Upload task output 1
Browse files- .gitattributes +1 -0
- README.md +209 -0
- adapter_config.json +46 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- loss.txt +1 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- trainer_state.json +1843 -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: None
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:/workspace/sft_submission/1
|
| 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": null,
|
| 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 |
+
"gate_proj",
|
| 33 |
+
"down_proj",
|
| 34 |
+
"q_proj",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"v_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"o_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 sha256:614597a3c9852181a2574379b1844bc615cee43f1b835ac0ed9abc6423ec5cc2
|
| 3 |
+
size 70430032
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# 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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
loss.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
75,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": "<|endoftext|>",
|
| 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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0005625056250562506,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 75,
|
| 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": 1.0,
|
| 19 |
+
"completions/max_length": 1250.0,
|
| 20 |
+
"completions/max_terminated_length": 0.0,
|
| 21 |
+
"completions/mean_length": 465.16668701171875,
|
| 22 |
+
"completions/mean_terminated_length": 0.0,
|
| 23 |
+
"completions/min_length": 128.0,
|
| 24 |
+
"completions/min_terminated_length": 0.0,
|
| 25 |
+
"entropy": 10.142642656962076,
|
| 26 |
+
"epoch": 7.500075000750007e-06,
|
| 27 |
+
"frac_reward_zero_std": 0.0,
|
| 28 |
+
"grad_norm": 0.0,
|
| 29 |
+
"kl": 0.0,
|
| 30 |
+
"learning_rate": 0.0,
|
| 31 |
+
"loss": 0.0,
|
| 32 |
+
"num_tokens": 27405.0,
|
| 33 |
+
"reward": -55.42028045654297,
|
| 34 |
+
"reward_std": 14.156389236450195,
|
| 35 |
+
"rewards/rollout_reward_func/mean": -55.420284271240234,
|
| 36 |
+
"rewards/rollout_reward_func/std": 14.949880599975586,
|
| 37 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 38 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 39 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 40 |
+
"sampling/sampling_logp_difference/max": 15.271873474121094,
|
| 41 |
+
"sampling/sampling_logp_difference/mean": 3.1089508533477783,
|
| 42 |
+
"step": 1,
|
| 43 |
+
"step_time": 20.82328461799989
|
| 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": 10.142642656962076,
|
| 52 |
+
"epoch": 1.5000150001500015e-05,
|
| 53 |
+
"grad_norm": 0.0,
|
| 54 |
+
"kl": 0.0,
|
| 55 |
+
"learning_rate": 9.428571428571429e-07,
|
| 56 |
+
"loss": 0.0,
|
| 57 |
+
"step": 2,
|
| 58 |
+
"step_time": 1.7083880239997598
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"clip_ratio/high_max": 0.0,
|
| 62 |
+
"clip_ratio/high_mean": 0.0,
|
| 63 |
+
"clip_ratio/low_mean": 0.0,
|
| 64 |
+
"clip_ratio/low_min": 0.0,
|
| 65 |
+
"clip_ratio/region_mean": 0.0,
|
| 66 |
+
"completions/clipped_ratio": 1.0,
|
| 67 |
+
"completions/max_length": 1583.0,
|
| 68 |
+
"completions/max_terminated_length": 0.0,
|
| 69 |
+
"completions/mean_length": 629.4583740234375,
|
| 70 |
+
"completions/mean_terminated_length": 0.0,
|
| 71 |
+
"completions/min_length": 128.0,
|
| 72 |
+
"completions/min_terminated_length": 0.0,
|
| 73 |
+
"entropy": 10.019515991210938,
|
| 74 |
+
"epoch": 2.250022500225002e-05,
|
| 75 |
+
"frac_reward_zero_std": 0.0,
|
| 76 |
+
"grad_norm": 0.0,
|
| 77 |
+
"kl": 0.0,
|
| 78 |
+
"learning_rate": 1.8857142857142858e-06,
|
| 79 |
+
"loss": 0.0,
|
| 80 |
+
"num_tokens": 58385.0,
|
| 81 |
+
"reward": -44.9024772644043,
|
| 82 |
+
"reward_std": 21.128307342529297,
|
| 83 |
+
"rewards/rollout_reward_func/mean": -44.9024772644043,
|
| 84 |
+
"rewards/rollout_reward_func/std": 20.625934600830078,
|
| 85 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 86 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 87 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 88 |
+
"sampling/sampling_logp_difference/max": 15.504789352416992,
|
| 89 |
+
"sampling/sampling_logp_difference/mean": 3.0316898822784424,
|
| 90 |
+
"step": 3,
|
| 91 |
+
"step_time": 21.70512620000045
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"clip_ratio/high_max": 0.0,
|
| 95 |
+
"clip_ratio/high_mean": 0.0,
|
| 96 |
+
"clip_ratio/low_mean": 0.0,
|
| 97 |
+
"clip_ratio/low_min": 0.0,
|
| 98 |
+
"clip_ratio/region_mean": 0.0,
|
| 99 |
+
"entropy": 10.019515991210938,
|
| 100 |
+
"epoch": 3.000030000300003e-05,
|
| 101 |
+
"grad_norm": 0.0,
|
| 102 |
+
"kl": 0.0,
|
| 103 |
+
"learning_rate": 2.8285714285714288e-06,
|
| 104 |
+
"loss": 0.0,
|
| 105 |
+
"step": 4,
|
| 106 |
+
"step_time": 1.955569071001264
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"clip_ratio/high_max": 0.0,
|
| 110 |
+
"clip_ratio/high_mean": 0.0,
|
| 111 |
+
"clip_ratio/low_mean": 0.0,
|
| 112 |
+
"clip_ratio/low_min": 0.0,
|
| 113 |
+
"clip_ratio/region_mean": 0.0,
|
| 114 |
+
"completions/clipped_ratio": 1.0,
|
| 115 |
+
"completions/max_length": 1297.0,
|
| 116 |
+
"completions/max_terminated_length": 0.0,
|
| 117 |
+
"completions/mean_length": 617.125,
|
| 118 |
+
"completions/mean_terminated_length": 0.0,
|
| 119 |
+
"completions/min_length": 128.0,
|
| 120 |
+
"completions/min_terminated_length": 0.0,
|
| 121 |
+
"entropy": 10.11839516957601,
|
| 122 |
+
"epoch": 3.7500375003750034e-05,
|
| 123 |
+
"frac_reward_zero_std": 0.0,
|
| 124 |
+
"grad_norm": 0.0,
|
| 125 |
+
"kl": 0.0,
|
| 126 |
+
"learning_rate": 3.7714285714285716e-06,
|
| 127 |
+
"loss": 0.0,
|
| 128 |
+
"num_tokens": 89832.0,
|
| 129 |
+
"reward": -52.47894287109375,
|
| 130 |
+
"reward_std": 14.024870872497559,
|
| 131 |
+
"rewards/rollout_reward_func/mean": -52.47894287109375,
|
| 132 |
+
"rewards/rollout_reward_func/std": 15.634257316589355,
|
| 133 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 134 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 135 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 136 |
+
"sampling/sampling_logp_difference/max": 16.115659713745117,
|
| 137 |
+
"sampling/sampling_logp_difference/mean": 3.077618360519409,
|
| 138 |
+
"step": 5,
|
| 139 |
+
"step_time": 20.300307900998632
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"clip_ratio/high_max": 0.0,
|
| 143 |
+
"clip_ratio/high_mean": 0.0,
|
| 144 |
+
"clip_ratio/low_mean": 0.0,
|
| 145 |
+
"clip_ratio/low_min": 0.0,
|
| 146 |
+
"clip_ratio/region_mean": 0.0,
|
| 147 |
+
"entropy": 10.11839516957601,
|
| 148 |
+
"epoch": 4.500045000450004e-05,
|
| 149 |
+
"grad_norm": 0.0,
|
| 150 |
+
"kl": 0.0,
|
| 151 |
+
"learning_rate": 4.714285714285715e-06,
|
| 152 |
+
"loss": 0.0,
|
| 153 |
+
"step": 6,
|
| 154 |
+
"step_time": 1.7449414639986571
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"clip_ratio/high_max": 0.0,
|
| 158 |
+
"clip_ratio/high_mean": 0.0,
|
| 159 |
+
"clip_ratio/low_mean": 0.0,
|
| 160 |
+
"clip_ratio/low_min": 0.0,
|
| 161 |
+
"clip_ratio/region_mean": 0.0,
|
| 162 |
+
"completions/clipped_ratio": 1.0,
|
| 163 |
+
"completions/max_length": 1512.0,
|
| 164 |
+
"completions/max_terminated_length": 0.0,
|
| 165 |
+
"completions/mean_length": 669.3333740234375,
|
| 166 |
+
"completions/mean_terminated_length": 0.0,
|
| 167 |
+
"completions/min_length": 128.0,
|
| 168 |
+
"completions/min_terminated_length": 0.0,
|
| 169 |
+
"entropy": 9.932727654774984,
|
| 170 |
+
"epoch": 5.250052500525005e-05,
|
| 171 |
+
"frac_reward_zero_std": 0.0,
|
| 172 |
+
"grad_norm": 0.0,
|
| 173 |
+
"kl": 0.0,
|
| 174 |
+
"learning_rate": 5.6571428571428576e-06,
|
| 175 |
+
"loss": 0.0,
|
| 176 |
+
"num_tokens": 121624.0,
|
| 177 |
+
"reward": -39.97017288208008,
|
| 178 |
+
"reward_std": 15.512527465820312,
|
| 179 |
+
"rewards/rollout_reward_func/mean": -39.97017288208008,
|
| 180 |
+
"rewards/rollout_reward_func/std": 18.193031311035156,
|
| 181 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 182 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 183 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 184 |
+
"sampling/sampling_logp_difference/max": 14.845789909362793,
|
| 185 |
+
"sampling/sampling_logp_difference/mean": 3.0627593994140625,
|
| 186 |
+
"step": 7,
|
| 187 |
+
"step_time": 23.506451233000007
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"clip_ratio/high_max": 0.0,
|
| 191 |
+
"clip_ratio/high_mean": 0.0,
|
| 192 |
+
"clip_ratio/low_mean": 0.0,
|
| 193 |
+
"clip_ratio/low_min": 0.0,
|
| 194 |
+
"clip_ratio/region_mean": 0.0,
|
| 195 |
+
"entropy": 9.932727654774984,
|
| 196 |
+
"epoch": 6.000060000600006e-05,
|
| 197 |
+
"grad_norm": 0.0,
|
| 198 |
+
"kl": 0.0,
|
| 199 |
+
"learning_rate": 6.600000000000001e-06,
|
| 200 |
+
"loss": 0.0,
|
| 201 |
+
"step": 8,
|
| 202 |
+
"step_time": 2.360350576000201
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"clip_ratio/high_max": 0.0,
|
| 206 |
+
"clip_ratio/high_mean": 0.0,
|
| 207 |
+
"clip_ratio/low_mean": 0.0,
|
| 208 |
+
"clip_ratio/low_min": 0.0,
|
| 209 |
+
"clip_ratio/region_mean": 0.0,
|
| 210 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 211 |
+
"completions/max_length": 1098.0,
|
| 212 |
+
"completions/max_terminated_length": 117.0,
|
| 213 |
+
"completions/mean_length": 474.8333435058594,
|
| 214 |
+
"completions/mean_terminated_length": 117.0,
|
| 215 |
+
"completions/min_length": 117.0,
|
| 216 |
+
"completions/min_terminated_length": 117.0,
|
| 217 |
+
"entropy": 10.16798194249471,
|
| 218 |
+
"epoch": 6.750067500675007e-05,
|
| 219 |
+
"frac_reward_zero_std": 0.0,
|
| 220 |
+
"grad_norm": 0.0,
|
| 221 |
+
"kl": 0.0,
|
| 222 |
+
"learning_rate": 7.542857142857143e-06,
|
| 223 |
+
"loss": 0.0,
|
| 224 |
+
"num_tokens": 149483.0,
|
| 225 |
+
"reward": -43.48188018798828,
|
| 226 |
+
