Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +209 -0
- adapter_config.json +46 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +28 -0
- chat_template.jinja +61 -0
- loss.txt +1 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +2035 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
|
| 7 |
+
- grpo
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "/cache/models/Qwen--Qwen3-4B-Instruct-2507",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 32,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"down_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"gate_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ef77f1c459d6bc3a23ef214661eafa56d59c8491aa15bc5a3a10e00cab04091
|
| 3 |
+
size 264308896
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
loss.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
83,no_eval
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2035 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.00083,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 83,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"clip_ratio/high_max": 0.0,
|
| 14 |
+
"clip_ratio/high_mean": 0.0,
|
| 15 |
+
"clip_ratio/low_mean": 0.0,
|
| 16 |
+
"clip_ratio/low_min": 0.0,
|
| 17 |
+
"clip_ratio/region_mean": 0.0,
|
| 18 |
+
"completions/clipped_ratio": 0.0,
|
| 19 |
+
"completions/max_length": 13588.0,
|
| 20 |
+
"completions/max_terminated_length": 13588.0,
|
| 21 |
+
"completions/mean_length": 11062.28125,
|
| 22 |
+
"completions/mean_terminated_length": 11062.28125,
|
| 23 |
+
"completions/min_length": 3240.0,
|
| 24 |
+
"completions/min_terminated_length": 3240.0,
|
| 25 |
+
"entropy": 0.024793223245069385,
|
| 26 |
+
"epoch": 1e-05,
|
| 27 |
+
"frac_reward_zero_std": 0.0,
|
| 28 |
+
"grad_norm": 8.580889701843262,
|
| 29 |
+
"kl": 0.0,
|
| 30 |
+
"learning_rate": 0.0,
|
| 31 |
+
"loss": 0.3828,
|
| 32 |
+
"num_tokens": 380760.0,
|
| 33 |
+
"reward": -0.18871402740478516,
|
| 34 |
+
"reward_std": 0.6556680202484131,
|
| 35 |
+
"rewards/rollout_reward_func/mean": -0.18871402740478516,
|
| 36 |
+
"rewards/rollout_reward_func/std": 0.7358422875404358,
|
| 37 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 38 |
+
"sampling/importance_sampling_ratio/mean": 1.0005069971084595,
|
| 39 |
+
"sampling/importance_sampling_ratio/min": 0.2118072211742401,
|
| 40 |
+
"sampling/sampling_logp_difference/max": 1.5520787239074707,
|
| 41 |
+
"sampling/sampling_logp_difference/mean": 0.007466587238013744,
|
| 42 |
+
"step": 1,
|
| 43 |
+
"step_time": 164.69555583700276
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"clip_ratio/high_max": 0.0,
|
| 47 |
+
"clip_ratio/high_mean": 0.0,
|
| 48 |
+
"clip_ratio/low_mean": 0.0,
|
| 49 |
+
"clip_ratio/low_min": 0.0,
|
| 50 |
+
"clip_ratio/region_mean": 0.0,
|
| 51 |
+
"entropy": 0.024793223245069385,
|
| 52 |
+
"epoch": 2e-05,
|
| 53 |
+
"grad_norm": 8.476791381835938,
|
| 54 |
+
"kl": 0.0,
|
| 55 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 56 |
+
"loss": 0.3828,
|
| 57 |
+
"step": 2,
|
| 58 |
+
"step_time": 76.13254943499851
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"clip_ratio/high_max": 0.007962517178384587,
|
| 62 |
+
"clip_ratio/high_mean": 0.004406428648508154,
|
| 63 |
+
"clip_ratio/low_mean": 0.004677400924265385,
|
| 64 |
+
"clip_ratio/low_min": 0.0013333333772607148,
|
| 65 |
+
"clip_ratio/region_mean": 0.009083829529117793,
|
| 66 |
+
"completions/clipped_ratio": 0.0,
|
| 67 |
+
"completions/max_length": 13187.0,
|
| 68 |
+
"completions/max_terminated_length": 13187.0,
|
| 69 |
+
"completions/mean_length": 10307.78125,
|
| 70 |
+
"completions/mean_terminated_length": 10307.78125,
|
| 71 |
+
"completions/min_length": 1148.0,
|
| 72 |
+
"completions/min_terminated_length": 1148.0,
|
| 73 |
+
"entropy": 0.02775774576002732,
|
| 74 |
+
"epoch": 3e-05,
|
| 75 |
+
"frac_reward_zero_std": 0.0,
|
| 76 |
+
"grad_norm": 7.864254951477051,
|
| 77 |
+
"kl": 0.003300241682154592,
|
| 78 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 79 |
+
"loss": -0.359,
|
| 80 |
+
"num_tokens": 737612.0,
|
| 81 |
+
"reward": 0.12486958503723145,
|
| 82 |
+
"reward_std": 0.6849837303161621,
|
| 83 |
+
"rewards/rollout_reward_func/mean": 0.12486958503723145,
|
| 84 |
+
"rewards/rollout_reward_func/std": 0.7890143394470215,
|
| 85 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 86 |
+
"sampling/importance_sampling_ratio/mean": 0.9988386631011963,
|
| 87 |
+
"sampling/importance_sampling_ratio/min": 0.06573130935430527,
|
| 88 |
+
"sampling/sampling_logp_difference/max": 2.722179889678955,
|
| 89 |
+
"sampling/sampling_logp_difference/mean": 0.009859845042228699,
|
| 90 |
+
"step": 3,
|
| 91 |
+
"step_time": 162.92369715300083
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"clip_ratio/high_max": 0.006946050678379834,
|
| 95 |
+
"clip_ratio/high_mean": 0.003898195398505777,
|
| 96 |
+
"clip_ratio/low_mean": 0.002575721693574451,
|
| 97 |
+
"clip_ratio/low_min": 0.0,
|
| 98 |
+
"clip_ratio/region_mean": 0.006473917106632143,
|
| 99 |
+
"entropy": 0.02751988806994632,
|
| 100 |
+
"epoch": 4e-05,
|
| 101 |
+
"grad_norm": 5.452242851257324,
|
| 102 |
+
"kl": 0.002423067733161588,
|
| 103 |
+
"learning_rate": 4.285714285714286e-06,
|
| 104 |
+
"loss": -0.3579,
|
| 105 |
+
"step": 4,
|
| 106 |
+
"step_time": 72.9002098730034
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"clip_ratio/high_max": 0.0,
|
| 110 |
+
"clip_ratio/high_mean": 0.0,
|
| 111 |
+
"clip_ratio/low_mean": 0.003770460345549509,
|
| 112 |
+
"clip_ratio/low_min": 0.0,
|
| 113 |
+
"clip_ratio/region_mean": 0.003770460345549509,
|
| 114 |
+
"completions/clipped_ratio": 0.0,
|
| 115 |
+
"completions/max_length": 13268.0,
|
| 116 |
+
"completions/max_terminated_length": 13268.0,
|
| 117 |
+
"completions/mean_length": 10374.875,
|
| 118 |
+
"completions/mean_terminated_length": 10374.875,
|
| 119 |
+
"completions/min_length": 1137.0,
|
| 120 |
+
"completions/min_terminated_length": 1137.0,
|
| 121 |
+
"entropy": 0.019460081937722862,
|
| 122 |
+
"epoch": 5e-05,
|
| 123 |
+
"frac_reward_zero_std": 0.0,
|
| 124 |
+
"grad_norm": 2.471012830734253,
|
| 125 |
+
"kl": 0.004856036448204648,
|
| 126 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 127 |
+
"loss": 0.641,
|
| 128 |
+
"num_tokens": 1096168.0,
|
| 129 |
+
"reward": 0.023967057466506958,
|
| 130 |
+
"reward_std": 0.8080207109451294,
|
| 131 |
+
"rewards/rollout_reward_func/mean": 0.023967057466506958,
|
| 132 |
+
"rewards/rollout_reward_func/std": 0.7734705805778503,
|
| 133 |
+
"sampling/importance_sampling_ratio/max": 2.3860788345336914,
|
| 134 |
+
"sampling/importance_sampling_ratio/mean": 0.9997902512550354,
|
| 135 |
+
"sampling/importance_sampling_ratio/min": 0.24590186774730682,
|
| 136 |
+
"sampling/sampling_logp_difference/max": 1.402822732925415,
|
| 137 |
+
"sampling/sampling_logp_difference/mean": 0.006388354115188122,
|
| 138 |
+
"step": 5,
|
| 139 |
+
"step_time": 163.10432826500255
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"clip_ratio/high_max": 0.0008591166697442532,
|
| 143 |
+
"clip_ratio/high_mean": 0.0004295583348721266,
|
| 144 |
+
"clip_ratio/low_mean": 0.002894193778047338,
|
| 145 |
+
"clip_ratio/low_min": 0.00044014083687216043,
|
| 146 |
+
"clip_ratio/region_mean": 0.0033237521129194647,
|
| 147 |
+
"entropy": 0.019741965195862576,
|
| 148 |
+
"epoch": 6e-05,
|
| 149 |
+
"grad_norm": 2.724069595336914,
|
| 150 |
+
"kl": 0.0028640855837238632,
|
| 151 |
+
"learning_rate": 7.142857142857143e-06,
|
| 152 |
+
"loss": 0.6421,
|
| 153 |
+
"step": 6,
|
| 154 |
+
"step_time": 72.53219779800384
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"clip_ratio/high_max": 0.002466684323735535,
|
| 158 |
+
"clip_ratio/high_mean": 0.0014459271915256977,
|
| 159 |
+
"clip_ratio/low_mean": 0.003938428315450437,
|
| 160 |
+
"clip_ratio/low_min": 0.0,
|
| 161 |
+
"clip_ratio/region_mean": 0.00538435549242422,
|
| 162 |
+
"completions/clipped_ratio": 0.0,
|
| 163 |
+
"completions/max_length": 13555.0,
|
| 164 |
+
"completions/max_terminated_length": 13555.0,
|
| 165 |
+
"completions/mean_length": 10355.03125,
|
| 166 |
+
"completions/mean_terminated_length": 10355.03125,
|
| 167 |
+
"completions/min_length": 671.0,
|
| 168 |
+
"completions/min_terminated_length": 671.0,
|
| 169 |
+
"entropy": 0.022901446820469573,
|
| 170 |
+
"epoch": 7e-05,
|
| 171 |
+
"frac_reward_zero_std": 0.0,
|
| 172 |
+
"grad_norm": 2.8263163566589355,
|
| 173 |
+
"kl": 0.003971936868765624,
|
| 174 |
+
"learning_rate": 8.571428571428573e-06,
|
| 175 |
+
"loss": 0.1888,
|
| 176 |
+
"num_tokens": 1454826.0,
|
| 177 |
+
"reward": -0.312838077545166,
|
| 178 |
+
"reward_std": 0.7269577980041504,
|
| 179 |
+
"rewards/rollout_reward_func/mean": -0.312838077545166,
|
| 180 |
+
"rewards/rollout_reward_func/std": 0.8357037305831909,
|
| 181 |
+
"sampling/importance_sampling_ratio/max": 2.0568044185638428,
|
| 182 |
+
"sampling/importance_sampling_ratio/mean": 1.000103235244751,
|
| 183 |
+
"sampling/importance_sampling_ratio/min": 0.08904052525758743,
|
| 184 |
+
"sampling/sampling_logp_difference/max": 2.418663740158081,
|
| 185 |
+
"sampling/sampling_logp_difference/mean": 0.0077797044068574905,
|
| 186 |
+
"step": 7,
|
| 187 |
+
"step_time": 162.22604865499852
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"clip_ratio/high_max": 0.0032546367147006094,
|
| 191 |
+
"clip_ratio/high_mean": 0.0018399033870082349,
|
| 192 |
+
"clip_ratio/low_mean": 0.003713095487910323,
|
| 193 |
+
"clip_ratio/low_min": 0.0010530821746215224,
|
| 194 |
+
"clip_ratio/region_mean": 0.005552998904022388,
|
| 195 |
+
"entropy": 0.02342148229945451,
|
| 196 |
+
"epoch": 8e-05,
|
| 197 |
+
"grad_norm": 2.752257823944092,
|
| 198 |
+
"kl": 0.004395232397655491,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 0.1866,
|
| 201 |
+
"step": 8,
|
| 202 |
+
"step_time": 74.18662748600218
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"clip_ratio/high_max": 0.005761671985965222,
|
| 206 |
+
"clip_ratio/high_mean": 0.0031964925583451986,
|
| 207 |
+
"clip_ratio/low_mean": 0.0030218699539545923,
|
| 208 |
+
"clip_ratio/low_min": 0.0,
|
| 209 |
+
"clip_ratio/region_mean": 0.0062183625414036214,
|
| 210 |
+
"completions/clipped_ratio": 0.0,
|
| 211 |
+
"completions/max_length": 13308.0,
|
| 212 |
+
"completions/max_terminated_length": 13308.0,
|
| 213 |
+
"completions/mean_length": 10721.71875,
|
| 214 |
+
"completions/mean_terminated_length": 10721.71875,
|
| 215 |
+
"completions/min_length": 1860.0,
|
| 216 |
+
"completions/min_terminated_length": 1860.0,
|
| 217 |
+
"entropy": 0.02882851444883272,
|
| 218 |
+
"epoch": 9e-05,
|
| 219 |
+
"frac_reward_zero_std": 0.0,
|
| 220 |
+
"grad_norm": 4.064320087432861,
|
| 221 |
+
"kl": 0.011813669728326204,
|
| 222 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 223 |
+
"loss": -0.7679,
|
| 224 |
+
"num_tokens": 1824780.0,
|
| 225 |
+
"reward": -0.08607947826385498,
|
| 226 |
+
"reward_std": 0.5436858534812927,
|
| 227 |
+
"rewards/rollout_reward_func/mean": -0.08607947826385498,
|
| 228 |
+
"rewards/rollout_reward_func/std": 0.6569795608520508,
|
| 229 |
+
"sampling/importance_sampling_ratio/max": 1.9653983116149902,
|
| 230 |
+
"sampling/importance_sampling_ratio/mean": 0.9994874000549316,
|
| 231 |
+
"sampling/importance_sampling_ratio/min": 0.12670548260211945,
|
| 232 |
+
"sampling/sampling_logp_difference/max": 2.065889835357666,
|
| 233 |
+
"sampling/sampling_logp_difference/mean": 0.008421818725764751,
|
| 234 |
+
"step": 9,
|
| 235 |
+
"step_time": 166.1723138519992
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"clip_ratio/high_max": 0.006464897654950619,
|
| 239 |
+
"clip_ratio/high_mean": 0.0037041135947220027,
|
| 240 |
+
"clip_ratio/low_mean": 0.00621041064732708,
|
| 241 |
+
"clip_ratio/low_min": 0.00045289855916053057,
|
| 242 |
+
"clip_ratio/region_mean": 0.009914524242049083,
|
| 243 |
+
"entropy": 0.030018516205018386,
|
| 244 |
+
"epoch": 0.0001,
|
| 245 |
+
"grad_norm": 3.770601511001587,
|
| 246 |
+
"kl": 0.0105567153639754,
|
| 247 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 248 |
+
"loss": -0.7706,
|
| 249 |
+
"step": 10,
|
| 250 |
+
"step_time": 73.40501256899915
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"clip_ratio/high_max": 0.0021470933861564845,
|
| 254 |
+
