Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-16/README.md +202 -0
- checkpoint-16/adapter_config.json +34 -0
- checkpoint-16/adapter_model.safetensors +3 -0
- checkpoint-16/added_tokens.json +3 -0
- checkpoint-16/optimizer.pt +3 -0
- checkpoint-16/rng_state.pth +3 -0
- checkpoint-16/scheduler.pt +3 -0
- checkpoint-16/special_tokens_map.json +30 -0
- checkpoint-16/tokenizer.json +0 -0
- checkpoint-16/tokenizer.model +3 -0
- checkpoint-16/tokenizer_config.json +52 -0
- checkpoint-16/trainer_state.json +373 -0
- checkpoint-16/training_args.bin +3 -0
- checkpoint-24/README.md +202 -0
- checkpoint-24/adapter_config.json +34 -0
- checkpoint-24/adapter_model.safetensors +3 -0
- checkpoint-24/added_tokens.json +3 -0
- checkpoint-24/optimizer.pt +3 -0
- checkpoint-24/rng_state.pth +3 -0
- checkpoint-24/scheduler.pt +3 -0
- checkpoint-24/special_tokens_map.json +30 -0
- checkpoint-24/tokenizer.json +0 -0
- checkpoint-24/tokenizer.model +3 -0
- checkpoint-24/tokenizer_config.json +52 -0
- checkpoint-24/trainer_state.json +549 -0
- checkpoint-24/training_args.bin +3 -0
- checkpoint-32/README.md +202 -0
- checkpoint-32/adapter_config.json +34 -0
- checkpoint-32/adapter_model.safetensors +3 -0
- checkpoint-32/added_tokens.json +3 -0
- checkpoint-32/optimizer.pt +3 -0
- checkpoint-32/rng_state.pth +3 -0
- checkpoint-32/scheduler.pt +3 -0
- checkpoint-32/special_tokens_map.json +30 -0
- checkpoint-32/tokenizer.json +0 -0
- checkpoint-32/tokenizer.model +3 -0
- checkpoint-32/tokenizer_config.json +52 -0
- checkpoint-32/trainer_state.json +789 -0
- checkpoint-32/training_args.bin +3 -0
- checkpoint-40/README.md +202 -0
- checkpoint-40/adapter_config.json +34 -0
- checkpoint-40/adapter_model.safetensors +3 -0
- checkpoint-40/added_tokens.json +3 -0
- checkpoint-40/optimizer.pt +3 -0
- checkpoint-40/rng_state.pth +3 -0
- checkpoint-40/scheduler.pt +3 -0
- checkpoint-40/special_tokens_map.json +30 -0
- checkpoint-40/tokenizer.json +0 -0
- checkpoint-40/tokenizer.model +3 -0
- checkpoint-40/tokenizer_config.json +52 -0
checkpoint-16/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-16/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-16/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ba1b2dea2b4d88aa8df28542da3af492c041a4e12236e8ceaff64467efeeee
|
| 3 |
+
size 167832240
|
checkpoint-16/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-16/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff20af72475e98254302a950904624c19884e6d5c51db06e96d02a7a93eb585
|
| 3 |
+
size 335812858
|
checkpoint-16/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3e5515ca2410a65004dc2725089379fb2e0709b763bc6d9131bca4c5b7ddfe
|
| 3 |
+
size 14244
|
checkpoint-16/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d29fe1dfef8899b21178adddd54c3556b29cb1e4290c170b5b147f1a46d5f27b
|
| 3 |
+
size 1064
|
checkpoint-16/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-16/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-16/tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 41 |
+
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "</s>",
|
| 43 |
+
"legacy": true,
|
| 44 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
+
"padding_side": "left",
|
| 47 |
+
"sp_model_kwargs": {},
|
| 48 |
+
"spaces_between_special_tokens": false,
|
| 49 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 50 |
+
"unk_token": "<unk>",
|
| 51 |
+
"use_default_system_prompt": false
|
| 52 |
+
}
|
checkpoint-16/trainer_state.json
ADDED
|
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.002535004852157725,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0001584378032598578,
|
| 13 |
+
"grad_norm": 6.941703031770885e-05,
|
| 14 |
+
"learning_rate": 2.9998415465061005e-05,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
+
"loss/policy_avg": 9.534414857625961e-08,
|
| 17 |
+
"objective/entropy": 66.7407455444336,
|
| 18 |
+
"objective/kl": 0.0,
|
| 19 |
+
"objective/rlhf_reward": 1.9394512176513672,
|
| 20 |
+
"objective/scores": 1.9393310546875,
|
| 21 |
+
"policy/approxkl_avg": 0.0,
|
| 22 |
+
"policy/clipfrac_avg": 0.0,
|
| 23 |
+
"policy/entropy_avg": 0.501089334487915,
|
| 24 |
+
"step": 1,
|
| 25 |
+
"timer/calc_advantages": 1.838552713394165,
|
| 26 |
+
"timer/calc_loss": 0.718826174736023,
|
| 27 |
+
"timer/get_reward": 0.5057681202888489,
|
| 28 |
+
"timer/training_step": 5.023805141448975,
|
| 29 |
+
"val/num_eos_tokens": 0.0,
|
| 30 |
+
"val/ratio": 1.0,
|
| 31 |
+
"val/ratio_var": NaN
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0003168756065197156,
|
| 35 |
+
"grad_norm": 8.962108612060547,
|
| 36 |
+
"learning_rate": 2.999683093012201e-05,
|
| 37 |
+
"loss": 0.0079,
|
| 38 |
+
"loss/policy_avg": 0.007912077941000462,
|
| 39 |
+
"objective/entropy": 58.23992919921875,
|
| 40 |
+
"objective/kl": 0.006753697991371155,
|
| 41 |
+
"objective/rlhf_reward": 2.58967924118042,
|
| 42 |
+
"objective/scores": 2.59033203125,
|
| 43 |
+
"policy/approxkl_avg": 0.143972247838974,
|
| 44 |
+
"policy/clipfrac_avg": 0.376953125,
|
| 45 |
+
"policy/entropy_avg": 0.437211811542511,
|
| 46 |
+
"step": 2,
|
| 47 |
+
"timer/calc_advantages": 1.693800687789917,
|
| 48 |
+
"timer/calc_loss": 0.6173452734947205,
|
| 49 |
+
"timer/get_reward": 0.431838721036911,
|
| 50 |
+
"timer/training_step": 4.488475322723389,
|
| 51 |
+
"val/num_eos_tokens": 0.0,
|
| 52 |
+
"val/ratio": 1.0006933212280273,
|
| 53 |
+
"val/ratio_var": NaN
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.0004753134097795734,
|
| 57 |
+
"grad_norm": 8.80933666229248,
|
| 58 |
+
"learning_rate": 2.9995246395183014e-05,
|
| 59 |
+
"loss": 0.0087,
|
| 60 |
+
"loss/policy_avg": 0.008671796880662441,
|
| 61 |
+
"objective/entropy": 60.747886657714844,
|
| 62 |
+
"objective/kl": 0.19268979132175446,
|
| 63 |
+
"objective/rlhf_reward": 2.797236442565918,
|
| 64 |
+
"objective/scores": 2.8162841796875,
|
| 65 |
+
"policy/approxkl_avg": 0.22207684814929962,
|
| 66 |
+
"policy/clipfrac_avg": 0.369140625,
|
| 67 |
+
"policy/entropy_avg": 0.47127196192741394,
|
| 68 |
+
"step": 3,
|
| 69 |
+
"timer/calc_advantages": 2.117703437805176,
|
| 70 |
+
"timer/calc_loss": 0.8592336773872375,
|
| 71 |
+
"timer/get_reward": 0.5989187955856323,
|
| 72 |
+
"timer/training_step": 5.804616928100586,
|
| 73 |
+
"val/num_eos_tokens": 0.0,
|
| 74 |
+
"val/ratio": 0.9997344613075256,
|
| 75 |
+
"val/ratio_var": NaN
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.0006337512130394313,
|
| 79 |
+
"grad_norm": 15.397004127502441,
|
| 80 |
+
"learning_rate": 2.999366186024402e-05,
|
| 81 |
+
"loss": 0.0181,
|
| 82 |
+
"loss/policy_avg": 0.018090050667524338,
|
| 83 |
+
"objective/entropy": 59.366294860839844,
|
| 84 |
+
"objective/kl": 0.16402865946292877,
|