"reward_std": 17.433856964111328,
|
| 227 |
+
"rewards/rollout_reward_func/mean": -43.481876373291016,
|
| 228 |
+
"rewards/rollout_reward_func/std": 17.40215301513672,
|
| 229 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 230 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 231 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 232 |
+
"sampling/sampling_logp_difference/max": 15.133698463439941,
|
| 233 |
+
"sampling/sampling_logp_difference/mean": 3.2317543029785156,
|
| 234 |
+
"step": 9,
|
| 235 |
+
"step_time": 21.789242212999852
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"clip_ratio/high_max": 0.0,
|
| 239 |
+
"clip_ratio/high_mean": 0.0,
|
| 240 |
+
"clip_ratio/low_mean": 0.0,
|
| 241 |
+
"clip_ratio/low_min": 0.0,
|
| 242 |
+
"clip_ratio/region_mean": 0.0,
|
| 243 |
+
"entropy": 10.16798194249471,
|
| 244 |
+
"epoch": 7.500075000750007e-05,
|
| 245 |
+
"grad_norm": 0.0,
|
| 246 |
+
"kl": 0.0,
|
| 247 |
+
"learning_rate": 8.485714285714285e-06,
|
| 248 |
+
"loss": 0.0,
|
| 249 |
+
"step": 10,
|
| 250 |
+
"step_time": 1.6317280789990036
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"clip_ratio/high_max": 0.0,
|
| 254 |
+
"clip_ratio/high_mean": 0.0,
|
| 255 |
+
"clip_ratio/low_mean": 0.0,
|
| 256 |
+
"clip_ratio/low_min": 0.0,
|
| 257 |
+
"clip_ratio/region_mean": 0.0,
|
| 258 |
+
"completions/clipped_ratio": 1.0,
|
| 259 |
+
"completions/max_length": 1519.0,
|
| 260 |
+
"completions/max_terminated_length": 0.0,
|
| 261 |
+
"completions/mean_length": 477.0,
|
| 262 |
+
"completions/mean_terminated_length": 0.0,
|
| 263 |
+
"completions/min_length": 128.0,
|
| 264 |
+
"completions/min_terminated_length": 0.0,
|
| 265 |
+
"entropy": 10.115420500437418,
|
| 266 |
+
"epoch": 8.250082500825008e-05,
|
| 267 |
+
"frac_reward_zero_std": 0.0,
|
| 268 |
+
"grad_norm": 0.0,
|
| 269 |
+
"kl": 0.0,
|
| 270 |
+
"learning_rate": 9.42857142857143e-06,
|
| 271 |
+
"loss": 0.0,
|
| 272 |
+
"num_tokens": 177306.0,
|
| 273 |
+
"reward": -49.76444625854492,
|
| 274 |
+
"reward_std": 17.622684478759766,
|
| 275 |
+
"rewards/rollout_reward_func/mean": -49.76444625854492,
|
| 276 |
+
"rewards/rollout_reward_func/std": 17.78196907043457,
|
| 277 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 278 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 279 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 280 |
+
"sampling/sampling_logp_difference/max": 14.594074249267578,
|
| 281 |
+
"sampling/sampling_logp_difference/mean": 3.12507963180542,
|
| 282 |
+
"step": 11,
|
| 283 |
+
"step_time": 21.353458720001072
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"clip_ratio/high_max": 0.0,
|
| 287 |
+
"clip_ratio/high_mean": 0.0,
|
| 288 |
+
"clip_ratio/low_mean": 0.0,
|
| 289 |
+
"clip_ratio/low_min": 0.0,
|
| 290 |
+
"clip_ratio/region_mean": 0.0,
|
| 291 |
+
"entropy": 10.115420500437418,
|
| 292 |
+
"epoch": 9.000090000900009e-05,
|
| 293 |
+
"grad_norm": 0.0,
|
| 294 |
+
"kl": 0.0,
|
| 295 |
+
"learning_rate": 1.0371428571428572e-05,
|
| 296 |
+
"loss": 0.0,
|
| 297 |
+
"step": 12,
|
| 298 |
+
"step_time": 1.9042143349997787
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"clip_ratio/high_max": 0.0,
|
| 302 |
+
"clip_ratio/high_mean": 0.0,
|
| 303 |
+
"clip_ratio/low_mean": 0.0,
|
| 304 |
+
"clip_ratio/low_min": 0.0,
|
| 305 |
+
"clip_ratio/region_mean": 0.0,
|
| 306 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 307 |
+
"completions/max_length": 1335.0,
|
| 308 |
+
"completions/max_terminated_length": 850.0,
|
| 309 |
+
"completions/mean_length": 461.04168701171875,
|
| 310 |
+
"completions/mean_terminated_length": 850.0,
|
| 311 |
+
"completions/min_length": 128.0,
|
| 312 |
+
"completions/min_terminated_length": 850.0,
|
| 313 |
+
"entropy": 10.036355336507162,
|
| 314 |
+
"epoch": 9.75009750097501e-05,
|
| 315 |
+
"frac_reward_zero_std": 0.0,
|
| 316 |
+
"grad_norm": 0.0,
|
| 317 |
+
"kl": 0.0,
|
| 318 |
+
"learning_rate": 1.1314285714285715e-05,
|
| 319 |
+
"loss": 0.0,
|
| 320 |
+
"num_tokens": 204986.0,
|
| 321 |
+
"reward": -49.08823776245117,
|
| 322 |
+
"reward_std": 15.106697082519531,
|
| 323 |
+
"rewards/rollout_reward_func/mean": -49.08823776245117,
|
| 324 |
+
"rewards/rollout_reward_func/std": 15.08985710144043,
|
| 325 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 326 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 327 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 328 |
+
"sampling/sampling_logp_difference/max": 15.450621604919434,
|
| 329 |
+
"sampling/sampling_logp_difference/mean": 3.1363472938537598,
|
| 330 |
+
"step": 13,
|
| 331 |
+
"step_time": 21.459205156999815
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"clip_ratio/high_max": 0.0,
|
| 335 |
+
"clip_ratio/high_mean": 0.0,
|
| 336 |
+
"clip_ratio/low_mean": 0.0,
|
| 337 |
+
"clip_ratio/low_min": 0.0,
|
| 338 |
+
"clip_ratio/region_mean": 0.0,
|
| 339 |
+
"entropy": 10.036355336507162,
|
| 340 |
+
"epoch": 0.0001050010500105001,
|
| 341 |
+
"grad_norm": 0.0,
|
| 342 |
+
"kl": 0.0,
|
| 343 |
+
"learning_rate": 1.2257142857142858e-05,
|
| 344 |
+
"loss": 0.0,
|
| 345 |
+
"step": 14,
|
| 346 |
+
"step_time": 1.7608847870005775
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"clip_ratio/high_max": 0.0,
|
| 350 |
+
"clip_ratio/high_mean": 0.0,
|
| 351 |
+
"clip_ratio/low_mean": 0.0,
|
| 352 |
+
"clip_ratio/low_min": 0.0,
|
| 353 |
+
"clip_ratio/region_mean": 0.0,
|
| 354 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 355 |
+
"completions/max_length": 1320.0,
|
| 356 |
+
"completions/max_terminated_length": 199.0,
|
| 357 |
+
"completions/mean_length": 546.9583740234375,
|
| 358 |
+
"completions/mean_terminated_length": 199.0,
|
| 359 |
+
"completions/min_length": 32.0,
|
| 360 |
+
"completions/min_terminated_length": 199.0,
|
| 361 |
+
"entropy": 10.22978941599528,
|
| 362 |
+
"epoch": 0.00011250112501125012,
|
| 363 |
+
"frac_reward_zero_std": 0.0,
|
| 364 |
+
"grad_norm": 0.0,
|
| 365 |
+
"kl": 0.0,
|
| 366 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 367 |
+
"loss": -0.0,
|
| 368 |
+
"num_tokens": 234036.0,
|
| 369 |
+
"reward": -45.839088439941406,
|
| 370 |
+
"reward_std": 21.189510345458984,
|
| 371 |
+
"rewards/rollout_reward_func/mean": -45.83908462524414,
|
| 372 |
+
"rewards/rollout_reward_func/std": 21.63396644592285,
|
| 373 |
+
"sampling/importance_sampling_ratio/max": 1.9689644722228005e-41,
|
| 374 |
+
"sampling/importance_sampling_ratio/mean": 8.19759601630018e-43,
|
| 375 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 376 |
+
"sampling/sampling_logp_difference/max": 14.650032043457031,
|
| 377 |
+
"sampling/sampling_logp_difference/mean": 3.18168044090271,
|
| 378 |
+
"step": 15,
|
| 379 |
+
"step_time": 20.74833343499995
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"clip_ratio/high_max": 0.0,
|
| 383 |
+
"clip_ratio/high_mean": 0.0,
|
| 384 |
+
"clip_ratio/low_mean": 0.0,
|
| 385 |
+
"clip_ratio/low_min": 0.0,
|
| 386 |
+
"clip_ratio/region_mean": 0.0,
|
| 387 |
+
"entropy": 10.22978941599528,
|
| 388 |
+
"epoch": 0.00012000120001200012,
|
| 389 |
+
"grad_norm": 0.0,
|
| 390 |
+
"kl": 0.0,
|
| 391 |
+
"learning_rate": 1.4142857142857143e-05,
|
| 392 |
+
"loss": -0.0,
|
| 393 |
+
"step": 16,
|
| 394 |
+
"step_time": 1.7528818500013585
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"clip_ratio/high_max": 0.0,
|
| 398 |
+
"clip_ratio/high_mean": 0.0,
|
| 399 |
+
"clip_ratio/low_mean": 0.0,
|
| 400 |
+
"clip_ratio/low_min": 0.0,
|
| 401 |
+
"clip_ratio/region_mean": 0.0,
|
| 402 |
+
"completions/clipped_ratio": 1.0,
|
| 403 |
+
"completions/max_length": 1465.0,
|
| 404 |
+
"completions/max_terminated_length": 0.0,
|
| 405 |
+
"completions/mean_length": 534.5416870117188,
|
| 406 |
+
"completions/mean_terminated_length": 0.0,
|
| 407 |
+
"completions/min_length": 128.0,
|
| 408 |
+
"completions/min_terminated_length": 0.0,
|
| 409 |
+
"entropy": 10.08104912439982,
|
| 410 |
+
"epoch": 0.00012750127501275012,
|
| 411 |
+
"frac_reward_zero_std": 0.0,
|
| 412 |
+
"grad_norm": 0.0,
|
| 413 |
+
"kl": 0.0,
|
| 414 |
+
"learning_rate": 1.5085714285714286e-05,
|
| 415 |
+
"loss": 0.0,
|
| 416 |
+
"num_tokens": 262530.0,
|
| 417 |
+
"reward": -44.546234130859375,
|
| 418 |
+
"reward_std": 21.182384490966797,
|
| 419 |
+
"rewards/rollout_reward_func/mean": -44.546234130859375,
|
| 420 |
+
"rewards/rollout_reward_func/std": 20.58904457092285,
|
| 421 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 422 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 423 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 424 |
+
"sampling/sampling_logp_difference/max": 15.177563667297363,
|
| 425 |
+
"sampling/sampling_logp_difference/mean": 3.1732728481292725,
|
| 426 |
+
"step": 17,
|
| 427 |
+
"step_time": 22.080905613998766
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"clip_ratio/high_max": 0.0,
|
| 431 |
+
"clip_ratio/high_mean": 0.0,
|
| 432 |
+
"clip_ratio/low_mean": 0.0,
|
| 433 |
+
"clip_ratio/low_min": 0.0,
|
| 434 |
+
"clip_ratio/region_mean": 0.0,
|
| 435 |
+
"entropy": 10.08104912439982,
|
| 436 |
+
"epoch": 0.00013500135001350013,
|
| 437 |
+
"grad_norm": 0.0,
|
| 438 |
+
"kl": 0.0,
|
| 439 |
+
"learning_rate": 1.602857142857143e-05,
|
| 440 |
+
"loss": 0.0,
|
| 441 |
+
"step": 18,
|
| 442 |
+
"step_time": 1.857407227999829
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"clip_ratio/high_max": 0.0,
|
| 446 |
+
"clip_ratio/high_mean": 0.0,
|
| 447 |
+
"clip_ratio/low_mean": 0.0,
|
| 448 |
+
"clip_ratio/low_min": 0.0,
|
| 449 |
+
"clip_ratio/region_mean": 0.0,
|
| 450 |
+
"completions/clipped_ratio": 1.0,
|
| 451 |
+
"completions/max_length": 1961.0,
|
| 452 |
+
"completions/max_terminated_length": 0.0,
|
| 453 |
+
"completions/mean_length": 599.7083740234375,
|
| 454 |
+
"completions/mean_terminated_length": 0.0,
|
| 455 |
+
"completions/min_length": 207.0,
|
| 456 |
+
"completions/min_terminated_length": 0.0,
|
| 457 |
+