"clip_ratio/high_mean": 0.0010735466930782422,
|
| 255 |
+
"clip_ratio/low_mean": 0.005622330281767063,
|
| 256 |
+
"clip_ratio/low_min": 0.0,
|
| 257 |
+
"clip_ratio/region_mean": 0.006695876887533814,
|
| 258 |
+
"completions/clipped_ratio": 0.0,
|
| 259 |
+
"completions/max_length": 13362.0,
|
| 260 |
+
"completions/max_terminated_length": 13362.0,
|
| 261 |
+
"completions/mean_length": 10876.53125,
|
| 262 |
+
"completions/mean_terminated_length": 10876.53125,
|
| 263 |
+
"completions/min_length": 1132.0,
|
| 264 |
+
"completions/min_terminated_length": 1132.0,
|
| 265 |
+
"entropy": 0.0270388865028508,
|
| 266 |
+
"epoch": 0.00011,
|
| 267 |
+
"frac_reward_zero_std": 0.0,
|
| 268 |
+
"grad_norm": 3.835709571838379,
|
| 269 |
+
"kl": 0.01752202024363214,
|
| 270 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 271 |
+
"loss": -0.382,
|
| 272 |
+
"num_tokens": 2199775.0,
|
| 273 |
+
"reward": -0.10052897781133652,
|
| 274 |
+
"reward_std": 0.4733438193798065,
|
| 275 |
+
"rewards/rollout_reward_func/mean": -0.10052897781133652,
|
| 276 |
+
"rewards/rollout_reward_func/std": 0.5049359202384949,
|
| 277 |
+
"sampling/importance_sampling_ratio/max": 2.5024189949035645,
|
| 278 |
+
"sampling/importance_sampling_ratio/mean": 0.9998884201049805,
|
| 279 |
+
"sampling/importance_sampling_ratio/min": 0.030437257140874863,
|
| 280 |
+
"sampling/sampling_logp_difference/max": 3.4920878410339355,
|
| 281 |
+
"sampling/sampling_logp_difference/mean": 0.007882161997258663,
|
| 282 |
+
"step": 11,
|
| 283 |
+
"step_time": 168.9051820099976
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"clip_ratio/high_max": 0.0065168983419425786,
|
| 287 |
+
"clip_ratio/high_mean": 0.0032584491709712893,
|
| 288 |
+
"clip_ratio/low_mean": 0.007071279003866948,
|
| 289 |
+
"clip_ratio/low_min": 0.0019379844889044762,
|
| 290 |
+
"clip_ratio/region_mean": 0.010329728116630577,
|
| 291 |
+
"entropy": 0.02872419002233073,
|
| 292 |
+
"epoch": 0.00012,
|
| 293 |
+
"grad_norm": 3.390139579772949,
|
| 294 |
+
"kl": 0.026051949804241303,
|
| 295 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 296 |
+
"loss": -0.3917,
|
| 297 |
+
"step": 12,
|
| 298 |
+
"step_time": 75.23061114399752
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"clip_ratio/high_max": 0.005910941952606663,
|
| 302 |
+
"clip_ratio/high_mean": 0.003374952997546643,
|
| 303 |
+
"clip_ratio/low_mean": 0.0033144439657917246,
|
| 304 |
+
"clip_ratio/low_min": 0.00042517005931586027,
|
| 305 |
+
"clip_ratio/region_mean": 0.006689396948786452,
|
| 306 |
+
"completions/clipped_ratio": 0.0,
|
| 307 |
+
"completions/max_length": 13292.0,
|
| 308 |
+
"completions/max_terminated_length": 13292.0,
|
| 309 |
+
"completions/mean_length": 10776.84375,
|
| 310 |
+
"completions/mean_terminated_length": 10776.84375,
|
| 311 |
+
"completions/min_length": 506.0,
|
| 312 |
+
"completions/min_terminated_length": 506.0,
|
| 313 |
+
"entropy": 0.023527769571956014,
|
| 314 |
+
"epoch": 0.00013,
|
| 315 |
+
"frac_reward_zero_std": 0.0,
|
| 316 |
+
"grad_norm": 7.241506099700928,
|
| 317 |
+
"kl": 0.038550363320811964,
|
| 318 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 319 |
+
"loss": -0.3493,
|
| 320 |
+
"num_tokens": 2571951.0,
|
| 321 |
+
"reward": -0.014623546972870827,
|
| 322 |
+
"reward_std": 0.896544337272644,
|
| 323 |
+
"rewards/rollout_reward_func/mean": -0.014623546972870827,
|
| 324 |
+
"rewards/rollout_reward_func/std": 1.0157890319824219,
|
| 325 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 326 |
+
"sampling/importance_sampling_ratio/mean": 1.0013093948364258,
|
| 327 |
+
"sampling/importance_sampling_ratio/min": 0.1680545210838318,
|
| 328 |
+
"sampling/sampling_logp_difference/max": 1.7834668159484863,
|
| 329 |
+
"sampling/sampling_logp_difference/mean": 0.010352442041039467,
|
| 330 |
+
"step": 13,
|
| 331 |
+
"step_time": 166.36859219799953
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"clip_ratio/high_max": 0.008198851748602465,
|
| 335 |
+
"clip_ratio/high_mean": 0.004307759183575399,
|
| 336 |
+
"clip_ratio/low_mean": 0.003082827272010036,
|
| 337 |
+
"clip_ratio/low_min": 0.0008474673668388277,
|
| 338 |
+
"clip_ratio/region_mean": 0.007390586411929689,
|
| 339 |
+
"entropy": 0.024192788765503792,
|
| 340 |
+
"epoch": 0.00014,
|
| 341 |
+
"grad_norm": 4.684647083282471,
|
| 342 |
+
"kl": 0.047261360837082655,
|
| 343 |
+
"learning_rate": 1.8571428571428572e-05,
|
| 344 |
+
"loss": -0.3576,
|
| 345 |
+
"step": 14,
|
| 346 |
+
"step_time": 74.20421179199911
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"clip_ratio/high_max": 0.006833544030087069,
|
| 350 |
+
"clip_ratio/high_mean": 0.00451569254801143,
|
| 351 |
+
"clip_ratio/low_mean": 0.003979612258262932,
|
| 352 |
+
"clip_ratio/low_min": 0.0012784616847056895,
|
| 353 |
+
"clip_ratio/region_mean": 0.008495304791722447,
|
| 354 |
+
"completions/clipped_ratio": 0.0,
|
| 355 |
+
"completions/max_length": 13161.0,
|
| 356 |
+
"completions/max_terminated_length": 13161.0,
|
| 357 |
+
"completions/mean_length": 11274.875,
|
| 358 |
+
"completions/mean_terminated_length": 11274.875,
|
| 359 |
+
"completions/min_length": 677.0,
|
| 360 |
+
"completions/min_terminated_length": 677.0,
|
| 361 |
+
"entropy": 0.030410012637730688,
|
| 362 |
+
"epoch": 0.00015,
|
| 363 |
+
"frac_reward_zero_std": 0.0,
|
| 364 |
+
"grad_norm": 7.206306457519531,
|
| 365 |
+
"kl": 0.16209679024177603,
|
| 366 |
+
"learning_rate": 2e-05,
|
| 367 |
+
"loss": -0.6323,
|
| 368 |
+
"num_tokens": 2959792.0,
|
| 369 |
+
"reward": -0.04547331482172012,
|
| 370 |
+
"reward_std": 0.512954592704773,
|
| 371 |
+
"rewards/rollout_reward_func/mean": -0.04547331482172012,
|
| 372 |
+
"rewards/rollout_reward_func/std": 0.5874266028404236,
|
| 373 |
+
"sampling/importance_sampling_ratio/max": 1.758615493774414,
|
| 374 |
+
"sampling/importance_sampling_ratio/mean": 0.9982211589813232,
|
| 375 |
+
"sampling/importance_sampling_ratio/min": 0.14112254977226257,
|
| 376 |
+
"sampling/sampling_logp_difference/max": 1.9581265449523926,
|
| 377 |
+
"sampling/sampling_logp_difference/mean": 0.010034291073679924,
|
| 378 |
+
"step": 15,
|
| 379 |
+
"step_time": 172.67286533600054
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"clip_ratio/high_max": 0.009126297401962802,
|
| 383 |
+
"clip_ratio/high_mean": 0.00564141028735321,
|
| 384 |
+
"clip_ratio/low_mean": 0.0038173396605998278,
|
| 385 |
+
"clip_ratio/low_min": 0.0017036317440215498,
|
| 386 |
+
"clip_ratio/region_mean": 0.009458749933401123,
|
| 387 |
+
"entropy": 0.030430902494117618,
|
| 388 |
+
"epoch": 0.00016,
|
| 389 |
+
"grad_norm": 5.043717861175537,
|
| 390 |
+
"kl": 0.09108352061593905,
|
| 391 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 392 |
+
"loss": -0.6478,
|
| 393 |
+
"step": 16,
|
| 394 |
+
"step_time": 75.43593462200079
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"clip_ratio/high_max": 0.0034075405565090477,
|
| 398 |
+
"clip_ratio/high_mean": 0.002120436984114349,
|
| 399 |
+
"clip_ratio/low_mean": 0.0051906249864259735,
|
| 400 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 401 |
+
"clip_ratio/region_mean": 0.007311061970540322,
|
| 402 |
+
"completions/clipped_ratio": 0.0,
|
| 403 |
+
"completions/max_length": 13232.0,
|
| 404 |
+
"completions/max_terminated_length": 13232.0,
|
| 405 |
+
"completions/mean_length": 10035.0,
|
| 406 |
+
"completions/mean_terminated_length": 10035.0,
|
| 407 |
+
"completions/min_length": 692.0,
|
| 408 |
+
"completions/min_terminated_length": 692.0,
|
| 409 |
+
"entropy": 0.03239170782035217,
|
| 410 |
+
"epoch": 0.00017,
|
| 411 |
+
"frac_reward_zero_std": 0.0,
|
| 412 |
+
"grad_norm": 26.07994842529297,
|
| 413 |
+
"kl": 0.5745490518165752,
|
| 414 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 415 |
+
"loss": -0.4504,
|
| 416 |
+
"num_tokens": 3308089.0,
|
| 417 |
+
"reward": -0.21278375387191772,
|
| 418 |
+
"reward_std": 0.5441625118255615,
|
| 419 |
+
"rewards/rollout_reward_func/mean": -0.21278375387191772,
|
| 420 |
+
"rewards/rollout_reward_func/std": 0.612115204334259,
|
| 421 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 422 |
+
"sampling/importance_sampling_ratio/mean": 0.9986231327056885,
|
| 423 |
+
"sampling/importance_sampling_ratio/min": 0.07349392026662827,
|
| 424 |
+
"sampling/sampling_logp_difference/max": 2.6105525493621826,
|
| 425 |
+
"sampling/sampling_logp_difference/mean": 0.010844497010111809,
|
| 426 |
+
"step": 17,
|
| 427 |
+
"step_time": 161.29507867800203
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"clip_ratio/high_max": 0.009956223861081526,
|
| 431 |
+
"clip_ratio/high_mean": 0.005192153024836443,
|
| 432 |
+
"clip_ratio/low_mean": 0.008039093692786992,
|
| 433 |
+
"clip_ratio/low_min": 0.0030091897933743894,
|
| 434 |
+
"clip_ratio/region_mean": 0.013231246688519605,
|
| 435 |
+
"entropy": 0.034400187025312334,
|
| 436 |
+
"epoch": 0.00018,
|
| 437 |
+
"grad_norm": 17.663053512573242,
|
| 438 |
+
"kl": 0.061504869983764365,
|
| 439 |
+
"learning_rate": 2.4285714285714288e-05,
|
| 440 |
+
"loss": -0.4629,
|
| 441 |
+
"step": 18,
|
| 442 |
+
"step_time": 74.907978645002
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"clip_ratio/high_max": 0.009938271541614085,
|
| 446 |
+
"clip_ratio/high_mean": 0.005400170251959935,
|
| 447 |
+
"clip_ratio/low_mean": 0.0053618835809174925,
|
| 448 |
+
"clip_ratio/low_min": 0.0013297871919348836,
|
| 449 |
+
"clip_ratio/region_mean": 0.010762053818325512,
|
| 450 |
+
"completions/clipped_ratio": 0.0,
|
| 451 |
+
"completions/max_length": 13178.0,
|
| 452 |
+
"completions/max_terminated_length": 13178.0,
|
| 453 |
+
"completions/mean_length": 10745.46875,
|
| 454 |
+
"completions/mean_terminated_length": 10745.46875,
|
| 455 |
+
"completions/min_length": 1214.0,
|
| 456 |
+
"completions/min_terminated_length": 1214.0,
|
| 457 |
+
"entropy": 0.037911236577201635,
|
| 458 |
+
"epoch": 0.00019,
|
| 459 |
+
"frac_reward_zero_std": 0.0,
|
| 460 |
+
"grad_norm": 5.704324722290039,
|
| 461 |
+
"kl": 0.07061941432766616,
|
| 462 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 463 |
+
"loss": 0.201,
|
| 464 |
+
"num_tokens": 3679071.0,
|
| 465 |
+
"reward": 0.08096315711736679,
|
| 466 |
+
"reward_std": 0.6758204698562622,
|
| 467 |
+
"rewards/rollout_reward_func/mean": 0.08096315711736679,
|
| 468 |
+
"rewards/rollout_reward_func/std": 0.6970977783203125,
|
| 469 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 470 |
+
"sampling/importance_sampling_ratio/mean": 0.9999469518661499,
|
| 471 |
+
"sampling/importance_sampling_ratio/min": 0.22013714909553528,
|
| 472 |
+
"sampling/sampling_logp_difference/max": 1.5135045051574707,
|
| 473 |
+
"sampling/sampling_logp_difference/mean": 0.013475988060235977,
|
| 474 |
+
"step": 19,
|
| 475 |
+
"step_time": 167.33121058399774
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"clip_ratio/high_max": 0.0077229262969922274,
|
| 479 |
+
"clip_ratio/high_mean": 0.0049346807500114664,
|
| 480 |
+
"clip_ratio/low_mean": 0.007034420879790559,
|
| 481 |
+
"clip_ratio/low_min": 0.00042808218859136105,
|
| 482 |
+
"clip_ratio/region_mean": 0.011969101600698195,
|
| 483 |
+
"entropy": 0.03793096466688439,
|
| 484 |
+
"epoch": 0.0002,
|
| 485 |
+
"grad_norm": 4.580775737762451,
|
| 486 |
+
"kl": 0.0702707355376333,
|
| 487 |
+
"learning_rate": 2.714285714285714e-05,
|
| 488 |
+
"loss": 0.1831,
|
| 489 |
+
"step": 20,
|
| 490 |
+
"step_time": 74.7389482260005
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"clip_ratio/high_max": 0.012402922351611778,
|
| 494 |
+
"clip_ratio/high_mean": 0.007489239520509727,
|
| 495 |
+
"clip_ratio/low_mean": 0.005276143303490244,
|
| 496 |
+
"clip_ratio/low_min": 0.0012991318944841623,
|
| 497 |
+
"clip_ratio/region_mean": 0.012765382809448056,
|
| 498 |
+
"completions/clipped_ratio": 0.0,
|
| 499 |
+
"completions/max_length": 13736.0,
|
| 500 |
+
"completions/max_terminated_length": 13736.0,
|
| 501 |
+
"completions/mean_length": 11500.34375,
|
| 502 |
+
"completions/mean_terminated_length": 11500.34375,
|
| 503 |
+
"completions/min_length": 699.0,
|
| 504 |
+
"completions/min_terminated_length": 699.0,
|
| 505 |
+
"entropy": 0.0338919882196933,
|
| 506 |
+
"epoch": 0.00021,
|
| 507 |
+
"frac_reward_zero_std": 0.0,
|
| 508 |
+
"grad_norm": 4.951229572296143,
|
| 509 |
+
