |
+
"logps/chosen": -281.0010070800781,
|
| 437 |
+
"logps/rejected": -553.43017578125,
|
| 438 |
+
"loss": 0.0149,
|
| 439 |
+
"rewards/accuracies": 1.0,
|
| 440 |
+
"rewards/chosen": -3.836461067199707,
|
| 441 |
+
"rewards/margins": 9.380411148071289,
|
| 442 |
+
"rewards/rejected": -13.216873168945312,
|
| 443 |
+
"step": 31
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.04,
|
| 447 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 448 |
+
"logits/chosen": -2.033914566040039,
|
| 449 |
+
"logits/rejected": -1.9804089069366455,
|
| 450 |
+
"logps/chosen": -261.31103515625,
|
| 451 |
+
"logps/rejected": -545.380126953125,
|
| 452 |
+
"loss": 0.0123,
|
| 453 |
+
"rewards/accuracies": 1.0,
|
| 454 |
+
"rewards/chosen": -4.321026802062988,
|
| 455 |
+
"rewards/margins": 9.96163272857666,
|
| 456 |
+
"rewards/rejected": -14.282659530639648,
|
| 457 |
+
"step": 32
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.04,
|
| 461 |
+
"learning_rate": 1.65e-05,
|
| 462 |
+
"logits/chosen": -1.652747631072998,
|
| 463 |
+
"logits/rejected": -1.6527116298675537,
|
| 464 |
+
"logps/chosen": -250.82638549804688,
|
| 465 |
+
"logps/rejected": -536.0584106445312,
|
| 466 |
+
"loss": 0.0017,
|
| 467 |
+
"rewards/accuracies": 1.0,
|
| 468 |
+
"rewards/chosen": -4.393105506896973,
|
| 469 |
+
"rewards/margins": 11.006621360778809,
|
| 470 |
+
"rewards/rejected": -15.399725914001465,
|
| 471 |
+
"step": 33
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.04,
|
| 475 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 476 |
+
"logits/chosen": -1.5870184898376465,
|
| 477 |
+
"logits/rejected": -1.9295532703399658,
|
| 478 |
+
"logps/chosen": -276.73248291015625,
|
| 479 |
+
"logps/rejected": -588.6087646484375,
|
| 480 |
+
"loss": 0.2671,
|
| 481 |
+
"rewards/accuracies": 0.875,
|
| 482 |
+
"rewards/chosen": -5.017908573150635,
|
| 483 |
+
"rewards/margins": 12.34096908569336,
|
| 484 |
+
"rewards/rejected": -17.35887908935547,
|
| 485 |
+
"step": 34
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.04,
|
| 489 |
+
"learning_rate": 1.75e-05,
|
| 490 |
+
"logits/chosen": -1.9227735996246338,
|
| 491 |
+
"logits/rejected": -1.954828143119812,
|
| 492 |
+
"logps/chosen": -266.1369323730469,
|
| 493 |
+
"logps/rejected": -550.742919921875,
|
| 494 |
+
"loss": 0.0035,
|
| 495 |
+
"rewards/accuracies": 1.0,
|
| 496 |
+
"rewards/chosen": -4.8841400146484375,
|
| 497 |
+
"rewards/margins": 13.669473648071289,
|
| 498 |
+
"rewards/rejected": -18.553613662719727,
|
| 499 |
+
"step": 35
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.04,
|
| 503 |
+
"learning_rate": 1.8e-05,
|
| 504 |
+
"logits/chosen": -1.6637210845947266,
|
| 505 |
+
"logits/rejected": -1.3936012983322144,
|
| 506 |
+
"logps/chosen": -256.7511901855469,
|
| 507 |
+
"logps/rejected": -591.1787109375,
|
| 508 |
+
"loss": 0.0022,
|
| 509 |
+
"rewards/accuracies": 1.0,
|
| 510 |
+
"rewards/chosen": -6.027996063232422,
|
| 511 |
+
"rewards/margins": 13.286176681518555,
|
| 512 |
+
"rewards/rejected": -19.314172744750977,
|
| 513 |
+
"step": 36
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.05,
|
| 517 |
+
"learning_rate": 1.85e-05,
|
| 518 |
+
"logits/chosen": -1.6170068979263306,
|
| 519 |
+
"logits/rejected": -1.6388572454452515,
|
| 520 |
+
"logps/chosen": -257.0255126953125,
|
| 521 |
+
"logps/rejected": -605.7335205078125,
|
| 522 |
+
"loss": 0.0008,
|
| 523 |
+
"rewards/accuracies": 1.0,
|
| 524 |
+
"rewards/chosen": -5.929409027099609,
|
| 525 |
+
"rewards/margins": 14.035564422607422,
|
| 526 |
+
"rewards/rejected": -19.9649715423584,
|
| 527 |
+
"step": 37
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.05,
|
| 531 |
+
"learning_rate": 1.9e-05,
|
| 532 |
+
"logits/chosen": -1.967097520828247,
|
| 533 |
+
"logits/rejected": -1.778485894203186,
|
| 534 |
+
"logps/chosen": -239.90533447265625,
|
| 535 |
+
"logps/rejected": -570.31787109375,
|
| 536 |
+
"loss": 0.0839,
|
| 537 |
+
"rewards/accuracies": 0.9375,
|
| 538 |
+
"rewards/chosen": -6.8724775314331055,
|
| 539 |
+
"rewards/margins": 13.892675399780273,
|
| 540 |
+
"rewards/rejected": -20.765153884887695,
|
| 541 |
+
"step": 38
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.05,
|
| 545 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 546 |
+
"logits/chosen": -1.6693722009658813,
|
| 547 |
+
"logits/rejected": -1.573314905166626,
|
| 548 |
+
"logps/chosen": -349.86480712890625,
|
| 549 |
+
"logps/rejected": -702.0185546875,
|
| 550 |
+
"loss": 0.0008,
|
| 551 |
+
"rewards/accuracies": 1.0,
|
| 552 |
+
"rewards/chosen": -7.373364448547363,
|
| 553 |
+
"rewards/margins": 15.567668914794922,
|
| 554 |
+
"rewards/rejected": -22.941036224365234,
|
| 555 |
+
"step": 39
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.05,
|
| 559 |
+
"learning_rate": 2e-05,
|
| 560 |
+
"logits/chosen": -1.556606650352478,
|
| 561 |
+
"logits/rejected": -1.394392967224121,
|
| 562 |
+
"logps/chosen": -213.81959533691406,
|
| 563 |
+
"logps/rejected": -637.4287109375,
|
| 564 |
+
"loss": 0.041,
|
| 565 |
+
"rewards/accuracies": 1.0,
|
| 566 |
+
"rewards/chosen": -4.418168067932129,
|
| 567 |
+
"rewards/margins": 17.626686096191406,
|
| 568 |
+
"rewards/rejected": -22.04485321044922,
|
| 569 |
+
"step": 40
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.05,
|
| 573 |
+
"learning_rate": 2.05e-05,
|
| 574 |
+
"logits/chosen": -1.6436810493469238,
|
| 575 |
+
"logits/rejected": -1.7172099351882935,
|
| 576 |
+
"logps/chosen": -304.43438720703125,
|
| 577 |
+
"logps/rejected": -704.897216796875,
|
| 578 |
+
"loss": 0.0002,
|
| 579 |
+
"rewards/accuracies": 1.0,
|
| 580 |
+
"rewards/chosen": -6.733709812164307,
|
| 581 |
+
"rewards/margins": 19.767263412475586,
|
| 582 |
+
"rewards/rejected": -26.500972747802734,
|
| 583 |
+
"step": 41
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.05,
|
| 587 |
+
"learning_rate": 2.1e-05,
|
| 588 |
+
"logits/chosen": -1.5168399810791016,
|
| 589 |
+
"logits/rejected": -1.508206844329834,
|
| 590 |
+
"logps/chosen": -262.28515625,
|
| 591 |
+
"logps/rejected": -556.9771118164062,
|
| 592 |
+
"loss": 0.062,
|
| 593 |
+
"rewards/accuracies": 0.9375,
|
| 594 |
+
"rewards/chosen": -5.817533493041992,
|
| 595 |
+
"rewards/margins": 13.013591766357422,
|
| 596 |
+