"entropy": 9.975990613301596,
|
| 458 |
+
"epoch": 0.00014250142501425015,
|
| 459 |
+
"frac_reward_zero_std": 0.0,
|
| 460 |
+
"grad_norm": 0.0,
|
| 461 |
+
"kl": 0.0,
|
| 462 |
+
"learning_rate": 1.697142857142857e-05,
|
| 463 |
+
"loss": 0.0,
|
| 464 |
+
"num_tokens": 293166.0,
|
| 465 |
+
"reward": -48.2664909362793,
|
| 466 |
+
"reward_std": 27.311491012573242,
|
| 467 |
+
"rewards/rollout_reward_func/mean": -48.2664909362793,
|
| 468 |
+
"rewards/rollout_reward_func/std": 26.92763328552246,
|
| 469 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 470 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 471 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 472 |
+
"sampling/sampling_logp_difference/max": 13.656001091003418,
|
| 473 |
+
"sampling/sampling_logp_difference/mean": 3.007814407348633,
|
| 474 |
+
"step": 19,
|
| 475 |
+
"step_time": 21.696408987000723
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"clip_ratio/high_max": 0.0,
|
| 479 |
+
"clip_ratio/high_mean": 0.0,
|
| 480 |
+
"clip_ratio/low_mean": 0.0,
|
| 481 |
+
"clip_ratio/low_min": 0.0,
|
| 482 |
+
"clip_ratio/region_mean": 0.0,
|
| 483 |
+
"entropy": 9.975990613301596,
|
| 484 |
+
"epoch": 0.00015000150001500014,
|
| 485 |
+
"grad_norm": 0.0,
|
| 486 |
+
"kl": 0.0,
|
| 487 |
+
"learning_rate": 1.7914285714285715e-05,
|
| 488 |
+
"loss": 0.0,
|
| 489 |
+
"step": 20,
|
| 490 |
+
"step_time": 2.2191366179995384
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"clip_ratio/high_max": 0.0,
|
| 494 |
+
"clip_ratio/high_mean": 0.0,
|
| 495 |
+
"clip_ratio/low_mean": 0.0,
|
| 496 |
+
"clip_ratio/low_min": 0.0,
|
| 497 |
+
"clip_ratio/region_mean": 0.0,
|
| 498 |
+
"completions/clipped_ratio": 1.0,
|
| 499 |
+
"completions/max_length": 1628.0,
|
| 500 |
+
"completions/max_terminated_length": 0.0,
|
| 501 |
+
"completions/mean_length": 574.875,
|
| 502 |
+
"completions/mean_terminated_length": 0.0,
|
| 503 |
+
"completions/min_length": 128.0,
|
| 504 |
+
"completions/min_terminated_length": 0.0,
|
| 505 |
+
"entropy": 10.216261068979898,
|
| 506 |
+
"epoch": 0.00015750157501575015,
|
| 507 |
+
"frac_reward_zero_std": 0.0,
|
| 508 |
+
"grad_norm": 0.0,
|
| 509 |
+
"kl": 0.0,
|
| 510 |
+
"learning_rate": 1.885714285714286e-05,
|
| 511 |
+
"loss": 0.0,
|
| 512 |
+
"num_tokens": 323248.0,
|
| 513 |
+
"reward": -47.44938659667969,
|
| 514 |
+
"reward_std": 18.540122985839844,
|
| 515 |
+
"rewards/rollout_reward_func/mean": -47.44938659667969,
|
| 516 |
+
"rewards/rollout_reward_func/std": 19.742595672607422,
|
| 517 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 518 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 519 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 520 |
+
"sampling/sampling_logp_difference/max": 15.002847671508789,
|
| 521 |
+
"sampling/sampling_logp_difference/mean": 3.182793617248535,
|
| 522 |
+
"step": 21,
|
| 523 |
+
"step_time": 21.242170976000125
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"clip_ratio/high_max": 0.0,
|
| 527 |
+
"clip_ratio/high_mean": 0.0,
|
| 528 |
+
"clip_ratio/low_mean": 0.0,
|
| 529 |
+
"clip_ratio/low_min": 0.0,
|
| 530 |
+
"clip_ratio/region_mean": 0.0,
|
| 531 |
+
"entropy": 10.216261068979898,
|
| 532 |
+
"epoch": 0.00016500165001650017,
|
| 533 |
+
"grad_norm": 0.0,
|
| 534 |
+
"kl": 0.0,
|
| 535 |
+
"learning_rate": 1.98e-05,
|
| 536 |
+
"loss": 0.0,
|
| 537 |
+
"step": 22,
|
| 538 |
+
"step_time": 1.98696188500071
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"clip_ratio/high_max": 0.0,
|
| 542 |
+
"clip_ratio/high_mean": 0.0,
|
| 543 |
+
"clip_ratio/low_mean": 0.0,
|
| 544 |
+
"clip_ratio/low_min": 0.0,
|
| 545 |
+
"clip_ratio/region_mean": 0.0,
|
| 546 |
+
"completions/clipped_ratio": 1.0,
|
| 547 |
+
"completions/max_length": 1505.0,
|
| 548 |
+
"completions/max_terminated_length": 0.0,
|
| 549 |
+
"completions/mean_length": 566.75,
|
| 550 |
+
"completions/mean_terminated_length": 0.0,
|
| 551 |
+
"completions/min_length": 128.0,
|
| 552 |
+
"completions/min_terminated_length": 0.0,
|
| 553 |
+
"entropy": 10.105806827545166,
|
| 554 |
+
"epoch": 0.00017250172501725018,
|
| 555 |
+
"frac_reward_zero_std": 0.0,
|
| 556 |
+
"grad_norm": 0.0,
|
| 557 |
+
"kl": 0.0,
|
| 558 |
+
"learning_rate": 2.0742857142857145e-05,
|
| 559 |
+
"loss": 0.0,
|
| 560 |
+
"num_tokens": 353295.0,
|
| 561 |
+
"reward": -47.93909454345703,
|
| 562 |
+
"reward_std": 21.568241119384766,
|
| 563 |
+
"rewards/rollout_reward_func/mean": -47.9390983581543,
|
| 564 |
+
"rewards/rollout_reward_func/std": 21.119380950927734,
|
| 565 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 566 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 567 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 568 |
+
"sampling/sampling_logp_difference/max": 15.182104110717773,
|
| 569 |
+
"sampling/sampling_logp_difference/mean": 3.005905866622925,
|
| 570 |
+
"step": 23,
|
| 571 |
+
"step_time": 21.250609902998804
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"clip_ratio/high_max": 0.0,
|
| 575 |
+
"clip_ratio/high_mean": 0.0,
|
| 576 |
+
"clip_ratio/low_mean": 0.0,
|
| 577 |
+
"clip_ratio/low_min": 0.0,
|
| 578 |
+
"clip_ratio/region_mean": 0.0,
|
| 579 |
+
"entropy": 10.105806827545166,
|
| 580 |
+
"epoch": 0.00018000180001800017,
|
| 581 |
+
"grad_norm": 0.0,
|
| 582 |
+
"kl": 0.0,
|
| 583 |
+
"learning_rate": 2.1685714285714286e-05,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 24,
|
| 586 |
+
"step_time": 1.9004714529983175
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"clip_ratio/high_max": 0.0,
|
| 590 |
+
"clip_ratio/high_mean": 0.0,
|
| 591 |
+
"clip_ratio/low_mean": 0.0,
|
| 592 |
+
"clip_ratio/low_min": 0.0,
|
| 593 |
+
"clip_ratio/region_mean": 0.0,
|
| 594 |
+
"completions/clipped_ratio": 1.0,
|
| 595 |
+
"completions/max_length": 1371.0,
|
| 596 |
+
"completions/max_terminated_length": 0.0,
|
| 597 |
+
"completions/mean_length": 490.4583435058594,
|
| 598 |
+
"completions/mean_terminated_length": 0.0,
|
| 599 |
+
"completions/min_length": 119.0,
|
| 600 |
+
"completions/min_terminated_length": 0.0,
|
| 601 |
+
"entropy": 10.06377108891805,
|
| 602 |
+
"epoch": 0.00018750187501875019,
|
| 603 |
+
"frac_reward_zero_std": 0.0,
|
| 604 |
+
"grad_norm": 0.0,
|
| 605 |
+
"kl": 0.0,
|
| 606 |
+
"learning_rate": 2.262857142857143e-05,
|
| 607 |
+
"loss": 0.0,
|
| 608 |
+
"num_tokens": 381535.0,
|
| 609 |
+
"reward": -45.13935089111328,
|
| 610 |
+
"reward_std": 19.477066040039062,
|
| 611 |
+
"rewards/rollout_reward_func/mean": -45.13934326171875,
|
| 612 |
+
"rewards/rollout_reward_func/std": 20.111757278442383,
|
| 613 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 614 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 615 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 616 |
+
"sampling/sampling_logp_difference/max": 14.868183135986328,
|
| 617 |
+
"sampling/sampling_logp_difference/mean": 3.132169246673584,
|
| 618 |
+
"step": 25,
|
| 619 |
+
"step_time": 20.922161000000415
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"clip_ratio/high_max": 0.0,
|
| 623 |
+
"clip_ratio/high_mean": 0.0,
|
| 624 |
+
"clip_ratio/low_mean": 0.0,
|
| 625 |
+
"clip_ratio/low_min": 0.0,
|
| 626 |
+
"clip_ratio/region_mean": 0.0,
|
| 627 |
+
"entropy": 10.06377108891805,
|
| 628 |
+
"epoch": 0.0001950019500195002,
|
| 629 |
+
"grad_norm": 0.0,
|
| 630 |
+
"kl": 0.0,
|
| 631 |
+
"learning_rate": 2.3571428571428575e-05,
|
| 632 |
+
"loss": 0.0,
|
| 633 |
+
"step": 26,
|
| 634 |
+
"step_time": 1.8088220660001753
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"clip_ratio/high_max": 0.0,
|
| 638 |
+
"clip_ratio/high_mean": 0.0,
|
| 639 |
+
"clip_ratio/low_mean": 0.0,
|
| 640 |
+
"clip_ratio/low_min": 0.0,
|
| 641 |
+
"clip_ratio/region_mean": 0.0,
|
| 642 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 643 |
+
"completions/max_length": 1358.0,
|
| 644 |
+
"completions/max_terminated_length": 587.0,
|
| 645 |
+
"completions/mean_length": 520.7916870117188,
|
| 646 |
+
"completions/mean_terminated_length": 587.0,
|
| 647 |
+
"completions/min_length": 128.0,
|
| 648 |
+
"completions/min_terminated_length": 587.0,
|
| 649 |
+
"entropy": 10.113564809163412,
|
| 650 |
+
"epoch": 0.00020250202502025022,
|
| 651 |
+
"frac_reward_zero_std": 0.0,
|
| 652 |
+
"grad_norm": 0.0,
|
| 653 |
+
"kl": 0.0,
|
| 654 |
+
"learning_rate": 2.4514285714285716e-05,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"num_tokens": 410593.0,
|
| 657 |
+
"reward": -44.441925048828125,
|
| 658 |
+
"reward_std": 25.591054916381836,
|
| 659 |
+
"rewards/rollout_reward_func/mean": -44.441925048828125,
|
| 660 |
+
"rewards/rollout_reward_func/std": 26.473356246948242,
|
| 661 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 662 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 663 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 664 |
+
"sampling/sampling_logp_difference/max": 14.11213493347168,
|
| 665 |
+
"sampling/sampling_logp_difference/mean": 3.1286377906799316,
|
| 666 |
+
"step": 27,
|
| 667 |
+
"step_time": 21.701382299001125
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"clip_ratio/high_max": 0.0,
|
| 671 |
+
"clip_ratio/high_mean": 0.0,
|
| 672 |
+
"clip_ratio/low_mean": 0.0,
|
| 673 |
+
"clip_ratio/low_min": 0.0,
|
| 674 |
+
"clip_ratio/region_mean": 0.0,
|
| 675 |
+
"entropy": 10.113564809163412,
|
| 676 |
+
"epoch": 0.0002100021000210002,
|
| 677 |
+
"grad_norm": 0.0,
|
| 678 |
+
"kl": 0.0,
|
| 679 |
+
"learning_rate": 2.545714285714286e-05,
|
| 680 |
+
"loss": 0.0,
|
| 681 |
+
"step": 28,
|
| 682 |
+
"step_time": 1.7842601579986876
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"clip_ratio/high_max": 0.0,
|
| 686 |
+
"clip_ratio/high_mean": 0.0,
|
| 687 |
+
"clip_ratio/low_mean": 0.0,
|
| 688 |
+
"clip_ratio/low_min": 0.0,
|
| 689 |
+
"clip_ratio/region_mean": 0.0,
|
| 690 |
+
"completions/clipped_ratio": 1.0,
|
| 691 |
+
"completions/max_length": 1249.0,