"kl": 0.08188517112284899,
|
| 510 |
+
"learning_rate": 2.857142857142857e-05,
|
| 511 |
+
"loss": -0.7709,
|
| 512 |
+
"num_tokens": 4074157.0,
|
| 513 |
+
"reward": -0.03381938114762306,
|
| 514 |
+
"reward_std": 0.35305583477020264,
|
| 515 |
+
"rewards/rollout_reward_func/mean": -0.03381938114762306,
|
| 516 |
+
"rewards/rollout_reward_func/std": 0.3805231750011444,
|
| 517 |
+
"sampling/importance_sampling_ratio/max": 2.957324266433716,
|
| 518 |
+
"sampling/importance_sampling_ratio/mean": 0.9992592930793762,
|
| 519 |
+
"sampling/importance_sampling_ratio/min": 0.08525566011667252,
|
| 520 |
+
"sampling/sampling_logp_difference/max": 2.4621007442474365,
|
| 521 |
+
"sampling/sampling_logp_difference/mean": 0.012218999676406384,
|
| 522 |
+
"step": 21,
|
| 523 |
+
"step_time": 172.31501902600212
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"clip_ratio/high_max": 0.015019576210761443,
|
| 527 |
+
"clip_ratio/high_mean": 0.008796090245596133,
|
| 528 |
+
"clip_ratio/low_mean": 0.0036695960588986054,
|
| 529 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 530 |
+
"clip_ratio/region_mean": 0.012465686231735162,
|
| 531 |
+
"entropy": 0.033622618939261883,
|
| 532 |
+
"epoch": 0.00022,
|
| 533 |
+
"grad_norm": 3.219212293624878,
|
| 534 |
+
"kl": 0.07884596765507013,
|
| 535 |
+
"learning_rate": 3e-05,
|
| 536 |
+
"loss": -0.7798,
|
| 537 |
+
"step": 22,
|
| 538 |
+
"step_time": 77.3749247250089
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"clip_ratio/high_max": 0.0047400579787790775,
|
| 542 |
+
"clip_ratio/high_mean": 0.002854942809790373,
|
| 543 |
+
"clip_ratio/low_mean": 0.0032737747678766027,
|
| 544 |
+
"clip_ratio/low_min": 0.002108728658640757,
|
| 545 |
+
"clip_ratio/region_mean": 0.0061287175776669756,
|
| 546 |
+
"completions/clipped_ratio": 0.0,
|
| 547 |
+
"completions/max_length": 13377.0,
|
| 548 |
+
"completions/max_terminated_length": 13377.0,
|
| 549 |
+
"completions/mean_length": 12026.28125,
|
| 550 |
+
"completions/mean_terminated_length": 12026.28125,
|
| 551 |
+
"completions/min_length": 3719.0,
|
| 552 |
+
"completions/min_terminated_length": 3719.0,
|
| 553 |
+
"entropy": 0.03219945449382067,
|
| 554 |
+
"epoch": 0.00023,
|
| 555 |
+
"frac_reward_zero_std": 0.0,
|
| 556 |
+
"grad_norm": 5.014606475830078,
|
| 557 |
+
"kl": 0.06574048777110875,
|
| 558 |
+
"learning_rate": 3.142857142857143e-05,
|
| 559 |
+
"loss": 0.1808,
|
| 560 |
+
"num_tokens": 4485860.0,
|
| 561 |
+
"reward": 0.021906912326812744,
|
| 562 |
+
"reward_std": 0.6035071015357971,
|
| 563 |
+
"rewards/rollout_reward_func/mean": 0.021906912326812744,
|
| 564 |
+
"rewards/rollout_reward_func/std": 0.6828868389129639,
|
| 565 |
+
"sampling/importance_sampling_ratio/max": 2.2410309314727783,
|
| 566 |
+
"sampling/importance_sampling_ratio/mean": 0.9987294673919678,
|
| 567 |
+
"sampling/importance_sampling_ratio/min": 0.14094144105911255,
|
| 568 |
+
"sampling/sampling_logp_difference/max": 1.9594107866287231,
|
| 569 |
+
"sampling/sampling_logp_difference/mean": 0.01040736399590969,
|
| 570 |
+
"step": 23,
|
| 571 |
+
"step_time": 174.87443501801317
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"clip_ratio/high_max": 0.007845318003091961,
|
| 575 |
+
"clip_ratio/high_mean": 0.004138176242122427,
|
| 576 |
+
"clip_ratio/low_mean": 0.006086511944886297,
|
| 577 |
+
"clip_ratio/low_min": 0.0018401192501187325,
|
| 578 |
+
"clip_ratio/region_mean": 0.010224688216112554,
|
| 579 |
+
"entropy": 0.03171470231609419,
|
| 580 |
+
"epoch": 0.00024,
|
| 581 |
+
"grad_norm": 3.639631748199463,
|
| 582 |
+
"kl": 0.09756560530513525,
|
| 583 |
+
"learning_rate": 3.285714285714286e-05,
|
| 584 |
+
"loss": 0.1634,
|
| 585 |
+
"step": 24,
|
| 586 |
+
"step_time": 76.57009659699543
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"clip_ratio/high_max": 0.005132828722707927,
|
| 590 |
+
"clip_ratio/high_mean": 0.002983081038109958,
|
| 591 |
+
"clip_ratio/low_mean": 0.0029943463450763375,
|
| 592 |
+
"clip_ratio/low_min": 0.0004310344811528921,
|
| 593 |
+
"clip_ratio/region_mean": 0.005977427397738211,
|
| 594 |
+
"completions/clipped_ratio": 0.0,
|
| 595 |
+
"completions/max_length": 13353.0,
|
| 596 |
+
"completions/max_terminated_length": 13353.0,
|
| 597 |
+
"completions/mean_length": 11107.46875,
|
| 598 |
+
"completions/mean_terminated_length": 11107.46875,
|
| 599 |
+
"completions/min_length": 1148.0,
|
| 600 |
+
"completions/min_terminated_length": 1148.0,
|
| 601 |
+
"entropy": 0.03088551398832351,
|
| 602 |
+
"epoch": 0.00025,
|
| 603 |
+
"frac_reward_zero_std": 0.0,
|
| 604 |
+
"grad_norm": 5.480138778686523,
|
| 605 |
+
"kl": 0.07383820961695164,
|
| 606 |
+
"learning_rate": 3.428571428571429e-05,
|
| 607 |
+
"loss": -0.0496,
|
| 608 |
+
"num_tokens": 4867735.0,
|
| 609 |
+
"reward": 0.1064801961183548,
|
| 610 |
+
"reward_std": 0.7724429368972778,
|
| 611 |
+
"rewards/rollout_reward_func/mean": 0.1064801961183548,
|
| 612 |
+
"rewards/rollout_reward_func/std": 0.7649414539337158,
|
| 613 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 614 |
+
"sampling/importance_sampling_ratio/mean": 1.0009795427322388,
|
| 615 |
+
"sampling/importance_sampling_ratio/min": 0.29720377922058105,
|
| 616 |
+
"sampling/sampling_logp_difference/max": 1.2752747535705566,
|
| 617 |
+
"sampling/sampling_logp_difference/mean": 0.007685038261115551,
|
| 618 |
+
"step": 25,
|
| 619 |
+
"step_time": 167.8738094909968
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"clip_ratio/high_max": 0.011608412605710328,
|
| 623 |
+
"clip_ratio/high_mean": 0.0062891200941521674,
|
| 624 |
+
"clip_ratio/low_mean": 0.004773339023813605,
|
| 625 |
+
"clip_ratio/low_min": 0.0009652225417084992,
|
| 626 |
+
"clip_ratio/region_mean": 0.011062459088861942,
|
| 627 |
+
"entropy": 0.030013347961357795,
|
| 628 |
+
"epoch": 0.00026,
|
| 629 |
+
"grad_norm": 3.696756362915039,
|
| 630 |
+
"kl": 0.08500297460705042,
|
| 631 |
+
"learning_rate": 3.571428571428572e-05,
|
| 632 |
+
"loss": -0.0613,
|
| 633 |
+
"step": 26,
|
| 634 |
+
"step_time": 74.28590359098962
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"clip_ratio/high_max": 0.008908686431823298,
|
| 638 |
+
"clip_ratio/high_mean": 0.004666928187361918,
|
| 639 |
+
"clip_ratio/low_mean": 0.002849717377102934,
|
| 640 |
+
"clip_ratio/low_min": 0.0,
|
| 641 |
+
"clip_ratio/region_mean": 0.007516645535361022,
|
| 642 |
+
"completions/clipped_ratio": 0.0,
|
| 643 |
+
"completions/max_length": 12989.0,
|
| 644 |
+
"completions/max_terminated_length": 12989.0,
|
| 645 |
+
"completions/mean_length": 11003.25,
|
| 646 |
+
"completions/mean_terminated_length": 11003.25,
|
| 647 |
+
"completions/min_length": 646.0,
|
| 648 |
+
"completions/min_terminated_length": 646.0,
|
| 649 |
+
"entropy": 0.0298636804218404,
|
| 650 |
+
"epoch": 0.00027,
|
| 651 |
+
"frac_reward_zero_std": 0.0,
|
| 652 |
+
"grad_norm": 3.567798376083374,
|
| 653 |
+
"kl": 0.06775169487809762,
|
| 654 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 655 |
+
"loss": 0.1227,
|
| 656 |
+
"num_tokens": 5246228.0,
|
| 657 |
+
"reward": -0.022418564185500145,
|
| 658 |
+
"reward_std": 0.5492140054702759,
|
| 659 |
+
"rewards/rollout_reward_func/mean": -0.022418564185500145,
|
| 660 |
+
"rewards/rollout_reward_func/std": 0.568433403968811,
|
| 661 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 662 |
+
"sampling/importance_sampling_ratio/mean": 1.001232385635376,
|
| 663 |
+
"sampling/importance_sampling_ratio/min": 0.21295833587646484,
|
| 664 |
+
"sampling/sampling_logp_difference/max": 1.5466587543487549,
|
| 665 |
+
"sampling/sampling_logp_difference/mean": 0.009141004644334316,
|
| 666 |
+
"step": 27,
|
| 667 |
+
"step_time": 167.0670825299967
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"clip_ratio/high_max": 0.00908595250803046,
|
| 671 |
+
"clip_ratio/high_mean": 0.004751309592393227,
|
| 672 |
+
"clip_ratio/low_mean": 0.0031262846459867433,
|
| 673 |
+
"clip_ratio/low_min": 0.0,
|
| 674 |
+
"clip_ratio/region_mean": 0.007877594252931885,
|
| 675 |
+
"entropy": 0.028611631889361888,
|
| 676 |
+
"epoch": 0.00028,
|
| 677 |
+
"grad_norm": 4.556273937225342,
|
| 678 |
+
"kl": 0.08138555369805545,
|
| 679 |
+
"learning_rate": 3.857142857142858e-05,
|
| 680 |
+
"loss": 0.1296,
|
| 681 |
+
"step": 28,
|
| 682 |
+
"step_time": 73.89199204599572
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"clip_ratio/high_max": 0.006030527874827385,
|
| 686 |
+
"clip_ratio/high_mean": 0.0032235972757916898,
|
| 687 |
+
"clip_ratio/low_mean": 0.0035321618779562414,
|
| 688 |
+
"clip_ratio/low_min": 0.00042229730752296746,
|
| 689 |
+
"clip_ratio/region_mean": 0.006755759153747931,
|
| 690 |
+
"completions/clipped_ratio": 0.0,
|
| 691 |
+
"completions/max_length": 12965.0,
|
| 692 |
+
"completions/max_terminated_length": 12965.0,
|
| 693 |
+
"completions/mean_length": 11042.71875,
|
| 694 |
+
"completions/mean_terminated_length": 11042.71875,
|
| 695 |
+
"completions/min_length": 679.0,
|
| 696 |
+
"completions/min_terminated_length": 679.0,
|
| 697 |
+
"entropy": 0.035136714577674866,
|
| 698 |
+
"epoch": 0.00029,
|
| 699 |
+
"frac_reward_zero_std": 0.0,
|
| 700 |
+
"grad_norm": 3.9678425788879395,
|
| 701 |
+
"kl": 0.12332394430995919,
|
| 702 |
+
"learning_rate": 4e-05,
|
| 703 |
+
"loss": 0.0405,
|
| 704 |
+
"num_tokens": 5625953.0,
|
| 705 |
+
"reward": 0.09734156727790833,
|
| 706 |
+
"reward_std": 0.8730854988098145,
|
| 707 |
+
"rewards/rollout_reward_func/mean": 0.09734156727790833,
|
| 708 |
+
"rewards/rollout_reward_func/std": 0.8854982256889343,
|
| 709 |
+
"sampling/importance_sampling_ratio/max": 2.165529251098633,
|
| 710 |
+
"sampling/importance_sampling_ratio/mean": 1.0002460479736328,
|
| 711 |
+
"sampling/importance_sampling_ratio/min": 0.1636945754289627,
|
| 712 |
+
"sampling/sampling_logp_difference/max": 1.8097529411315918,
|
| 713 |
+
"sampling/sampling_logp_difference/mean": 0.010431939736008644,
|
| 714 |
+
"step": 29,
|
| 715 |
+
"step_time": 166.6891715229831
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"clip_ratio/high_max": 0.008942051383201033,
|
| 719 |
+
"clip_ratio/high_mean": 0.004679359000874683,
|
| 720 |
+
"clip_ratio/low_mean": 0.011221011402085423,
|
| 721 |
+
"clip_ratio/low_min": 0.0025366951304022223,
|
| 722 |
+
"clip_ratio/region_mean": 0.015900370432063937,
|
| 723 |
+
"entropy": 0.03758203284814954,
|
| 724 |
+
"epoch": 0.0003,
|
| 725 |
+
"grad_norm": 3.95874285697937,
|
| 726 |
+
"kl": 0.1673376166727394,
|
| 727 |
+
"learning_rate": 4.1428571428571437e-05,
|
| 728 |
+
"loss": 0.0305,
|
| 729 |
+
"step": 30,
|
| 730 |
+
"step_time": 73.23714858698804
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"clip_ratio/high_max": 0.005954384687356651,
|
| 734 |
+
"clip_ratio/high_mean": 0.0029771923436783254,
|
| 735 |
+
"clip_ratio/low_mean": 0.002211941609857604,
|
| 736 |
+
"clip_ratio/low_min": 0.00042229730752296746,
|
| 737 |
+
"clip_ratio/region_mean": 0.005189133953535929,
|
| 738 |
+
"completions/clipped_ratio": 0.0,
|
| 739 |
+
"completions/max_length": 13006.0,
|
| 740 |
+
"completions/max_terminated_length": 13006.0,
|
| 741 |
+
"completions/mean_length": 10191.125,
|
| 742 |
+
"completions/mean_terminated_length": 10191.125,
|
| 743 |
+
"completions/min_length": 407.0,
|
| 744 |
+
"completions/min_terminated_length": 407.0,
|
| 745 |
+
"entropy": 0.02958523586858064,
|
| 746 |
+
"epoch": 0.00031,
|
| 747 |
+
"frac_reward_zero_std": 0.0,
|
| 748 |
+
"grad_norm": 5.264285564422607,
|
| 749 |
+
"kl": 0.15118286339566112,
|
| 750 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 751 |
+
"loss": -0.1601,
|
| 752 |
+
"num_tokens": 5978592.0,
|
| 753 |
+
"reward": 0.15017695724964142,
|
| 754 |
+
"reward_std": 0.7236286401748657,
|
| 755 |
+
"rewards/rollout_reward_func/mean": 0.15017695724964142,
|
| 756 |
+
"rewards/rollout_reward_func/std": 0.810089647769928,
|
| 757 |
+
"sampling/importance_sampling_ratio/max": 2.8205833435058594,
|
| 758 |
+
"sampling/importance_sampling_ratio/mean": 1.0002295970916748,
|
| 759 |
+
"sampling/importance_sampling_ratio/min": 0.11224253475666046,
|
| 760 |
+
"sampling/sampling_logp_difference/max": 2.1870932579040527,
|
| 761 |
+
"sampling/sampling_logp_difference/mean": 0.011024706065654755,
|
| 762 |
+
"step": 31,
|
| 763 |
+
"step_time": 159.12965879299736