"rewards/rejected": -18.831125259399414,
|
| 597 |
+
"step": 42
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.05,
|
| 601 |
+
"learning_rate": 2.15e-05,
|
| 602 |
+
"logits/chosen": -1.3590738773345947,
|
| 603 |
+
"logits/rejected": -1.1529805660247803,
|
| 604 |
+
"logps/chosen": -205.32371520996094,
|
| 605 |
+
"logps/rejected": -576.4129638671875,
|
| 606 |
+
"loss": 0.002,
|
| 607 |
+
"rewards/accuracies": 1.0,
|
| 608 |
+
"rewards/chosen": -5.326513290405273,
|
| 609 |
+
"rewards/margins": 15.988494873046875,
|
| 610 |
+
"rewards/rejected": -21.315006256103516,
|
| 611 |
+
"step": 43
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.05,
|
| 615 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 616 |
+
"logits/chosen": -1.5084015130996704,
|
| 617 |
+
"logits/rejected": -1.5834801197052002,
|
| 618 |
+
"logps/chosen": -332.94580078125,
|
| 619 |
+
"logps/rejected": -685.3295288085938,
|
| 620 |
+
"loss": 0.0038,
|
| 621 |
+
"rewards/accuracies": 1.0,
|
| 622 |
+
"rewards/chosen": -7.390817642211914,
|
| 623 |
+
"rewards/margins": 18.214908599853516,
|
| 624 |
+
"rewards/rejected": -25.60572624206543,
|
| 625 |
+
"step": 44
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.06,
|
| 629 |
+
"learning_rate": 2.25e-05,
|
| 630 |
+
"logits/chosen": -1.4891091585159302,
|
| 631 |
+
"logits/rejected": -1.5173286199569702,
|
| 632 |
+
"logps/chosen": -250.24951171875,
|
| 633 |
+
"logps/rejected": -675.5242309570312,
|
| 634 |
+
"loss": 0.0026,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/chosen": -6.26884126663208,
|
| 637 |
+
"rewards/margins": 19.75680160522461,
|
| 638 |
+
"rewards/rejected": -26.025644302368164,
|
| 639 |
+
"step": 45
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.06,
|
| 643 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 644 |
+
"logits/chosen": -1.433956265449524,
|
| 645 |
+
"logits/rejected": -1.5273690223693848,
|
| 646 |
+
"logps/chosen": -366.8013000488281,
|
| 647 |
+
"logps/rejected": -703.315185546875,
|
| 648 |
+
"loss": 0.0103,
|
| 649 |
+
"rewards/accuracies": 1.0,
|
| 650 |
+
"rewards/chosen": -6.857599258422852,
|
| 651 |
+
"rewards/margins": 19.714298248291016,
|
| 652 |
+
"rewards/rejected": -26.571901321411133,
|
| 653 |
+
"step": 46
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.06,
|
| 657 |
+
"learning_rate": 2.35e-05,
|
| 658 |
+
"logits/chosen": -1.351868987083435,
|
| 659 |
+
"logits/rejected": -1.2347944974899292,
|
| 660 |
+
"logps/chosen": -292.37091064453125,
|
| 661 |
+
"logps/rejected": -687.9886474609375,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"rewards/accuracies": 1.0,
|
| 664 |
+
"rewards/chosen": -7.611140251159668,
|
| 665 |
+
"rewards/margins": 19.30370330810547,
|
| 666 |
+
"rewards/rejected": -26.91484260559082,
|
| 667 |
+
"step": 47
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.06,
|
| 671 |
+
"learning_rate": 2.4e-05,
|
| 672 |
+
"logits/chosen": -1.3243939876556396,
|
| 673 |
+
"logits/rejected": -1.0474777221679688,
|
| 674 |
+
"logps/chosen": -292.1935729980469,
|
| 675 |
+
"logps/rejected": -626.897705078125,
|
| 676 |
+
"loss": 0.0025,
|
| 677 |
+
"rewards/accuracies": 1.0,
|
| 678 |
+
"rewards/chosen": -6.425950527191162,
|
| 679 |
+
"rewards/margins": 17.86639404296875,
|
| 680 |
+
"rewards/rejected": -24.292346954345703,
|
| 681 |
+
"step": 48
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.06,
|
| 685 |
+
"learning_rate": 2.45e-05,
|
| 686 |
+
"logits/chosen": -0.9694186449050903,
|
| 687 |
+
"logits/rejected": -1.2784701585769653,
|
| 688 |
+
"logps/chosen": -260.8387756347656,
|
| 689 |
+
"logps/rejected": -618.62451171875,
|
| 690 |
+
"loss": 0.1257,
|
| 691 |
+
"rewards/accuracies": 0.9375,
|
| 692 |
+
"rewards/chosen": -6.1030497550964355,
|
| 693 |
+
"rewards/margins": 18.54592514038086,
|
| 694 |
+
"rewards/rejected": -24.648975372314453,
|
| 695 |
+
"step": 49
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.06,
|
| 699 |
+
"learning_rate": 2.5e-05,
|
| 700 |
+
"logits/chosen": -0.9199879765510559,
|
| 701 |
+
"logits/rejected": -1.2466750144958496,
|
| 702 |
+
"logps/chosen": -430.0943603515625,
|
| 703 |
+
"logps/rejected": -720.2520141601562,
|
| 704 |
+
"loss": 0.0001,
|
| 705 |
+
"rewards/accuracies": 1.0,
|
| 706 |
+
"rewards/chosen": -8.701850891113281,
|
| 707 |
+
"rewards/margins": 16.992839813232422,
|
| 708 |
+
"rewards/rejected": -25.694692611694336,
|
| 709 |
+
"step": 50
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.06,
|
| 713 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 714 |
+
"logits/chosen": -0.9574620127677917,
|
| 715 |
+
"logits/rejected": -1.1837575435638428,
|
| 716 |
+
"logps/chosen": -301.4226379394531,
|
| 717 |
+
"logps/rejected": -568.0577392578125,
|
| 718 |
+
"loss": 0.0033,
|
| 719 |
+
"rewards/accuracies": 1.0,
|
| 720 |
+
"rewards/chosen": -6.406881332397461,
|
| 721 |
+
"rewards/margins": 13.906658172607422,
|
| 722 |
+
"rewards/rejected": -20.313539505004883,
|
| 723 |
+
"step": 51
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.06,
|
| 727 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 728 |
+
"logits/chosen": -1.3775969743728638,
|
| 729 |
+
"logits/rejected": -1.1746721267700195,
|
| 730 |
+
"logps/chosen": -292.12841796875,
|
| 731 |
+
"logps/rejected": -541.6993408203125,
|
| 732 |
+
"loss": 0.0143,
|
| 733 |
+
"rewards/accuracies": 1.0,
|
| 734 |
+
"rewards/chosen": -6.582497596740723,
|
| 735 |
+
"rewards/margins": 13.31058120727539,
|
| 736 |
+
"rewards/rejected": -19.893077850341797,
|
| 737 |
+
"step": 52
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.07,
|
| 741 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 742 |
+
"logits/chosen": -1.5340209007263184,
|
| 743 |
+
"logits/rejected": -1.5800985097885132,
|
| 744 |
+
"logps/chosen": -274.92852783203125,
|
| 745 |
+
"logps/rejected": -618.4048461914062,
|
| 746 |
+
"loss": 0.0005,
|
| 747 |
+
"rewards/accuracies": 1.0,
|
| 748 |
+
"rewards/chosen": -6.103458404541016,
|
| 749 |
+
"rewards/margins": 16.42413330078125,
|
| 750 |
+
"rewards/rejected": -22.527591705322266,
|
| 751 |
+
"step": 53
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.07,
|
| 755 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 756 |
+
"logits/chosen": -1.1566357612609863,