|
| 692 |
+
"completions/max_terminated_length": 0.0,
|
| 693 |
+
"completions/mean_length": 547.2916870117188,
|
| 694 |
+
"completions/mean_terminated_length": 0.0,
|
| 695 |
+
"completions/min_length": 128.0,
|
| 696 |
+
"completions/min_terminated_length": 0.0,
|
| 697 |
+
"entropy": 10.082143624623617,
|
| 698 |
+
"epoch": 0.00021750217502175022,
|
| 699 |
+
"frac_reward_zero_std": 0.0,
|
| 700 |
+
"grad_norm": 0.0,
|
| 701 |
+
"kl": 0.0,
|
| 702 |
+
"learning_rate": 2.6400000000000005e-05,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"num_tokens": 440182.0,
|
| 705 |
+
"reward": -45.103240966796875,
|
| 706 |
+
"reward_std": 21.529327392578125,
|
| 707 |
+
"rewards/rollout_reward_func/mean": -45.103240966796875,
|
| 708 |
+
"rewards/rollout_reward_func/std": 20.876861572265625,
|
| 709 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 710 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 711 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 712 |
+
"sampling/sampling_logp_difference/max": 14.8016996383667,
|
| 713 |
+
"sampling/sampling_logp_difference/mean": 3.1039717197418213,
|
| 714 |
+
"step": 29,
|
| 715 |
+
"step_time": 21.481158237000272
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"clip_ratio/high_max": 0.0,
|
| 719 |
+
"clip_ratio/high_mean": 0.0,
|
| 720 |
+
"clip_ratio/low_mean": 0.0,
|
| 721 |
+
"clip_ratio/low_min": 0.0,
|
| 722 |
+
"clip_ratio/region_mean": 0.0,
|
| 723 |
+
"entropy": 10.082143624623617,
|
| 724 |
+
"epoch": 0.00022500225002250023,
|
| 725 |
+
"grad_norm": 0.0,
|
| 726 |
+
"kl": 0.0,
|
| 727 |
+
"learning_rate": 2.7342857142857146e-05,
|
| 728 |
+
"loss": 0.0,
|
| 729 |
+
"step": 30,
|
| 730 |
+
"step_time": 2.1532514040018214
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"clip_ratio/high_max": 0.0,
|
| 734 |
+
"clip_ratio/high_mean": 0.0,
|
| 735 |
+
"clip_ratio/low_mean": 0.0,
|
| 736 |
+
"clip_ratio/low_min": 0.0,
|
| 737 |
+
"clip_ratio/region_mean": 0.0,
|
| 738 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 739 |
+
"completions/max_length": 1320.0,
|
| 740 |
+
"completions/max_terminated_length": 545.0,
|
| 741 |
+
"completions/mean_length": 434.9583435058594,
|
| 742 |
+
"completions/mean_terminated_length": 545.0,
|
| 743 |
+
"completions/min_length": 128.0,
|
| 744 |
+
"completions/min_terminated_length": 545.0,
|
| 745 |
+
"entropy": 10.205902258555094,
|
| 746 |
+
"epoch": 0.00023250232502325022,
|
| 747 |
+
"frac_reward_zero_std": 0.0,
|
| 748 |
+
"grad_norm": 0.0,
|
| 749 |
+
"kl": 0.0,
|
| 750 |
+
"learning_rate": 2.8285714285714287e-05,
|
| 751 |
+
"loss": 0.0,
|
| 752 |
+
"num_tokens": 467213.0,
|
| 753 |
+
"reward": -46.596885681152344,
|
| 754 |
+
"reward_std": 16.725446701049805,
|
| 755 |
+
"rewards/rollout_reward_func/mean": -46.59688186645508,
|
| 756 |
+
"rewards/rollout_reward_func/std": 16.85680389404297,
|
| 757 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 758 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 759 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 760 |
+
"sampling/sampling_logp_difference/max": 15.102117538452148,
|
| 761 |
+
"sampling/sampling_logp_difference/mean": 3.278193712234497,
|
| 762 |
+
"step": 31,
|
| 763 |
+
"step_time": 21.168742055999246
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"clip_ratio/high_max": 0.0,
|
| 767 |
+
"clip_ratio/high_mean": 0.0,
|
| 768 |
+
"clip_ratio/low_mean": 0.0,
|
| 769 |
+
"clip_ratio/low_min": 0.0,
|
| 770 |
+
"clip_ratio/region_mean": 0.0,
|
| 771 |
+
"entropy": 10.205902258555094,
|
| 772 |
+
"epoch": 0.00024000240002400024,
|
| 773 |
+
"grad_norm": 0.0,
|
| 774 |
+
"kl": 0.0,
|
| 775 |
+
"learning_rate": 2.9228571428571428e-05,
|
| 776 |
+
"loss": 0.0,
|
| 777 |
+
"step": 32,
|
| 778 |
+
"step_time": 1.750853970001117
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"clip_ratio/high_max": 0.0,
|
| 782 |
+
"clip_ratio/high_mean": 0.0,
|
| 783 |
+
"clip_ratio/low_mean": 0.0,
|
| 784 |
+
"clip_ratio/low_min": 0.0,
|
| 785 |
+
"clip_ratio/region_mean": 0.0,
|
| 786 |
+
"completions/clipped_ratio": 1.0,
|
| 787 |
+
"completions/max_length": 1175.0,
|
| 788 |
+
"completions/max_terminated_length": 0.0,
|
| 789 |
+
"completions/mean_length": 483.5,
|
| 790 |
+
"completions/mean_terminated_length": 0.0,
|
| 791 |
+
"completions/min_length": 128.0,
|
| 792 |
+
"completions/min_terminated_length": 0.0,
|
| 793 |
+
"entropy": 10.10767682393392,
|
| 794 |
+
"epoch": 0.00024750247502475025,
|
| 795 |
+
"frac_reward_zero_std": 0.0,
|
| 796 |
+
"grad_norm": 0.0,
|
| 797 |
+
"kl": 0.0,
|
| 798 |
+
"learning_rate": 3.0171428571428572e-05,
|
| 799 |
+
"loss": 0.0,
|
| 800 |
+
"num_tokens": 494889.0,
|
| 801 |
+
"reward": -54.67100143432617,
|
| 802 |
+
"reward_std": 15.08906364440918,
|
| 803 |
+
"rewards/rollout_reward_func/mean": -54.67100143432617,
|
| 804 |
+
"rewards/rollout_reward_func/std": 14.835305213928223,
|
| 805 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 806 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 807 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 808 |
+
"sampling/sampling_logp_difference/max": 13.920793533325195,
|
| 809 |
+
"sampling/sampling_logp_difference/mean": 3.077173948287964,
|
| 810 |
+
"step": 33,
|
| 811 |
+
"step_time": 18.65274686000157
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"clip_ratio/high_max": 0.0,
|
| 815 |
+
"clip_ratio/high_mean": 0.0,
|
| 816 |
+
"clip_ratio/low_mean": 0.0,
|
| 817 |
+
"clip_ratio/low_min": 0.0,
|
| 818 |
+
"clip_ratio/region_mean": 0.0,
|
| 819 |
+
"entropy": 10.10767682393392,
|
| 820 |
+
"epoch": 0.00025500255002550024,
|
| 821 |
+
"grad_norm": 0.0,
|
| 822 |
+
"kl": 0.0,
|
| 823 |
+
"learning_rate": 3.1114285714285714e-05,
|
| 824 |
+
"loss": 0.0,
|
| 825 |
+
"step": 34,
|
| 826 |
+
"step_time": 1.6550644490016566
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"clip_ratio/high_max": 0.0,
|
| 830 |
+
"clip_ratio/high_mean": 0.0,
|
| 831 |
+
"clip_ratio/low_mean": 0.0,
|
| 832 |
+
"clip_ratio/low_min": 0.0,
|
| 833 |
+
"clip_ratio/region_mean": 0.0,
|
| 834 |
+
"completions/clipped_ratio": 1.0,
|
| 835 |
+
"completions/max_length": 1209.0,
|
| 836 |
+
"completions/max_terminated_length": 0.0,
|
| 837 |
+
"completions/mean_length": 526.3333740234375,
|
| 838 |
+
"completions/mean_terminated_length": 0.0,
|
| 839 |
+
"completions/min_length": 128.0,
|
| 840 |
+
"completions/min_terminated_length": 0.0,
|
| 841 |
+
"entropy": 10.051785469055176,
|
| 842 |
+
"epoch": 0.0002625026250262503,
|
| 843 |
+
"frac_reward_zero_std": 0.0,
|
| 844 |
+
"grad_norm": 0.0,
|
| 845 |
+
"kl": 0.0,
|
| 846 |
+
"learning_rate": 3.205714285714286e-05,
|
| 847 |
+
"loss": 0.0,
|
| 848 |
+
"num_tokens": 524061.0,
|
| 849 |
+
"reward": -45.748435974121094,
|
| 850 |
+
"reward_std": 21.241294860839844,
|
| 851 |
+
"rewards/rollout_reward_func/mean": -45.74843978881836,
|
| 852 |
+
"rewards/rollout_reward_func/std": 21.725393295288086,
|
| 853 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 854 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 855 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 856 |
+
"sampling/sampling_logp_difference/max": 15.848544120788574,
|
| 857 |
+
"sampling/sampling_logp_difference/mean": 3.12214994430542,
|
| 858 |
+
"step": 35,
|
| 859 |
+
"step_time": 21.866697636000026
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"clip_ratio/high_max": 0.0,
|
| 863 |
+
"clip_ratio/high_mean": 0.0,
|
| 864 |
+
"clip_ratio/low_mean": 0.0,
|
| 865 |
+
"clip_ratio/low_min": 0.0,
|
| 866 |
+
"clip_ratio/region_mean": 0.0,
|
| 867 |
+
"entropy": 10.051785469055176,
|
| 868 |
+
"epoch": 0.00027000270002700027,
|
| 869 |
+
"grad_norm": 0.0,
|
| 870 |
+
"kl": 0.0,
|
| 871 |
+
"learning_rate": 3.3e-05,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"step": 36,
|
| 874 |
+
"step_time": 1.6678288799994334
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"clip_ratio/high_max": 0.0,
|
| 878 |
+
"clip_ratio/high_mean": 0.0,
|
| 879 |
+
"clip_ratio/low_mean": 0.0,
|
| 880 |
+
"clip_ratio/low_min": 0.0,
|
| 881 |
+
"clip_ratio/region_mean": 0.0,
|
| 882 |
+
"completions/clipped_ratio": 1.0,
|
| 883 |
+
"completions/max_length": 1409.0,
|
| 884 |
+
"completions/max_terminated_length": 0.0,
|
| 885 |
+
"completions/mean_length": 479.75,
|
| 886 |
+
"completions/mean_terminated_length": 0.0,
|
| 887 |
+
"completions/min_length": 117.0,
|
| 888 |
+
"completions/min_terminated_length": 0.0,
|
| 889 |
+
"entropy": 10.13319698969523,
|
| 890 |
+
"epoch": 0.00027750277502775026,
|
| 891 |
+
"frac_reward_zero_std": 0.0,
|
| 892 |
+
"grad_norm": 0.0,
|
| 893 |
+
"kl": 0.0,
|
| 894 |
+
"learning_rate": 3.299999999986258e-05,
|
| 895 |
+
"loss": 0.0,
|
| 896 |
+
"num_tokens": 551502.0,
|
| 897 |
+
"reward": -49.105323791503906,
|
| 898 |
+
"reward_std": 17.612197875976562,
|
| 899 |
+
"rewards/rollout_reward_func/mean": -49.105316162109375,
|
| 900 |
+
"rewards/rollout_reward_func/std": 17.828832626342773,
|
| 901 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 902 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 903 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 904 |
+
"sampling/sampling_logp_difference/max": 14.797318458557129,
|
| 905 |
+
"sampling/sampling_logp_difference/mean": 3.0804805755615234,
|
| 906 |
+
"step": 37,
|
| 907 |
+
"step_time": 21.77108188600141
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"clip_ratio/high_max": 0.0,
|
| 911 |
+
"clip_ratio/high_mean": 0.0,
|
| 912 |
+
"clip_ratio/low_mean": 0.0,
|
| 913 |
+
"clip_ratio/low_min": 0.0,
|
| 914 |
+
"clip_ratio/region_mean": 0.0,
|
| 915 |
+
"entropy": 10.13319698969523,
|
| 916 |
+
"epoch": 0.0002850028500285003,
|
| 917 |
+
"grad_norm": 0.0,
|
| 918 |
+
"kl": 0.0,
|
| 919 |
+
"learning_rate": 3.299999999945032e-05,
|
| 920 |
+
"loss": 0.0,
|
| 921 |
+
"step": 38,
|
| 922 |
+
"step_time": 1.8092515669995919