| 85 |
+
"objective/rlhf_reward": 2.7970707416534424,
|
| 86 |
+
"objective/scores": 2.8134765625,
|
| 87 |
+
"policy/approxkl_avg": 0.30915290117263794,
|
| 88 |
+
"policy/clipfrac_avg": 0.41796875,
|
| 89 |
+
"policy/entropy_avg": 0.4661800265312195,
|
| 90 |
+
"step": 4,
|
| 91 |
+
"timer/calc_advantages": 2.018901824951172,
|
| 92 |
+
"timer/calc_loss": 0.8049512505531311,
|
| 93 |
+
"timer/get_reward": 0.5547392964363098,
|
| 94 |
+
"timer/training_step": 5.506021022796631,
|
| 95 |
+
"val/num_eos_tokens": 0.0,
|
| 96 |
+
"val/ratio": 1.0003275871276855,
|
| 97 |
+
"val/ratio_var": NaN
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.000792189016299289,
|
| 101 |
+
"grad_norm": 6.137847231002524e-05,
|
| 102 |
+
"learning_rate": 2.9992077325305024e-05,
|
| 103 |
+
"loss": 0.0,
|
| 104 |
+
"loss/policy_avg": 1.0040821507573128e-07,
|
| 105 |
+
"objective/entropy": 61.850738525390625,
|
| 106 |
+
"objective/kl": 0.0,
|
| 107 |
+
"objective/rlhf_reward": 2.3658785820007324,
|
| 108 |
+
"objective/scores": 2.36578369140625,
|
| 109 |
+
"policy/approxkl_avg": 0.0,
|
| 110 |
+
"policy/clipfrac_avg": 0.0,
|
| 111 |
+
"policy/entropy_avg": 0.48403242230415344,
|
| 112 |
+
"step": 5,
|
| 113 |
+
"timer/calc_advantages": 1.889434576034546,
|
| 114 |
+
"timer/calc_loss": 0.7489800453186035,
|
| 115 |
+
"timer/get_reward": 0.5218558311462402,
|
| 116 |
+
"timer/training_step": 5.19569206237793,
|
| 117 |
+
"val/num_eos_tokens": 0.0,
|
| 118 |
+
"val/ratio": 1.0,
|
| 119 |
+
"val/ratio_var": NaN
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.0009506268195591468,
|
| 123 |
+
"grad_norm": 3.129560947418213,
|
| 124 |
+
"learning_rate": 2.9990492790366028e-05,
|
| 125 |
+
"loss": 0.002,
|
| 126 |
+
"loss/policy_avg": 0.002019597217440605,
|
| 127 |
+
"objective/entropy": 64.70206451416016,
|
| 128 |
+
"objective/kl": -0.011846143752336502,
|
| 129 |
+
"objective/rlhf_reward": 2.4429714679718018,
|
| 130 |
+
"objective/scores": 2.44146728515625,
|
| 131 |
+
"policy/approxkl_avg": 0.05796036496758461,
|
| 132 |
+
"policy/clipfrac_avg": 0.224609375,
|
| 133 |
+
"policy/entropy_avg": 0.4975966215133667,
|
| 134 |
+
"step": 6,
|
| 135 |
+
"timer/calc_advantages": 1.939255714416504,
|
| 136 |
+
"timer/calc_loss": 0.7629643082618713,
|
| 137 |
+
"timer/get_reward": 0.5286913514137268,
|
| 138 |
+
"timer/training_step": 5.261943340301514,
|
| 139 |
+
"val/num_eos_tokens": 0.0,
|
| 140 |
+
"val/ratio": 1.0005271434783936,
|
| 141 |
+
"val/ratio_var": NaN
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.0011090646228190046,
|
| 145 |
+
"grad_norm": 4.28013277053833,
|
| 146 |
+
"learning_rate": 2.9988908255427033e-05,
|
| 147 |
+
"loss": 0.0037,
|
| 148 |
+
"loss/policy_avg": 0.0036908092442899942,
|
| 149 |
+
"objective/entropy": 68.02294158935547,
|
| 150 |
+
"objective/kl": 0.15080219507217407,
|
| 151 |
+
"objective/rlhf_reward": 3.149240016937256,
|
| 152 |
+
"objective/scores": 3.1646728515625,
|
| 153 |
+
"policy/approxkl_avg": 0.11497651040554047,
|
| 154 |
+
"policy/clipfrac_avg": 0.25,
|
| 155 |
+
"policy/entropy_avg": 0.5161693692207336,
|
| 156 |
+
"step": 7,
|
| 157 |
+
"timer/calc_advantages": 2.2946014404296875,
|
| 158 |
+
"timer/calc_loss": 0.96665358543396,
|
| 159 |
+
"timer/get_reward": 0.6638086438179016,
|
| 160 |
+
"timer/training_step": 6.369439125061035,
|
| 161 |
+
"val/num_eos_tokens": 0.0,
|
| 162 |
+
"val/ratio": 0.99953293800354,
|
| 163 |
+
"val/ratio_var": NaN
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0012675024260788625,
|
| 167 |
+
"grad_norm": 8.370040893554688,
|
| 168 |
+
"learning_rate": 2.9987323720488037e-05,
|
| 169 |
+
"loss": 0.0078,
|
| 170 |
+
"loss/policy_avg": 0.00783943198621273,
|
| 171 |
+
"objective/entropy": 66.24089813232422,
|
| 172 |
+
"objective/kl": 0.0030039921402931213,
|
| 173 |
+
"objective/rlhf_reward": 3.1140072345733643,
|
| 174 |
+
"objective/scores": 3.1142501831054688,
|
| 175 |
+
"policy/approxkl_avg": 0.13499276340007782,
|
| 176 |
+
"policy/clipfrac_avg": 0.345703125,
|
| 177 |
+
"policy/entropy_avg": 0.4966353476047516,
|
| 178 |
+
"step": 8,
|
| 179 |
+
"timer/calc_advantages": 2.4299309253692627,
|
| 180 |
+
"timer/calc_loss": 1.046256422996521,
|
| 181 |
+
"timer/get_reward": 0.7162653207778931,
|
| 182 |
+
"timer/training_step": 6.773098945617676,
|
| 183 |
+
"val/num_eos_tokens": 0.0,
|
| 184 |
+
"val/ratio": 1.0011930465698242,
|
| 185 |
+
"val/ratio_var": NaN
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0014259402293387202,
|
| 189 |
+
"grad_norm": 5.985812094877474e-05,
|
| 190 |
+
"learning_rate": 2.9985739185549042e-05,
|
| 191 |
+
"loss": 0.0,
|
| 192 |
+
"loss/policy_avg": 1.3085082173347473e-07,
|
| 193 |
+
"objective/entropy": 57.91233825683594,
|
| 194 |
+
"objective/kl": 0.0,
|
| 195 |
+
"objective/rlhf_reward": 2.9793567657470703,
|
| 196 |
+
"objective/scores": 2.9791259765625,
|
| 197 |
+
"policy/approxkl_avg": 0.0,
|
| 198 |
+
"policy/clipfrac_avg": 0.0,
|
| 199 |
+
"policy/entropy_avg": 0.4229130744934082,
|
| 200 |
+
"step": 9,
|
| 201 |
+
"timer/calc_advantages": 2.2175822257995605,
|
| 202 |
+
"timer/calc_loss": 0.940474271774292,
|
| 203 |
+
"timer/get_reward": 0.6452049016952515,
|
| 204 |
+
"timer/training_step": 6.192902565002441,
|
| 205 |
+
"val/num_eos_tokens": 0.0,
|
| 206 |
+
"val/ratio": 1.0,
|
| 207 |
+
"val/ratio_var": NaN
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.001584378032598578,
|
| 211 |
+
"grad_norm": 2.061887502670288,
|
| 212 |
+
"learning_rate": 2.9984154650610046e-05,
|
| 213 |
+
"loss": 0.0012,
|
| 214 |
+
"loss/policy_avg": 0.00118393381126225,
|
| 215 |
+
"objective/entropy": 57.78638458251953,
|
| 216 |
+
"objective/kl": 0.016596710309386253,
|
| 217 |
+
"objective/rlhf_reward": 2.493161916732788,
|
| 218 |
+
"objective/scores": 2.494873046875,
|
| 219 |
+
"policy/approxkl_avg": 0.04327381029725075,
|
| 220 |
+
"policy/clipfrac_avg": 0.220703125,
|
| 221 |
+
"policy/entropy_avg": 0.45412811636924744,
|
| 222 |
+
"step": 10,
|
| 223 |
+
"timer/calc_advantages": 1.9425208568572998,
|
| 224 |
+
"timer/calc_loss": 0.7499428987503052,
|
| 225 |
+
"timer/get_reward": 0.5237178802490234,
|
| 226 |
+
"timer/training_step": 5.241105556488037,
|
| 227 |
+
"val/num_eos_tokens": 0.0,
|
| 228 |
+
"val/ratio": 1.0002281665802002,
|
| 229 |
+
"val/ratio_var": NaN
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.0017428158358584358,
|
| 233 |
+
"grad_norm": 3.437352180480957,
|
| 234 |
+
"learning_rate": 2.998257011567105e-05,
|
| 235 |
+
"loss": 0.003,
|
| 236 |
+
"loss/policy_avg": 0.003013810608536005,
|
| 237 |
+
"objective/entropy": 62.60158920288086,
|
| 238 |
+
"objective/kl": 0.04900990426540375,
|
| 239 |
+
"objective/rlhf_reward": 3.26180362701416,