|
| 757 |
+
"logits/rejected": -1.3419249057769775,
|
| 758 |
+
"logps/chosen": -266.595458984375,
|
| 759 |
+
"logps/rejected": -609.8141479492188,
|
| 760 |
+
"loss": 0.0001,
|
| 761 |
+
"rewards/accuracies": 1.0,
|
| 762 |
+
"rewards/chosen": -5.4973931312561035,
|
| 763 |
+
"rewards/margins": 17.105182647705078,
|
| 764 |
+
"rewards/rejected": -22.602575302124023,
|
| 765 |
+
"step": 54
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.07,
|
| 769 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 770 |
+
"logits/chosen": -1.1755287647247314,
|
| 771 |
+
"logits/rejected": -1.436917781829834,
|
| 772 |
+
"logps/chosen": -293.0464172363281,
|
| 773 |
+
"logps/rejected": -614.6860961914062,
|
| 774 |
+
"loss": 0.038,
|
| 775 |
+
"rewards/accuracies": 1.0,
|
| 776 |
+
"rewards/chosen": -6.360505104064941,
|
| 777 |
+
"rewards/margins": 17.14010238647461,
|
| 778 |
+
"rewards/rejected": -23.5006103515625,
|
| 779 |
+
"step": 55
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.07,
|
| 783 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 784 |
+
"logits/chosen": -0.9510018825531006,
|
| 785 |
+
"logits/rejected": -1.4989765882492065,
|
| 786 |
+
"logps/chosen": -246.72573852539062,
|
| 787 |
+
"logps/rejected": -593.3004760742188,
|
| 788 |
+
"loss": 0.0019,
|
| 789 |
+
"rewards/accuracies": 1.0,
|
| 790 |
+
"rewards/chosen": -5.071164131164551,
|
| 791 |
+
"rewards/margins": 16.324851989746094,
|
| 792 |
+
"rewards/rejected": -21.396015167236328,
|
| 793 |
+
"step": 56
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.07,
|
| 797 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 798 |
+
"logits/chosen": -0.8883547782897949,
|
| 799 |
+
"logits/rejected": -0.8475340604782104,
|
| 800 |
+
"logps/chosen": -284.69122314453125,
|
| 801 |
+
"logps/rejected": -582.0223999023438,
|
| 802 |
+
"loss": 0.092,
|
| 803 |
+
"rewards/accuracies": 0.9375,
|
| 804 |
+
"rewards/chosen": -5.555781364440918,
|
| 805 |
+
"rewards/margins": 15.147626876831055,
|
| 806 |
+
"rewards/rejected": -20.703407287597656,
|
| 807 |
+
"step": 57
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.07,
|
| 811 |
+
"learning_rate": 2.9e-05,
|
| 812 |
+
"logits/chosen": -1.420696496963501,
|
| 813 |
+
"logits/rejected": -1.3382985591888428,
|
| 814 |
+
"logps/chosen": -223.16297912597656,
|
| 815 |
+
"logps/rejected": -681.352294921875,
|
| 816 |
+
"loss": 0.0027,
|
| 817 |
+
"rewards/accuracies": 1.0,
|
| 818 |
+
"rewards/chosen": -4.9901018142700195,
|
| 819 |
+
"rewards/margins": 20.429107666015625,
|
| 820 |
+
"rewards/rejected": -25.419208526611328,
|
| 821 |
+
"step": 58
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.07,
|
| 825 |
+
"learning_rate": 2.95e-05,
|
| 826 |
+
"logits/chosen": -1.037627100944519,
|
| 827 |
+
"logits/rejected": -1.745126485824585,
|
| 828 |
+
"logps/chosen": -249.64974975585938,
|
| 829 |
+
"logps/rejected": -605.685546875,
|
| 830 |
+
"loss": 0.097,
|
| 831 |
+
"rewards/accuracies": 0.9375,
|
| 832 |
+
"rewards/chosen": -5.2863945960998535,
|
| 833 |
+
"rewards/margins": 16.568225860595703,
|
| 834 |
+
"rewards/rejected": -21.8546199798584,
|
| 835 |
+
"step": 59
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.07,
|
| 839 |
+
"learning_rate": 3e-05,
|
| 840 |
+
"logits/chosen": -1.1528346538543701,
|
| 841 |
+
"logits/rejected": -1.5133743286132812,
|
| 842 |
+
"logps/chosen": -319.42352294921875,
|
| 843 |
+
"logps/rejected": -627.826171875,
|
| 844 |
+
"loss": 0.0002,
|
| 845 |
+
"rewards/accuracies": 1.0,
|
| 846 |
+
"rewards/chosen": -5.5534515380859375,
|
| 847 |
+
"rewards/margins": 16.326492309570312,
|
| 848 |
+
"rewards/rejected": -21.87994384765625,
|
| 849 |
+
"step": 60
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.08,
|
| 853 |
+
"learning_rate": 3.05e-05,
|
| 854 |
+
"logits/chosen": -1.4599294662475586,
|
| 855 |
+
"logits/rejected": -1.4529486894607544,
|
| 856 |
+
"logps/chosen": -292.13299560546875,
|
| 857 |
+
"logps/rejected": -663.6395263671875,
|
| 858 |
+
"loss": 0.0036,
|
| 859 |
+
"rewards/accuracies": 1.0,
|
| 860 |
+
"rewards/chosen": -5.249754905700684,
|
| 861 |
+
"rewards/margins": 16.525672912597656,
|
| 862 |
+
"rewards/rejected": -21.775428771972656,
|
| 863 |
+
"step": 61
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.08,
|
| 867 |
+
"learning_rate": 3.1e-05,
|
| 868 |
+
"logits/chosen": -1.3739594221115112,
|
| 869 |
+
"logits/rejected": -1.441535472869873,
|
| 870 |
+
"logps/chosen": -361.3265380859375,
|
| 871 |
+
"logps/rejected": -623.9736938476562,
|
| 872 |
+
"loss": 0.0001,
|
| 873 |
+
"rewards/accuracies": 1.0,
|
| 874 |
+
"rewards/chosen": -4.781492233276367,
|
| 875 |
+
"rewards/margins": 16.213455200195312,
|
| 876 |
+
"rewards/rejected": -20.99494743347168,
|
| 877 |
+
"step": 62
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.08,
|
| 881 |
+
"learning_rate": 3.15e-05,
|
| 882 |
+
"logits/chosen": -1.0977773666381836,
|
| 883 |
+
"logits/rejected": -1.2894166707992554,
|
| 884 |
+
"logps/chosen": -272.4936828613281,
|
| 885 |
+
"logps/rejected": -633.6181640625,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"rewards/accuracies": 1.0,
|
| 888 |
+
"rewards/chosen": -5.058845520019531,
|
| 889 |
+
"rewards/margins": 18.464832305908203,
|
| 890 |
+
"rewards/rejected": -23.523677825927734,
|
| 891 |
+
"step": 63
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.08,
|
| 895 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 896 |
+
"logits/chosen": -1.8300187587738037,
|
| 897 |
+
"logits/rejected": -1.3356730937957764,
|
| 898 |
+
"logps/chosen": -311.8466796875,
|
| 899 |
+
"logps/rejected": -677.257568359375,
|
| 900 |
+
"loss": 0.0002,
|
| 901 |
+
"rewards/accuracies": 1.0,
|
| 902 |
+
"rewards/chosen": -5.877348899841309,
|
| 903 |
+
"rewards/margins": 16.247228622436523,
|
| 904 |
+
"rewards/rejected": -22.124576568603516,
|
| 905 |
+
"step": 64
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.08,
|
| 909 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 910 |
+
"logits/chosen": -1.6267454624176025,
|
| 911 |
+
"logits/rejected": -1.1310009956359863,
|
| 912 |
+
"logps/chosen": -358.5579833984375,
|
| 913 |
+
"logps/rejected": -641.7317504882812,
|
| 914 |
+
"loss": 0.0001,
|
| 915 |
+