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"clip_ratio/high_max": 0.0,
|
| 926 |
+
"clip_ratio/high_mean": 0.0,
|
| 927 |
+
"clip_ratio/low_mean": 0.0,
|
| 928 |
+
"clip_ratio/low_min": 0.0,
|
| 929 |
+
"clip_ratio/region_mean": 0.0,
|
| 930 |
+
"completions/clipped_ratio": 1.0,
|
| 931 |
+
"completions/max_length": 1230.0,
|
| 932 |
+
"completions/max_terminated_length": 0.0,
|
| 933 |
+
"completions/mean_length": 487.7083435058594,
|
| 934 |
+
"completions/mean_terminated_length": 0.0,
|
| 935 |
+
"completions/min_length": 128.0,
|
| 936 |
+
"completions/min_terminated_length": 0.0,
|
| 937 |
+
"entropy": 10.18622620900472,
|
| 938 |
+
"epoch": 0.0002925029250292503,
|
| 939 |
+
"frac_reward_zero_std": 0.0,
|
| 940 |
+
"grad_norm": 0.0,
|
| 941 |
+
"kl": 0.0,
|
| 942 |
+
"learning_rate": 3.299999999876322e-05,
|
| 943 |
+
"loss": 0.0,
|
| 944 |
+
"num_tokens": 579575.0,
|
| 945 |
+
"reward": -52.96455001831055,
|
| 946 |
+
"reward_std": 15.875425338745117,
|
| 947 |
+
"rewards/rollout_reward_func/mean": -52.96455001831055,
|
| 948 |
+
"rewards/rollout_reward_func/std": 15.511474609375,
|
| 949 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 950 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 951 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 952 |
+
"sampling/sampling_logp_difference/max": 14.835306167602539,
|
| 953 |
+
"sampling/sampling_logp_difference/mean": 3.1505439281463623,
|
| 954 |
+
"step": 39,
|
| 955 |
+
"step_time": 17.71383904600225
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"clip_ratio/high_max": 0.0,
|
| 959 |
+
"clip_ratio/high_mean": 0.0,
|
| 960 |
+
"clip_ratio/low_mean": 0.0,
|
| 961 |
+
"clip_ratio/low_min": 0.0,
|
| 962 |
+
"clip_ratio/region_mean": 0.0,
|
| 963 |
+
"entropy": 10.18622620900472,
|
| 964 |
+
"epoch": 0.0003000030000300003,
|
| 965 |
+
"grad_norm": 0.0,
|
| 966 |
+
"kl": 0.0,
|
| 967 |
+
"learning_rate": 3.299999999780127e-05,
|
| 968 |
+
"loss": 0.0,
|
| 969 |
+
"step": 40,
|
| 970 |
+
"step_time": 1.6824162199991406
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"clip_ratio/high_max": 0.0,
|
| 974 |
+
"clip_ratio/high_mean": 0.0,
|
| 975 |
+
"clip_ratio/low_mean": 0.0,
|
| 976 |
+
"clip_ratio/low_min": 0.0,
|
| 977 |
+
"clip_ratio/region_mean": 0.0,
|
| 978 |
+
"completions/clipped_ratio": 1.0,
|
| 979 |
+
"completions/max_length": 1092.0,
|
| 980 |
+
"completions/max_terminated_length": 0.0,
|
| 981 |
+
"completions/mean_length": 420.2083435058594,
|
| 982 |
+
"completions/mean_terminated_length": 0.0,
|
| 983 |
+
"completions/min_length": 128.0,
|
| 984 |
+
"completions/min_terminated_length": 0.0,
|
| 985 |
+
"entropy": 10.118754863739014,
|
| 986 |
+
"epoch": 0.0003075030750307503,
|
| 987 |
+
"frac_reward_zero_std": 0.0,
|
| 988 |
+
"grad_norm": 0.0,
|
| 989 |
+
"kl": 0.0,
|
| 990 |
+
"learning_rate": 3.299999999656449e-05,
|
| 991 |
+
"loss": 0.0,
|
| 992 |
+
"num_tokens": 606180.0,
|
| 993 |
+
"reward": -46.9930534362793,
|
| 994 |
+
"reward_std": 20.2467041015625,
|
| 995 |
+
"rewards/rollout_reward_func/mean": -46.9930534362793,
|
| 996 |
+
"rewards/rollout_reward_func/std": 19.9199161529541,
|
| 997 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 998 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 999 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1000 |
+
"sampling/sampling_logp_difference/max": 15.123610496520996,
|
| 1001 |
+
"sampling/sampling_logp_difference/mean": 3.206780195236206,
|
| 1002 |
+
"step": 41,
|
| 1003 |
+
"step_time": 21.204631595998762
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"clip_ratio/high_max": 0.0,
|
| 1007 |
+
"clip_ratio/high_mean": 0.0,
|
| 1008 |
+
"clip_ratio/low_mean": 0.0,
|
| 1009 |
+
"clip_ratio/low_min": 0.0,
|
| 1010 |
+
"clip_ratio/region_mean": 0.0,
|
| 1011 |
+
"entropy": 10.118754863739014,
|
| 1012 |
+
"epoch": 0.0003150031500315003,
|
| 1013 |
+
"grad_norm": 0.0,
|
| 1014 |
+
"kl": 0.0,
|
| 1015 |
+
"learning_rate": 3.299999999505286e-05,
|
| 1016 |
+
"loss": 0.0,
|
| 1017 |
+
"step": 42,
|
| 1018 |
+
"step_time": 2.068030981999982
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"clip_ratio/high_max": 0.0,
|
| 1022 |
+
"clip_ratio/high_mean": 0.0,
|
| 1023 |
+
"clip_ratio/low_mean": 0.0,
|
| 1024 |
+
"clip_ratio/low_min": 0.0,
|
| 1025 |
+
"clip_ratio/region_mean": 0.0,
|
| 1026 |
+
"completions/clipped_ratio": 1.0,
|
| 1027 |
+
"completions/max_length": 1052.0,
|
| 1028 |
+
"completions/max_terminated_length": 0.0,
|
| 1029 |
+
"completions/mean_length": 458.91668701171875,
|
| 1030 |
+
"completions/mean_terminated_length": 0.0,
|
| 1031 |
+
"completions/min_length": 199.0,
|
| 1032 |
+
"completions/min_terminated_length": 0.0,
|
| 1033 |
+
"entropy": 10.044801712036133,
|
| 1034 |
+
"epoch": 0.00032250322503225035,
|
| 1035 |
+
"frac_reward_zero_std": 0.0,
|
| 1036 |
+
"grad_norm": 0.0,
|
| 1037 |
+
"kl": 0.0,
|
| 1038 |
+
"learning_rate": 3.2999999993266396e-05,
|
| 1039 |
+
"loss": 0.0,
|
| 1040 |
+
"num_tokens": 632958.0,
|
| 1041 |
+
"reward": -49.451873779296875,
|
| 1042 |
+
"reward_std": 19.586355209350586,
|
| 1043 |
+
"rewards/rollout_reward_func/mean": -49.451873779296875,
|
| 1044 |
+
"rewards/rollout_reward_func/std": 19.92502784729004,
|
| 1045 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1046 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1047 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1048 |
+
"sampling/sampling_logp_difference/max": 14.691810607910156,
|
| 1049 |
+
"sampling/sampling_logp_difference/mean": 3.104357957839966,
|
| 1050 |
+
"step": 43,
|
| 1051 |
+
"step_time": 20.662249461999636
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"clip_ratio/high_max": 0.0,
|
| 1055 |
+
"clip_ratio/high_mean": 0.0,
|
| 1056 |
+
"clip_ratio/low_mean": 0.0,
|
| 1057 |
+
"clip_ratio/low_min": 0.0,
|
| 1058 |
+
"clip_ratio/region_mean": 0.0,
|
| 1059 |
+
"entropy": 10.044801712036133,
|
| 1060 |
+
"epoch": 0.00033000330003300033,
|
| 1061 |
+
"grad_norm": 0.0,
|
| 1062 |
+
"kl": 0.0,
|
| 1063 |
+
"learning_rate": 3.299999999120509e-05,
|
| 1064 |
+
"loss": 0.0,
|
| 1065 |
+
"step": 44,
|
| 1066 |
+
"step_time": 1.6131189530015035
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"clip_ratio/high_max": 0.0,
|
| 1070 |
+
"clip_ratio/high_mean": 0.0,
|
| 1071 |
+
"clip_ratio/low_mean": 0.0,
|
| 1072 |
+
"clip_ratio/low_min": 0.0,
|
| 1073 |
+
"clip_ratio/region_mean": 0.0,
|
| 1074 |
+
"completions/clipped_ratio": 1.0,
|
| 1075 |
+
"completions/max_length": 1517.0,
|
| 1076 |
+
"completions/max_terminated_length": 0.0,
|
| 1077 |
+
"completions/mean_length": 572.25,
|
| 1078 |
+
"completions/mean_terminated_length": 0.0,
|
| 1079 |
+
"completions/min_length": 128.0,
|
| 1080 |
+
"completions/min_terminated_length": 0.0,
|
| 1081 |
+
"entropy": 10.101013978322348,
|
| 1082 |
+
"epoch": 0.0003375033750337503,
|
| 1083 |
+
"frac_reward_zero_std": 0.0,
|
| 1084 |
+
"grad_norm": 0.0,
|
| 1085 |
+
"kl": 0.0,
|
| 1086 |
+
"learning_rate": 3.299999998886893e-05,
|
| 1087 |
+
"loss": 0.0,
|
| 1088 |
+
"num_tokens": 662770.0,
|
| 1089 |
+
"reward": -43.31492233276367,
|
| 1090 |
+
"reward_std": 21.76721954345703,
|
| 1091 |
+
"rewards/rollout_reward_func/mean": -43.31492233276367,
|
| 1092 |
+
"rewards/rollout_reward_func/std": 21.667734146118164,
|
| 1093 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1094 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1095 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1096 |
+
"sampling/sampling_logp_difference/max": 14.86938190460205,
|
| 1097 |
+
"sampling/sampling_logp_difference/mean": 3.125654935836792,
|
| 1098 |
+
"step": 45,
|
| 1099 |
+
"step_time": 22.175719804000437
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"clip_ratio/high_max": 0.0,
|
| 1103 |
+
"clip_ratio/high_mean": 0.0,
|
| 1104 |
+
"clip_ratio/low_mean": 0.0,
|
| 1105 |
+
"clip_ratio/low_min": 0.0,
|
| 1106 |
+
"clip_ratio/region_mean": 0.0,
|
| 1107 |
+
"entropy": 10.101013978322348,
|
| 1108 |
+
"epoch": 0.00034500345003450036,
|
| 1109 |
+
"grad_norm": 0.0,
|
| 1110 |
+
"kl": 0.0,
|
| 1111 |
+
"learning_rate": 3.299999998625794e-05,
|
| 1112 |
+
"loss": 0.0,
|
| 1113 |
+
"step": 46,
|
| 1114 |
+
"step_time": 1.9093814330008172
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"clip_ratio/high_max": 0.0,
|
| 1118 |
+
"clip_ratio/high_mean": 0.0,
|
| 1119 |
+
"clip_ratio/low_mean": 0.0,
|
| 1120 |
+
"clip_ratio/low_min": 0.0,
|
| 1121 |
+
"clip_ratio/region_mean": 0.0,
|
| 1122 |
+
"completions/clipped_ratio": 1.0,
|
| 1123 |
+
"completions/max_length": 1180.0,
|
| 1124 |
+
"completions/max_terminated_length": 0.0,
|
| 1125 |
+
"completions/mean_length": 510.8333435058594,
|
| 1126 |
+
"completions/mean_terminated_length": 0.0,
|
| 1127 |
+
"completions/min_length": 128.0,
|
| 1128 |
+
"completions/min_terminated_length": 0.0,
|
| 1129 |
+
"entropy": 10.153699239095053,
|
| 1130 |
+
"epoch": 0.00035250352503525035,
|
| 1131 |
+
"frac_reward_zero_std": 0.0,
|
| 1132 |
+
"grad_norm": 0.0,
|
| 1133 |
+
"kl": 0.0,
|
| 1134 |
+
"learning_rate": 3.2999999983372116e-05,
|
| 1135 |
+
"loss": 0.0,
|
| 1136 |
+
"num_tokens": 691021.0,
|
| 1137 |
+
"reward": -52.171714782714844,
|
| 1138 |
+
"reward_std": 15.545321464538574,
|
| 1139 |
+
"rewards/rollout_reward_func/mean": -52.17171096801758,
|
| 1140 |
+
"rewards/rollout_reward_func/std": 17.01911735534668,
|
| 1141 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1142 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1143 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1144 |
+
"sampling/sampling_logp_difference/max": 14.297968864440918,
|
| 1145 |
+
"sampling/sampling_logp_difference/mean": 3.1078176498413086,
|
| 1146 |
+
"step": 47,
|
| 1147 |
+
"step_time": 18.611535334998734
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"clip_ratio/high_max": 0.0,
|
| 1151 |
+
"clip_ratio/high_mean": 0.0,
|
| 1152 |
+
"clip_ratio/low_mean": 0.0,
|
| 1153 |
+