|
| 240 |
+
"objective/scores": 3.2667236328125,
|
| 241 |
+
"policy/approxkl_avg": 0.08036807179450989,
|
| 242 |
+
"policy/clipfrac_avg": 0.2734375,
|
| 243 |
+
"policy/entropy_avg": 0.49370765686035156,
|
| 244 |
+
"step": 11,
|
| 245 |
+
"timer/calc_advantages": 2.010678768157959,
|
| 246 |
+
"timer/calc_loss": 0.8044981956481934,
|
| 247 |
+
"timer/get_reward": 0.5571302771568298,
|
| 248 |
+
"timer/training_step": 5.486995220184326,
|
| 249 |
+
"val/num_eos_tokens": 0.0,
|
| 250 |
+
"val/ratio": 1.0001283884048462,
|
| 251 |
+
"val/ratio_var": NaN
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.0019012536391182935,
|
| 255 |
+
"grad_norm": 3.6680727005004883,
|
| 256 |
+
"learning_rate": 2.9980985580732055e-05,
|
| 257 |
+
"loss": 0.0026,
|
| 258 |
+
"loss/policy_avg": 0.002624134300276637,
|
| 259 |
+
"objective/entropy": 70.5216064453125,
|
| 260 |
+
"objective/kl": 0.039649978280067444,
|
| 261 |
+
"objective/rlhf_reward": 1.9454692602157593,
|
| 262 |
+
"objective/scores": 1.94927978515625,
|
| 263 |
+
"policy/approxkl_avg": 0.07172106206417084,
|
| 264 |
+
"policy/clipfrac_avg": 0.34375,
|
| 265 |
+
"policy/entropy_avg": 0.5483217239379883,
|
| 266 |
+
"step": 12,
|
| 267 |
+
"timer/calc_advantages": 1.708000898361206,
|
| 268 |
+
"timer/calc_loss": 0.6391787528991699,
|
| 269 |
+
"timer/get_reward": 0.4455040693283081,
|
| 270 |
+
"timer/training_step": 4.587984085083008,
|
| 271 |
+
"val/num_eos_tokens": 0.0,
|
| 272 |
+
"val/ratio": 1.0003334283828735,
|
| 273 |
+
"val/ratio_var": NaN
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.0020596914423781513,
|
| 277 |
+
"grad_norm": 5.551970753003843e-05,
|
| 278 |
+
"learning_rate": 2.997940104579306e-05,
|
| 279 |
+
"loss": 0.0,
|
| 280 |
+
"loss/policy_avg": 6.216578185558319e-08,
|
| 281 |
+
"objective/entropy": 58.013153076171875,
|
| 282 |
+
"objective/kl": 0.0,
|
| 283 |
+
"objective/rlhf_reward": 1.9868602752685547,
|
| 284 |
+
"objective/scores": 1.9864273071289062,
|
| 285 |
+
"policy/approxkl_avg": 0.0,
|
| 286 |
+
"policy/clipfrac_avg": 0.0,
|
| 287 |
+
"policy/entropy_avg": 0.44822999835014343,
|
| 288 |
+
"step": 13,
|
| 289 |
+
"timer/calc_advantages": 2.0904719829559326,
|
| 290 |
+
"timer/calc_loss": 0.8480838537216187,
|
| 291 |
+
"timer/get_reward": 0.587557315826416,
|
| 292 |
+
"timer/training_step": 5.7307024002075195,
|
| 293 |
+
"val/num_eos_tokens": 0.0,
|
| 294 |
+
"val/ratio": 1.0,
|
| 295 |
+
"val/ratio_var": NaN
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.002218129245638009,
|
| 299 |
+
"grad_norm": 2.7803940773010254,
|
| 300 |
+
"learning_rate": 2.9977816510854064e-05,
|
| 301 |
+
"loss": 0.0015,
|
| 302 |
+
"loss/policy_avg": 0.0014500978868454695,
|
| 303 |
+
"objective/entropy": 69.96898651123047,
|
| 304 |
+
"objective/kl": 0.06745042651891708,
|
| 305 |
+
"objective/rlhf_reward": 2.469928741455078,
|
| 306 |
+
"objective/scores": 2.477020263671875,
|
| 307 |
+
"policy/approxkl_avg": 0.053128380328416824,
|
| 308 |
+
"policy/clipfrac_avg": 0.2734375,
|
| 309 |
+
"policy/entropy_avg": 0.5138126015663147,
|
| 310 |
+
"step": 14,
|
| 311 |
+
"timer/calc_advantages": 1.917910099029541,
|
| 312 |
+
"timer/calc_loss": 0.7225819230079651,
|
| 313 |
+
"timer/get_reward": 0.5053159594535828,
|
| 314 |
+
"timer/training_step": 5.0998334884643555,
|
| 315 |
+
"val/num_eos_tokens": 0.0,
|
| 316 |
+
"val/ratio": 0.9998296499252319,
|
| 317 |
+
"val/ratio_var": NaN
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.002376567048897867,
|
| 321 |
+
"grad_norm": 2.532649278640747,
|
| 322 |
+
"learning_rate": 2.997623197591507e-05,
|
| 323 |
+
"loss": 0.0018,
|
| 324 |
+
"loss/policy_avg": 0.0017822147347033024,
|
| 325 |
+
"objective/entropy": 58.39247131347656,
|
| 326 |
+
"objective/kl": -0.011621108278632164,
|
| 327 |
+
"objective/rlhf_reward": 2.397026538848877,
|
| 328 |
+
"objective/scores": 2.39556884765625,
|
| 329 |
+
"policy/approxkl_avg": 0.05379398912191391,
|
| 330 |
+
"policy/clipfrac_avg": 0.248046875,
|
| 331 |
+
"policy/entropy_avg": 0.4527440071105957,
|
| 332 |
+
"step": 15,
|
| 333 |
+
"timer/calc_advantages": 2.565062999725342,
|
| 334 |
+
"timer/calc_loss": 1.1112425327301025,
|
| 335 |
+
"timer/get_reward": 0.7521659731864929,
|
| 336 |
+
"timer/training_step": 7.156440734863281,
|
| 337 |
+
"val/num_eos_tokens": 0.0,
|
| 338 |
+
"val/ratio": 1.0004982948303223,
|
| 339 |
+
"val/ratio_var": NaN
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.002535004852157725,
|
| 343 |
+
"grad_norm": 5.747053623199463,
|
| 344 |
+
"learning_rate": 2.9974647440976074e-05,
|
| 345 |
+
"loss": 0.0039,
|
| 346 |
+
"loss/policy_avg": 0.0039013477507978678,
|
| 347 |
+
"objective/entropy": 58.41150665283203,
|
| 348 |
+
"objective/kl": -0.03636426478624344,
|
| 349 |
+
"objective/rlhf_reward": 2.3745107650756836,
|
| 350 |
+
"objective/scores": 2.370819091796875,
|
| 351 |
+
"policy/approxkl_avg": 0.07460636645555496,
|
| 352 |
+
"policy/clipfrac_avg": 0.310546875,
|
| 353 |
+
"policy/entropy_avg": 0.4354715943336487,
|
| 354 |
+
"step": 16,
|
| 355 |
+
"timer/calc_advantages": 2.135810136795044,
|
| 356 |
+
"timer/calc_loss": 0.8651329278945923,
|
| 357 |
+
"timer/get_reward": 0.5979053378105164,
|
| 358 |
+
"timer/training_step": 5.837425231933594,
|
| 359 |
+
"val/num_eos_tokens": 0.0,
|
| 360 |
+
"val/ratio": 1.0008955001831055,
|
| 361 |
+
"val/ratio_var": NaN
|
| 362 |
+
}
|
| 363 |
+
],
|
| 364 |
+
"logging_steps": 1,
|
| 365 |
+
"max_steps": 18933,
|
| 366 |
+
"num_input_tokens_seen": 0,
|
| 367 |
+
"num_train_epochs": 3,
|
| 368 |
+
"save_steps": 8,
|
| 369 |
+
"total_flos": 8202719718014976.0,
|
| 370 |
+
"train_batch_size": 4,
|
| 371 |
+
"trial_name": null,
|
| 372 |
+
"trial_params": null
|
| 373 |
+
}
|
checkpoint-16/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c727d9c9a10a7db9d4081bf55f4438b2dcd8d7295f98937237880d56ae13932
|
| 3 |
+
size 5240
|
checkpoint-24/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-24/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-24/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098e1fa3d4ed3bd04c9ab5624f72ef3df155c145d883c74c636f6b66c952a29e
|
| 3 |
+
size 167832240
|
checkpoint-24/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-24/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dadb6597bc55d1a794c775d861593d591aca89fdee9592ae0906e3642ef6d35
|
| 3 |
+
size 335812858
|
checkpoint-24/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632d39540c8e84e25f4caf9b59078317f09628f8eb2c2c5d9262b86018db9544
|
| 3 |
+
size 14244
|
checkpoint-24/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e73c5baf881f5be94192297f198c908f984658687aa3627377ec491ae341976
|
| 3 |
+
size 1064
|