"rewards/accuracies": 1.0,
|
| 916 |
+
"rewards/chosen": -5.5671796798706055,
|
| 917 |
+
"rewards/margins": 15.705550193786621,
|
| 918 |
+
"rewards/rejected": -21.27273178100586,
|
| 919 |
+
"step": 65
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.08,
|
| 923 |
+
"learning_rate": 3.3e-05,
|
| 924 |
+
"logits/chosen": -1.8895033597946167,
|
| 925 |
+
"logits/rejected": -1.6860744953155518,
|
| 926 |
+
"logps/chosen": -486.3850402832031,
|
| 927 |
+
"logps/rejected": -664.045166015625,
|
| 928 |
+
"loss": 0.0,
|
| 929 |
+
"rewards/accuracies": 1.0,
|
| 930 |
+
"rewards/chosen": -5.0797834396362305,
|
| 931 |
+
"rewards/margins": 13.979126930236816,
|
| 932 |
+
"rewards/rejected": -19.058910369873047,
|
| 933 |
+
"step": 66
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.08,
|
| 937 |
+
"learning_rate": 3.35e-05,
|
| 938 |
+
"logits/chosen": -1.836645483970642,
|
| 939 |
+
"logits/rejected": -1.4774869680404663,
|
| 940 |
+
"logps/chosen": -261.5281982421875,
|
| 941 |
+
"logps/rejected": -621.8162841796875,
|
| 942 |
+
"loss": 0.0011,
|
| 943 |
+
"rewards/accuracies": 1.0,
|
| 944 |
+
"rewards/chosen": -4.790907382965088,
|
| 945 |
+
"rewards/margins": 14.66439437866211,
|
| 946 |
+
"rewards/rejected": -19.45530128479004,
|
| 947 |
+
"step": 67
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.08,
|
| 951 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 952 |
+
"logits/chosen": -1.4897315502166748,
|
| 953 |
+
"logits/rejected": -1.2426286935806274,
|
| 954 |
+
"logps/chosen": -225.94337463378906,
|
| 955 |
+
"logps/rejected": -547.6304321289062,
|
| 956 |
+
"loss": 0.0002,
|
| 957 |
+
"rewards/accuracies": 1.0,
|
| 958 |
+
"rewards/chosen": -4.037389755249023,
|
| 959 |
+
"rewards/margins": 13.804460525512695,
|
| 960 |
+
"rewards/rejected": -17.84185028076172,
|
| 961 |
+
"step": 68
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.09,
|
| 965 |
+
"learning_rate": 3.45e-05,
|
| 966 |
+
"logits/chosen": -1.3410481214523315,
|
| 967 |
+
"logits/rejected": -1.2696239948272705,
|
| 968 |
+
"logps/chosen": -220.23153686523438,
|
| 969 |
+
"logps/rejected": -545.1270751953125,
|
| 970 |
+
"loss": 0.0035,
|
| 971 |
+
"rewards/accuracies": 1.0,
|
| 972 |
+
"rewards/chosen": -4.0619893074035645,
|
| 973 |
+
"rewards/margins": 14.104720115661621,
|
| 974 |
+
"rewards/rejected": -18.166709899902344,
|
| 975 |
+
"step": 69
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.09,
|
| 979 |
+
"learning_rate": 3.5e-05,
|
| 980 |
+
"logits/chosen": -1.1692075729370117,
|
| 981 |
+
"logits/rejected": -1.4098597764968872,
|
| 982 |
+
"logps/chosen": -291.9318542480469,
|
| 983 |
+
"logps/rejected": -606.8259887695312,
|
| 984 |
+
"loss": 0.037,
|
| 985 |
+
"rewards/accuracies": 1.0,
|
| 986 |
+
"rewards/chosen": -4.749131679534912,
|
| 987 |
+
"rewards/margins": 13.3434476852417,
|
| 988 |
+
"rewards/rejected": -18.09257698059082,
|
| 989 |
+
"step": 70
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.09,
|
| 993 |
+
"learning_rate": 3.55e-05,
|
| 994 |
+
"logits/chosen": -1.291015386581421,
|
| 995 |
+
"logits/rejected": -1.0744752883911133,
|
| 996 |
+
"logps/chosen": -235.30746459960938,
|
| 997 |
+
"logps/rejected": -571.0240478515625,
|
| 998 |
+
"loss": 0.0002,
|
| 999 |
+
"rewards/accuracies": 1.0,
|
| 1000 |
+
"rewards/chosen": -3.615610122680664,
|
| 1001 |
+
"rewards/margins": 14.394880294799805,
|
| 1002 |
+
"rewards/rejected": -18.01049041748047,
|
| 1003 |
+
"step": 71
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.09,
|
| 1007 |
+
"learning_rate": 3.6e-05,
|
| 1008 |
+
"logits/chosen": -1.3118032217025757,
|
| 1009 |
+
"logits/rejected": -1.3245186805725098,
|
| 1010 |
+
"logps/chosen": -278.8104248046875,
|
| 1011 |
+
"logps/rejected": -621.2532958984375,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"rewards/accuracies": 1.0,
|
| 1014 |
+
"rewards/chosen": -4.277045249938965,
|
| 1015 |
+
"rewards/margins": 17.554424285888672,
|
| 1016 |
+
"rewards/rejected": -21.831466674804688,
|
| 1017 |
+
"step": 72
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.09,
|
| 1021 |
+
"learning_rate": 3.65e-05,
|
| 1022 |
+
"logits/chosen": -1.5896751880645752,
|
| 1023 |
+
"logits/rejected": -1.3609411716461182,
|
| 1024 |
+
"logps/chosen": -243.6151123046875,
|
| 1025 |
+
"logps/rejected": -572.5302124023438,
|
| 1026 |
+
"loss": 0.0006,
|
| 1027 |
+
"rewards/accuracies": 1.0,
|
| 1028 |
+
"rewards/chosen": -4.514758110046387,
|
| 1029 |
+
"rewards/margins": 12.668429374694824,
|
| 1030 |
+
"rewards/rejected": -17.183185577392578,
|
| 1031 |
+
"step": 73
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.09,
|
| 1035 |
+
"learning_rate": 3.7e-05,
|
| 1036 |
+
"logits/chosen": -1.431384801864624,
|
| 1037 |
+
"logits/rejected": -1.5531063079833984,
|
| 1038 |
+
"logps/chosen": -306.5356750488281,
|
| 1039 |
+
"logps/rejected": -600.71484375,
|
| 1040 |
+
"loss": 0.0001,
|
| 1041 |
+
"rewards/accuracies": 1.0,
|
| 1042 |
+
"rewards/chosen": -4.694637298583984,
|
| 1043 |
+
"rewards/margins": 18.718229293823242,
|
| 1044 |
+
"rewards/rejected": -23.412864685058594,
|
| 1045 |
+
"step": 74
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.09,
|
| 1049 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1050 |
+
"logits/chosen": -1.557645559310913,
|
| 1051 |
+
"logits/rejected": -1.5208816528320312,
|
| 1052 |
+
"logps/chosen": -258.01324462890625,
|
| 1053 |
+
"logps/rejected": -619.49462890625,
|
| 1054 |
+
"loss": 0.0005,
|
| 1055 |
+
"rewards/accuracies": 1.0,
|
| 1056 |
+
"rewards/chosen": -5.0902862548828125,
|
| 1057 |
+
"rewards/margins": 15.939676284790039,
|
| 1058 |
+
"rewards/rejected": -21.029964447021484,
|
| 1059 |
+
"step": 75
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.09,
|
| 1063 |
+
"learning_rate": 3.8e-05,
|
| 1064 |
+
"logits/chosen": -1.0553147792816162,
|
| 1065 |
+
"logits/rejected": -1.5524070262908936,
|
| 1066 |
+
"logps/chosen": -309.97412109375,
|
| 1067 |
+
"logps/rejected": -524.318603515625,
|
| 1068 |
+
"loss": 0.0002,
|
| 1069 |
+
"rewards/accuracies": 1.0,
|
| 1070 |
+
"rewards/chosen": -4.439201354980469,
|
| 1071 |
+
"rewards/margins": 13.217429161071777,
|
| 1072 |
+
"rewards/rejected": -17.656631469726562,
|
| 1073 |
+
"step": 76