"clip_ratio/low_min": 0.0,
|
| 1154 |
+
"clip_ratio/region_mean": 0.0,
|
| 1155 |
+
"entropy": 10.153699239095053,
|
| 1156 |
+
"epoch": 0.00036000360003600034,
|
| 1157 |
+
"grad_norm": 0.0,
|
| 1158 |
+
"kl": 0.0,
|
| 1159 |
+
"learning_rate": 3.2999999980211436e-05,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 48,
|
| 1162 |
+
"step_time": 1.658304570000837
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"clip_ratio/high_max": 0.0,
|
| 1166 |
+
"clip_ratio/high_mean": 0.0,
|
| 1167 |
+
"clip_ratio/low_mean": 0.0,
|
| 1168 |
+
"clip_ratio/low_min": 0.0,
|
| 1169 |
+
"clip_ratio/region_mean": 0.0,
|
| 1170 |
+
"completions/clipped_ratio": 1.0,
|
| 1171 |
+
"completions/max_length": 1470.0,
|
| 1172 |
+
"completions/max_terminated_length": 0.0,
|
| 1173 |
+
"completions/mean_length": 560.8333740234375,
|
| 1174 |
+
"completions/mean_terminated_length": 0.0,
|
| 1175 |
+
"completions/min_length": 128.0,
|
| 1176 |
+
"completions/min_terminated_length": 0.0,
|
| 1177 |
+
"entropy": 10.123283545176188,
|
| 1178 |
+
"epoch": 0.0003675036750367504,
|
| 1179 |
+
"frac_reward_zero_std": 0.0,
|
| 1180 |
+
"grad_norm": 0.0,
|
| 1181 |
+
"kl": 0.0,
|
| 1182 |
+
"learning_rate": 3.2999999976775924e-05,
|
| 1183 |
+
"loss": 0.0,
|
| 1184 |
+
"num_tokens": 720151.0,
|
| 1185 |
+
"reward": -46.37849044799805,
|
| 1186 |
+
"reward_std": 20.132478713989258,
|
| 1187 |
+
"rewards/rollout_reward_func/mean": -46.37849044799805,
|
| 1188 |
+
"rewards/rollout_reward_func/std": 20.508827209472656,
|
| 1189 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1190 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1191 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1192 |
+
"sampling/sampling_logp_difference/max": 14.414722442626953,
|
| 1193 |
+
"sampling/sampling_logp_difference/mean": 3.121212959289551,
|
| 1194 |
+
"step": 49,
|
| 1195 |
+
"step_time": 20.764608049001254
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"clip_ratio/high_max": 0.0,
|
| 1199 |
+
"clip_ratio/high_mean": 0.0,
|
| 1200 |
+
"clip_ratio/low_mean": 0.0,
|
| 1201 |
+
"clip_ratio/low_min": 0.0,
|
| 1202 |
+
"clip_ratio/region_mean": 0.0,
|
| 1203 |
+
"entropy": 10.123283545176188,
|
| 1204 |
+
"epoch": 0.00037500375003750037,
|
| 1205 |
+
"grad_norm": 0.0,
|
| 1206 |
+
"kl": 0.0,
|
| 1207 |
+
"learning_rate": 3.2999999973065575e-05,
|
| 1208 |
+
"loss": 0.0,
|
| 1209 |
+
"step": 50,
|
| 1210 |
+
"step_time": 1.8636344930000632
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"clip_ratio/high_max": 0.0,
|
| 1214 |
+
"clip_ratio/high_mean": 0.0,
|
| 1215 |
+
"clip_ratio/low_mean": 0.0,
|
| 1216 |
+
"clip_ratio/low_min": 0.0,
|
| 1217 |
+
"clip_ratio/region_mean": 0.0,
|
| 1218 |
+
"completions/clipped_ratio": 1.0,
|
| 1219 |
+
"completions/max_length": 1200.0,
|
| 1220 |
+
"completions/max_terminated_length": 0.0,
|
| 1221 |
+
"completions/mean_length": 597.5,
|
| 1222 |
+
"completions/mean_terminated_length": 0.0,
|
| 1223 |
+
"completions/min_length": 128.0,
|
| 1224 |
+
"completions/min_terminated_length": 0.0,
|
| 1225 |
+
"entropy": 10.12819274266561,
|
| 1226 |
+
"epoch": 0.00038250382503825036,
|
| 1227 |
+
"frac_reward_zero_std": 0.0,
|
| 1228 |
+
"grad_norm": 0.0,
|
| 1229 |
+
"kl": 0.0,
|
| 1230 |
+
"learning_rate": 3.299999996908037e-05,
|
| 1231 |
+
"loss": 0.0,
|
| 1232 |
+
"num_tokens": 751114.0,
|
| 1233 |
+
"reward": -45.675315856933594,
|
| 1234 |
+
"reward_std": 19.463340759277344,
|
| 1235 |
+
"rewards/rollout_reward_func/mean": -45.67531204223633,
|
| 1236 |
+
"rewards/rollout_reward_func/std": 19.729412078857422,
|
| 1237 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1238 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1239 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1240 |
+
"sampling/sampling_logp_difference/max": 14.647856712341309,
|
| 1241 |
+
"sampling/sampling_logp_difference/mean": 3.114715337753296,
|
| 1242 |
+
"step": 51,
|
| 1243 |
+
"step_time": 21.510169729001063
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"clip_ratio/high_max": 0.0,
|
| 1247 |
+
"clip_ratio/high_mean": 0.0,
|
| 1248 |
+
"clip_ratio/low_mean": 0.0,
|
| 1249 |
+
"clip_ratio/low_min": 0.0,
|
| 1250 |
+
"clip_ratio/region_mean": 0.0,
|
| 1251 |
+
"entropy": 10.12819274266561,
|
| 1252 |
+
"epoch": 0.0003900039000390004,
|
| 1253 |
+
"grad_norm": 0.0,
|
| 1254 |
+
"kl": 0.0,
|
| 1255 |
+
"learning_rate": 3.299999996482033e-05,
|
| 1256 |
+
"loss": 0.0,
|
| 1257 |
+
"step": 52,
|
| 1258 |
+
"step_time": 1.669872710999698
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"clip_ratio/high_max": 0.0,
|
| 1262 |
+
"clip_ratio/high_mean": 0.0,
|
| 1263 |
+
"clip_ratio/low_mean": 0.0,
|
| 1264 |
+
"clip_ratio/low_min": 0.0,
|
| 1265 |
+
"clip_ratio/region_mean": 0.0,
|
| 1266 |
+
"completions/clipped_ratio": 0.9583333730697632,
|
| 1267 |
+
"completions/max_length": 1084.0,
|
| 1268 |
+
"completions/max_terminated_length": 273.0,
|
| 1269 |
+
"completions/mean_length": 531.5833740234375,
|
| 1270 |
+
"completions/mean_terminated_length": 273.0,
|
| 1271 |
+
"completions/min_length": 128.0,
|
| 1272 |
+
"completions/min_terminated_length": 273.0,
|
| 1273 |
+
"entropy": 10.146964073181152,
|
| 1274 |
+
"epoch": 0.0003975039750397504,
|
| 1275 |
+
"frac_reward_zero_std": 0.0,
|
| 1276 |
+
"grad_norm": 0.0,
|
| 1277 |
+
"kl": 0.0,
|
| 1278 |
+
"learning_rate": 3.299999996028545e-05,
|
| 1279 |
+
"loss": 0.0,
|
| 1280 |
+
"num_tokens": 779983.0,
|
| 1281 |
+
"reward": -46.03662109375,
|
| 1282 |
+
"reward_std": 19.839950561523438,
|
| 1283 |
+
"rewards/rollout_reward_func/mean": -46.03662109375,
|
| 1284 |
+
"rewards/rollout_reward_func/std": 21.031444549560547,
|
| 1285 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1286 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1287 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1288 |
+
"sampling/sampling_logp_difference/max": 14.309167861938477,
|
| 1289 |
+
"sampling/sampling_logp_difference/mean": 3.155137777328491,
|
| 1290 |
+
"step": 53,
|
| 1291 |
+
"step_time": 22.573047874000622
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"clip_ratio/high_max": 0.0,
|
| 1295 |
+
"clip_ratio/high_mean": 0.0,
|
| 1296 |
+
"clip_ratio/low_mean": 0.0,
|
| 1297 |
+
"clip_ratio/low_min": 0.0,
|
| 1298 |
+
"clip_ratio/region_mean": 0.0,
|
| 1299 |
+
"entropy": 10.146964073181152,
|
| 1300 |
+
"epoch": 0.00040500405004050043,
|
| 1301 |
+
"grad_norm": 0.0,
|
| 1302 |
+
"kl": 0.0,
|
| 1303 |
+
"learning_rate": 3.2999999955475736e-05,
|
| 1304 |
+
"loss": 0.0,
|
| 1305 |
+
"step": 54,
|
| 1306 |
+
"step_time": 1.612867594999443
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"clip_ratio/high_max": 0.0,
|
| 1310 |
+
"clip_ratio/high_mean": 0.0,
|
| 1311 |
+
"clip_ratio/low_mean": 0.0,
|
| 1312 |
+
"clip_ratio/low_min": 0.0,
|
| 1313 |
+
"clip_ratio/region_mean": 0.0,
|
| 1314 |
+
"completions/clipped_ratio": 1.0,
|
| 1315 |
+
"completions/max_length": 1096.0,
|
| 1316 |
+
"completions/max_terminated_length": 0.0,
|
| 1317 |
+
"completions/mean_length": 520.2083740234375,
|
| 1318 |
+
"completions/mean_terminated_length": 0.0,
|
| 1319 |
+
"completions/min_length": 128.0,
|
| 1320 |
+
"completions/min_terminated_length": 0.0,
|
| 1321 |
+
"entropy": 10.004105885823568,
|
| 1322 |
+
"epoch": 0.0004125041250412504,
|
| 1323 |
+
"frac_reward_zero_std": 0.0,
|
| 1324 |
+
"grad_norm": 0.0,
|
| 1325 |
+
"kl": 0.0,
|
| 1326 |
+
"learning_rate": 3.299999995039117e-05,
|
| 1327 |
+
"loss": 0.0,
|
| 1328 |
+
"num_tokens": 808253.0,
|
| 1329 |
+
"reward": -50.46704864501953,
|
| 1330 |
+
"reward_std": 17.44925308227539,
|
| 1331 |
+
"rewards/rollout_reward_func/mean": -50.467044830322266,
|
| 1332 |
+
"rewards/rollout_reward_func/std": 16.909671783447266,
|
| 1333 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1334 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1335 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1336 |
+
"sampling/sampling_logp_difference/max": 13.991758346557617,
|
| 1337 |
+
"sampling/sampling_logp_difference/mean": 3.0269718170166016,
|
| 1338 |
+
"step": 55,
|
| 1339 |
+
"step_time": 20.465181108998877
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"clip_ratio/high_max": 0.0,
|
| 1343 |
+
"clip_ratio/high_mean": 0.0,
|
| 1344 |
+
"clip_ratio/low_mean": 0.0,
|
| 1345 |
+
"clip_ratio/low_min": 0.0,
|
| 1346 |
+
"clip_ratio/region_mean": 0.0,
|
| 1347 |
+
"entropy": 10.004105885823568,
|
| 1348 |
+
"epoch": 0.0004200042000420004,
|
| 1349 |
+
"grad_norm": 0.0,
|
| 1350 |
+
"kl": 0.0,
|
| 1351 |
+
"learning_rate": 3.299999994503177e-05,
|
| 1352 |
+
"loss": 0.0,
|
| 1353 |
+
"step": 56,
|
| 1354 |
+
"step_time": 1.6323036710000451
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"clip_ratio/high_max": 0.0,
|
| 1358 |
+
"clip_ratio/high_mean": 0.0,
|
| 1359 |
+
"clip_ratio/low_mean": 0.0,
|
| 1360 |
+
"clip_ratio/low_min": 0.0,
|
| 1361 |
+
"clip_ratio/region_mean": 0.0,
|
| 1362 |
+
"completions/clipped_ratio": 1.0,
|
| 1363 |
+
"completions/max_length": 1126.0,
|
| 1364 |
+
"completions/max_terminated_length": 0.0,
|
| 1365 |
+
"completions/mean_length": 500.25,
|
| 1366 |
+
"completions/mean_terminated_length": 0.0,
|
| 1367 |
+
"completions/min_length": 128.0,
|
| 1368 |
+
"completions/min_terminated_length": 0.0,
|
| 1369 |
+
"entropy": 10.095836321512857,
|
| 1370 |
+
"epoch": 0.00042750427504275045,
|
| 1371 |
+
"frac_reward_zero_std": 0.0,
|
| 1372 |
+
"grad_norm": 0.0,
|
| 1373 |
+
"kl": 0.0,
|
| 1374 |
+
"learning_rate": 3.299999993939753e-05,
|
| 1375 |
+
"loss": 0.0,
|
| 1376 |
+
"num_tokens": 836831.0,
|
| 1377 |
+
"reward": -47.74729537963867,
|
| 1378 |
+
"reward_std": 17.828411102294922,
|
| 1379 |
+
"rewards/rollout_reward_func/mean": -47.74729537963867,
|
| 1380 |
+
"rewards/rollout_reward_func/std": 17.13072395324707,
|
| 1381 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1382 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1383 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1384 |