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"clip_ratio/high_max": 0.009853226481936872,
|
| 767 |
+
"clip_ratio/high_mean": 0.004926613240968436,
|
| 768 |
+
"clip_ratio/low_mean": 0.006775343528715894,
|
| 769 |
+
"clip_ratio/low_min": 0.0013721397845074534,
|
| 770 |
+
"clip_ratio/region_mean": 0.0117019567405805,
|
| 771 |
+
"entropy": 0.02985566615825519,
|
| 772 |
+
"epoch": 0.00032,
|
| 773 |
+
"grad_norm": 4.398590087890625,
|
| 774 |
+
"kl": 0.12289534416049719,
|
| 775 |
+
"learning_rate": 4.428571428571428e-05,
|
| 776 |
+
"loss": -0.1953,
|
| 777 |
+
"step": 32,
|
| 778 |
+
"step_time": 72.89587214800122
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"clip_ratio/high_max": 0.004788487451151013,
|
| 782 |
+
"clip_ratio/high_mean": 0.003007469786098227,
|
| 783 |
+
"clip_ratio/low_mean": 0.002534152939915657,
|
| 784 |
+
"clip_ratio/low_min": 0.0,
|
| 785 |
+
"clip_ratio/region_mean": 0.005541622740565799,
|
| 786 |
+
"completions/clipped_ratio": 0.0,
|
| 787 |
+
"completions/max_length": 13141.0,
|
| 788 |
+
"completions/max_terminated_length": 13141.0,
|
| 789 |
+
"completions/mean_length": 11030.53125,
|
| 790 |
+
"completions/mean_terminated_length": 11030.53125,
|
| 791 |
+
"completions/min_length": 2621.0,
|
| 792 |
+
"completions/min_terminated_length": 2621.0,
|
| 793 |
+
"entropy": 0.030806915485300124,
|
| 794 |
+
"epoch": 0.00033,
|
| 795 |
+
"frac_reward_zero_std": 0.0,
|
| 796 |
+
"grad_norm": 10.662086486816406,
|
| 797 |
+
"kl": 0.12435430695768446,
|
| 798 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 799 |
+
"loss": 0.0348,
|
| 800 |
+
"num_tokens": 6357887.0,
|
| 801 |
+
"reward": 0.0787108913064003,
|
| 802 |
+
"reward_std": 0.6069952249526978,
|
| 803 |
+
"rewards/rollout_reward_func/mean": 0.0787108913064003,
|
| 804 |
+
"rewards/rollout_reward_func/std": 0.6843085289001465,
|
| 805 |
+
"sampling/importance_sampling_ratio/max": 2.1111693382263184,
|
| 806 |
+
"sampling/importance_sampling_ratio/mean": 0.9992009997367859,
|
| 807 |
+
"sampling/importance_sampling_ratio/min": 0.3298701345920563,
|
| 808 |
+
"sampling/sampling_logp_difference/max": 1.1090562343597412,
|
| 809 |
+
"sampling/sampling_logp_difference/mean": 0.00803404301404953,
|
| 810 |
+
"step": 33,
|
| 811 |
+
"step_time": 171.64439654499802
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"clip_ratio/high_max": 0.008590338955400512,
|
| 815 |
+
"clip_ratio/high_mean": 0.004512183382757939,
|
| 816 |
+
"clip_ratio/low_mean": 0.0033453173091402277,
|
| 817 |
+
"clip_ratio/low_min": 0.0,
|
| 818 |
+
"clip_ratio/region_mean": 0.007857500677346252,
|
| 819 |
+
"entropy": 0.03131913376273587,
|
| 820 |
+
"epoch": 0.00034,
|
| 821 |
+
"grad_norm": 4.566284656524658,
|
| 822 |
+
"kl": 0.19618933752644807,
|
| 823 |
+
"learning_rate": 4.714285714285714e-05,
|
| 824 |
+
"loss": 0.0389,
|
| 825 |
+
"step": 34,
|
| 826 |
+
"step_time": 75.43813904400304
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"clip_ratio/high_max": 0.007634009321918711,
|
| 830 |
+
"clip_ratio/high_mean": 0.004664549152948894,
|
| 831 |
+
"clip_ratio/low_mean": 0.002761319585260935,
|
| 832 |
+
"clip_ratio/low_min": 0.0,
|
| 833 |
+
"clip_ratio/region_mean": 0.007425868738209829,
|
| 834 |
+
"completions/clipped_ratio": 0.0,
|
| 835 |
+
"completions/max_length": 13050.0,
|
| 836 |
+
"completions/max_terminated_length": 13050.0,
|
| 837 |
+
"completions/mean_length": 11396.5,
|
| 838 |
+
"completions/mean_terminated_length": 11396.5,
|
| 839 |
+
"completions/min_length": 1138.0,
|
| 840 |
+
"completions/min_terminated_length": 1138.0,
|
| 841 |
+
"entropy": 0.03832057095132768,
|
| 842 |
+
"epoch": 0.00035,
|
| 843 |
+
"frac_reward_zero_std": 0.0,
|
| 844 |
+
"grad_norm": 5.9035139083862305,
|
| 845 |
+
"kl": 0.11720841797068715,
|
| 846 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 847 |
+
"loss": -0.8942,
|
| 848 |
+
"num_tokens": 6749218.0,
|
| 849 |
+
"reward": -0.07082575559616089,
|
| 850 |
+
"reward_std": 0.47015607357025146,
|
| 851 |
+
"rewards/rollout_reward_func/mean": -0.07082575559616089,
|
| 852 |
+
"rewards/rollout_reward_func/std": 0.5316166281700134,
|
| 853 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 854 |
+
"sampling/importance_sampling_ratio/mean": 0.9994174242019653,
|
| 855 |
+
"sampling/importance_sampling_ratio/min": 0.2981066107749939,
|
| 856 |
+
"sampling/sampling_logp_difference/max": 1.524237871170044,
|
| 857 |
+
"sampling/sampling_logp_difference/mean": 0.012385983020067215,
|
| 858 |
+
"step": 35,
|
| 859 |
+
"step_time": 168.27690360299312
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"clip_ratio/high_max": 0.010596543666906655,
|
| 863 |
+
"clip_ratio/high_mean": 0.006154476490337402,
|
| 864 |
+
"clip_ratio/low_mean": 0.007853075832827017,
|
| 865 |
+
"clip_ratio/low_min": 0.0018445946625433862,
|
| 866 |
+
"clip_ratio/region_mean": 0.014007552264956757,
|
| 867 |
+
"entropy": 0.04002648440655321,
|
| 868 |
+
"epoch": 0.00036,
|
| 869 |
+
"grad_norm": 4.1411895751953125,
|
| 870 |
+
"kl": 0.13405020465143025,
|
| 871 |
+
"learning_rate": 5e-05,
|
| 872 |
+
"loss": -0.903,
|
| 873 |
+
"step": 36,
|
| 874 |
+
"step_time": 72.99781238099604
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"clip_ratio/high_max": 0.005275360541418195,
|
| 878 |
+
"clip_ratio/high_mean": 0.0026376802707090974,
|
| 879 |
+
"clip_ratio/low_mean": 0.0028754653612850234,
|
| 880 |
+
"clip_ratio/low_min": 0.00042517005931586027,
|
| 881 |
+
"clip_ratio/region_mean": 0.005513145631994121,
|
| 882 |
+
"completions/clipped_ratio": 0.0,
|
| 883 |
+
"completions/max_length": 13047.0,
|
| 884 |
+
"completions/max_terminated_length": 13047.0,
|
| 885 |
+
"completions/mean_length": 9878.625,
|
| 886 |
+
"completions/mean_terminated_length": 9878.625,
|
| 887 |
+
"completions/min_length": 657.0,
|
| 888 |
+
"completions/min_terminated_length": 657.0,
|
| 889 |
+
"entropy": 0.03371463587973267,
|
| 890 |
+
"epoch": 0.00037,
|
| 891 |
+
"frac_reward_zero_std": 0.0,
|
| 892 |
+
"grad_norm": 3.8389480113983154,
|
| 893 |
+
"kl": 0.14478663937188685,
|
| 894 |
+
"learning_rate": 4.999300402366083e-05,
|
| 895 |
+
"loss": -0.0642,
|
| 896 |
+
"num_tokens": 7091798.0,
|
| 897 |
+
"reward": 0.2947101891040802,
|
| 898 |
+
"reward_std": 0.9005900621414185,
|
| 899 |
+
"rewards/rollout_reward_func/mean": 0.2947101891040802,
|
| 900 |
+
"rewards/rollout_reward_func/std": 0.9348424077033997,
|
| 901 |
+
"sampling/importance_sampling_ratio/max": 2.4184277057647705,
|
| 902 |
+
"sampling/importance_sampling_ratio/mean": 0.9990720152854919,
|
| 903 |
+
"sampling/importance_sampling_ratio/min": 0.15915784239768982,
|
| 904 |
+
"sampling/sampling_logp_difference/max": 1.83785879611969,
|
| 905 |
+
"sampling/sampling_logp_difference/mean": 0.009822597727179527,
|
| 906 |
+
"step": 37,
|
| 907 |
+
"step_time": 157.96763956499854
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"clip_ratio/high_max": 0.008132616407237947,
|
| 911 |
+
"clip_ratio/high_mean": 0.004482974822167307,
|
| 912 |
+
"clip_ratio/low_mean": 0.00759831492905505,
|
| 913 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 914 |
+
"clip_ratio/region_mean": 0.012081289780326188,
|
| 915 |
+
"entropy": 0.03477160807233304,
|
| 916 |
+
"epoch": 0.00038,
|
| 917 |
+
"grad_norm": 2.4872944355010986,
|
| 918 |
+
"kl": 0.13733661081641912,
|
| 919 |
+
"learning_rate": 4.997202131530303e-05,
|
| 920 |
+
"loss": -0.0742,
|
| 921 |
+
"step": 38,
|
| 922 |
+
"step_time": 69.91781051699581
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"clip_ratio/high_max": 0.008490972220897675,
|
| 926 |
+
"clip_ratio/high_mean": 0.005065609118901193,
|
| 927 |
+
"clip_ratio/low_mean": 0.005926517609623261,
|
| 928 |
+
"clip_ratio/low_min": 0.0008651451207697392,
|
| 929 |
+
"clip_ratio/region_mean": 0.010992126757628284,
|
| 930 |
+
"completions/clipped_ratio": 0.0,
|
| 931 |
+
"completions/max_length": 13241.0,
|
| 932 |
+
"completions/max_terminated_length": 13241.0,
|
| 933 |
+
"completions/mean_length": 9449.46875,
|
| 934 |
+
"completions/mean_terminated_length": 9449.46875,
|
| 935 |
+
"completions/min_length": 724.0,
|
| 936 |
+
"completions/min_terminated_length": 724.0,
|
| 937 |
+
"entropy": 0.04318245640024543,
|
| 938 |
+
"epoch": 0.00039,
|
| 939 |
+
"frac_reward_zero_std": 0.0,
|
| 940 |
+
"grad_norm": 4.977228164672852,
|
| 941 |
+
"kl": 0.15251367259770632,
|
| 942 |
+
"learning_rate": 4.993706753300993e-05,
|
| 943 |
+
"loss": -0.2261,
|
| 944 |
+
"num_tokens": 7421075.0,
|
| 945 |
+
"reward": -0.10847704857587814,
|
| 946 |
+
"reward_std": 0.6628357172012329,
|
| 947 |
+
"rewards/rollout_reward_func/mean": -0.10847704857587814,
|
| 948 |
+
"rewards/rollout_reward_func/std": 0.6781213283538818,
|
| 949 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 950 |
+
"sampling/importance_sampling_ratio/mean": 1.0004980564117432,
|
| 951 |
+
"sampling/importance_sampling_ratio/min": 0.38631442189216614,
|
| 952 |
+
"sampling/sampling_logp_difference/max": 1.6516692638397217,
|
| 953 |
+
"sampling/sampling_logp_difference/mean": 0.012933445163071156,
|
| 954 |
+
"step": 39,
|
| 955 |
+
"step_time": 159.9343009430013
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"clip_ratio/high_max": 0.00801005051471293,
|
| 959 |
+
"clip_ratio/high_mean": 0.00463565593236126,
|
| 960 |
+
"clip_ratio/low_mean": 0.0074972594738937914,
|
| 961 |
+
"clip_ratio/low_min": 0.0017302902415394783,
|
| 962 |
+
"clip_ratio/region_mean": 0.012132915493566543,
|
| 963 |
+
"entropy": 0.04298010759521276,
|
| 964 |
+
"epoch": 0.0004,
|
| 965 |
+
"grad_norm": 3.2948248386383057,
|
| 966 |
+
"kl": 0.14709224458783865,
|
| 967 |
+
"learning_rate": 4.988816876060381e-05,
|
| 968 |
+
"loss": -0.2293,
|
| 969 |
+
"step": 40,
|
| 970 |
+
"step_time": 71.67063941899687
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"clip_ratio/high_max": 0.0078367855749093,
|
| 974 |
+
"clip_ratio/high_mean": 0.00391839278745465,
|
| 975 |
+
"clip_ratio/low_mean": 0.004580665918183513,
|
| 976 |
+
"clip_ratio/low_min": 0.0016778901626821607,
|
| 977 |
+
"clip_ratio/region_mean": 0.008499058720190078,
|
| 978 |
+
"completions/clipped_ratio": 0.0,
|
| 979 |
+
"completions/max_length": 13282.0,
|
| 980 |
+
"completions/max_terminated_length": 13282.0,
|
| 981 |
+
"completions/mean_length": 11286.65625,
|
| 982 |
+
"completions/mean_terminated_length": 11286.65625,
|
| 983 |
+
"completions/min_length": 5097.0,
|
| 984 |
+
"completions/min_terminated_length": 5097.0,
|
| 985 |
+
"entropy": 0.040187596692703664,
|
| 986 |
+
"epoch": 0.00041,
|
| 987 |
+
"frac_reward_zero_std": 0.0,
|
| 988 |
+
"grad_norm": 6.325024127960205,
|
| 989 |
+
"kl": 0.1349788053194061,
|
| 990 |
+
"learning_rate": 4.98253614881812e-05,
|
| 991 |
+
"loss": 0.4806,
|
| 992 |
+
"num_tokens": 7808749.0,
|
| 993 |
+
"reward": 0.17059466242790222,
|
| 994 |
+
"reward_std": 0.8136788010597229,
|
| 995 |
+
"rewards/rollout_reward_func/mean": 0.17059466242790222,
|
| 996 |
+
"rewards/rollout_reward_func/std": 0.7990698218345642,
|
| 997 |
+
"sampling/importance_sampling_ratio/max": 2.513362169265747,
|
| 998 |
+
"sampling/importance_sampling_ratio/mean": 1.0001041889190674,
|
| 999 |
+
"sampling/importance_sampling_ratio/min": 0.04595469310879707,
|
| 1000 |
+
"sampling/sampling_logp_difference/max": 3.08009934425354,
|
| 1001 |
+
"sampling/sampling_logp_difference/mean": 0.012912388890981674,
|
| 1002 |
+
"step": 41,
|
| 1003 |
+
"step_time": 168.68965952500002
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"clip_ratio/high_max": 0.010451015492435545,
|
| 1007 |
+
"clip_ratio/high_mean": 0.0054425216221716255,
|
| 1008 |
+
"clip_ratio/low_mean": 0.011983542804955505,
|
| 1009 |
+
"clip_ratio/low_min": 0.005103718169266358,
|
| 1010 |
+
"clip_ratio/region_mean": 0.017426064412575215,
|
| 1011 |
+
"entropy": 0.042241197486873716,
|
| 1012 |
+
"epoch": 0.00042,
|
| 1013 |
+
"grad_norm": 3.489445209503174,
|
| 1014 |
+
"kl": 0.12189190601930022,
|
| 1015 |
+
"learning_rate": 4.974869258488254e-05,
|
| 1016 |
+
"loss": 0.4733,
|
| 1017 |
+
"step": 42,
|
| 1018 |
+
"step_time": 74.903593405008
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"clip_ratio/high_max": 0.009101398580241948,
|
| 1022 |
+
"clip_ratio/high_mean": 0.005175699247047305,
|
| 1023 |
+
"clip_ratio/low_mean": 0.0022814181866124272,