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.1,
|
| 1077 |
+
"learning_rate": 3.85e-05,
|
| 1078 |
+
"logits/chosen": -1.3808860778808594,
|
| 1079 |
+
"logits/rejected": -1.490052342414856,
|
| 1080 |
+
"logps/chosen": -249.54974365234375,
|
| 1081 |
+
"logps/rejected": -647.080078125,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"rewards/accuracies": 1.0,
|
| 1084 |
+
"rewards/chosen": -5.671748161315918,
|
| 1085 |
+
"rewards/margins": 17.54851531982422,
|
| 1086 |
+
"rewards/rejected": -23.220260620117188,
|
| 1087 |
+
"step": 77
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.1,
|
| 1091 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 1092 |
+
"logits/chosen": -1.6017792224884033,
|
| 1093 |
+
"logits/rejected": -1.437800407409668,
|
| 1094 |
+
"logps/chosen": -270.47894287109375,
|
| 1095 |
+
"logps/rejected": -523.1994018554688,
|
| 1096 |
+
"loss": 0.0107,
|
| 1097 |
+
"rewards/accuracies": 1.0,
|
| 1098 |
+
"rewards/chosen": -5.677766799926758,
|
| 1099 |
+
"rewards/margins": 13.664579391479492,
|
| 1100 |
+
"rewards/rejected": -19.34234619140625,
|
| 1101 |
+
"step": 78
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.1,
|
| 1105 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 1106 |
+
"logits/chosen": -1.7644150257110596,
|
| 1107 |
+
"logits/rejected": -1.1649854183197021,
|
| 1108 |
+
"logps/chosen": -352.513671875,
|
| 1109 |
+
"logps/rejected": -660.660888671875,
|
| 1110 |
+
"loss": 0.0002,
|
| 1111 |
+
"rewards/accuracies": 1.0,
|
| 1112 |
+
"rewards/chosen": -6.161036968231201,
|
| 1113 |
+
"rewards/margins": 15.742412567138672,
|
| 1114 |
+
"rewards/rejected": -21.90345001220703,
|
| 1115 |
+
"step": 79
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.1,
|
| 1119 |
+
"learning_rate": 4e-05,
|
| 1120 |
+
"logits/chosen": -1.7110097408294678,
|
| 1121 |
+
"logits/rejected": -1.4986464977264404,
|
| 1122 |
+
"logps/chosen": -285.781005859375,
|
| 1123 |
+
"logps/rejected": -601.8524780273438,
|
| 1124 |
+
"loss": 0.0002,
|
| 1125 |
+
"rewards/accuracies": 1.0,
|
| 1126 |
+
"rewards/chosen": -6.4479594230651855,
|
| 1127 |
+
"rewards/margins": 17.196250915527344,
|
| 1128 |
+
"rewards/rejected": -23.644210815429688,
|
| 1129 |
+
"step": 80
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.1,
|
| 1133 |
+
"learning_rate": 4.05e-05,
|
| 1134 |
+
"logits/chosen": -1.5364179611206055,
|
| 1135 |
+
"logits/rejected": -1.5603926181793213,
|
| 1136 |
+
"logps/chosen": -205.1665802001953,
|
| 1137 |
+
"logps/rejected": -514.8365478515625,
|
| 1138 |
+
"loss": 0.0004,
|
| 1139 |
+
"rewards/accuracies": 1.0,
|
| 1140 |
+
"rewards/chosen": -5.383946418762207,
|
| 1141 |
+
"rewards/margins": 13.479593276977539,
|
| 1142 |
+
"rewards/rejected": -18.863540649414062,
|
| 1143 |
+
"step": 81
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.1,
|
| 1147 |
+
"learning_rate": 4.1e-05,
|
| 1148 |
+
"logits/chosen": -1.2903649806976318,
|
| 1149 |
+
"logits/rejected": -1.077599287033081,
|
| 1150 |
+
"logps/chosen": -240.99749755859375,
|
| 1151 |
+
"logps/rejected": -672.7728271484375,
|
| 1152 |
+
"loss": 0.0001,
|
| 1153 |
+
"rewards/accuracies": 1.0,
|
| 1154 |
+
"rewards/chosen": -5.660610675811768,
|
| 1155 |
+
"rewards/margins": 18.02043914794922,
|
| 1156 |
+
"rewards/rejected": -23.681049346923828,
|
| 1157 |
+
"step": 82
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.1,
|
| 1161 |
+
"learning_rate": 4.15e-05,
|
| 1162 |
+
"logits/chosen": -1.2030022144317627,
|
| 1163 |
+
"logits/rejected": -1.4182593822479248,
|
| 1164 |
+
"logps/chosen": -302.1430358886719,
|
| 1165 |
+
"logps/rejected": -677.5120849609375,
|
| 1166 |
+
"loss": 0.0056,
|
| 1167 |
+
"rewards/accuracies": 1.0,
|
| 1168 |
+
"rewards/chosen": -6.275785446166992,
|
| 1169 |
+
"rewards/margins": 16.768428802490234,
|
| 1170 |
+
"rewards/rejected": -23.044212341308594,
|
| 1171 |
+
"step": 83
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.1,
|
| 1175 |
+
"learning_rate": 4.2e-05,
|
| 1176 |
+
"logits/chosen": -1.459336519241333,
|
| 1177 |
+
"logits/rejected": -1.0312726497650146,
|
| 1178 |
+
"logps/chosen": -303.3758544921875,
|
| 1179 |
+
"logps/rejected": -617.7279052734375,
|
| 1180 |
+
"loss": 0.0002,
|
| 1181 |
+
"rewards/accuracies": 1.0,
|
| 1182 |
+
"rewards/chosen": -7.219513416290283,
|
| 1183 |
+
"rewards/margins": 14.163326263427734,
|
| 1184 |
+
"rewards/rejected": -21.38283920288086,
|
| 1185 |
+
"step": 84
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.11,
|
| 1189 |
+
"learning_rate": 4.25e-05,
|
| 1190 |
+
"logits/chosen": -1.6425917148590088,
|
| 1191 |
+
"logits/rejected": -1.1666898727416992,
|
| 1192 |
+
"logps/chosen": -349.3736267089844,
|
| 1193 |
+
"logps/rejected": -678.3955078125,
|
| 1194 |
+
"loss": 0.0,
|
| 1195 |
+
"rewards/accuracies": 1.0,
|
| 1196 |
+
"rewards/chosen": -7.792992115020752,
|
| 1197 |
+
"rewards/margins": 19.550434112548828,
|
| 1198 |
+
"rewards/rejected": -27.343425750732422,
|
| 1199 |
+
"step": 85
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.11,
|
| 1203 |
+
"learning_rate": 4.3e-05,
|
| 1204 |
+
"logits/chosen": -1.159060001373291,
|
| 1205 |
+
"logits/rejected": -1.2317029237747192,
|
| 1206 |
+
"logps/chosen": -377.60040283203125,
|
| 1207 |
+
"logps/rejected": -658.4701538085938,
|
| 1208 |
+
"loss": 0.0001,
|
| 1209 |
+
"rewards/accuracies": 1.0,
|
| 1210 |
+
"rewards/chosen": -8.494105339050293,
|
| 1211 |
+
"rewards/margins": 16.188596725463867,
|
| 1212 |
+
"rewards/rejected": -24.682701110839844,
|
| 1213 |
+
"step": 86
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.11,
|
| 1217 |
+
"learning_rate": 4.35e-05,
|
| 1218 |
+
"logits/chosen": -1.5545859336853027,
|
| 1219 |
+
"logits/rejected": -1.2424968481063843,
|
| 1220 |
+
"logps/chosen": -332.1812744140625,
|
| 1221 |
+
"logps/rejected": -686.550537109375,
|
| 1222 |
+
"loss": 0.0002,
|
| 1223 |
+
"rewards/accuracies": 1.0,
|
| 1224 |
+
"rewards/chosen": -7.362907409667969,
|
| 1225 |
+
"rewards/margins": 18.219987869262695,
|
| 1226 |
+
"rewards/rejected": -25.58289337158203,
|
| 1227 |
+
"step": 87
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.11,
|
| 1231 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 1232 |
+
"logits/chosen": -1.329568862915039,
|
| 1233 |
+