+
"sampling/sampling_logp_difference/max": 15.644685745239258,
|
| 1385 |
+
"sampling/sampling_logp_difference/mean": 3.2078018188476562,
|
| 1386 |
+
"step": 57,
|
| 1387 |
+
"step_time": 20.712939544999244
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"clip_ratio/high_max": 0.0,
|
| 1391 |
+
"clip_ratio/high_mean": 0.0,
|
| 1392 |
+
"clip_ratio/low_mean": 0.0,
|
| 1393 |
+
"clip_ratio/low_min": 0.0,
|
| 1394 |
+
"clip_ratio/region_mean": 0.0,
|
| 1395 |
+
"entropy": 10.095836321512857,
|
| 1396 |
+
"epoch": 0.00043500435004350044,
|
| 1397 |
+
"grad_norm": 0.0,
|
| 1398 |
+
"kl": 0.0,
|
| 1399 |
+
"learning_rate": 3.299999993348844e-05,
|
| 1400 |
+
"loss": 0.0,
|
| 1401 |
+
"step": 58,
|
| 1402 |
+
"step_time": 1.6430280170015976
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"clip_ratio/high_max": 0.0,
|
| 1406 |
+
"clip_ratio/high_mean": 0.0,
|
| 1407 |
+
"clip_ratio/low_mean": 0.0,
|
| 1408 |
+
"clip_ratio/low_min": 0.0,
|
| 1409 |
+
"clip_ratio/region_mean": 0.0,
|
| 1410 |
+
"completions/clipped_ratio": 1.0,
|
| 1411 |
+
"completions/max_length": 1045.0,
|
| 1412 |
+
"completions/max_terminated_length": 0.0,
|
| 1413 |
+
"completions/mean_length": 562.9166870117188,
|
| 1414 |
+
"completions/mean_terminated_length": 0.0,
|
| 1415 |
+
"completions/min_length": 201.0,
|
| 1416 |
+
"completions/min_terminated_length": 0.0,
|
| 1417 |
+
"entropy": 10.027901649475098,
|
| 1418 |
+
"epoch": 0.0004425044250442504,
|
| 1419 |
+
"frac_reward_zero_std": 0.0,
|
| 1420 |
+
"grad_norm": 0.0,
|
| 1421 |
+
"kl": 0.0,
|
| 1422 |
+
"learning_rate": 3.299999992730452e-05,
|
| 1423 |
+
"loss": 0.0,
|
| 1424 |
+
"num_tokens": 866235.0,
|
| 1425 |
+
"reward": -54.31364059448242,
|
| 1426 |
+
"reward_std": 16.991008758544922,
|
| 1427 |
+
"rewards/rollout_reward_func/mean": -54.31363296508789,
|
| 1428 |
+
"rewards/rollout_reward_func/std": 16.77975082397461,
|
| 1429 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1430 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1431 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1432 |
+
"sampling/sampling_logp_difference/max": 15.359244346618652,
|
| 1433 |
+
"sampling/sampling_logp_difference/mean": 2.992715835571289,
|
| 1434 |
+
"step": 59,
|
| 1435 |
+
"step_time": 18.364870030999555
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"clip_ratio/high_max": 0.0,
|
| 1439 |
+
"clip_ratio/high_mean": 0.0,
|
| 1440 |
+
"clip_ratio/low_mean": 0.0,
|
| 1441 |
+
"clip_ratio/low_min": 0.0,
|
| 1442 |
+
"clip_ratio/region_mean": 0.0,
|
| 1443 |
+
"entropy": 10.027901649475098,
|
| 1444 |
+
"epoch": 0.00045000450004500047,
|
| 1445 |
+
"grad_norm": 0.0,
|
| 1446 |
+
"kl": 0.0,
|
| 1447 |
+
"learning_rate": 3.299999992084575e-05,
|
| 1448 |
+
"loss": 0.0,
|
| 1449 |
+
"step": 60,
|
| 1450 |
+
"step_time": 1.6135677440006475
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"clip_ratio/high_max": 0.0,
|
| 1454 |
+
"clip_ratio/high_mean": 0.0,
|
| 1455 |
+
"clip_ratio/low_mean": 0.0,
|
| 1456 |
+
"clip_ratio/low_min": 0.0,
|
| 1457 |
+
"clip_ratio/region_mean": 0.0,
|
| 1458 |
+
"completions/clipped_ratio": 1.0,
|
| 1459 |
+
"completions/max_length": 1237.0,
|
| 1460 |
+
"completions/max_terminated_length": 0.0,
|
| 1461 |
+
"completions/mean_length": 583.125,
|
| 1462 |
+
"completions/mean_terminated_length": 0.0,
|
| 1463 |
+
"completions/min_length": 116.0,
|
| 1464 |
+
"completions/min_terminated_length": 0.0,
|
| 1465 |
+
"entropy": 10.05492369333903,
|
| 1466 |
+
"epoch": 0.00045750457504575045,
|
| 1467 |
+
"frac_reward_zero_std": 0.0,
|
| 1468 |
+
"grad_norm": 0.0,
|
| 1469 |
+
"kl": 0.0,
|
| 1470 |
+
"learning_rate": 3.299999991411214e-05,
|
| 1471 |
+
"loss": 0.0,
|
| 1472 |
+
"num_tokens": 896524.0,
|
| 1473 |
+
"reward": -43.963714599609375,
|
| 1474 |
+
"reward_std": 17.849592208862305,
|
| 1475 |
+
"rewards/rollout_reward_func/mean": -43.963714599609375,
|
| 1476 |
+
"rewards/rollout_reward_func/std": 19.37680435180664,
|
| 1477 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1478 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1479 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1480 |
+
"sampling/sampling_logp_difference/max": 14.769742012023926,
|
| 1481 |
+
"sampling/sampling_logp_difference/mean": 3.1108696460723877,
|
| 1482 |
+
"step": 61,
|
| 1483 |
+
"step_time": 23.026458983998964
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"clip_ratio/high_max": 0.0,
|
| 1487 |
+
"clip_ratio/high_mean": 0.0,
|
| 1488 |
+
"clip_ratio/low_mean": 0.0,
|
| 1489 |
+
"clip_ratio/low_min": 0.0,
|
| 1490 |
+
"clip_ratio/region_mean": 0.0,
|
| 1491 |
+
"entropy": 10.05492369333903,
|
| 1492 |
+
"epoch": 0.00046500465004650044,
|
| 1493 |
+
"grad_norm": 0.0,
|
| 1494 |
+
"kl": 0.0,
|
| 1495 |
+
"learning_rate": 3.299999990710369e-05,
|
| 1496 |
+
"loss": 0.0,
|
| 1497 |
+
"step": 62,
|
| 1498 |
+
"step_time": 1.680401769999662
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"clip_ratio/high_max": 0.0,
|
| 1502 |
+
"clip_ratio/high_mean": 0.0,
|
| 1503 |
+
"clip_ratio/low_mean": 0.0,
|
| 1504 |
+
"clip_ratio/low_min": 0.0,
|
| 1505 |
+
"clip_ratio/region_mean": 0.0,
|
| 1506 |
+
"completions/clipped_ratio": 1.0,
|
| 1507 |
+
"completions/max_length": 1481.0,
|
| 1508 |
+
"completions/max_terminated_length": 0.0,
|
| 1509 |
+
"completions/mean_length": 542.0833740234375,
|
| 1510 |
+
"completions/mean_terminated_length": 0.0,
|
| 1511 |
+
"completions/min_length": 128.0,
|
| 1512 |
+
"completions/min_terminated_length": 0.0,
|
| 1513 |
+
"entropy": 9.974092801411947,
|
| 1514 |
+
"epoch": 0.0004725047250472505,
|
| 1515 |
+
"frac_reward_zero_std": 0.0,
|
| 1516 |
+
"grad_norm": 0.0,
|
| 1517 |
+
"kl": 0.0,
|
| 1518 |
+
"learning_rate": 3.2999999899820406e-05,
|
| 1519 |
+
"loss": 0.0,
|
| 1520 |
+
"num_tokens": 925351.0,
|
| 1521 |
+
"reward": -47.469757080078125,
|
| 1522 |
+
"reward_std": 16.11382484436035,
|
| 1523 |
+
"rewards/rollout_reward_func/mean": -47.469757080078125,
|
| 1524 |
+
"rewards/rollout_reward_func/std": 16.915918350219727,
|
| 1525 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1526 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1527 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1528 |
+
"sampling/sampling_logp_difference/max": 14.969949722290039,
|
| 1529 |
+
"sampling/sampling_logp_difference/mean": 3.0506622791290283,
|
| 1530 |
+
"step": 63,
|
| 1531 |
+
"step_time": 22.066013471999213
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"clip_ratio/high_max": 0.0,
|
| 1535 |
+
"clip_ratio/high_mean": 0.0,
|
| 1536 |
+
"clip_ratio/low_mean": 0.0,
|
| 1537 |
+
"clip_ratio/low_min": 0.0,
|
| 1538 |
+
"clip_ratio/region_mean": 0.0,
|
| 1539 |
+
"entropy": 9.974092801411947,
|
| 1540 |
+
"epoch": 0.00048000480004800047,
|
| 1541 |
+
"grad_norm": 0.0,
|
| 1542 |
+
"kl": 0.0,
|
| 1543 |
+
"learning_rate": 3.299999989226227e-05,
|
| 1544 |
+
"loss": 0.0,
|
| 1545 |
+
"step": 64,
|
| 1546 |
+
"step_time": 2.3155115009976726
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"clip_ratio/high_max": 0.0,
|
| 1550 |
+
"clip_ratio/high_mean": 0.0,
|
| 1551 |
+
"clip_ratio/low_mean": 0.0,
|
| 1552 |
+
"clip_ratio/low_min": 0.0,
|
| 1553 |
+
"clip_ratio/region_mean": 0.0,
|
| 1554 |
+
"completions/clipped_ratio": 1.0,
|
| 1555 |
+
"completions/max_length": 1072.0,
|
| 1556 |
+
"completions/max_terminated_length": 0.0,
|
| 1557 |
+
"completions/mean_length": 535.0,
|
| 1558 |
+
"completions/mean_terminated_length": 0.0,
|
| 1559 |
+
"completions/min_length": 128.0,
|
| 1560 |
+
"completions/min_terminated_length": 0.0,
|
| 1561 |
+
"entropy": 10.121665000915527,
|
| 1562 |
+
"epoch": 0.0004875048750487505,
|
| 1563 |
+
"frac_reward_zero_std": 0.0,
|
| 1564 |
+
"grad_norm": 0.0,
|
| 1565 |
+
"kl": 0.0,
|
| 1566 |
+
"learning_rate": 3.2999999884429296e-05,
|
| 1567 |
+
"loss": 0.0,
|
| 1568 |
+
"num_tokens": 954640.0,
|
| 1569 |
+
"reward": -47.75408172607422,
|
| 1570 |
+
"reward_std": 16.36182975769043,
|
| 1571 |
+
"rewards/rollout_reward_func/mean": -47.75407791137695,
|
| 1572 |
+
"rewards/rollout_reward_func/std": 19.085969924926758,
|
| 1573 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1574 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1575 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1576 |
+
"sampling/sampling_logp_difference/max": 14.185979843139648,
|
| 1577 |
+
"sampling/sampling_logp_difference/mean": 3.126000165939331,
|
| 1578 |
+
"step": 65,
|
| 1579 |
+
"step_time": 19.784562730999824
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"clip_ratio/high_max": 0.0,
|
| 1583 |
+
"clip_ratio/high_mean": 0.0,
|
| 1584 |
+
"clip_ratio/low_mean": 0.0,
|
| 1585 |
+
"clip_ratio/low_min": 0.0,
|
| 1586 |
+
"clip_ratio/region_mean": 0.0,
|
| 1587 |
+
"entropy": 10.121665000915527,
|
| 1588 |
+
"epoch": 0.0004950049500495005,
|
| 1589 |
+
"grad_norm": 0.0,
|
| 1590 |
+
"kl": 0.0,
|
| 1591 |
+
"learning_rate": 3.299999987632149e-05,
|
| 1592 |
+
"loss": 0.0,
|
| 1593 |
+
"step": 66,
|
| 1594 |
+
"step_time": 1.618170978001217
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"clip_ratio/high_max": 0.0,
|
| 1598 |
+
"clip_ratio/high_mean": 0.0,
|
| 1599 |
+
"clip_ratio/low_mean": 0.0,
|
| 1600 |
+
"clip_ratio/low_min": 0.0,
|
| 1601 |
+
"clip_ratio/region_mean": 0.0,
|
| 1602 |
+
"completions/clipped_ratio": 1.0,
|
| 1603 |
+
"completions/max_length": 1122.0,
|
| 1604 |
+
"completions/max_terminated_length": 0.0,
|
| 1605 |
+
"completions/mean_length": 500.8333435058594,
|
| 1606 |
+
"completions/mean_terminated_length": 0.0,
|
| 1607 |
+
"completions/min_length": 128.0,
|
| 1608 |
+
"completions/min_terminated_length": 0.0,
|
| 1609 |
+
"entropy": 10.120317935943604,
|
| 1610 |
+
"epoch": 0.0005025050250502505,
|
| 1611 |
+
"frac_reward_zero_std": 0.0,
|
| 1612 |
+
"grad_norm": 0.0,
|
| 1613 |
+
"kl": 0.0,
|