|
| 1024 |
+
"clip_ratio/low_min": 0.0,
|
| 1025 |
+
"clip_ratio/region_mean": 0.007457117491867393,
|
| 1026 |
+
"completions/clipped_ratio": 0.0,
|
| 1027 |
+
"completions/max_length": 13482.0,
|
| 1028 |
+
"completions/max_terminated_length": 13482.0,
|
| 1029 |
+
"completions/mean_length": 10740.0625,
|
| 1030 |
+
"completions/mean_terminated_length": 10740.0625,
|
| 1031 |
+
"completions/min_length": 512.0,
|
| 1032 |
+
"completions/min_terminated_length": 512.0,
|
| 1033 |
+
"entropy": 0.051280891231726855,
|
| 1034 |
+
"epoch": 0.00043,
|
| 1035 |
+
"frac_reward_zero_std": 0.0,
|
| 1036 |
+
"grad_norm": 4.938914775848389,
|
| 1037 |
+
"kl": 0.1590550672262907,
|
| 1038 |
+
"learning_rate": 4.965821926391673e-05,
|
| 1039 |
+
"loss": -1.2291,
|
| 1040 |
+
"num_tokens": 8178979.0,
|
| 1041 |
+
"reward": -0.07395707070827484,
|
| 1042 |
+
"reward_std": 0.6287177205085754,
|
| 1043 |
+
"rewards/rollout_reward_func/mean": -0.07395707070827484,
|
| 1044 |
+
"rewards/rollout_reward_func/std": 0.6483203172683716,
|
| 1045 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1046 |
+
"sampling/importance_sampling_ratio/mean": 1.0006033182144165,
|
| 1047 |
+
"sampling/importance_sampling_ratio/min": 0.17635640501976013,
|
| 1048 |
+
"sampling/sampling_logp_difference/max": 1.735248327255249,
|
| 1049 |
+
"sampling/sampling_logp_difference/mean": 0.01553763635456562,
|
| 1050 |
+
"step": 43,
|
| 1051 |
+
"step_time": 167.16221409800346
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"clip_ratio/high_max": 0.015113038418348879,
|
| 1055 |
+
"clip_ratio/high_mean": 0.008806519123027101,
|
| 1056 |
+
"clip_ratio/low_mean": 0.008764334983425215,
|
| 1057 |
+
"clip_ratio/low_min": 0.002106164349243045,
|
| 1058 |
+
"clip_ratio/region_mean": 0.017570854048244655,
|
| 1059 |
+
"entropy": 0.051857893471606076,
|
| 1060 |
+
"epoch": 0.00044,
|
| 1061 |
+
"grad_norm": 4.257857322692871,
|
| 1062 |
+
"kl": 0.1681835250928998,
|
| 1063 |
+
"learning_rate": 4.9554009039866464e-05,
|
| 1064 |
+
"loss": -1.259,
|
| 1065 |
+
"step": 44,
|
| 1066 |
+
"step_time": 75.09785533400282
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"clip_ratio/high_max": 0.014557944756234065,
|
| 1070 |
+
"clip_ratio/high_mean": 0.00841726346698124,
|
| 1071 |
+
"clip_ratio/low_mean": 0.007099654772900976,
|
| 1072 |
+
"clip_ratio/low_min": 0.0015867681941017509,
|
| 1073 |
+
"clip_ratio/region_mean": 0.015516918079811148,
|
| 1074 |
+
"completions/clipped_ratio": 0.0,
|
| 1075 |
+
"completions/max_length": 13154.0,
|
| 1076 |
+
"completions/max_terminated_length": 13154.0,
|
| 1077 |
+
"completions/mean_length": 9749.5,
|
| 1078 |
+
"completions/mean_terminated_length": 9749.5,
|
| 1079 |
+
"completions/min_length": 1209.0,
|
| 1080 |
+
"completions/min_terminated_length": 1209.0,
|
| 1081 |
+
"entropy": 0.07222186587750912,
|
| 1082 |
+
"epoch": 0.00045,
|
| 1083 |
+
"frac_reward_zero_std": 0.0,
|
| 1084 |
+
"grad_norm": 4.37516975402832,
|
| 1085 |
+
"kl": 0.18799102026969194,
|
| 1086 |
+
"learning_rate": 4.9436139678306335e-05,
|
| 1087 |
+
"loss": -1.0063,
|
| 1088 |
+
"num_tokens": 8517773.0,
|
| 1089 |
+
"reward": 0.27246785163879395,
|
| 1090 |
+
"reward_std": 0.9603098034858704,
|
| 1091 |
+
"rewards/rollout_reward_func/mean": 0.27246785163879395,
|
| 1092 |
+
"rewards/rollout_reward_func/std": 0.9796059131622314,
|
| 1093 |
+
"sampling/importance_sampling_ratio/max": 2.65130352973938,
|
| 1094 |
+
"sampling/importance_sampling_ratio/mean": 0.9977819919586182,
|
| 1095 |
+
"sampling/importance_sampling_ratio/min": 0.19320373237133026,
|
| 1096 |
+
"sampling/sampling_logp_difference/max": 1.644010066986084,
|
| 1097 |
+
"sampling/sampling_logp_difference/mean": 0.018468504771590233,
|
| 1098 |
+
"step": 45,
|
| 1099 |
+
"step_time": 157.59911965499487
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"clip_ratio/high_max": 0.018529696972109377,
|
| 1103 |
+
"clip_ratio/high_mean": 0.011184744304046035,
|
| 1104 |
+
"clip_ratio/low_mean": 0.014836993927019648,
|
| 1105 |
+
"clip_ratio/low_min": 0.00389691605232656,
|
| 1106 |
+
"clip_ratio/region_mean": 0.02602173836203292,
|
| 1107 |
+
"entropy": 0.07017613667994738,
|
| 1108 |
+
"epoch": 0.00046,
|
| 1109 |
+
"grad_norm": 4.444145679473877,
|
| 1110 |
+
"kl": 0.19352262001484632,
|
| 1111 |
+
"learning_rate": 4.930469913777124e-05,
|
| 1112 |
+
"loss": -1.0142,
|
| 1113 |
+
"step": 46,
|
| 1114 |
+
"step_time": 72.60382612999456
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"clip_ratio/high_max": 0.009264436783269048,
|
| 1118 |
+
"clip_ratio/high_mean": 0.0050559911178424954,
|
| 1119 |
+
"clip_ratio/low_mean": 0.005405787727795541,
|
| 1120 |
+
"clip_ratio/low_min": 0.0017123287543654442,
|
| 1121 |
+
"clip_ratio/region_mean": 0.010461778845638037,
|
| 1122 |
+
"completions/clipped_ratio": 0.0,
|
| 1123 |
+
"completions/max_length": 13436.0,
|
| 1124 |
+
"completions/max_terminated_length": 13436.0,
|
| 1125 |
+
"completions/mean_length": 9738.90625,
|
| 1126 |
+
"completions/mean_terminated_length": 9738.90625,
|
| 1127 |
+
"completions/min_length": 2217.0,
|
| 1128 |
+
"completions/min_terminated_length": 2217.0,
|
| 1129 |
+
"entropy": 0.06129000161308795,
|
| 1130 |
+
"epoch": 0.00047,
|
| 1131 |
+
"frac_reward_zero_std": 0.0,
|
| 1132 |
+
"grad_norm": 5.193581581115723,
|
| 1133 |
+
"kl": 0.22149202227592468,
|
| 1134 |
+
"learning_rate": 4.91597855041184e-05,
|
| 1135 |
+
"loss": -0.5912,
|
| 1136 |
+
"num_tokens": 8856267.0,
|
| 1137 |
+
"reward": 0.06697382032871246,
|
| 1138 |
+
"reward_std": 0.7488831877708435,
|
| 1139 |
+
"rewards/rollout_reward_func/mean": 0.06697382032871246,
|
| 1140 |
+
"rewards/rollout_reward_func/std": 0.8408234119415283,
|
| 1141 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1142 |
+
"sampling/importance_sampling_ratio/mean": 0.9977284669876099,
|
| 1143 |
+
"sampling/importance_sampling_ratio/min": 0.14137963950634003,
|
| 1144 |
+
"sampling/sampling_logp_difference/max": 1.9563064575195312,
|
| 1145 |
+
"sampling/sampling_logp_difference/mean": 0.019741810858249664,
|
| 1146 |
+
"step": 47,
|
| 1147 |
+
"step_time": 162.02058434099672
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"clip_ratio/high_max": 0.01009550440357998,
|
| 1151 |
+
"clip_ratio/high_mean": 0.005703912320313975,
|
| 1152 |
+
"clip_ratio/low_mean": 0.012514074885984883,
|
| 1153 |
+
"clip_ratio/low_min": 0.003124057315289974,
|
| 1154 |
+
"clip_ratio/region_mean": 0.018217987177195027,
|
| 1155 |
+
"entropy": 0.059198580449447036,
|
| 1156 |
+
"epoch": 0.00048,
|
| 1157 |
+
"grad_norm": 4.741568565368652,
|
| 1158 |
+
"kl": 0.33581918594427407,
|
| 1159 |
+
"learning_rate": 4.900150691733207e-05,
|
| 1160 |
+
"loss": -0.5888,
|
| 1161 |
+
"step": 48,
|
| 1162 |
+
"step_time": 72.85700078900118
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"clip_ratio/high_max": 0.006105485779698938,
|
| 1166 |
+
"clip_ratio/high_mean": 0.0032638915290590376,
|
| 1167 |
+
"clip_ratio/low_mean": 0.005087121811811812,
|
| 1168 |
+
"clip_ratio/low_min": 0.0012962963082827628,
|
| 1169 |
+
"clip_ratio/region_mean": 0.008351013195351698,
|
| 1170 |
+
"completions/clipped_ratio": 0.0,
|
| 1171 |
+
"completions/max_length": 13361.0,
|
| 1172 |
+
"completions/max_terminated_length": 13361.0,
|
| 1173 |
+
"completions/mean_length": 10574.78125,
|
| 1174 |
+
"completions/mean_terminated_length": 10574.78125,
|
| 1175 |
+
"completions/min_length": 2209.0,
|
| 1176 |
+
"completions/min_terminated_length": 2209.0,
|
| 1177 |
+
"entropy": 0.06214652210474014,
|
| 1178 |
+
"epoch": 0.00049,
|
| 1179 |
+
"frac_reward_zero_std": 0.0,
|
| 1180 |
+
"grad_norm": 5.913769245147705,
|
| 1181 |
+
"kl": 0.2271044417284429,
|
| 1182 |
+
"learning_rate": 4.8829981490825384e-05,
|
| 1183 |
+
"loss": 0.0406,
|
| 1184 |
+
"num_tokens": 9221107.0,
|
| 1185 |
+
"reward": 0.0014273226261138916,
|
| 1186 |
+
"reward_std": 1.042165994644165,
|
| 1187 |
+
"rewards/rollout_reward_func/mean": 0.0014273226261138916,
|
| 1188 |
+
"rewards/rollout_reward_func/std": 1.1747405529022217,
|
| 1189 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1190 |
+
"sampling/importance_sampling_ratio/mean": 1.0004156827926636,
|
| 1191 |
+
"sampling/importance_sampling_ratio/min": 0.03238532319664955,
|
| 1192 |
+
"sampling/sampling_logp_difference/max": 3.4300498962402344,
|
| 1193 |
+
"sampling/sampling_logp_difference/mean": 0.020954634994268417,
|
| 1194 |
+
"step": 49,
|
| 1195 |
+
"step_time": 167.1314073070098
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"clip_ratio/high_max": 0.011936334864003584,
|
| 1199 |
+
"clip_ratio/high_mean": 0.00661664160725195,
|
| 1200 |
+
"clip_ratio/low_mean": 0.011766647483455017,
|
| 1201 |
+
"clip_ratio/low_min": 0.0026851851725950837,
|
| 1202 |
+
"clip_ratio/region_mean": 0.018383289090706967,
|
| 1203 |
+
"entropy": 0.05987148266285658,
|
| 1204 |
+
"epoch": 0.0005,
|
| 1205 |
+
"grad_norm": 4.5713090896606445,
|
| 1206 |
+
"kl": 0.25915910955518484,
|
| 1207 |
+
"learning_rate": 4.864533722329971e-05,
|
| 1208 |
+
"loss": 0.032,
|
| 1209 |
+
"step": 50,
|
| 1210 |
+
"step_time": 73.75267140600772
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"clip_ratio/high_max": 0.005659546091919765,
|
| 1214 |
+
"clip_ratio/high_mean": 0.003255021831137128,
|
| 1215 |
+
"clip_ratio/low_mean": 0.005070317463832907,
|
| 1216 |
+
"clip_ratio/low_min": 0.002108652319293469,
|
| 1217 |
+
"clip_ratio/region_mean": 0.008325339294970036,
|
| 1218 |
+
"completions/clipped_ratio": 0.0,
|
| 1219 |
+
"completions/max_length": 13190.0,
|
| 1220 |
+
"completions/max_terminated_length": 13190.0,
|
| 1221 |
+
"completions/mean_length": 11075.46875,
|
| 1222 |
+
"completions/mean_terminated_length": 11075.46875,
|
| 1223 |
+
"completions/min_length": 3639.0,
|
| 1224 |
+
"completions/min_terminated_length": 3639.0,
|
| 1225 |
+
"entropy": 0.04613603337202221,
|
| 1226 |
+
"epoch": 0.00051,
|
| 1227 |
+
"frac_reward_zero_std": 0.0,
|
| 1228 |
+
"grad_norm": 6.114112854003906,
|
| 1229 |
+
"kl": 0.16452285135164857,
|
| 1230 |
+
"learning_rate": 4.8447711903227245e-05,
|
| 1231 |
+
"loss": 0.3885,
|
| 1232 |
+
"num_tokens": 9601902.0,
|
| 1233 |
+
"reward": 0.20258194208145142,
|
| 1234 |
+
"reward_std": 0.9743450880050659,
|
| 1235 |
+
"rewards/rollout_reward_func/mean": 0.20258194208145142,
|
| 1236 |
+
"rewards/rollout_reward_func/std": 1.0126794576644897,
|
| 1237 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1238 |
+
"sampling/importance_sampling_ratio/mean": 1.001020073890686,
|
| 1239 |
+
"sampling/importance_sampling_ratio/min": 0.14685897529125214,
|
| 1240 |
+
"sampling/sampling_logp_difference/max": 1.9182825088500977,
|
| 1241 |
+
"sampling/sampling_logp_difference/mean": 0.01429649069905281,
|
| 1242 |
+
"step": 51,
|
| 1243 |
+
"step_time": 167.67579722999653
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"clip_ratio/high_max": 0.00904727095621638,
|
| 1247 |
+
"clip_ratio/high_mean": 0.005424798160674982,
|
| 1248 |
+
"clip_ratio/low_mean": 0.008320969296619296,
|
| 1249 |
+
"clip_ratio/low_min": 0.0025309495395049453,
|
| 1250 |
+
"clip_ratio/region_mean": 0.013745767500950024,
|
| 1251 |
+
"entropy": 0.04530790273565799,
|
| 1252 |
+
"epoch": 0.00052,
|
| 1253 |
+
"grad_norm": 4.374583721160889,
|
| 1254 |
+
"kl": 0.1778181241825223,
|
| 1255 |
+
"learning_rate": 4.8237253006028074e-05,
|
| 1256 |
+
"loss": 0.373,
|
| 1257 |
+
"step": 52,
|
| 1258 |
+
"step_time": 73.67422152999279
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"clip_ratio/high_max": 0.008981934457551688,
|
| 1262 |
+
"clip_ratio/high_mean": 0.005327096936525777,
|
| 1263 |
+
"clip_ratio/low_mean": 0.0028215366910444573,
|
| 1264 |
+
"clip_ratio/low_min": 0.0,
|
| 1265 |
+
"clip_ratio/region_mean": 0.00814863367122598,
|
| 1266 |
+
"completions/clipped_ratio": 0.0,
|
| 1267 |
+
"completions/max_length": 13266.0,
|
| 1268 |
+
"completions/max_terminated_length": 13266.0,
|
| 1269 |
+
"completions/mean_length": 10068.46875,
|
| 1270 |
+
"completions/mean_terminated_length": 10068.46875,
|
| 1271 |
+
"completions/min_length": 2111.0,
|
| 1272 |
+
"completions/min_terminated_length": 2111.0,
|
| 1273 |
+
"entropy": 0.052251385175623,
|
| 1274 |
+
"epoch": 0.00053,
|
| 1275 |
+
"frac_reward_zero_std": 0.0,
|