"logits/rejected": -1.5836312770843506,
|
| 1234 |
+
"logps/chosen": -344.522705078125,
|
| 1235 |
+
"logps/rejected": -663.6416015625,
|
| 1236 |
+
"loss": 0.0001,
|
| 1237 |
+
"rewards/accuracies": 1.0,
|
| 1238 |
+
"rewards/chosen": -8.556987762451172,
|
| 1239 |
+
"rewards/margins": 16.531614303588867,
|
| 1240 |
+
"rewards/rejected": -25.08860206604004,
|
| 1241 |
+
"step": 88
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.11,
|
| 1245 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 1246 |
+
"logits/chosen": -0.9687823057174683,
|
| 1247 |
+
"logits/rejected": -1.0615956783294678,
|
| 1248 |
+
"logps/chosen": -248.99139404296875,
|
| 1249 |
+
"logps/rejected": -666.9677734375,
|
| 1250 |
+
"loss": 0.0001,
|
| 1251 |
+
"rewards/accuracies": 1.0,
|
| 1252 |
+
"rewards/chosen": -7.284422874450684,
|
| 1253 |
+
"rewards/margins": 18.494182586669922,
|
| 1254 |
+
"rewards/rejected": -25.778606414794922,
|
| 1255 |
+
"step": 89
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.11,
|
| 1259 |
+
"learning_rate": 4.5e-05,
|
| 1260 |
+
"logits/chosen": -1.5608181953430176,
|
| 1261 |
+
"logits/rejected": -1.603400707244873,
|
| 1262 |
+
"logps/chosen": -406.6678161621094,
|
| 1263 |
+
"logps/rejected": -738.91015625,
|
| 1264 |
+
"loss": 0.0006,
|
| 1265 |
+
"rewards/accuracies": 1.0,
|
| 1266 |
+
"rewards/chosen": -8.280235290527344,
|
| 1267 |
+
"rewards/margins": 20.654300689697266,
|
| 1268 |
+
"rewards/rejected": -28.93453598022461,
|
| 1269 |
+
"step": 90
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.11,
|
| 1273 |
+
"learning_rate": 4.55e-05,
|
| 1274 |
+
"logits/chosen": -1.1856168508529663,
|
| 1275 |
+
"logits/rejected": -1.2493767738342285,
|
| 1276 |
+
"logps/chosen": -248.82559204101562,
|
| 1277 |
+
"logps/rejected": -637.666259765625,
|
| 1278 |
+
"loss": 0.0007,
|
| 1279 |
+
"rewards/accuracies": 1.0,
|
| 1280 |
+
"rewards/chosen": -6.917981147766113,
|
| 1281 |
+
"rewards/margins": 18.320941925048828,
|
| 1282 |
+
"rewards/rejected": -25.238922119140625,
|
| 1283 |
+
"step": 91
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.11,
|
| 1287 |
+
"learning_rate": 4.600000000000001e-05,
|
| 1288 |
+
"logits/chosen": -1.4266817569732666,
|
| 1289 |
+
"logits/rejected": -1.3622314929962158,
|
| 1290 |
+
"logps/chosen": -236.7372283935547,
|
| 1291 |
+
"logps/rejected": -677.9640502929688,
|
| 1292 |
+
"loss": 0.0001,
|
| 1293 |
+
"rewards/accuracies": 1.0,
|
| 1294 |
+
"rewards/chosen": -7.995168685913086,
|
| 1295 |
+
"rewards/margins": 21.01068687438965,
|
| 1296 |
+
"rewards/rejected": -29.005855560302734,
|
| 1297 |
+
"step": 92
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.12,
|
| 1301 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 1302 |
+
"logits/chosen": -1.1082837581634521,
|
| 1303 |
+
"logits/rejected": -1.383658528327942,
|
| 1304 |
+
"logps/chosen": -314.92681884765625,
|
| 1305 |
+
"logps/rejected": -658.524169921875,
|
| 1306 |
+
"loss": 0.0,
|
| 1307 |
+
"rewards/accuracies": 1.0,
|
| 1308 |
+
"rewards/chosen": -9.042872428894043,
|
| 1309 |
+
"rewards/margins": 17.163429260253906,
|
| 1310 |
+
"rewards/rejected": -26.206302642822266,
|
| 1311 |
+
"step": 93
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.12,
|
| 1315 |
+
"learning_rate": 4.7e-05,
|
| 1316 |
+
"logits/chosen": -1.5014522075653076,
|
| 1317 |
+
"logits/rejected": -1.7101225852966309,
|
| 1318 |
+
"logps/chosen": -260.1839904785156,
|
| 1319 |
+
"logps/rejected": -683.700927734375,
|
| 1320 |
+
"loss": 0.0,
|
| 1321 |
+
"rewards/accuracies": 1.0,
|
| 1322 |
+
"rewards/chosen": -9.463061332702637,
|
| 1323 |
+
"rewards/margins": 17.54586410522461,
|
| 1324 |
+
"rewards/rejected": -27.008926391601562,
|
| 1325 |
+
"step": 94
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.12,
|
| 1329 |
+
"learning_rate": 4.75e-05,
|
| 1330 |
+
"logits/chosen": -1.5970165729522705,
|
| 1331 |
+
"logits/rejected": -1.3586769104003906,
|
| 1332 |
+
"logps/chosen": -318.0454406738281,
|
| 1333 |
+
"logps/rejected": -684.9884033203125,
|
| 1334 |
+
"loss": 0.0,
|
| 1335 |
+
"rewards/accuracies": 1.0,
|
| 1336 |
+
"rewards/chosen": -9.960655212402344,
|
| 1337 |
+
"rewards/margins": 20.025028228759766,
|
| 1338 |
+
"rewards/rejected": -29.985679626464844,
|
| 1339 |
+
"step": 95
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.12,
|
| 1343 |
+
"learning_rate": 4.8e-05,
|
| 1344 |
+
"logits/chosen": -1.1033860445022583,
|
| 1345 |
+
"logits/rejected": -0.8102812767028809,
|
| 1346 |
+
"logps/chosen": -301.2135925292969,
|
| 1347 |
+
"logps/rejected": -720.0145263671875,
|
| 1348 |
+
"loss": 0.0,
|
| 1349 |
+
"rewards/accuracies": 1.0,
|
| 1350 |
+
"rewards/chosen": -8.136268615722656,
|
| 1351 |
+
"rewards/margins": 20.93104362487793,
|
| 1352 |
+
"rewards/rejected": -29.067312240600586,
|
| 1353 |
+
"step": 96
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.12,
|
| 1357 |
+
"learning_rate": 4.85e-05,
|
| 1358 |
+
"logits/chosen": -1.1413370370864868,
|
| 1359 |
+
"logits/rejected": -0.9585047960281372,
|
| 1360 |
+
"logps/chosen": -329.30133056640625,
|
| 1361 |
+
"logps/rejected": -630.4498291015625,
|
| 1362 |
+
"loss": 0.0,
|
| 1363 |
+
"rewards/accuracies": 1.0,
|
| 1364 |
+
"rewards/chosen": -9.226066589355469,
|
| 1365 |
+
"rewards/margins": 16.47555923461914,
|
| 1366 |
+
"rewards/rejected": -25.70162582397461,
|
| 1367 |
+
"step": 97
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.12,
|
| 1371 |
+
"learning_rate": 4.9e-05,
|
| 1372 |
+
"logits/chosen": -1.5005364418029785,
|
| 1373 |
+
"logits/rejected": -1.1674431562423706,
|
| 1374 |
+
"logps/chosen": -264.9545593261719,
|
| 1375 |
+
"logps/rejected": -639.041259765625,
|
| 1376 |
+
"loss": 0.0,
|
| 1377 |
+
"rewards/accuracies": 1.0,
|
| 1378 |
+
"rewards/chosen": -8.097036361694336,
|
| 1379 |
+
"rewards/margins": 17.606611251831055,
|
| 1380 |
+
"rewards/rejected": -25.70364761352539,
|
| 1381 |
+
"step": 98
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.12,
|
| 1385 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 1386 |
+
"logits/chosen": -1.181979775428772,
|
| 1387 |
+
"logits/rejected": -1.1194593906402588,
|
| 1388 |
+
"logps/chosen": -295.6553955078125,
|
| 1389 |
+
"logps/rejected": -625.8030395507812,
|
| 1390 |