| 1614 |
+
"learning_rate": 3.299999986793883e-05,
|
| 1615 |
+
"loss": 0.0,
|
| 1616 |
+
"num_tokens": 982892.0,
|
| 1617 |
+
"reward": -53.79902267456055,
|
| 1618 |
+
"reward_std": 15.497881889343262,
|
| 1619 |
+
"rewards/rollout_reward_func/mean": -53.79902267456055,
|
| 1620 |
+
"rewards/rollout_reward_func/std": 17.754192352294922,
|
| 1621 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1622 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1623 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1624 |
+
"sampling/sampling_logp_difference/max": 13.600709915161133,
|
| 1625 |
+
"sampling/sampling_logp_difference/mean": 3.1041884422302246,
|
| 1626 |
+
"step": 67,
|
| 1627 |
+
"step_time": 19.112115680999523
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"clip_ratio/high_max": 0.0,
|
| 1631 |
+
"clip_ratio/high_mean": 0.0,
|
| 1632 |
+
"clip_ratio/low_mean": 0.0,
|
| 1633 |
+
"clip_ratio/low_min": 0.0,
|
| 1634 |
+
"clip_ratio/region_mean": 0.0,
|
| 1635 |
+
"entropy": 10.120317935943604,
|
| 1636 |
+
"epoch": 0.0005100051000510005,
|
| 1637 |
+
"grad_norm": 0.0,
|
| 1638 |
+
"kl": 0.0,
|
| 1639 |
+
"learning_rate": 3.2999999859281335e-05,
|
| 1640 |
+
"loss": 0.0,
|
| 1641 |
+
"step": 68,
|
| 1642 |
+
"step_time": 1.6533779979999963
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"clip_ratio/high_max": 0.0,
|
| 1646 |
+
"clip_ratio/high_mean": 0.0,
|
| 1647 |
+
"clip_ratio/low_mean": 0.0,
|
| 1648 |
+
"clip_ratio/low_min": 0.0,
|
| 1649 |
+
"clip_ratio/region_mean": 0.0,
|
| 1650 |
+
"completions/clipped_ratio": 1.0,
|
| 1651 |
+
"completions/max_length": 1001.0,
|
| 1652 |
+
"completions/max_terminated_length": 0.0,
|
| 1653 |
+
"completions/mean_length": 545.875,
|
| 1654 |
+
"completions/mean_terminated_length": 0.0,
|
| 1655 |
+
"completions/min_length": 202.0,
|
| 1656 |
+
"completions/min_terminated_length": 0.0,
|
| 1657 |
+
"entropy": 9.890536467234293,
|
| 1658 |
+
"epoch": 0.0005175051750517505,
|
| 1659 |
+
"frac_reward_zero_std": 0.0,
|
| 1660 |
+
"grad_norm": 0.0,
|
| 1661 |
+
"kl": 0.0,
|
| 1662 |
+
"learning_rate": 3.2999999850349e-05,
|
| 1663 |
+
"loss": 0.0,
|
| 1664 |
+
"num_tokens": 1012345.0,
|
| 1665 |
+
"reward": -59.80120849609375,
|
| 1666 |
+
"reward_std": 9.581160545349121,
|
| 1667 |
+
"rewards/rollout_reward_func/mean": -59.80120849609375,
|
| 1668 |
+
"rewards/rollout_reward_func/std": 10.057110786437988,
|
| 1669 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1670 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1671 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1672 |
+
"sampling/sampling_logp_difference/max": 13.439180374145508,
|
| 1673 |
+
"sampling/sampling_logp_difference/mean": 2.835329532623291,
|
| 1674 |
+
"step": 69,
|
| 1675 |
+
"step_time": 18.08387734600001
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"clip_ratio/high_max": 0.0,
|
| 1679 |
+
"clip_ratio/high_mean": 0.0,
|
| 1680 |
+
"clip_ratio/low_mean": 0.0,
|
| 1681 |
+
"clip_ratio/low_min": 0.0,
|
| 1682 |
+
"clip_ratio/region_mean": 0.0,
|
| 1683 |
+
"entropy": 9.890536467234293,
|
| 1684 |
+
"epoch": 0.0005250052500525006,
|
| 1685 |
+
"grad_norm": 0.0,
|
| 1686 |
+
"kl": 0.0,
|
| 1687 |
+
"learning_rate": 3.299999984114182e-05,
|
| 1688 |
+
"loss": 0.0,
|
| 1689 |
+
"step": 70,
|
| 1690 |
+
"step_time": 1.6130178840003282
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"clip_ratio/high_max": 0.0,
|
| 1694 |
+
"clip_ratio/high_mean": 0.0,
|
| 1695 |
+
"clip_ratio/low_mean": 0.0,
|
| 1696 |
+
"clip_ratio/low_min": 0.0,
|
| 1697 |
+
"clip_ratio/region_mean": 0.0,
|
| 1698 |
+
"completions/clipped_ratio": 1.0,
|
| 1699 |
+
"completions/max_length": 1181.0,
|
| 1700 |
+
"completions/max_terminated_length": 0.0,
|
| 1701 |
+
"completions/mean_length": 559.75,
|
| 1702 |
+
"completions/mean_terminated_length": 0.0,
|
| 1703 |
+
"completions/min_length": 128.0,
|
| 1704 |
+
"completions/min_terminated_length": 0.0,
|
| 1705 |
+
"entropy": 9.979540348052979,
|
| 1706 |
+
"epoch": 0.0005325053250532505,
|
| 1707 |
+
"frac_reward_zero_std": 0.0,
|
| 1708 |
+
"grad_norm": 0.0,
|
| 1709 |
+
"kl": 0.0,
|
| 1710 |
+
"learning_rate": 3.29999998316598e-05,
|
| 1711 |
+
"loss": 0.0,
|
| 1712 |
+
"num_tokens": 1041646.0,
|
| 1713 |
+
"reward": -48.28936004638672,
|
| 1714 |
+
"reward_std": 18.08314323425293,
|
| 1715 |
+
"rewards/rollout_reward_func/mean": -48.28935623168945,
|
| 1716 |
+
"rewards/rollout_reward_func/std": 17.737323760986328,
|
| 1717 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1718 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1719 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1720 |
+
"sampling/sampling_logp_difference/max": 14.49035930633545,
|
| 1721 |
+
"sampling/sampling_logp_difference/mean": 3.0069854259490967,
|
| 1722 |
+
"step": 71,
|
| 1723 |
+
"step_time": 20.73087897000096
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"clip_ratio/high_max": 0.0,
|
| 1727 |
+
"clip_ratio/high_mean": 0.0,
|
| 1728 |
+
"clip_ratio/low_mean": 0.0,
|
| 1729 |
+
"clip_ratio/low_min": 0.0,
|
| 1730 |
+
"clip_ratio/region_mean": 0.0,
|
| 1731 |
+
"entropy": 9.979540348052979,
|
| 1732 |
+
"epoch": 0.0005400054000540005,
|
| 1733 |
+
"grad_norm": 0.0,
|
| 1734 |
+
"kl": 0.0,
|
| 1735 |
+
"learning_rate": 3.2999999821902936e-05,
|
| 1736 |
+
"loss": 0.0,
|
| 1737 |
+
"step": 72,
|
| 1738 |
+
"step_time": 1.673831482999958
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"clip_ratio/high_max": 0.0,
|
| 1742 |
+
"clip_ratio/high_mean": 0.0,
|
| 1743 |
+
"clip_ratio/low_mean": 0.0,
|
| 1744 |
+
"clip_ratio/low_min": 0.0,
|
| 1745 |
+
"clip_ratio/region_mean": 0.0,
|
| 1746 |
+
"completions/clipped_ratio": 1.0,
|
| 1747 |
+
"completions/max_length": 1129.0,
|
| 1748 |
+
"completions/max_terminated_length": 0.0,
|
| 1749 |
+
"completions/mean_length": 479.875,
|
| 1750 |
+
"completions/mean_terminated_length": 0.0,
|
| 1751 |
+
"completions/min_length": 125.0,
|
| 1752 |
+
"completions/min_terminated_length": 0.0,
|
| 1753 |
+
"entropy": 9.990771611531576,
|
| 1754 |
+
"epoch": 0.0005475054750547505,
|
| 1755 |
+
"frac_reward_zero_std": 0.0,
|
| 1756 |
+
"grad_norm": 0.0,
|
| 1757 |
+
"kl": 0.0,
|
| 1758 |
+
"learning_rate": 3.2999999811871234e-05,
|
| 1759 |
+
"loss": 0.0,
|
| 1760 |
+
"num_tokens": 1069537.0,
|
| 1761 |
+
"reward": -46.58069610595703,
|
| 1762 |
+
"reward_std": 21.29560661315918,
|
| 1763 |
+
"rewards/rollout_reward_func/mean": -46.5806884765625,
|
| 1764 |
+
"rewards/rollout_reward_func/std": 21.10353660583496,
|
| 1765 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1766 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1767 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1768 |
+
"sampling/sampling_logp_difference/max": 15.358684539794922,
|
| 1769 |
+
"sampling/sampling_logp_difference/mean": 3.0600218772888184,
|
| 1770 |
+
"step": 73,
|
| 1771 |
+
"step_time": 20.745255362002354
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"clip_ratio/high_max": 0.0,
|
| 1775 |
+
"clip_ratio/high_mean": 0.0,
|
| 1776 |
+
"clip_ratio/low_mean": 0.0,
|
| 1777 |
+
"clip_ratio/low_min": 0.0,
|
| 1778 |
+
"clip_ratio/region_mean": 0.0,
|
| 1779 |
+
"entropy": 9.990771611531576,
|
| 1780 |
+
"epoch": 0.0005550055500555005,
|
| 1781 |
+
"grad_norm": 0.0,
|
| 1782 |
+
"kl": 0.0,
|
| 1783 |
+
"learning_rate": 3.299999980156469e-05,
|
| 1784 |
+
"loss": 0.0,
|
| 1785 |
+
"step": 74,
|
| 1786 |
+
"step_time": 1.65707921000012
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"clip_ratio/high_max": 0.0,
|
| 1790 |
+
"clip_ratio/high_mean": 0.0,
|
| 1791 |
+
"clip_ratio/low_mean": 0.0,
|
| 1792 |
+
"clip_ratio/low_min": 0.0,
|
| 1793 |
+
"clip_ratio/region_mean": 0.0,
|
| 1794 |
+
"completions/clipped_ratio": 1.0,
|
| 1795 |
+
"completions/max_length": 1571.0,
|
| 1796 |
+
"completions/max_terminated_length": 0.0,
|
| 1797 |
+
"completions/mean_length": 533.5833740234375,
|
| 1798 |
+
"completions/mean_terminated_length": 0.0,
|
| 1799 |
+
"completions/min_length": 128.0,
|
| 1800 |
+
"completions/min_terminated_length": 0.0,
|
| 1801 |
+
"entropy": 10.04587491353353,
|
| 1802 |
+
"epoch": 0.0005625056250562506,
|
| 1803 |
+
"frac_reward_zero_std": 0.0,
|
| 1804 |
+
"grad_norm": 0.0,
|
| 1805 |
+
"kl": 0.0,
|
| 1806 |
+
"learning_rate": 3.2999999790983306e-05,
|
| 1807 |
+
"loss": 0.0,
|
| 1808 |
+
"num_tokens": 1098538.0,
|
| 1809 |
+
"reward": -43.66608428955078,
|
| 1810 |
+
"reward_std": 16.150455474853516,
|
| 1811 |
+
"rewards/rollout_reward_func/mean": -43.66608810424805,
|
| 1812 |
+
"rewards/rollout_reward_func/std": 18.750696182250977,
|
| 1813 |
+
"sampling/importance_sampling_ratio/max": 0.0,
|
| 1814 |
+
"sampling/importance_sampling_ratio/mean": 0.0,
|
| 1815 |
+
"sampling/importance_sampling_ratio/min": 0.0,
|
| 1816 |
+
"sampling/sampling_logp_difference/max": 15.10157299041748,
|
| 1817 |
+
"sampling/sampling_logp_difference/mean": 3.069899320602417,
|
| 1818 |
+
"step": 75,
|
| 1819 |
+
"step_time": 23.273216087998662
|
| 1820 |
+
}
|
| 1821 |
+
],
|
| 1822 |
+
"logging_steps": 1.0,
|
| 1823 |
+
"max_steps": 666660,
|
| 1824 |
+
"num_input_tokens_seen": 1098538,
|
| 1825 |
+
"num_train_epochs": 5,
|
| 1826 |
+
"save_steps": 500,
|
| 1827 |
+
"stateful_callbacks": {
|
| 1828 |
+
"TrainerControl": {
|
| 1829 |
+
"args": {
|
| 1830 |
+
"should_epoch_stop": false,
|
| 1831 |
+
"should_evaluate": false,
|
| 1832 |
+
"should_log": false,
|
| 1833 |
+
"should_save": true,
|
| 1834 |
+
"should_training_stop": false
|
| 1835 |
+
},
|
| 1836 |
+
"attributes": {}
|
| 1837 |
+
}
|
| 1838 |
+
},
|
| 1839 |
+
"total_flos": 0.0,
|
| 1840 |
+
"train_batch_size": 4,
|
| 1841 |
+
"trial_name": null,
|
| 1842 |
+
"trial_params": null
|
| 1843 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5cd7b53ab8750334432b5d49deaf7eafca15a9b32030c3a9f8ef4e5f45eb0f4
|
| 3 |
+
size 8081
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|