| 1276 |
+
"grad_norm": 4.039042949676514,
|
| 1277 |
+
"kl": 0.15936051355674863,
|
| 1278 |
+
"learning_rate": 4.801411758401846e-05,
|
| 1279 |
+
"loss": -0.8609,
|
| 1280 |
+
"num_tokens": 9950736.0,
|
| 1281 |
+
"reward": -0.07826434075832367,
|
| 1282 |
+
"reward_std": 0.8228805065155029,
|
| 1283 |
+
"rewards/rollout_reward_func/mean": -0.07826434075832367,
|
| 1284 |
+
"rewards/rollout_reward_func/std": 0.9726049900054932,
|
| 1285 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1286 |
+
"sampling/importance_sampling_ratio/mean": 0.9996135234832764,
|
| 1287 |
+
"sampling/importance_sampling_ratio/min": 0.1369163990020752,
|
| 1288 |
+
"sampling/sampling_logp_difference/max": 1.98838472366333,
|
| 1289 |
+
"sampling/sampling_logp_difference/mean": 0.014011010527610779,
|
| 1290 |
+
"step": 53,
|
| 1291 |
+
"step_time": 166.02416877299765
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"clip_ratio/high_max": 0.011853837757371366,
|
| 1295 |
+
"clip_ratio/high_mean": 0.007465479196980596,
|
| 1296 |
+
"clip_ratio/low_mean": 0.010039673798019066,
|
| 1297 |
+
"clip_ratio/low_min": 0.0014534883666783571,
|
| 1298 |
+
"clip_ratio/region_mean": 0.017505153038655408,
|
| 1299 |
+
"entropy": 0.050861918134614825,
|
| 1300 |
+
"epoch": 0.00054,
|
| 1301 |
+
"grad_norm": 2.7967240810394287,
|
| 1302 |
+
"kl": 0.1533252433873713,
|
| 1303 |
+
"learning_rate": 4.777847214921259e-05,
|
| 1304 |
+
"loss": -0.8692,
|
| 1305 |
+
"step": 54,
|
| 1306 |
+
"step_time": 74.05675573799817
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"clip_ratio/high_max": 0.01076295055099763,
|
| 1310 |
+
"clip_ratio/high_mean": 0.006015452978317626,
|
| 1311 |
+
"clip_ratio/low_mean": 0.004845005663810298,
|
| 1312 |
+
"clip_ratio/low_min": 0.00041666667675599456,
|
| 1313 |
+
"clip_ratio/region_mean": 0.010860458569368348,
|
| 1314 |
+
"completions/clipped_ratio": 0.0,
|
| 1315 |
+
"completions/max_length": 13128.0,
|
| 1316 |
+
"completions/max_terminated_length": 13128.0,
|
| 1317 |
+
"completions/mean_length": 11066.8125,
|
| 1318 |
+
"completions/mean_terminated_length": 11066.8125,
|
| 1319 |
+
"completions/min_length": 899.0,
|
| 1320 |
+
"completions/min_terminated_length": 899.0,
|
| 1321 |
+
"entropy": 0.052756483550183475,
|
| 1322 |
+
"epoch": 0.00055,
|
| 1323 |
+
"frac_reward_zero_std": 0.0,
|
| 1324 |
+
"grad_norm": 5.2398858070373535,
|
| 1325 |
+
"kl": 0.16460610833019018,
|
| 1326 |
+
"learning_rate": 4.753049254906501e-05,
|
| 1327 |
+
"loss": 0.0265,
|
| 1328 |
+
"num_tokens": 10330842.0,
|
| 1329 |
+
"reward": 0.053395774215459824,
|
| 1330 |
+
"reward_std": 0.7901345491409302,
|
| 1331 |
+
"rewards/rollout_reward_func/mean": 0.053395774215459824,
|
| 1332 |
+
"rewards/rollout_reward_func/std": 0.8272984623908997,
|
| 1333 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1334 |
+
"sampling/importance_sampling_ratio/mean": 1.0008231401443481,
|
| 1335 |
+
"sampling/importance_sampling_ratio/min": 0.21802321076393127,
|
| 1336 |
+
"sampling/sampling_logp_difference/max": 1.5231537818908691,
|
| 1337 |
+
"sampling/sampling_logp_difference/mean": 0.01787828654050827,
|
| 1338 |
+
"step": 55,
|
| 1339 |
+
"step_time": 168.7718367270063
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"clip_ratio/high_max": 0.012885269446996972,
|
| 1343 |
+
"clip_ratio/high_mean": 0.006856542007881217,
|
| 1344 |
+
"clip_ratio/low_mean": 0.013156471701222472,
|
| 1345 |
+
"clip_ratio/low_min": 0.0017187500488944352,
|
| 1346 |
+
"clip_ratio/region_mean": 0.020013013621792197,
|
| 1347 |
+
"entropy": 0.04982141393702477,
|
| 1348 |
+
"epoch": 0.00056,
|
| 1349 |
+
"grad_norm": 4.425920486450195,
|
| 1350 |
+
"kl": 0.19017641432583332,
|
| 1351 |
+
"learning_rate": 4.727036383524666e-05,
|
| 1352 |
+
"loss": 0.0102,
|
| 1353 |
+
"step": 56,
|
| 1354 |
+
"step_time": 73.32767669900568
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"clip_ratio/high_max": 0.008151731628458947,
|
| 1358 |
+
"clip_ratio/high_mean": 0.004496746012591757,
|
| 1359 |
+
"clip_ratio/low_mean": 0.0041994539787992835,
|
| 1360 |
+
"clip_ratio/low_min": 0.0016025641234591603,
|
| 1361 |
+
"clip_ratio/region_mean": 0.00869619999139104,
|
| 1362 |
+
"completions/clipped_ratio": 0.0,
|
| 1363 |
+
"completions/max_length": 13100.0,
|
| 1364 |
+
"completions/max_terminated_length": 13100.0,
|
| 1365 |
+
"completions/mean_length": 10688.53125,
|
| 1366 |
+
"completions/mean_terminated_length": 10688.53125,
|
| 1367 |
+
"completions/min_length": 1659.0,
|
| 1368 |
+
"completions/min_terminated_length": 1659.0,
|
| 1369 |
+
"entropy": 0.041110213147476315,
|
| 1370 |
+
"epoch": 0.00057,
|
| 1371 |
+
"frac_reward_zero_std": 0.0,
|
| 1372 |
+
"grad_norm": 4.053499221801758,
|
| 1373 |
+
"kl": 0.16082082968205214,
|
| 1374 |
+
"learning_rate": 4.699828012555243e-05,
|
| 1375 |
+
"loss": -0.2207,
|
| 1376 |
+
"num_tokens": 10698978.0,
|
| 1377 |
+
"reward": 0.07224054634571075,
|
| 1378 |
+
"reward_std": 0.7553356885910034,
|
| 1379 |
+
"rewards/rollout_reward_func/mean": 0.07224054634571075,
|
| 1380 |
+
"rewards/rollout_reward_func/std": 0.7995120286941528,
|
| 1381 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1382 |
+
"sampling/importance_sampling_ratio/mean": 0.9975321292877197,
|
| 1383 |
+
"sampling/importance_sampling_ratio/min": 0.21801193058490753,
|
| 1384 |
+
"sampling/sampling_logp_difference/max": 2.1512062549591064,
|
| 1385 |
+
"sampling/sampling_logp_difference/mean": 0.012901031412184238,
|
| 1386 |
+
"step": 57,
|
| 1387 |
+
"step_time": 166.55692352800543
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"clip_ratio/high_max": 0.01201454337569885,
|
| 1391 |
+
"clip_ratio/high_mean": 0.0074542641377775,
|
| 1392 |
+
"clip_ratio/low_mean": 0.005944907039520331,
|
| 1393 |
+
"clip_ratio/low_min": 0.00042517005931586027,
|
| 1394 |
+
"clip_ratio/region_mean": 0.01339917117729783,
|
| 1395 |
+
"entropy": 0.04046116629615426,
|
| 1396 |
+
"epoch": 0.00058,
|
| 1397 |
+
"grad_norm": 2.3814172744750977,
|
| 1398 |
+
"kl": 0.18354935571551323,
|
| 1399 |
+
"learning_rate": 4.671444445904316e-05,
|
| 1400 |
+
"loss": -0.2364,
|
| 1401 |
+
"step": 58,
|
| 1402 |
+
"step_time": 73.06675892299609
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"clip_ratio/high_max": 0.004129695822484791,
|
| 1406 |
+
"clip_ratio/high_mean": 0.00248151458799839,
|
| 1407 |
+
"clip_ratio/low_mean": 0.0025588898279238492,
|
| 1408 |
+
"clip_ratio/low_min": 0.00041666667675599456,
|
| 1409 |
+
"clip_ratio/region_mean": 0.005040404415922239,
|
| 1410 |
+
"completions/clipped_ratio": 0.0,
|
| 1411 |
+
"completions/max_length": 13176.0,
|
| 1412 |
+
"completions/max_terminated_length": 13176.0,
|
| 1413 |
+
"completions/mean_length": 9803.90625,
|
| 1414 |
+
"completions/mean_terminated_length": 9803.90625,
|
| 1415 |
+
"completions/min_length": 663.0,
|
| 1416 |
+
"completions/min_terminated_length": 663.0,
|
| 1417 |
+
"entropy": 0.04748129227664322,
|
| 1418 |
+
"epoch": 0.00059,
|
| 1419 |
+
"frac_reward_zero_std": 0.0,
|
| 1420 |
+
"grad_norm": 4.284725189208984,
|
| 1421 |
+
"kl": 0.18153538985643536,
|
| 1422 |
+
"learning_rate": 4.641906864453027e-05,
|
| 1423 |
+
"loss": -0.7635,
|
| 1424 |
+
"num_tokens": 11038846.0,
|
| 1425 |
+
"reward": 0.13717541098594666,
|
| 1426 |
+
"reward_std": 0.9412651062011719,
|
| 1427 |
+
"rewards/rollout_reward_func/mean": 0.13717541098594666,
|
| 1428 |
+
"rewards/rollout_reward_func/std": 0.9482499361038208,
|
| 1429 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1430 |
+
"sampling/importance_sampling_ratio/mean": 0.9980131983757019,
|
| 1431 |
+
"sampling/importance_sampling_ratio/min": 0.18534508347511292,
|
| 1432 |
+
"sampling/sampling_logp_difference/max": 1.6855359077453613,
|
| 1433 |
+
"sampling/sampling_logp_difference/mean": 0.0141033586114645,
|
| 1434 |
+
"step": 59,
|
| 1435 |
+
"step_time": 160.25458542300476
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"clip_ratio/high_max": 0.009755878942087293,
|
| 1439 |
+
"clip_ratio/high_mean": 0.005086272780317813,
|
| 1440 |
+
"clip_ratio/low_mean": 0.010913642530795187,
|
| 1441 |
+
"clip_ratio/low_min": 0.00582064944319427,
|
| 1442 |
+
"clip_ratio/region_mean": 0.015999915311113,
|
| 1443 |
+
"entropy": 0.04707136598881334,
|
| 1444 |
+
"epoch": 0.0006,
|
| 1445 |
+
"grad_norm": 3.2246789932250977,
|
| 1446 |
+
"kl": 0.2255641722586006,
|
| 1447 |
+
"learning_rate": 4.6112373102516095e-05,
|
| 1448 |
+
"loss": -0.789,
|
| 1449 |
+
"step": 60,
|
| 1450 |
+
"step_time": 72.25460137299524
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"clip_ratio/high_max": 0.007714824576396495,
|
| 1454 |
+
"clip_ratio/high_mean": 0.004483810480451211,
|
| 1455 |
+
"clip_ratio/low_mean": 0.003787761408602819,
|
| 1456 |
+
"clip_ratio/low_min": 0.00042229730752296746,
|
| 1457 |
+
"clip_ratio/region_mean": 0.008271571874502115,
|
| 1458 |
+
"completions/clipped_ratio": 0.0,
|
| 1459 |
+
"completions/max_length": 13179.0,
|
| 1460 |
+
"completions/max_terminated_length": 13179.0,
|
| 1461 |
+
"completions/mean_length": 10362.78125,
|
| 1462 |
+
"completions/mean_terminated_length": 10362.78125,
|
| 1463 |
+
"completions/min_length": 2001.0,
|
| 1464 |
+
"completions/min_terminated_length": 2001.0,
|
| 1465 |
+
"entropy": 0.038825739873573184,
|
| 1466 |
+
"epoch": 0.00061,
|
| 1467 |
+
"frac_reward_zero_std": 0.0,
|
| 1468 |
+
"grad_norm": 3.541637420654297,
|
| 1469 |
+
"kl": 0.1603014951106161,
|
| 1470 |
+
"learning_rate": 4.5794586700707875e-05,
|
| 1471 |
+
"loss": 0.1258,
|
| 1472 |
+
"num_tokens": 11396771.0,
|
| 1473 |
+
"reward": 0.24396184086799622,
|
| 1474 |
+
"reward_std": 0.822333037853241,
|
| 1475 |
+
"rewards/rollout_reward_func/mean": 0.24396184086799622,
|
| 1476 |
+
"rewards/rollout_reward_func/std": 0.7946814298629761,
|
| 1477 |
+
"sampling/importance_sampling_ratio/max": 2.8133909702301025,
|
| 1478 |
+
"sampling/importance_sampling_ratio/mean": 1.0008466243743896,
|
| 1479 |
+
"sampling/importance_sampling_ratio/min": 0.37330174446105957,
|
| 1480 |
+
"sampling/sampling_logp_difference/max": 1.0343904495239258,
|
| 1481 |
+
"sampling/sampling_logp_difference/mean": 0.009579579345881939,
|
| 1482 |
+
"step": 61,
|
| 1483 |
+
"step_time": 163.49556491199837
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"clip_ratio/high_max": 0.013337028271052986,
|
| 1487 |
+
"clip_ratio/high_mean": 0.007507459231419489,
|
| 1488 |
+
"clip_ratio/low_mean": 0.009406370008946396,
|
| 1489 |
+
"clip_ratio/low_min": 0.0033371542231179774,
|
| 1490 |
+
"clip_ratio/region_mean": 0.016913829240365885,
|
| 1491 |
+
"entropy": 0.039391311816871166,
|
| 1492 |
+
"epoch": 0.00062,
|
| 1493 |
+
"grad_norm": 1.9976162910461426,
|
| 1494 |
+
"kl": 0.17127820663154125,
|
| 1495 |
+
"learning_rate": 4.546594658322805e-05,
|
| 1496 |
+
"loss": 0.1168,
|
| 1497 |
+
"step": 62,
|
| 1498 |
+
"step_time": 72.66579336100767
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"clip_ratio/high_max": 0.007516533107263967,
|
| 1502 |
+
"clip_ratio/high_mean": 0.0037582665536319837,
|
| 1503 |
+
"clip_ratio/low_mean": 0.004609227966284379,
|
| 1504 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 1505 |
+
"clip_ratio/region_mean": 0.008367494549020194,
|
| 1506 |
+
"completions/clipped_ratio": 0.0,
|
| 1507 |
+
"completions/max_length": 12647.0,
|
| 1508 |
+
"completions/max_terminated_length": 12647.0,
|
| 1509 |
+
"completions/mean_length": 9626.34375,
|
| 1510 |
+
"completions/mean_terminated_length": 9626.34375,
|
| 1511 |
+
"completions/min_length": 2082.0,
|
| 1512 |
+
"completions/min_terminated_length": 2082.0,
|
| 1513 |
+
"entropy": 0.04371998517308384,
|
| 1514 |
+
"epoch": 0.00063,
|
| 1515 |
+
"frac_reward_zero_std": 0.0,
|
| 1516 |
+
"grad_norm": 3.0750207901000977,
|
| 1517 |
+
"kl": 0.23586172657087445,
|
| 1518 |
+
"learning_rate": 4.512669799364848e-05,
|
| 1519 |
+
"loss": 0.2851,
|
| 1520 |
+
"num_tokens": 11730926.0,
|
| 1521 |
+
"reward": 0.1786271631717682,
|
| 1522 |
+
"reward_std": 0.671964168548584,
|
| 1523 |
+
"rewards/rollout_reward_func/mean": 0.1786271631717682,
|
| 1524 |
+
"rewards/rollout_reward_func/std": 0.7027593851089478,
|
| 1525 |
+
"sampling/importance_sampling_ratio/max": 2.313385248184204,
|
| 1526 |
+
"sampling/importance_sampling_ratio/mean": 0.9989328384399414,