checkpoint-24/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-24/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-24/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-24/tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 41 |
+
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "</s>",
|
| 43 |
+
"legacy": true,
|
| 44 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
+
"padding_side": "left",
|
| 47 |
+
"sp_model_kwargs": {},
|
| 48 |
+
"spaces_between_special_tokens": false,
|
| 49 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 50 |
+
"unk_token": "<unk>",
|
| 51 |
+
"use_default_system_prompt": false
|
| 52 |
+
}
|
checkpoint-24/trainer_state.json
ADDED
|
@@ -0,0 +1,549 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.003802507278236587,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0001584378032598578,
|
| 13 |
+
"grad_norm": 6.941703031770885e-05,
|
| 14 |
+
"learning_rate": 2.9998415465061005e-05,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
+
"loss/policy_avg": 9.534414857625961e-08,
|
| 17 |
+
"objective/entropy": 66.7407455444336,
|
| 18 |
+
"objective/kl": 0.0,
|
| 19 |
+
"objective/rlhf_reward": 1.9394512176513672,
|
| 20 |
+
"objective/scores": 1.9393310546875,
|
| 21 |
+
"policy/approxkl_avg": 0.0,
|
| 22 |
+
"policy/clipfrac_avg": 0.0,
|
| 23 |
+
"policy/entropy_avg": 0.501089334487915,
|
| 24 |
+
"step": 1,
|
| 25 |
+
"timer/calc_advantages": 1.838552713394165,
|
| 26 |
+
"timer/calc_loss": 0.718826174736023,
|
| 27 |
+
"timer/get_reward": 0.5057681202888489,
|
| 28 |
+
"timer/training_step": 5.023805141448975,
|
| 29 |
+
"val/num_eos_tokens": 0.0,
|
| 30 |
+
"val/ratio": 1.0,
|
| 31 |
+
"val/ratio_var": NaN
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0003168756065197156,
|
| 35 |
+
"grad_norm": 8.962108612060547,
|
| 36 |
+
"learning_rate": 2.999683093012201e-05,
|
| 37 |
+
"loss": 0.0079,
|
| 38 |
+
"loss/policy_avg": 0.007912077941000462,
|
| 39 |
+
"objective/entropy": 58.23992919921875,
|
| 40 |
+
"objective/kl": 0.006753697991371155,
|
| 41 |
+
"objective/rlhf_reward": 2.58967924118042,
|
| 42 |
+
"objective/scores": 2.59033203125,
|
| 43 |
+
"policy/approxkl_avg": 0.143972247838974,
|
| 44 |
+
"policy/clipfrac_avg": 0.376953125,
|
| 45 |
+
"policy/entropy_avg": 0.437211811542511,
|
| 46 |
+
"step": 2,
|
| 47 |
+
"timer/calc_advantages": 1.693800687789917,
|
| 48 |
+
"timer/calc_loss": 0.6173452734947205,
|
| 49 |
+
"timer/get_reward": 0.431838721036911,
|
| 50 |
+
"timer/training_step": 4.488475322723389,
|
| 51 |
+
"val/num_eos_tokens": 0.0,
|
| 52 |
+
"val/ratio": 1.0006933212280273,
|
| 53 |
+
"val/ratio_var": NaN
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.0004753134097795734,
|
| 57 |
+
"grad_norm": 8.80933666229248,
|
| 58 |
+
"learning_rate": 2.9995246395183014e-05,
|
| 59 |
+
"loss": 0.0087,
|
| 60 |
+
"loss/policy_avg": 0.008671796880662441,
|
| 61 |
+
"objective/entropy": 60.747886657714844,
|
| 62 |
+
"objective/kl": 0.19268979132175446,
|
| 63 |
+
"objective/rlhf_reward": 2.797236442565918,
|
| 64 |
+
"objective/scores": 2.8162841796875,
|
| 65 |
+
"policy/approxkl_avg": 0.22207684814929962,
|
| 66 |
+
"policy/clipfrac_avg": 0.369140625,
|
| 67 |
+
"policy/entropy_avg": 0.47127196192741394,
|
| 68 |
+
"step": 3,
|
| 69 |
+
"timer/calc_advantages": 2.117703437805176,
|
| 70 |
+
"timer/calc_loss": 0.8592336773872375,
|
| 71 |
+
"timer/get_reward": 0.5989187955856323,
|
| 72 |
+
"timer/training_step": 5.804616928100586,
|
| 73 |
+
"val/num_eos_tokens": 0.0,
|
| 74 |
+
"val/ratio": 0.9997344613075256,
|
| 75 |
+
"val/ratio_var": NaN
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.0006337512130394313,
|
| 79 |
+
"grad_norm": 15.397004127502441,
|
| 80 |
+
"learning_rate": 2.999366186024402e-05,
|
| 81 |
+
"loss": 0.0181,
|
| 82 |
+
"loss/policy_avg": 0.018090050667524338,
|
| 83 |
+
"objective/entropy": 59.366294860839844,
|
| 84 |
+
"objective/kl": 0.16402865946292877,
|
| 85 |
+
"objective/rlhf_reward": 2.7970707416534424,
|
| 86 |
+
"objective/scores": 2.8134765625,
|
| 87 |
+
"policy/approxkl_avg": 0.30915290117263794,
|
| 88 |
+
"policy/clipfrac_avg": 0.41796875,
|
| 89 |
+
"policy/entropy_avg": 0.4661800265312195,
|
| 90 |
+
"step": 4,
|
| 91 |
+
"timer/calc_advantages": 2.018901824951172,
|
| 92 |
+
"timer/calc_loss": 0.8049512505531311,
|
| 93 |
+
"timer/get_reward": 0.5547392964363098,
|
| 94 |
+
"timer/training_step": 5.506021022796631,
|
| 95 |
+
"val/num_eos_tokens": 0.0,
|
| 96 |
+
"val/ratio": 1.0003275871276855,
|
| 97 |
+
"val/ratio_var": NaN
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.000792189016299289,
|
| 101 |
+
"grad_norm": 6.137847231002524e-05,
|
| 102 |
+
"learning_rate": 2.9992077325305024e-05,
|
| 103 |
+
"loss": 0.0,
|
| 104 |
+
"loss/policy_avg": 1.0040821507573128e-07,
|
| 105 |
+
"objective/entropy": 61.850738525390625,
|
| 106 |
+
"objective/kl": 0.0,
|
| 107 |
+
"objective/rlhf_reward": 2.3658785820007324,
|
| 108 |
+
"objective/scores": 2.36578369140625,
|
| 109 |
+
"policy/approxkl_avg": 0.0,
|
| 110 |
+
"policy/clipfrac_avg": 0.0,
|
| 111 |
+
"policy/entropy_avg": 0.48403242230415344,
|
| 112 |
+
"step": 5,
|
| 113 |
+
"timer/calc_advantages": 1.889434576034546,
|
| 114 |
+
"timer/calc_loss": 0.7489800453186035,
|
| 115 |
+
"timer/get_reward": 0.5218558311462402,
|
| 116 |
+
"timer/training_step": 5.19569206237793,
|
| 117 |
+
"val/num_eos_tokens": 0.0,
|
| 118 |
+
"val/ratio": 1.0,
|
| 119 |
+
"val/ratio_var": NaN
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.0009506268195591468,
|
| 123 |
+
"grad_norm": 3.129560947418213,
|
| 124 |
+
"learning_rate": 2.9990492790366028e-05,
|
| 125 |
+
"loss": 0.002,
|
| 126 |
+
"loss/policy_avg": 0.002019597217440605,
|
| 127 |
+
"objective/entropy": 64.70206451416016,
|
| 128 |
+
"objective/kl": -0.011846143752336502,
|
| 129 |
+
"objective/rlhf_reward": 2.4429714679718018,
|
| 130 |
+
"objective/scores": 2.44146728515625,
|
| 131 |
+
"policy/approxkl_avg": 0.05796036496758461,
|
| 132 |
+
"policy/clipfrac_avg": 0.224609375,
|
| 133 |
+
"policy/entropy_avg": 0.4975966215133667,
|
| 134 |
+
"step": 6,
|
| 135 |
+
"timer/calc_advantages": 1.939255714416504,
|
| 136 |
+
"timer/calc_loss": 0.7629643082618713,
|
| 137 |
+
"timer/get_reward": 0.5286913514137268,
|
| 138 |
+
"timer/training_step": 5.261943340301514,
|
| 139 |
+
"val/num_eos_tokens": 0.0,
|
| 140 |
+
"val/ratio": 1.0005271434783936,
|
| 141 |
+
"val/ratio_var": NaN
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.0011090646228190046,
|
| 145 |
+
"grad_norm": 4.28013277053833,
|
| 146 |
+
"learning_rate": 2.9988908255427033e-05,
|
| 147 |
+
"loss": 0.0037,
|
| 148 |
+
"loss/policy_avg": 0.0036908092442899942,
|
| 149 |
+
"objective/entropy": 68.02294158935547,