+
"loss": 0.0,
|
| 1391 |
+
"rewards/accuracies": 1.0,
|
| 1392 |
+
"rewards/chosen": -7.671294212341309,
|
| 1393 |
+
"rewards/margins": 18.466283798217773,
|
| 1394 |
+
"rewards/rejected": -26.1375789642334,
|
| 1395 |
+
"step": 99
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.12,
|
| 1399 |
+
"learning_rate": 5e-05,
|
| 1400 |
+
"logits/chosen": -1.6407731771469116,
|
| 1401 |
+
"logits/rejected": -1.7556546926498413,
|
| 1402 |
+
"logps/chosen": -251.4920654296875,
|
| 1403 |
+
"logps/rejected": -707.2771606445312,
|
| 1404 |
+
"loss": 0.0,
|
| 1405 |
+
"rewards/accuracies": 1.0,
|
| 1406 |
+
"rewards/chosen": -9.03681468963623,
|
| 1407 |
+
"rewards/margins": 19.950708389282227,
|
| 1408 |
+
"rewards/rejected": -28.98752212524414,
|
| 1409 |
+
"step": 100
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.13,
|
| 1413 |
+
"learning_rate": 4.998766400914329e-05,
|
| 1414 |
+
"logits/chosen": -1.49093496799469,
|
| 1415 |
+
"logits/rejected": -1.454042673110962,
|
| 1416 |
+
"logps/chosen": -401.38555908203125,
|
| 1417 |
+
"logps/rejected": -656.6805419921875,
|
| 1418 |
+
"loss": 0.0004,
|
| 1419 |
+
"rewards/accuracies": 1.0,
|
| 1420 |
+
"rewards/chosen": -9.029119491577148,
|
| 1421 |
+
"rewards/margins": 17.11648941040039,
|
| 1422 |
+
"rewards/rejected": -26.14560890197754,
|
| 1423 |
+
"step": 101
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.13,
|
| 1427 |
+
"learning_rate": 4.995066821070679e-05,
|
| 1428 |
+
"logits/chosen": -1.1679431200027466,
|
| 1429 |
+
"logits/rejected": -1.1486090421676636,
|
| 1430 |
+
"logps/chosen": -378.21893310546875,
|
| 1431 |
+
"logps/rejected": -720.4594116210938,
|
| 1432 |
+
"loss": 0.0,
|
| 1433 |
+
"rewards/accuracies": 1.0,
|
| 1434 |
+
"rewards/chosen": -9.716445922851562,
|
| 1435 |
+
"rewards/margins": 19.0845947265625,
|
| 1436 |
+
"rewards/rejected": -28.801040649414062,
|
| 1437 |
+
"step": 102
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.13,
|
| 1441 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 1442 |
+
"logits/chosen": -1.0046123266220093,
|
| 1443 |
+
"logits/rejected": -1.2339215278625488,
|
| 1444 |
+
"logps/chosen": -258.95635986328125,
|
| 1445 |
+
"logps/rejected": -639.7680053710938,
|
| 1446 |
+
"loss": 0.0002,
|
| 1447 |
+
"rewards/accuracies": 1.0,
|
| 1448 |
+
"rewards/chosen": -8.76823902130127,
|
| 1449 |
+
"rewards/margins": 18.9598388671875,
|
| 1450 |
+
"rewards/rejected": -27.728076934814453,
|
| 1451 |
+
"step": 103
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.13,
|
| 1455 |
+
"learning_rate": 4.980286753286195e-05,
|
| 1456 |
+
"logits/chosen": -0.9866207242012024,
|
| 1457 |
+
"logits/rejected": -1.2342731952667236,
|
| 1458 |
+
"logps/chosen": -353.4874267578125,
|
| 1459 |
+
"logps/rejected": -652.6710205078125,
|
| 1460 |
+
"loss": 0.0,
|
| 1461 |
+
"rewards/accuracies": 1.0,
|
| 1462 |
+
"rewards/chosen": -8.72028923034668,
|
| 1463 |
+
"rewards/margins": 18.17083740234375,
|
| 1464 |
+
"rewards/rejected": -26.891128540039062,
|
| 1465 |
+
"step": 104
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.13,
|
| 1469 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 1470 |
+
"logits/chosen": -1.644493818283081,
|
| 1471 |
+
"logits/rejected": -1.3671150207519531,
|
| 1472 |
+
"logps/chosen": -407.6358337402344,
|
| 1473 |
+
"logps/rejected": -680.9503784179688,
|
| 1474 |
+
"loss": 0.0001,
|
| 1475 |
+
"rewards/accuracies": 1.0,
|
| 1476 |
+
"rewards/chosen": -9.58061408996582,
|
| 1477 |
+
"rewards/margins": 16.537212371826172,
|
| 1478 |
+
"rewards/rejected": -26.117826461791992,
|
| 1479 |
+
"step": 105
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.13,
|
| 1483 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 1484 |
+
"logits/chosen": -1.3883347511291504,
|
| 1485 |
+
"logits/rejected": -1.1226028203964233,
|
| 1486 |
+
"logps/chosen": -298.3403625488281,
|
| 1487 |
+
"logps/rejected": -661.0068969726562,
|
| 1488 |
+
"loss": 0.0,
|
| 1489 |
+
"rewards/accuracies": 1.0,
|
| 1490 |
+
"rewards/chosen": -8.479090690612793,
|
| 1491 |
+
"rewards/margins": 19.53042984008789,
|
| 1492 |
+
"rewards/rejected": -28.009523391723633,
|
| 1493 |
+
"step": 106
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.13,
|
| 1497 |
+
"learning_rate": 4.939791904846869e-05,
|
| 1498 |
+
"logits/chosen": -1.2119803428649902,
|
| 1499 |
+
"logits/rejected": -1.5936832427978516,
|
| 1500 |
+
"logps/chosen": -269.82684326171875,
|
| 1501 |
+
"logps/rejected": -645.09619140625,
|
| 1502 |
+
"loss": 0.0,
|
| 1503 |
+
"rewards/accuracies": 1.0,
|
| 1504 |
+
"rewards/chosen": -8.107880592346191,
|
| 1505 |
+
"rewards/margins": 20.64764976501465,
|
| 1506 |
+
"rewards/rejected": -28.755531311035156,
|
| 1507 |
+
"step": 107
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.13,
|
| 1511 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 1512 |
+
"logits/chosen": -1.2132232189178467,
|
| 1513 |
+
"logits/rejected": -1.3179054260253906,
|
| 1514 |
+
"logps/chosen": -438.98321533203125,
|
| 1515 |
+
"logps/rejected": -713.7950439453125,
|
| 1516 |
+
"loss": 0.0,
|
| 1517 |
+
"rewards/accuracies": 1.0,
|
| 1518 |
+
"rewards/chosen": -10.158727645874023,
|
| 1519 |
+
"rewards/margins": 17.90839958190918,
|
| 1520 |
+
"rewards/rejected": -28.06713104248047,
|
| 1521 |
+
"step": 108
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.14,
|
| 1525 |
+
"learning_rate": 4.900734214192358e-05,
|
| 1526 |
+
"logits/chosen": -1.0279672145843506,
|
| 1527 |
+
"logits/rejected": -0.8536261320114136,
|
| 1528 |
+
"logps/chosen": -382.6248779296875,
|
| 1529 |
+
"logps/rejected": -738.4147338867188,
|
| 1530 |
+
"loss": 0.0034,
|
| 1531 |
+
"rewards/accuracies": 1.0,
|
| 1532 |
+
"rewards/chosen": -8.301639556884766,
|
| 1533 |
+
"rewards/margins": 20.556997299194336,
|
| 1534 |
+
"rewards/rejected": -28.858638763427734,
|
| 1535 |
+
"step": 109
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.14,
|
| 1539 |
+
"learning_rate": 4.877641290737884e-05,
|
| 1540 |
+
"logits/chosen": -1.1681768894195557,
|
| 1541 |
+
"logits/rejected": -0.6321386694908142,
|
| 1542 |
+
"logps/chosen": -295.9759521484375,
|
| 1543 |
+
"logps/rejected": -673.0234375,
|
| 1544 |
+
"loss": 0.0168,
|
| 1545 |
+
"rewards/accuracies": 1.0,