|
| 1527 |
+
"sampling/importance_sampling_ratio/min": 0.14483538269996643,
|
| 1528 |
+
"sampling/sampling_logp_difference/max": 1.9321575164794922,
|
| 1529 |
+
"sampling/sampling_logp_difference/mean": 0.012537499889731407,
|
| 1530 |
+
"step": 63,
|
| 1531 |
+
"step_time": 156.11718567599382
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"clip_ratio/high_max": 0.014760866208234802,
|
| 1535 |
+
"clip_ratio/high_mean": 0.00759016461961437,
|
| 1536 |
+
"clip_ratio/low_mean": 0.009175922066788189,
|
| 1537 |
+
"clip_ratio/low_min": 0.002094518975354731,
|
| 1538 |
+
"clip_ratio/region_mean": 0.01676608665729873,
|
| 1539 |
+
"entropy": 0.04859339352697134,
|
| 1540 |
+
"epoch": 0.00064,
|
| 1541 |
+
"grad_norm": 2.8551297187805176,
|
| 1542 |
+
"kl": 0.23367749294266105,
|
| 1543 |
+
"learning_rate": 4.477709409198042e-05,
|
| 1544 |
+
"loss": 0.2813,
|
| 1545 |
+
"step": 64,
|
| 1546 |
+
"step_time": 68.68542803400123
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"clip_ratio/high_max": 0.0030558938160538673,
|
| 1550 |
+
"clip_ratio/high_mean": 0.0015279469080269337,
|
| 1551 |
+
"clip_ratio/low_mean": 0.003682863956782967,
|
| 1552 |
+
"clip_ratio/low_min": 0.0,
|
| 1553 |
+
"clip_ratio/region_mean": 0.005210810893913731,
|
| 1554 |
+
"completions/clipped_ratio": 0.0,
|
| 1555 |
+
"completions/max_length": 12710.0,
|
| 1556 |
+
"completions/max_terminated_length": 12710.0,
|
| 1557 |
+
"completions/mean_length": 9393.03125,
|
| 1558 |
+
"completions/mean_terminated_length": 9393.03125,
|
| 1559 |
+
"completions/min_length": 1634.0,
|
| 1560 |
+
"completions/min_terminated_length": 1634.0,
|
| 1561 |
+
"entropy": 0.05264301272109151,
|
| 1562 |
+
"epoch": 0.00065,
|
| 1563 |
+
"frac_reward_zero_std": 0.0,
|
| 1564 |
+
"grad_norm": 4.439396858215332,
|
| 1565 |
+
"kl": 0.2075956475455314,
|
| 1566 |
+
"learning_rate": 4.441739576575714e-05,
|
| 1567 |
+
"loss": 0.701,
|
| 1568 |
+
"num_tokens": 12057521.0,
|
| 1569 |
+
"reward": 0.40391504764556885,
|
| 1570 |
+
"reward_std": 0.80250084400177,
|
| 1571 |
+
"rewards/rollout_reward_func/mean": 0.40391504764556885,
|
| 1572 |
+
"rewards/rollout_reward_func/std": 0.8927465081214905,
|
| 1573 |
+
"sampling/importance_sampling_ratio/max": 2.7482974529266357,
|
| 1574 |
+
"sampling/importance_sampling_ratio/mean": 1.0016303062438965,
|
| 1575 |
+
"sampling/importance_sampling_ratio/min": 0.26992499828338623,
|
| 1576 |
+
"sampling/sampling_logp_difference/max": 1.309611201286316,
|
| 1577 |
+
"sampling/sampling_logp_difference/mean": 0.012656865641474724,
|
| 1578 |
+
"step": 65,
|
| 1579 |
+
"step_time": 157.0456754090119
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"clip_ratio/high_max": 0.011578783625736833,
|
| 1583 |
+
"clip_ratio/high_mean": 0.006229532649740577,
|
| 1584 |
+
"clip_ratio/low_mean": 0.008213154564145952,
|
| 1585 |
+
"clip_ratio/low_min": 0.0016835207934491336,
|
| 1586 |
+
"clip_ratio/region_mean": 0.01444268724299036,
|
| 1587 |
+
"entropy": 0.05576217197813094,
|
| 1588 |
+
"epoch": 0.00066,
|
| 1589 |
+
"grad_norm": 2.467440605163574,
|
| 1590 |
+
"kl": 0.2055382311809808,
|
| 1591 |
+
"learning_rate": 4.404787143534977e-05,
|
| 1592 |
+
"loss": 0.6828,
|
| 1593 |
+
"step": 66,
|
| 1594 |
+
"step_time": 69.32088893900436
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"clip_ratio/high_max": 0.005042135278927162,
|
| 1598 |
+
"clip_ratio/high_mean": 0.003166579277603887,
|
| 1599 |
+
"clip_ratio/low_mean": 0.006012097903294489,
|
| 1600 |
+
"clip_ratio/low_min": 0.0017156008398160338,
|
| 1601 |
+
"clip_ratio/region_mean": 0.009178677151794545,
|
| 1602 |
+
"completions/clipped_ratio": 0.0,
|
| 1603 |
+
"completions/max_length": 13314.0,
|
| 1604 |
+
"completions/max_terminated_length": 13314.0,
|
| 1605 |
+
"completions/mean_length": 10746.4375,
|
| 1606 |
+
"completions/mean_terminated_length": 10746.4375,
|
| 1607 |
+
"completions/min_length": 413.0,
|
| 1608 |
+
"completions/min_terminated_length": 413.0,
|
| 1609 |
+
"entropy": 0.05329764215275645,
|
| 1610 |
+
"epoch": 0.00067,
|
| 1611 |
+
"frac_reward_zero_std": 0.0,
|
| 1612 |
+
"grad_norm": 3.5107641220092773,
|
| 1613 |
+
"kl": 0.19909493857994676,
|
| 1614 |
+
"learning_rate": 4.366879685366202e-05,
|
| 1615 |
+
"loss": -0.0363,
|
| 1616 |
+
"num_tokens": 12427620.0,
|
| 1617 |
+
"reward": -0.05278514325618744,
|
| 1618 |
+
"reward_std": 0.5065455436706543,
|
| 1619 |
+
"rewards/rollout_reward_func/mean": -0.05278514325618744,
|
| 1620 |
+
"rewards/rollout_reward_func/std": 0.6038879156112671,
|
| 1621 |
+
"sampling/importance_sampling_ratio/max": 1.9659762382507324,
|
| 1622 |
+
"sampling/importance_sampling_ratio/mean": 0.9986153841018677,
|
| 1623 |
+
"sampling/importance_sampling_ratio/min": 0.21797966957092285,
|
| 1624 |
+
"sampling/sampling_logp_difference/max": 1.5233535766601562,
|
| 1625 |
+
"sampling/sampling_logp_difference/mean": 0.012393541634082794,
|
| 1626 |
+
"step": 67,
|
| 1627 |
+
"step_time": 166.0341528559984
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"clip_ratio/high_max": 0.008735484327189624,
|
| 1631 |
+
"clip_ratio/high_mean": 0.005423485417850316,
|
| 1632 |
+
"clip_ratio/low_mean": 0.010732135677244514,
|
| 1633 |
+
"clip_ratio/low_min": 0.0028922114870510995,
|
| 1634 |
+
"clip_ratio/region_mean": 0.01615562100778334,
|
| 1635 |
+
"entropy": 0.05276717653032392,
|
| 1636 |
+
"epoch": 0.00068,
|
| 1637 |
+
"grad_norm": 5.79787540435791,
|
| 1638 |
+
"kl": 0.2132586808875203,
|
| 1639 |
+
"learning_rate": 4.3280454900353015e-05,
|
| 1640 |
+
"loss": -0.0566,
|
| 1641 |
+
"step": 68,
|
| 1642 |
+
"step_time": 73.57829091900203
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"clip_ratio/high_max": 0.011086496990174055,
|
| 1646 |
+
"clip_ratio/high_mean": 0.0059599152009468526,
|
| 1647 |
+
"clip_ratio/low_mean": 0.003915530367521569,
|
| 1648 |
+
"clip_ratio/low_min": 0.0008503401186317205,
|
| 1649 |
+
"clip_ratio/region_mean": 0.009875445597572252,
|
| 1650 |
+
"completions/clipped_ratio": 0.0,
|
| 1651 |
+
"completions/max_length": 13366.0,
|
| 1652 |
+
"completions/max_terminated_length": 13366.0,
|
| 1653 |
+
"completions/mean_length": 8519.09375,
|
| 1654 |
+
"completions/mean_terminated_length": 8519.09375,
|
| 1655 |
+
"completions/min_length": 403.0,
|
| 1656 |
+
"completions/min_terminated_length": 403.0,
|
| 1657 |
+
"entropy": 0.06176481384318322,
|
| 1658 |
+
"epoch": 0.00069,
|
| 1659 |
+
"frac_reward_zero_std": 0.0,
|
| 1660 |
+
"grad_norm": 4.625095367431641,
|
| 1661 |
+
"kl": 0.22681198676582426,
|
| 1662 |
+
"learning_rate": 4.288313537074191e-05,
|
| 1663 |
+
"loss": -0.8238,
|
| 1664 |
+
"num_tokens": 12726508.0,
|
| 1665 |
+
"reward": 0.10592889785766602,
|
| 1666 |
+
"reward_std": 0.8413736820220947,
|
| 1667 |
+
"rewards/rollout_reward_func/mean": 0.10592889785766602,
|
| 1668 |
+
"rewards/rollout_reward_func/std": 0.8298947811126709,
|
| 1669 |
+
"sampling/importance_sampling_ratio/max": 2.5253984928131104,
|
| 1670 |
+
"sampling/importance_sampling_ratio/mean": 0.9988598823547363,
|
| 1671 |
+
"sampling/importance_sampling_ratio/min": 0.3644062876701355,
|
| 1672 |
+
"sampling/sampling_logp_difference/max": 1.0094858407974243,
|
| 1673 |
+
"sampling/sampling_logp_difference/mean": 0.013074668124318123,
|
| 1674 |
+
"step": 69,
|
| 1675 |
+
"step_time": 160.9605769760019
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"clip_ratio/high_max": 0.010014714149292558,
|
| 1679 |
+
"clip_ratio/high_mean": 0.005424023693194613,
|
| 1680 |
+
"clip_ratio/low_mean": 0.009666147583629936,
|
| 1681 |
+
"clip_ratio/low_min": 0.0025510203558951616,
|
| 1682 |
+
"clip_ratio/region_mean": 0.015090171465999447,
|
| 1683 |
+
"entropy": 0.059861738176550716,
|
| 1684 |
+
"epoch": 0.0007,
|
| 1685 |
+
"grad_norm": 2.4509620666503906,
|
| 1686 |
+
"kl": 0.2412201176630333,
|
| 1687 |
+
"learning_rate": 4.2477134759551676e-05,
|
| 1688 |
+
"loss": -0.8366,
|
| 1689 |
+
"step": 70,
|
| 1690 |
+
"step_time": 72.93759117600348
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"clip_ratio/high_max": 0.004440079559572041,
|
| 1694 |
+
"clip_ratio/high_mean": 0.002428373132715933,
|
| 1695 |
+
"clip_ratio/low_mean": 0.0032831220742082223,
|
| 1696 |
+
"clip_ratio/low_min": 0.0,
|
| 1697 |
+
"clip_ratio/region_mean": 0.00571149516326841,
|
| 1698 |
+
"completions/clipped_ratio": 0.0,
|
| 1699 |
+
"completions/max_length": 12877.0,
|
| 1700 |
+
"completions/max_terminated_length": 12877.0,
|
| 1701 |
+
"completions/mean_length": 10483.0,
|
| 1702 |
+
"completions/mean_terminated_length": 10483.0,
|
| 1703 |
+
"completions/min_length": 400.0,
|
| 1704 |
+
"completions/min_terminated_length": 400.0,
|
| 1705 |
+
"entropy": 0.042265110299922526,
|
| 1706 |
+
"epoch": 0.00071,
|
| 1707 |
+
"frac_reward_zero_std": 0.0,
|
| 1708 |
+
"grad_norm": 6.566309928894043,
|
| 1709 |
+
"kl": 0.29861711349803954,
|
| 1710 |
+
"learning_rate": 4.206275603965376e-05,
|
| 1711 |
+
"loss": -0.0193,
|
| 1712 |
+
"num_tokens": 13088062.0,
|
| 1713 |
+
"reward": 0.2799592912197113,
|
| 1714 |
+
"reward_std": 0.8195935487747192,
|
| 1715 |
+
"rewards/rollout_reward_func/mean": 0.2799592912197113,
|
| 1716 |
+
"rewards/rollout_reward_func/std": 0.8185666799545288,
|
| 1717 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1718 |
+
"sampling/importance_sampling_ratio/mean": 0.9999350905418396,
|
| 1719 |
+
"sampling/importance_sampling_ratio/min": 0.20893976092338562,
|
| 1720 |
+
"sampling/sampling_logp_difference/max": 1.5657092332839966,
|
| 1721 |
+
"sampling/sampling_logp_difference/mean": 0.010059979744255543,
|
| 1722 |
+
"step": 71,
|
| 1723 |
+
"step_time": 163.97088142000212
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"clip_ratio/high_max": 0.009024532453622669,
|
| 1727 |
+
"clip_ratio/high_mean": 0.0049289329326711595,
|
| 1728 |
+
"clip_ratio/low_mean": 0.003570742075680755,
|
| 1729 |
+
"clip_ratio/low_min": 0.0,
|
| 1730 |
+
"clip_ratio/region_mean": 0.008499675037455745,
|
| 1731 |
+
"entropy": 0.04315118561498821,
|
| 1732 |
+
"epoch": 0.00072,
|
| 1733 |
+
"grad_norm": 3.726982355117798,
|
| 1734 |
+
"kl": 0.16696504969149828,
|
| 1735 |
+
"learning_rate": 4.1640308435978284e-05,
|
| 1736 |
+
"loss": -0.033,
|
| 1737 |
+
"step": 72,
|
| 1738 |
+
"step_time": 70.53560518000086
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"clip_ratio/high_max": 0.0072561182314530015,
|
| 1742 |
+
"clip_ratio/high_mean": 0.004068221780471504,
|
| 1743 |
+
"clip_ratio/low_mean": 0.005030757718486711,
|
| 1744 |
+
"clip_ratio/low_min": 0.0008477011579088867,
|
| 1745 |
+
"clip_ratio/region_mean": 0.0090989794844063,
|
| 1746 |
+
"completions/clipped_ratio": 0.0,
|
| 1747 |
+
"completions/max_length": 13527.0,
|
| 1748 |
+
"completions/max_terminated_length": 13527.0,
|
| 1749 |
+
"completions/mean_length": 10463.59375,
|
| 1750 |
+
"completions/mean_terminated_length": 10463.59375,
|
| 1751 |
+
"completions/min_length": 697.0,
|
| 1752 |
+
"completions/min_terminated_length": 697.0,
|
| 1753 |
+
"entropy": 0.06954505993053317,
|
| 1754 |
+
"epoch": 0.00073,
|
| 1755 |
+
"frac_reward_zero_std": 0.0,
|
| 1756 |
+
"grad_norm": 3.154179573059082,
|
| 1757 |
+
"kl": 0.2885348331183195,
|
| 1758 |
+
"learning_rate": 4.121010719475882e-05,
|
| 1759 |
+
"loss": 0.4437,
|
| 1760 |
+
"num_tokens": 13448939.0,
|
| 1761 |
+
"reward": 0.031230026856064796,
|
| 1762 |
+
"reward_std": 1.2288157939910889,
|
| 1763 |
+
"rewards/rollout_reward_func/mean": 0.031230026856064796,
|
| 1764 |
+
"rewards/rollout_reward_func/std": 1.4065639972686768,
|
| 1765 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1766 |
+
"sampling/importance_sampling_ratio/mean": 1.001633882522583,
|
| 1767 |
+
"sampling/importance_sampling_ratio/min": 0.07619146257638931,
|
| 1768 |
+
"sampling/sampling_logp_difference/max": 2.5745058059692383,
|
| 1769 |
+
"sampling/sampling_logp_difference/mean": 0.015677718445658684,
|
| 1770 |
+
"step": 73,
|
| 1771 |
+
"step_time": 168.45864097499725
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"clip_ratio/high_max": 0.01567425244138576,
|
| 1775 |
+
"clip_ratio/high_mean": 0.008502019758452661,
|
| 1776 |
+
"clip_ratio/low_mean": 0.007619034266099334,
|
| 1777 |
+
"clip_ratio/low_min": 0.0012556306610349566,
|
| 1778 |
+
"clip_ratio/region_mean": 0.0161210541264154,