|
| 150 |
+
"objective/kl": 0.15080219507217407,
|
| 151 |
+
"objective/rlhf_reward": 3.149240016937256,
|
| 152 |
+
"objective/scores": 3.1646728515625,
|
| 153 |
+
"policy/approxkl_avg": 0.11497651040554047,
|
| 154 |
+
"policy/clipfrac_avg": 0.25,
|
| 155 |
+
"policy/entropy_avg": 0.5161693692207336,
|
| 156 |
+
"step": 7,
|
| 157 |
+
"timer/calc_advantages": 2.2946014404296875,
|
| 158 |
+
"timer/calc_loss": 0.96665358543396,
|
| 159 |
+
"timer/get_reward": 0.6638086438179016,
|
| 160 |
+
"timer/training_step": 6.369439125061035,
|
| 161 |
+
"val/num_eos_tokens": 0.0,
|
| 162 |
+
"val/ratio": 0.99953293800354,
|
| 163 |
+
"val/ratio_var": NaN
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0012675024260788625,
|
| 167 |
+
"grad_norm": 8.370040893554688,
|
| 168 |
+
"learning_rate": 2.9987323720488037e-05,
|
| 169 |
+
"loss": 0.0078,
|
| 170 |
+
"loss/policy_avg": 0.00783943198621273,
|
| 171 |
+
"objective/entropy": 66.24089813232422,
|
| 172 |
+
"objective/kl": 0.0030039921402931213,
|
| 173 |
+
"objective/rlhf_reward": 3.1140072345733643,
|
| 174 |
+
"objective/scores": 3.1142501831054688,
|
| 175 |
+
"policy/approxkl_avg": 0.13499276340007782,
|
| 176 |
+
"policy/clipfrac_avg": 0.345703125,
|
| 177 |
+
"policy/entropy_avg": 0.4966353476047516,
|
| 178 |
+
"step": 8,
|
| 179 |
+
"timer/calc_advantages": 2.4299309253692627,
|
| 180 |
+
"timer/calc_loss": 1.046256422996521,
|
| 181 |
+
"timer/get_reward": 0.7162653207778931,
|
| 182 |
+
"timer/training_step": 6.773098945617676,
|
| 183 |
+
"val/num_eos_tokens": 0.0,
|
| 184 |
+
"val/ratio": 1.0011930465698242,
|
| 185 |
+
"val/ratio_var": NaN
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0014259402293387202,
|
| 189 |
+
"grad_norm": 5.985812094877474e-05,
|
| 190 |
+
"learning_rate": 2.9985739185549042e-05,
|
| 191 |
+
"loss": 0.0,
|
| 192 |
+
"loss/policy_avg": 1.3085082173347473e-07,
|
| 193 |
+
"objective/entropy": 57.91233825683594,
|
| 194 |
+
"objective/kl": 0.0,
|
| 195 |
+
"objective/rlhf_reward": 2.9793567657470703,
|
| 196 |
+
"objective/scores": 2.9791259765625,
|
| 197 |
+
"policy/approxkl_avg": 0.0,
|
| 198 |
+
"policy/clipfrac_avg": 0.0,
|
| 199 |
+
"policy/entropy_avg": 0.4229130744934082,
|
| 200 |
+
"step": 9,
|
| 201 |
+
"timer/calc_advantages": 2.2175822257995605,
|
| 202 |
+
"timer/calc_loss": 0.940474271774292,
|
| 203 |
+
"timer/get_reward": 0.6452049016952515,
|
| 204 |
+
"timer/training_step": 6.192902565002441,
|
| 205 |
+
"val/num_eos_tokens": 0.0,
|
| 206 |
+
"val/ratio": 1.0,
|
| 207 |
+
"val/ratio_var": NaN
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.001584378032598578,
|
| 211 |
+
"grad_norm": 2.061887502670288,
|
| 212 |
+
"learning_rate": 2.9984154650610046e-05,
|
| 213 |
+
"loss": 0.0012,
|
| 214 |
+
"loss/policy_avg": 0.00118393381126225,
|
| 215 |
+
"objective/entropy": 57.78638458251953,
|
| 216 |
+
"objective/kl": 0.016596710309386253,
|
| 217 |
+
"objective/rlhf_reward": 2.493161916732788,
|
| 218 |
+
"objective/scores": 2.494873046875,
|
| 219 |
+
"policy/approxkl_avg": 0.04327381029725075,
|
| 220 |
+
"policy/clipfrac_avg": 0.220703125,
|
| 221 |
+
"policy/entropy_avg": 0.45412811636924744,
|
| 222 |
+
"step": 10,
|
| 223 |
+
"timer/calc_advantages": 1.9425208568572998,
|
| 224 |
+
"timer/calc_loss": 0.7499428987503052,
|
| 225 |
+
"timer/get_reward": 0.5237178802490234,
|
| 226 |
+
"timer/training_step": 5.241105556488037,
|
| 227 |
+
"val/num_eos_tokens": 0.0,
|
| 228 |
+
"val/ratio": 1.0002281665802002,
|
| 229 |
+
"val/ratio_var": NaN
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.0017428158358584358,
|
| 233 |
+
"grad_norm": 3.437352180480957,
|
| 234 |
+
"learning_rate": 2.998257011567105e-05,
|
| 235 |
+
"loss": 0.003,
|
| 236 |
+
"loss/policy_avg": 0.003013810608536005,
|
| 237 |
+
"objective/entropy": 62.60158920288086,
|
| 238 |
+
"objective/kl": 0.04900990426540375,
|
| 239 |
+
"objective/rlhf_reward": 3.26180362701416,
|
| 240 |
+
"objective/scores": 3.2667236328125,
|
| 241 |
+
"policy/approxkl_avg": 0.08036807179450989,
|
| 242 |
+
"policy/clipfrac_avg": 0.2734375,
|
| 243 |
+
"policy/entropy_avg": 0.49370765686035156,
|
| 244 |
+
"step": 11,
|
| 245 |
+
"timer/calc_advantages": 2.010678768157959,
|
| 246 |
+
"timer/calc_loss": 0.8044981956481934,
|
| 247 |
+
"timer/get_reward": 0.5571302771568298,
|
| 248 |
+
"timer/training_step": 5.486995220184326,
|
| 249 |
+
"val/num_eos_tokens": 0.0,
|
| 250 |
+
"val/ratio": 1.0001283884048462,
|
| 251 |
+
"val/ratio_var": NaN
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.0019012536391182935,
|
| 255 |
+
"grad_norm": 3.6680727005004883,
|
| 256 |
+
"learning_rate": 2.9980985580732055e-05,
|
| 257 |
+
"loss": 0.0026,
|
| 258 |
+
"loss/policy_avg": 0.002624134300276637,
|
| 259 |
+
"objective/entropy": 70.5216064453125,
|
| 260 |
+
"objective/kl": 0.039649978280067444,
|
| 261 |
+
"objective/rlhf_reward": 1.9454692602157593,
|
| 262 |
+
"objective/scores": 1.94927978515625,
|
| 263 |
+
"policy/approxkl_avg": 0.07172106206417084,
|
| 264 |
+
"policy/clipfrac_avg": 0.34375,
|
| 265 |
+
"policy/entropy_avg": 0.5483217239379883,
|
| 266 |
+
"step": 12,
|
| 267 |
+
"timer/calc_advantages": 1.708000898361206,
|
| 268 |
+
"timer/calc_loss": 0.6391787528991699,
|
| 269 |
+
"timer/get_reward": 0.4455040693283081,
|
| 270 |
+
"timer/training_step": 4.587984085083008,
|
| 271 |
+
"val/num_eos_tokens": 0.0,
|
| 272 |
+
"val/ratio": 1.0003334283828735,
|
| 273 |
+
"val/ratio_var": NaN
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.0020596914423781513,
|
| 277 |
+
"grad_norm": 5.551970753003843e-05,
|
| 278 |
+
"learning_rate": 2.997940104579306e-05,
|
| 279 |
+
"loss": 0.0,
|
| 280 |
+
"loss/policy_avg": 6.216578185558319e-08,
|
| 281 |
+
"objective/entropy": 58.013153076171875,
|
| 282 |
+
"objective/kl": 0.0,
|
| 283 |
+
"objective/rlhf_reward": 1.9868602752685547,
|
| 284 |
+
"objective/scores": 1.9864273071289062,
|
| 285 |
+
"policy/approxkl_avg": 0.0,
|
| 286 |
+
"policy/clipfrac_avg": 0.0,
|
| 287 |
+
"policy/entropy_avg": 0.44822999835014343,
|
| 288 |
+
"step": 13,
|
| 289 |
+
"timer/calc_advantages": 2.0904719829559326,
|
| 290 |
+
"timer/calc_loss": 0.8480838537216187,
|
| 291 |
+
"timer/get_reward": 0.587557315826416,
|
| 292 |
+
"timer/training_step": 5.7307024002075195,
|
| 293 |
+
"val/num_eos_tokens": 0.0,
|
| 294 |
+
"val/ratio": 1.0,
|
| 295 |
+
"val/ratio_var": NaN
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.002218129245638009,
|
| 299 |
+
"grad_norm": 2.7803940773010254,
|
| 300 |
+
"learning_rate": 2.9977816510854064e-05,
|
| 301 |
+
"loss": 0.0015,
|
| 302 |
+
"loss/policy_avg": 0.0014500978868454695,
|
| 303 |
+
"objective/entropy": 69.96898651123047,
|
| 304 |