|
| 1546 |
+
"rewards/chosen": -10.42588996887207,
|
| 1547 |
+
"rewards/margins": 17.69922637939453,
|
| 1548 |
+
"rewards/rejected": -28.12511444091797,
|
| 1549 |
+
"step": 110
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.14,
|
| 1553 |
+
"learning_rate": 4.852201922385564e-05,
|
| 1554 |
+
"logits/chosen": -0.6276636123657227,
|
| 1555 |
+
"logits/rejected": -0.6425186991691589,
|
| 1556 |
+
"logps/chosen": -268.58050537109375,
|
| 1557 |
+
"logps/rejected": -601.134033203125,
|
| 1558 |
+
"loss": 0.0005,
|
| 1559 |
+
"rewards/accuracies": 1.0,
|
| 1560 |
+
"rewards/chosen": -6.623042583465576,
|
| 1561 |
+
"rewards/margins": 20.134323120117188,
|
| 1562 |
+
"rewards/rejected": -26.75736427307129,
|
| 1563 |
+
"step": 111
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.14,
|
| 1567 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1568 |
+
"logits/chosen": -1.298043966293335,
|
| 1569 |
+
"logits/rejected": -1.8934366703033447,
|
| 1570 |
+
"logps/chosen": -363.50616455078125,
|
| 1571 |
+
"logps/rejected": -793.5181274414062,
|
| 1572 |
+
"loss": 0.0,
|
| 1573 |
+
"rewards/accuracies": 1.0,
|
| 1574 |
+
"rewards/chosen": -9.013703346252441,
|
| 1575 |
+
"rewards/margins": 21.266841888427734,
|
| 1576 |
+
"rewards/rejected": -30.28054428100586,
|
| 1577 |
+
"step": 112
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.14,
|
| 1581 |
+
"learning_rate": 4.794386564209953e-05,
|
| 1582 |
+
"logits/chosen": -1.3218209743499756,
|
| 1583 |
+
"logits/rejected": -0.8168056011199951,
|
| 1584 |
+
"logps/chosen": -306.5829772949219,
|
| 1585 |
+
"logps/rejected": -696.270263671875,
|
| 1586 |
+
"loss": 0.0,
|
| 1587 |
+
"rewards/accuracies": 1.0,
|
| 1588 |
+
"rewards/chosen": -7.502519607543945,
|
| 1589 |
+
"rewards/margins": 23.955406188964844,
|
| 1590 |
+
"rewards/rejected": -31.457927703857422,
|
| 1591 |
+
"step": 113
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.14,
|
| 1595 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1596 |
+
"logits/chosen": -1.1450629234313965,
|
| 1597 |
+
"logits/rejected": -1.393950343132019,
|
| 1598 |
+
"logps/chosen": -376.8450622558594,
|
| 1599 |
+
"logps/rejected": -673.3822631835938,
|
| 1600 |
+
"loss": 0.0,
|
| 1601 |
+
"rewards/accuracies": 1.0,
|
| 1602 |
+
"rewards/chosen": -9.097296714782715,
|
| 1603 |
+
"rewards/margins": 18.731908798217773,
|
| 1604 |
+
"rewards/rejected": -27.829204559326172,
|
| 1605 |
+
"step": 114
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.14,
|
| 1609 |
+
"learning_rate": 4.72751631047092e-05,
|
| 1610 |
+
"logits/chosen": -1.3087085485458374,
|
| 1611 |
+
"logits/rejected": -1.6303530931472778,
|
| 1612 |
+
"logps/chosen": -272.7848205566406,
|
| 1613 |
+
"logps/rejected": -697.6502685546875,
|
| 1614 |
+
"loss": 0.0,
|
| 1615 |
+
"rewards/accuracies": 1.0,
|
| 1616 |
+
"rewards/chosen": -7.2123308181762695,
|
| 1617 |
+
"rewards/margins": 22.104957580566406,
|
| 1618 |
+
"rewards/rejected": -29.31728744506836,
|
| 1619 |
+
"step": 115
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.14,
|
| 1623 |
+
"learning_rate": 4.690766700109659e-05,
|
| 1624 |
+
"logits/chosen": -1.3388525247573853,
|
| 1625 |
+
"logits/rejected": -1.523690938949585,
|
| 1626 |
+
"logps/chosen": -281.05694580078125,
|
| 1627 |
+
"logps/rejected": -593.7879028320312,
|
| 1628 |
+
"loss": 0.0035,
|
| 1629 |
+
"rewards/accuracies": 1.0,
|
| 1630 |
+
"rewards/chosen": -5.953818321228027,
|
| 1631 |
+
"rewards/margins": 17.667112350463867,
|
| 1632 |
+
"rewards/rejected": -23.620929718017578,
|
| 1633 |
+
"step": 116
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.15,
|
| 1637 |
+
"learning_rate": 4.65185506750986e-05,
|
| 1638 |
+
"logits/chosen": -1.3922251462936401,
|
| 1639 |
+
"logits/rejected": -1.2891855239868164,
|
| 1640 |
+
"logps/chosen": -322.259765625,
|
| 1641 |
+
"logps/rejected": -654.0626220703125,
|
| 1642 |
+
"loss": 0.0001,
|
| 1643 |
+
"rewards/accuracies": 1.0,
|
| 1644 |
+
"rewards/chosen": -6.73513126373291,
|
| 1645 |
+
"rewards/margins": 19.120628356933594,
|
| 1646 |
+
"rewards/rejected": -25.855758666992188,
|
| 1647 |
+
"step": 117
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.15,
|
| 1651 |
+
"learning_rate": 4.610819813755038e-05,
|
| 1652 |
+
"logits/chosen": -1.0762147903442383,
|
| 1653 |
+
"logits/rejected": -1.2459900379180908,
|
| 1654 |
+
"logps/chosen": -339.0086364746094,
|
| 1655 |
+
"logps/rejected": -729.5966796875,
|
| 1656 |
+
"loss": 0.0,
|
| 1657 |
+
"rewards/accuracies": 1.0,
|
| 1658 |
+
"rewards/chosen": -7.075998306274414,
|
| 1659 |
+
"rewards/margins": 22.65298843383789,
|
| 1660 |
+
"rewards/rejected": -29.728988647460938,
|
| 1661 |
+
"step": 118
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.15,
|
| 1665 |
+
"learning_rate": 4.567701435686404e-05,
|
| 1666 |
+
"logits/chosen": -1.4852521419525146,
|
| 1667 |
+
"logits/rejected": -1.3211164474487305,
|
| 1668 |
+
"logps/chosen": -221.89089965820312,
|
| 1669 |
+
"logps/rejected": -554.428466796875,
|
| 1670 |
+
"loss": 0.0,
|
| 1671 |
+
"rewards/accuracies": 1.0,
|
| 1672 |
+
"rewards/chosen": -6.827755928039551,
|
| 1673 |
+
"rewards/margins": 15.966878890991211,
|
| 1674 |
+
"rewards/rejected": -22.794635772705078,
|
| 1675 |
+
"step": 119
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.15,
|
| 1679 |
+
"learning_rate": 4.522542485937369e-05,
|
| 1680 |
+
"logits/chosen": -1.4120067358016968,
|
| 1681 |
+
"logits/rejected": -1.1943210363388062,
|
| 1682 |
+
"logps/chosen": -251.79034423828125,
|
| 1683 |
+
"logps/rejected": -700.6851196289062,
|
| 1684 |
+
"loss": 0.0,
|
| 1685 |
+
"rewards/accuracies": 1.0,
|
| 1686 |
+
"rewards/chosen": -6.087055206298828,
|
| 1687 |
+
"rewards/margins": 20.131147384643555,
|
| 1688 |
+
"rewards/rejected": -26.218202590942383,
|
| 1689 |
+
"step": 120
|
| 1690 |
+
}
|
| 1691 |
+
],
|
| 1692 |
+
"logging_steps": 1,
|
| 1693 |
+
"max_steps": 200,
|
| 1694 |
+
"num_train_epochs": 1,
|
| 1695 |
+
"save_steps": 40,
|
| 1696 |
+
"total_flos": 0.0,
|
| 1697 |
+
"trial_name": null,
|
| 1698 |
+
"trial_params": null
|
| 1699 |
+
}
|
checkpoint-120/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b52ed983d3e7f22985f201323e2d10cf6955e6d68f6bfb834c007eae1cae02b3
|
| 3 |
+
size 4600
|