|
| 1779 |
+
"entropy": 0.06863664695993066,
|
| 1780 |
+
"epoch": 0.00074,
|
| 1781 |
+
"grad_norm": 3.359342098236084,
|
| 1782 |
+
"kl": 0.32731896825134754,
|
| 1783 |
+
"learning_rate": 4.077247334828387e-05,
|
| 1784 |
+
"loss": 0.4367,
|
| 1785 |
+
"step": 74,
|
| 1786 |
+
"step_time": 76.37142113899972
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"clip_ratio/high_max": 0.00919221993535757,
|
| 1790 |
+
"clip_ratio/high_mean": 0.004596109967678785,
|
| 1791 |
+
"clip_ratio/low_mean": 0.0027718102501239628,
|
| 1792 |
+
"clip_ratio/low_min": 0.0008627254865132272,
|
| 1793 |
+
"clip_ratio/region_mean": 0.007367920188698918,
|
| 1794 |
+
"completions/clipped_ratio": 0.0,
|
| 1795 |
+
"completions/max_length": 13662.0,
|
| 1796 |
+
"completions/max_terminated_length": 13662.0,
|
| 1797 |
+
"completions/mean_length": 12236.15625,
|
| 1798 |
+
"completions/mean_terminated_length": 12236.15625,
|
| 1799 |
+
"completions/min_length": 6765.0,
|
| 1800 |
+
"completions/min_terminated_length": 6765.0,
|
| 1801 |
+
"entropy": 0.05073382775299251,
|
| 1802 |
+
"epoch": 0.00075,
|
| 1803 |
+
"frac_reward_zero_std": 0.0,
|
| 1804 |
+
"grad_norm": 3.2718288898468018,
|
| 1805 |
+
"kl": 0.21677575819194317,
|
| 1806 |
+
"learning_rate": 4.032773347533051e-05,
|
| 1807 |
+
"loss": 0.4564,
|
| 1808 |
+
"num_tokens": 13866649.0,
|
| 1809 |
+
"reward": 0.2860051393508911,
|
| 1810 |
+
"reward_std": 0.8219031095504761,
|
| 1811 |
+
"rewards/rollout_reward_func/mean": 0.2860051393508911,
|
| 1812 |
+
"rewards/rollout_reward_func/std": 0.7910440564155579,
|
| 1813 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1814 |
+
"sampling/importance_sampling_ratio/mean": 0.99900221824646,
|
| 1815 |
+
"sampling/importance_sampling_ratio/min": 0.13723966479301453,
|
| 1816 |
+
"sampling/sampling_logp_difference/max": 1.9860265254974365,
|
| 1817 |
+
"sampling/sampling_logp_difference/mean": 0.012662259861826897,
|
| 1818 |
+
"step": 75,
|
| 1819 |
+
"step_time": 176.83860804200594
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"clip_ratio/high_max": 0.015345552063081414,
|
| 1823 |
+
"clip_ratio/high_mean": 0.008016182604478672,
|
| 1824 |
+
"clip_ratio/low_mean": 0.011612206522841007,
|
| 1825 |
+
"clip_ratio/low_min": 0.004224211996188387,
|
| 1826 |
+
"clip_ratio/region_mean": 0.019628389243735,
|
| 1827 |
+
"entropy": 0.05343453283421695,
|
| 1828 |
+
"epoch": 0.00076,
|
| 1829 |
+
"grad_norm": 3.2833566665649414,
|
| 1830 |
+
"kl": 0.24319026991724968,
|
| 1831 |
+
"learning_rate": 3.9876219457459105e-05,
|
| 1832 |
+
"loss": 0.4571,
|
| 1833 |
+
"step": 76,
|
| 1834 |
+
"step_time": 77.4465379820067
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"clip_ratio/high_max": 0.006052493612514809,
|
| 1838 |
+
"clip_ratio/high_mean": 0.003868083542329259,
|
| 1839 |
+
"clip_ratio/low_mean": 0.0047318042779807,
|
| 1840 |
+
"clip_ratio/low_min": 0.000838963984278962,
|
| 1841 |
+
"clip_ratio/region_mean": 0.00859988784941379,
|
| 1842 |
+
"completions/clipped_ratio": 0.0,
|
| 1843 |
+
"completions/max_length": 12997.0,
|
| 1844 |
+
"completions/max_terminated_length": 12997.0,
|
| 1845 |
+
"completions/mean_length": 10965.78125,
|
| 1846 |
+
"completions/mean_terminated_length": 10965.78125,
|
| 1847 |
+
"completions/min_length": 3016.0,
|
| 1848 |
+
"completions/min_terminated_length": 3016.0,
|
| 1849 |
+
"entropy": 0.0676007338333875,
|
| 1850 |
+
"epoch": 0.00077,
|
| 1851 |
+
"frac_reward_zero_std": 0.0,
|
| 1852 |
+
"grad_norm": 4.018630027770996,
|
| 1853 |
+
"kl": 0.3990188483148813,
|
| 1854 |
+
"learning_rate": 3.9418268231350794e-05,
|
| 1855 |
+
"loss": 0.3117,
|
| 1856 |
+
"num_tokens": 14243707.0,
|
| 1857 |
+
"reward": 0.3758563995361328,
|
| 1858 |
+
"reward_std": 0.6880111694335938,
|
| 1859 |
+
"rewards/rollout_reward_func/mean": 0.3758563995361328,
|
| 1860 |
+
"rewards/rollout_reward_func/std": 0.7155471444129944,
|
| 1861 |
+
"sampling/importance_sampling_ratio/max": 3.0,
|
| 1862 |
+
"sampling/importance_sampling_ratio/mean": 1.0001542568206787,
|
| 1863 |
+
"sampling/importance_sampling_ratio/min": 0.26981011033058167,
|
| 1864 |
+
"sampling/sampling_logp_difference/max": 1.7861847877502441,
|
| 1865 |
+
"sampling/sampling_logp_difference/mean": 0.014852023683488369,
|
| 1866 |
+
"step": 77,
|
| 1867 |
+
"step_time": 168.0876079659938
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"clip_ratio/high_max": 0.011769446049584076,
|
| 1871 |
+
"clip_ratio/high_mean": 0.007204167588497512,
|
| 1872 |
+
"clip_ratio/low_mean": 0.005082681338535622,
|
| 1873 |
+
"clip_ratio/low_min": 0.0016722972795832902,
|
| 1874 |
+
"clip_ratio/region_mean": 0.012286848752410151,
|
| 1875 |
+
"entropy": 0.07258684397675097,
|
| 1876 |
+
"epoch": 0.00078,
|
| 1877 |
+
"grad_norm": 3.411888360977173,
|
| 1878 |
+
"kl": 0.3419452579692006,
|
| 1879 |
+
"learning_rate": 3.8954221537372784e-05,
|
| 1880 |
+
"loss": 0.2974,
|
| 1881 |
+
"step": 78,
|
| 1882 |
+
"step_time": 74.37252307100789
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"clip_ratio/high_max": 0.005192018230445683,
|
| 1886 |
+
"clip_ratio/high_mean": 0.00372389325639233,
|
| 1887 |
+
"clip_ratio/low_mean": 0.004230349280987866,
|
| 1888 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 1889 |
+
"clip_ratio/region_mean": 0.007954242537380196,
|
| 1890 |
+
"completions/clipped_ratio": 0.0,
|
| 1891 |
+
"completions/max_length": 13711.0,
|
| 1892 |
+
"completions/max_terminated_length": 13711.0,
|
| 1893 |
+
"completions/mean_length": 9765.40625,
|
| 1894 |
+
"completions/mean_terminated_length": 9765.40625,
|
| 1895 |
+
"completions/min_length": 1120.0,
|
| 1896 |
+
"completions/min_terminated_length": 1120.0,
|
| 1897 |
+
"entropy": 0.07584212138317525,
|
| 1898 |
+
"epoch": 0.00079,
|
| 1899 |
+
"frac_reward_zero_std": 0.0,
|
| 1900 |
+
"grad_norm": 2.9946579933166504,
|
| 1901 |
+
"kl": 0.3551831729710102,
|
| 1902 |
+
"learning_rate": 3.848442566455879e-05,
|
| 1903 |
+
"loss": 0.3019,
|
| 1904 |
+
"num_tokens": 14582149.0,
|
| 1905 |
+
"reward": 0.6430723071098328,
|
| 1906 |
+
"reward_std": 0.8897272944450378,
|
| 1907 |
+
"rewards/rollout_reward_func/mean": 0.6430723071098328,
|
| 1908 |
+
"rewards/rollout_reward_func/std": 0.8830904364585876,
|
| 1909 |
+
"sampling/importance_sampling_ratio/max": 1.8536871671676636,
|
| 1910 |
+
"sampling/importance_sampling_ratio/mean": 0.9992114305496216,
|
| 1911 |
+
"sampling/importance_sampling_ratio/min": 0.13193820416927338,
|
| 1912 |
+
"sampling/sampling_logp_difference/max": 2.025421619415283,
|
| 1913 |
+
"sampling/sampling_logp_difference/mean": 0.015373140573501587,
|
| 1914 |
+
"step": 79,
|
| 1915 |
+
"step_time": 164.90890989500258
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"clip_ratio/high_max": 0.012501898920163512,
|
| 1919 |
+
"clip_ratio/high_mean": 0.006734387134201825,
|
| 1920 |
+
"clip_ratio/low_mean": 0.006024214468197897,
|
| 1921 |
+
"clip_ratio/low_min": 0.00042229730752296746,
|
| 1922 |
+
"clip_ratio/region_mean": 0.012758601747918874,
|
| 1923 |
+
"entropy": 0.07754075806587934,
|
| 1924 |
+
"epoch": 0.0008,
|
| 1925 |
+
"grad_norm": 2.0877890586853027,
|
| 1926 |
+
"kl": 0.3181155929341912,
|
| 1927 |
+
"learning_rate": 3.800923119219528e-05,
|
| 1928 |
+
"loss": 0.2807,
|
| 1929 |
+
"step": 80,
|
| 1930 |
+
"step_time": 75.99154542500037
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"clip_ratio/high_max": 0.006057915627025068,
|
| 1934 |
+
"clip_ratio/high_mean": 0.0034836535924114287,
|
| 1935 |
+
"clip_ratio/low_mean": 0.002263873800984584,
|
| 1936 |
+
"clip_ratio/low_min": 0.00041946308920159936,
|
| 1937 |
+
"clip_ratio/region_mean": 0.0057475273933960125,
|
| 1938 |
+
"completions/clipped_ratio": 0.0,
|
| 1939 |
+
"completions/max_length": 13044.0,
|
| 1940 |
+
"completions/max_terminated_length": 13044.0,
|
| 1941 |
+
"completions/mean_length": 9906.5625,
|
| 1942 |
+
"completions/mean_terminated_length": 9906.5625,
|
| 1943 |
+
"completions/min_length": 194.0,
|
| 1944 |
+
"completions/min_terminated_length": 194.0,
|
| 1945 |
+
"entropy": 0.07884204341098666,
|
| 1946 |
+
"epoch": 0.00081,
|
| 1947 |
+
"frac_reward_zero_std": 0.0,
|
| 1948 |
+
"grad_norm": 3.3087422847747803,
|
| 1949 |
+
"kl": 0.33128924760967493,
|
| 1950 |
+
"learning_rate": 3.752899272820599e-05,
|
| 1951 |
+
"loss": 0.5296,
|
| 1952 |
+
"num_tokens": 14925339.0,
|
| 1953 |
+
"reward": 0.6571594476699829,
|
| 1954 |
+
"reward_std": 0.9445677995681763,
|
| 1955 |
+
"rewards/rollout_reward_func/mean": 0.6571594476699829,
|
| 1956 |
+
"rewards/rollout_reward_func/std": 0.9522512555122375,
|
| 1957 |
+
"sampling/importance_sampling_ratio/max": 2.334723472595215,
|
| 1958 |
+
"sampling/importance_sampling_ratio/mean": 1.0011037588119507,
|
| 1959 |
+
"sampling/importance_sampling_ratio/min": 0.5123927593231201,
|
| 1960 |
+
"sampling/sampling_logp_difference/max": 0.847893476486206,
|
| 1961 |
+
"sampling/sampling_logp_difference/mean": 0.013168051838874817,
|
| 1962 |
+
"step": 81,
|
| 1963 |
+
"step_time": 160.75939445400218
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"clip_ratio/high_max": 0.00975386772188358,
|
| 1967 |
+
"clip_ratio/high_mean": 0.00487693386094179,
|
| 1968 |
+
"clip_ratio/low_mean": 0.003392288461327553,
|
| 1969 |
+
"clip_ratio/low_min": 0.00042808218859136105,
|
| 1970 |
+
"clip_ratio/region_mean": 0.008269222205854021,
|
| 1971 |
+
"entropy": 0.08188656461425126,
|
| 1972 |
+
"epoch": 0.00082,
|
| 1973 |
+
"grad_norm": 3.4174883365631104,
|
| 1974 |
+
"kl": 0.3137277886271477,
|
| 1975 |
+
"learning_rate": 3.7044068644530266e-05,
|
| 1976 |
+
"loss": 0.5072,
|
| 1977 |
+
"step": 82,
|
| 1978 |
+
"step_time": 72.33279583299736
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"clip_ratio/high_max": 0.006675469485344365,
|
| 1982 |
+
"clip_ratio/high_mean": 0.0033377347426721826,
|
| 1983 |
+
"clip_ratio/low_mean": 0.001848820800660178,
|
| 1984 |
+
"clip_ratio/low_min": 0.0,
|
| 1985 |
+
"clip_ratio/region_mean": 0.005186555499676615,
|
| 1986 |
+
"completions/clipped_ratio": 0.0,
|
| 1987 |
+
"completions/max_length": 13170.0,
|
| 1988 |
+
"completions/max_terminated_length": 13170.0,
|
| 1989 |
+
"completions/mean_length": 9203.78125,
|
| 1990 |
+
"completions/mean_terminated_length": 9203.78125,
|
| 1991 |
+
"completions/min_length": 1503.0,
|
| 1992 |
+
"completions/min_terminated_length": 1503.0,
|
| 1993 |
+
"entropy": 0.0853383056819439,
|
| 1994 |
+
"epoch": 0.00083,
|
| 1995 |
+
"frac_reward_zero_std": 0.0,
|
| 1996 |
+
"grad_norm": 3.260225296020508,
|
| 1997 |
+
"kl": 0.3031325452029705,
|
| 1998 |
+
"learning_rate": 3.6554820809692434e-05,
|
| 1999 |
+
"loss": 0.2749,
|
| 2000 |
+
"num_tokens": 15246024.0,
|
| 2001 |
+
"reward": 0.7069042325019836,
|
| 2002 |
+
"reward_std": 0.9800997972488403,
|
| 2003 |
+
"rewards/rollout_reward_func/mean": 0.7069042325019836,
|
| 2004 |
+
"rewards/rollout_reward_func/std": 0.9830536246299744,
|
| 2005 |
+
"sampling/importance_sampling_ratio/max": 1.983609914779663,
|
| 2006 |
+
"sampling/importance_sampling_ratio/mean": 0.9999707341194153,
|
| 2007 |
+
"sampling/importance_sampling_ratio/min": 0.27940061688423157,
|
| 2008 |
+
"sampling/sampling_logp_difference/max": 1.2751085758209229,
|
| 2009 |
+
"sampling/sampling_logp_difference/mean": 0.014450456015765667,
|
| 2010 |
+
"step": 83,
|
| 2011 |
+
"step_time": 154.39635029400597
|
| 2012 |
+
}
|
| 2013 |
+
],
|
| 2014 |
+
"logging_steps": 1.0,
|
| 2015 |
+
"max_steps": 150,
|
| 2016 |
+
"num_input_tokens_seen": 15246024,
|
| 2017 |
+
"num_train_epochs": 1,
|
| 2018 |
+
"save_steps": 500,
|
| 2019 |
+
"stateful_callbacks": {
|
| 2020 |
+
"TrainerControl": {
|
| 2021 |
+
"args": {
|
| 2022 |
+
"should_epoch_stop": false,
|
| 2023 |
+
"should_evaluate": false,
|
| 2024 |
+
"should_log": false,
|
| 2025 |
+
"should_save": true,
|
| 2026 |
+
"should_training_stop": false
|
| 2027 |
+
},
|
| 2028 |
+
"attributes": {}
|
| 2029 |
+
}
|
| 2030 |
+
},
|
| 2031 |
+
"total_flos": 0.0,
|
| 2032 |
+
"train_batch_size": 1,
|
| 2033 |
+
"trial_name": null,
|
| 2034 |
+
"trial_params": null
|
| 2035 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf2afd4c2e1d5c0ab3119cc46dbc965396a829819d96dc569939c4c2045adc2
|
| 3 |
+
size 8145
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|