+
"objective/kl": 0.06745042651891708,
|
| 305 |
+
"objective/rlhf_reward": 2.469928741455078,
|
| 306 |
+
"objective/scores": 2.477020263671875,
|
| 307 |
+
"policy/approxkl_avg": 0.053128380328416824,
|
| 308 |
+
"policy/clipfrac_avg": 0.2734375,
|
| 309 |
+
"policy/entropy_avg": 0.5138126015663147,
|
| 310 |
+
"step": 14,
|
| 311 |
+
"timer/calc_advantages": 1.917910099029541,
|
| 312 |
+
"timer/calc_loss": 0.7225819230079651,
|
| 313 |
+
"timer/get_reward": 0.5053159594535828,
|
| 314 |
+
"timer/training_step": 5.0998334884643555,
|
| 315 |
+
"val/num_eos_tokens": 0.0,
|
| 316 |
+
"val/ratio": 0.9998296499252319,
|
| 317 |
+
"val/ratio_var": NaN
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.002376567048897867,
|
| 321 |
+
"grad_norm": 2.532649278640747,
|
| 322 |
+
"learning_rate": 2.997623197591507e-05,
|
| 323 |
+
"loss": 0.0018,
|
| 324 |
+
"loss/policy_avg": 0.0017822147347033024,
|
| 325 |
+
"objective/entropy": 58.39247131347656,
|
| 326 |
+
"objective/kl": -0.011621108278632164,
|
| 327 |
+
"objective/rlhf_reward": 2.397026538848877,
|
| 328 |
+
"objective/scores": 2.39556884765625,
|
| 329 |
+
"policy/approxkl_avg": 0.05379398912191391,
|
| 330 |
+
"policy/clipfrac_avg": 0.248046875,
|
| 331 |
+
"policy/entropy_avg": 0.4527440071105957,
|
| 332 |
+
"step": 15,
|
| 333 |
+
"timer/calc_advantages": 2.565062999725342,
|
| 334 |
+
"timer/calc_loss": 1.1112425327301025,
|
| 335 |
+
"timer/get_reward": 0.7521659731864929,
|
| 336 |
+
"timer/training_step": 7.156440734863281,
|
| 337 |
+
"val/num_eos_tokens": 0.0,
|
| 338 |
+
"val/ratio": 1.0004982948303223,
|
| 339 |
+
"val/ratio_var": NaN
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.002535004852157725,
|
| 343 |
+
"grad_norm": 5.747053623199463,
|
| 344 |
+
"learning_rate": 2.9974647440976074e-05,
|
| 345 |
+
"loss": 0.0039,
|
| 346 |
+
"loss/policy_avg": 0.0039013477507978678,
|
| 347 |
+
"objective/entropy": 58.41150665283203,
|
| 348 |
+
"objective/kl": -0.03636426478624344,
|
| 349 |
+
"objective/rlhf_reward": 2.3745107650756836,
|
| 350 |
+
"objective/scores": 2.370819091796875,
|
| 351 |
+
"policy/approxkl_avg": 0.07460636645555496,
|
| 352 |
+
"policy/clipfrac_avg": 0.310546875,
|
| 353 |
+
"policy/entropy_avg": 0.4354715943336487,
|
| 354 |
+
"step": 16,
|
| 355 |
+
"timer/calc_advantages": 2.135810136795044,
|
| 356 |
+
"timer/calc_loss": 0.8651329278945923,
|
| 357 |
+
"timer/get_reward": 0.5979053378105164,
|
| 358 |
+
"timer/training_step": 5.837425231933594,
|
| 359 |
+
"val/num_eos_tokens": 0.0,
|
| 360 |
+
"val/ratio": 1.0008955001831055,
|
| 361 |
+
"val/ratio_var": NaN
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.0026934426554175825,
|
| 365 |
+
"grad_norm": 6.287374708335847e-05,
|
| 366 |
+
"learning_rate": 2.9973062906037078e-05,
|
| 367 |
+
"loss": 0.0,
|
| 368 |
+
"loss/policy_avg": 9.161794878309593e-08,
|
| 369 |
+
"objective/entropy": 71.59750366210938,
|
| 370 |
+
"objective/kl": 0.0,
|
| 371 |
+
"objective/rlhf_reward": 1.8474715948104858,
|
| 372 |
+
"objective/scores": 1.847381591796875,
|
| 373 |
+
"policy/approxkl_avg": 0.0,
|
| 374 |
+
"policy/clipfrac_avg": 0.0,
|
| 375 |
+
"policy/entropy_avg": 0.547500729560852,
|
| 376 |
+
"step": 17,
|
| 377 |
+
"timer/calc_advantages": 1.8003900051116943,
|
| 378 |
+
"timer/calc_loss": 0.6777751445770264,
|
| 379 |
+
"timer/get_reward": 0.47231921553611755,
|
| 380 |
+
"timer/training_step": 4.813199996948242,
|
| 381 |
+
"val/num_eos_tokens": 0.0,
|
| 382 |
+
"val/ratio": 1.0,
|
| 383 |
+
"val/ratio_var": NaN
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.0028518804586774404,
|
| 387 |
+
"grad_norm": 3.230647563934326,
|
| 388 |
+
"learning_rate": 2.9971478371098086e-05,
|
| 389 |
+
"loss": 0.0015,
|
| 390 |
+
"loss/policy_avg": 0.001512572169303894,
|
| 391 |
+
"objective/entropy": 65.72537994384766,
|
| 392 |
+
"objective/kl": -0.01090591587126255,
|
| 393 |
+
"objective/rlhf_reward": 2.5540518760681152,
|
| 394 |
+
"objective/scores": 2.5531005859375,
|
| 395 |
+
"policy/approxkl_avg": 0.045434024184942245,
|
| 396 |
+
"policy/clipfrac_avg": 0.306640625,
|
| 397 |
+
"policy/entropy_avg": 0.49296021461486816,
|
| 398 |
+
"step": 18,
|
| 399 |
+
"timer/calc_advantages": 2.015744686126709,
|
| 400 |
+
"timer/calc_loss": 0.798870325088501,
|
| 401 |
+
"timer/get_reward": 0.5532949566841125,
|
| 402 |
+
"timer/training_step": 5.489305019378662,
|
| 403 |
+
"val/num_eos_tokens": 0.0,
|
| 404 |
+
"val/ratio": 1.000435471534729,
|
| 405 |
+
"val/ratio_var": NaN
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.0030103182619372983,
|
| 409 |
+
"grad_norm": 3.198871374130249,
|
| 410 |
+
"learning_rate": 2.996989383615909e-05,
|
| 411 |
+
"loss": 0.0019,
|
| 412 |
+
"loss/policy_avg": 0.001899047987535596,
|
| 413 |
+
"objective/entropy": 57.27036666870117,
|
| 414 |
+
"objective/kl": 0.023365572094917297,
|
| 415 |
+
"objective/rlhf_reward": 2.107551336288452,
|
| 416 |
+
"objective/scores": 2.1098785400390625,
|
| 417 |
+
"policy/approxkl_avg": 0.05755549669265747,
|
| 418 |
+
"policy/clipfrac_avg": 0.287109375,
|
| 419 |
+
"policy/entropy_avg": 0.4354955852031708,
|
| 420 |
+
"step": 19,
|
| 421 |
+
"timer/calc_advantages": 1.9864205121994019,
|
| 422 |
+
"timer/calc_loss": 0.770275354385376,
|
| 423 |
+
"timer/get_reward": 0.5395585894584656,
|
| 424 |
+
"timer/training_step": 5.340071678161621,
|
| 425 |
+
"val/num_eos_tokens": 0.0,
|
| 426 |
+
"val/ratio": 1.0002330541610718,
|
| 427 |
+
"val/ratio_var": NaN
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.003168756065197156,
|
| 431 |
+
"grad_norm": 3.0474605560302734,
|
| 432 |
+
"learning_rate": 2.9968309301220095e-05,
|
| 433 |
+
"loss": 0.0023,
|
| 434 |
+
"loss/policy_avg": 0.0022917778696864843,
|
| 435 |
+
"objective/entropy": 63.32637023925781,
|
| 436 |
+
"objective/kl": 0.09173699468374252,
|
| 437 |
+
"objective/rlhf_reward": 2.2212512493133545,
|
| 438 |
+
"objective/scores": 2.23046875,
|
| 439 |
+
"policy/approxkl_avg": 0.07603129744529724,
|
| 440 |
+
"policy/clipfrac_avg": 0.28125,
|
| 441 |
+
"policy/entropy_avg": 0.4984070062637329,
|
| 442 |
+
"step": 20,
|
| 443 |
+
"timer/calc_advantages": 2.401278257369995,
|
| 444 |
+
"timer/calc_loss": 1.0309439897537231,
|
| 445 |
+
"timer/get_reward": 0.7035059928894043,
|
| 446 |
+
"timer/training_step": 6.705676555633545,
|
| 447 |
+
"val/num_eos_tokens": 0.0,
|
| 448 |
+
"val/ratio": 0.9999362230300903,
|
| 449 |
+
"val/ratio_var": NaN
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.0033271938684570138,
|
| 453 |
+
"grad_norm": 5.2485152991721407e-05,
|
| 454 |
+
"learning_rate": 2.99667247662811e-05,
|
| 455 |
+
"loss": 0.0,
|
| 456 |
+
"loss/policy_avg": 1.1641532182693481e-07,
|
| 457 |
+
"objective/entropy": 63.780208587646484,
|
| 458 |
+
"objective/kl": 0.0,
|
| 459 |
+
"objective/rlhf_reward": 2.867950916290283,
|
| 460 |
+
"objective/scores": 2.8680419921875,
|
| 461 |
+
"policy/approxkl_avg": 0.0,
|
| 462 |
+
"policy/clipfrac_avg": 0.0,
|
| 463 |
+
"policy/entropy_avg": 0.4937428832054138,
|
| 464 |
+
"step": 21,
|
| 465 |
+
"timer/calc_advantages": 1.9973487854003906,
|
| 466 |
+
"timer/calc_loss": 0.799564003944397,
|
| 467 |
+
"timer/get_reward": 0.5565282106399536,
|
| 468 |
+
"timer/training_step": 5.468988418579102,
|
| 469 |
+
"val/num_eos_tokens": 0.0,
|
| 470 |
+
"val/ratio": 1.0,
|
| 471 |
+
"val/ratio_var": NaN
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.0034856316717168717,
|
| 475 |
+
"grad_norm": 1.7639113664627075,
|
| 476 |
+
"learning_rate": 2.9965140231342104e-05,
|
| 477 |
+
"loss": 0.0008,
|
| 478 |
+
"loss/policy_avg": 0.0008156594703905284,
|
| 479 |
+
"objective/entropy": 53.04450225830078,
|
| 480 |
+
"objective/kl": -0.02643105760216713,
|
| 481 |
+
"objective/rlhf_reward": 3.207425355911255,
|
| 482 |
+
"objective/scores": 3.205322265625,
|
| 483 |
+
"policy/approxkl_avg": 0.033180996775627136,
|
| 484 |
+
"policy/clipfrac_avg": 0.1875,
|
| 485 |
+
"policy/entropy_avg": 0.40510252118110657,
|
| 486 |
+
"step": 22,
|
| 487 |
+
"timer/calc_advantages": 1.910763144493103,
|
| 488 |
+
"timer/calc_loss": 0.7438158392906189,
|
| 489 |
+
"timer/get_reward": 0.5141557455062866,
|
| 490 |
+
"timer/training_step": 5.157877445220947,
|
| 491 |
+
"val/num_eos_tokens": 0.0,
|
| 492 |
+
"val/ratio": 1.0004686117172241,
|
| 493 |
+
"val/ratio_var": NaN
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0036440694749767296,
|
| 497 |
+
"grad_norm": 2.1950137615203857,
|
| 498 |
+
"learning_rate": 2.996355569640311e-05,
|
| 499 |
+
"loss": 0.0009,
|
| 500 |
+
"loss/policy_avg": 0.0009003256564028561,
|
| 501 |
+
"objective/entropy": 62.4653205871582,
|
| 502 |
+
"objective/kl": 0.001978884916752577,
|
| 503 |
+
"objective/rlhf_reward": 2.033841848373413,
|
| 504 |
+
"objective/scores": 2.0343017578125,
|
| 505 |
+
"policy/approxkl_avg": 0.035770971328020096,
|
| 506 |
+
"policy/clipfrac_avg": 0.25390625,
|
| 507 |
+
"policy/entropy_avg": 0.47088196873664856,
|
| 508 |
+
"step": 23,
|
| 509 |
+
"timer/calc_advantages": 1.9022271633148193,
|
| 510 |
+
"timer/calc_loss": 0.73871910572052,
|
| 511 |
+
"timer/get_reward": 0.5146778225898743,
|
| 512 |
+
"timer/training_step": 5.153467178344727,
|
| 513 |
+
"val/num_eos_tokens": 0.0,
|
| 514 |
+
"val/ratio": 1.000369668006897,
|
| 515 |
+
"val/ratio_var": NaN
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.003802507278236587,
|
| 519 |
+
"grad_norm": 3.9163379669189453,
|
| 520 |
+
"learning_rate": 2.9961971161464113e-05,
|
| 521 |
+
"loss": 0.0024,
|
| 522 |
+
"loss/policy_avg": 0.0024069277569651604,
|
| 523 |
+
"objective/entropy": 74.16690826416016,
|
| 524 |
+
"objective/kl": -0.011084027588367462,
|
| 525 |
+
"objective/rlhf_reward": 2.49955415725708,
|
| 526 |
+
"objective/scores": 2.498291015625,
|
| 527 |
+
"policy/approxkl_avg": 0.07602480053901672,
|
| 528 |
+
"policy/clipfrac_avg": 0.37109375,
|
| 529 |
+
"policy/entropy_avg": 0.5638661980628967,
|
| 530 |
+
"step": 24,
|
| 531 |
+
"timer/calc_advantages": 2.4937758445739746,
|
| 532 |
+
"timer/calc_loss": 1.0552998781204224,
|
| 533 |
+
"timer/get_reward": 0.7326261401176453,
|
| 534 |
+
"timer/training_step": 6.899857521057129,
|
| 535 |
+
"val/num_eos_tokens": 0.0,
|
| 536 |
+
"val/ratio": 1.0005831718444824,
|
| 537 |
+
"val/ratio_var": NaN
|
| 538 |
+
}
|
| 539 |
+
],
|
| 540 |
+
"logging_steps": 1,
|
| 541 |
+
"max_steps": 18933,
|
| 542 |
+
"num_input_tokens_seen": 0,
|
| 543 |
+
"num_train_epochs": 3,
|
| 544 |
+
"save_steps": 8,
|
| 545 |
+
"total_flos": 1.2330858923163648e+16,
|
| 546 |
+
"train_batch_size": 4,
|
| 547 |
+
"trial_name": null,
|
| 548 |
+
"trial_params": null
|
| 549 |
+
}
|
checkpoint-24/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c727d9c9a10a7db9d4081bf55f4438b2dcd8d7295f98937237880d56ae13932
|
| 3 |
+
size 5240
|
checkpoint-32/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-32/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-32/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04b126313169f80798ffa5a6d53bc6d24f4ae18893fb2f4e6af2a83452d373d7
|
| 3 |
+
size 167832240
|
checkpoint-32/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-32/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:100c26d8270685d0001f1d81f623e91f386b304e661f409f6a6041ee3e044681
|
| 3 |
+
size 335812858
|
checkpoint-32/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91f1ad5db3cf1a4420d5a566f296f11888efa93c608a58160aa55b8f2ba4b626
|
| 3 |
+
size 14244
|
checkpoint-32/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f40a88d074f2f14cf1c8fe02e723f8c72313116d33f973f27e36a70b8029ab22
|
| 3 |
+
size 1064
|
checkpoint-32/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-32/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-32/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-32/tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 41 |
+
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "</s>",
|
| 43 |
+
"legacy": true,
|
| 44 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
+
"padding_side": "left",
|
| 47 |
+
"sp_model_kwargs": {},
|
| 48 |
+
"spaces_between_special_tokens": false,
|
| 49 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 50 |
+
"unk_token": "<unk>",
|
| 51 |
+
"use_default_system_prompt": false
|
| 52 |
+
}
|
checkpoint-32/trainer_state.json
ADDED
|
@@ -0,0 +1,789 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.00507000970431545,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 32,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0001584378032598578,
|
| 13 |
+
"grad_norm": 4.8242447519442067e-05,
|
| 14 |
+
"learning_rate": 0.0029998415465061004,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
+
"loss/policy_avg": 7.299240678548813e-08,
|
| 17 |
+
"objective/entropy": 67.43842315673828,
|
| 18 |
+
"objective/kl": 0.0,
|
| 19 |
+
"objective/rlhf_reward": 1.5219240188598633,
|
| 20 |
+
"objective/scores": 1.52203369140625,
|
| 21 |
+
"policy/approxkl_avg": 0.0,
|
| 22 |
+
"policy/clipfrac_avg": 0.0,
|
| 23 |
+
"step": 1,
|
| 24 |
+
"timer/active_model_forward": 0.7594873309135437,
|
| 25 |
+
"timer/calc_advantages": 31.33674430847168,
|
| 26 |
+
"timer/calc_loss": 0.774461030960083,
|
| 27 |
+
"timer/generate": 28.869869232177734,
|
| 28 |
+
"timer/get_reward": 0.5197552442550659,
|
| 29 |
+
"timer/model_forward": 0.7690438628196716,
|
| 30 |
+
"timer/ref_model_forward": 0.7777600884437561,
|
| 31 |
+
"timer/training_step": 34.545597076416016,
|
| 32 |
+
"val/num_eos_tokens": 0.0,
|
| 33 |
+
"val/ratio": 1.0
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.0003168756065197156,
|
| 37 |
+
"grad_norm": 0.00026670348597690463,
|
| 38 |
+
"learning_rate": 0.002999683093012201,
|
| 39 |
+
"loss": -0.0,
|
| 40 |
+
"loss/policy_avg": -1.7043203115463257e-07,
|
| 41 |
+
"objective/entropy": 118.22715759277344,
|
| 42 |
+
"objective/kl": 0.0,
|
| 43 |
+
"objective/rlhf_reward": -3.824268341064453,
|
| 44 |
+
"objective/scores": -3.82421875,
|
| 45 |
+
"policy/approxkl_avg": 0.0,
|
| 46 |
+
"policy/clipfrac_avg": 0.0,
|
| 47 |
+
"step": 2,
|
| 48 |
+
"timer/active_model_forward": 0.6569761037826538,
|
| 49 |
+
"timer/calc_advantages": 30.551788330078125,
|
| 50 |
+
"timer/calc_loss": 0.6658673286437988,
|
| 51 |
+
"timer/generate": 28.41728973388672,
|
| 52 |
+
"timer/get_reward": 0.43157756328582764,
|
| 53 |
+
"timer/model_forward": 0.6641299724578857,
|
| 54 |
+
"timer/ref_model_forward": 0.67349773645401,
|
| 55 |
+
"timer/training_step": 33.37031936645508,
|
| 56 |
+
"val/num_eos_tokens": 0.0,
|
| 57 |
+
"val/ratio": 1.0
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0004753134097795734,
|
| 61 |
+
"grad_norm": 0.00013700829003937542,
|
| 62 |
+
"learning_rate": 0.0029995246395183015,
|
| 63 |
+
"loss": -0.0,
|
| 64 |
+
"loss/policy_avg": -2.9243528842926025e-07,
|
| 65 |
+
"objective/entropy": 1081.7860107421875,
|
| 66 |
+
"objective/kl": 0.0,
|
| 67 |
+
"objective/rlhf_reward": -5.476104736328125,
|
| 68 |
+
"objective/scores": -5.476806640625,
|
| 69 |
+
"policy/approxkl_avg": 0.0,
|
| 70 |
+
"policy/clipfrac_avg": 0.0,
|
| 71 |
+
"step": 3,
|
| 72 |
+
"timer/active_model_forward": 0.9020705223083496,
|
| 73 |
+
"timer/calc_advantages": 32.11817169189453,
|
| 74 |
+
"timer/calc_loss": 0.9118615984916687,
|
| 75 |
+
"timer/generate": 29.300296783447266,
|
| 76 |
+
"timer/get_reward": 0.5959209203720093,
|
| 77 |
+
"timer/model_forward": 0.9100804924964905,
|
| 78 |
+
"timer/ref_model_forward": 0.9205952882766724,
|
| 79 |
+
"timer/training_step": 35.83306121826172,
|
| 80 |
+
"val/num_eos_tokens": 0.0,
|
| 81 |
+
"val/ratio": 1.0
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0006337512130394313,
|
| 85 |
+
"grad_norm": 7.692693907301873e-05,
|
| 86 |
+
"learning_rate": 0.002999366186024402,
|
| 87 |
+
"loss": -0.0,
|
| 88 |
+
"loss/policy_avg": -2.0489096641540527e-07,
|
| 89 |
+
"objective/entropy": 1181.2274169921875,
|
| 90 |
+
"objective/kl": 0.0,
|
| 91 |
+
"objective/rlhf_reward": -5.0478363037109375,
|
| 92 |
+
"objective/scores": -5.04833984375,
|
| 93 |
+
"policy/approxkl_avg": 0.0,
|
| 94 |
+
"policy/clipfrac_avg": 0.0,
|
| 95 |
+
"step": 4,
|
| 96 |
+
"timer/active_model_forward": 0.8427364826202393,
|
| 97 |
+
"timer/calc_advantages": 31.744182586669922,
|
| 98 |
+
"timer/calc_loss": 0.8533791899681091,
|
| 99 |
+
"timer/generate": 29.096416473388672,
|
| 100 |
+
"timer/get_reward": 0.5531487464904785,
|
| 101 |
+
"timer/model_forward": 0.851642906665802,
|
| 102 |
+
"timer/ref_model_forward": 0.8617820143699646,
|
| 103 |
+
"timer/training_step": 35.25868225097656,
|
| 104 |
+
"val/num_eos_tokens": 0.0,
|
| 105 |
+
"val/ratio": 1.0
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.000792189016299289,
|
| 109 |
+
"grad_norm": 3.911158273695037e-05,
|
| 110 |
+
"learning_rate": 0.0029992077325305022,
|
| 111 |
+
"loss": -0.0,
|
| 112 |
+
"loss/policy_avg": -2.1513551473617554e-07,
|
| 113 |
+
"objective/entropy": 1185.438232421875,
|
| 114 |
+
"objective/kl": 0.0,
|
| 115 |
+
"objective/rlhf_reward": -4.198909759521484,
|
| 116 |
+
"objective/scores": -4.198486328125,
|
| 117 |
+
"policy/approxkl_avg": 0.0,
|
| 118 |
+
"policy/clipfrac_avg": 0.0,
|
| 119 |
+
"step": 5,
|
| 120 |
+
"timer/active_model_forward": 0.791987955570221,
|
| 121 |
+
"timer/calc_advantages": 31.324127197265625,
|
| 122 |
+
"timer/calc_loss": 0.8030194044113159,
|
| 123 |
+
"timer/generate": 28.832427978515625,
|
| 124 |
+
"timer/get_reward": 0.5202938914299011,
|
| 125 |
+
"timer/model_forward": 0.8012962937355042,
|
| 126 |
+
"timer/ref_model_forward": 0.8093616366386414,
|
| 127 |
+
"timer/training_step": 34.65721130371094,
|
| 128 |
+
"val/num_eos_tokens": 0.0,
|
| 129 |
+
"val/ratio": 1.0
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0009506268195591468,
|
| 133 |
+
"grad_norm": 2.5278823159169406e-05,
|
| 134 |
+
"learning_rate": 0.002999049279036603,
|
| 135 |
+
"loss": -0.0,
|
| 136 |
+
"loss/policy_avg": -1.2619420886039734e-07,
|
| 137 |
+
"objective/entropy": 528.8932495117188,
|
| 138 |
+
"objective/kl": 0.0,
|
| 139 |
+
"objective/rlhf_reward": -3.1182708740234375,
|
| 140 |
+
"objective/scores": -3.1180419921875,
|
| 141 |
+
"policy/approxkl_avg": 0.0,
|
| 142 |
+
"policy/clipfrac_avg": 0.0,
|
| 143 |
+
"step": 6,
|
| 144 |
+
"timer/active_model_forward": 0.7996934652328491,
|
| 145 |
+
"timer/calc_advantages": 31.30746078491211,
|
| 146 |
+
"timer/calc_loss": 0.8107499480247498,
|
| 147 |
+
"timer/generate": 28.788341522216797,
|
| 148 |
+
"timer/get_reward": 0.5261460542678833,
|
| 149 |
+
"timer/model_forward": 0.8090219497680664,
|
| 150 |
+
"timer/ref_model_forward": 0.8171602487564087,
|
| 151 |
+
"timer/training_step": 34.65579605102539,
|
| 152 |
+
"val/num_eos_tokens": 0.0,
|
| 153 |
+
"val/ratio": 1.0
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.0011090646228190046,
|
| 157 |
+
"grad_norm": 1.0207173772869282e-06,
|
| 158 |
+
"learning_rate": 0.0029988908255427034,
|
| 159 |
+
"loss": -0.0,
|
| 160 |
+
"loss/policy_avg": -3.1781382858753204e-08,
|
| 161 |
+
"objective/entropy": 1.5396817922592163,
|
| 162 |
+
"objective/kl": 0.0,
|
| 163 |
+
"objective/rlhf_reward": -1.2192144393920898,
|
| 164 |
+
"objective/scores": -1.2193603515625,
|
| 165 |
+
"policy/approxkl_avg": 0.0,
|
| 166 |
+
"policy/clipfrac_avg": 0.0,
|
| 167 |
+
"step": 7,
|
| 168 |
+
"timer/active_model_forward": 1.0039308071136475,
|
| 169 |
+
"timer/calc_advantages": 32.610069274902344,
|
| 170 |
+
"timer/calc_loss": 1.0154139995574951,
|
| 171 |
+
"timer/generate": 29.52051544189453,
|
| 172 |
+
"timer/get_reward": 0.6604768633842468,
|
| 173 |
+
"timer/model_forward": 1.0136762857437134,
|
| 174 |
+
"timer/ref_model_forward": 1.0217972993850708,
|
| 175 |
+
"timer/training_step": 36.71036911010742,
|
| 176 |
+
"val/num_eos_tokens": 0.0,
|
| 177 |
+
"val/ratio": 1.0
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0012675024260788625,
|
| 181 |
+
"grad_norm": 1.4357982536239433e-06,
|
| 182 |
+
"learning_rate": 0.0029987323720488037,
|
| 183 |
+
"loss": -0.0,
|
| 184 |
+
"loss/policy_avg": -7.380731403827667e-08,
|
| 185 |
+
"objective/entropy": 2.126983404159546,
|
| 186 |
+
"objective/kl": 0.0,
|
| 187 |
+
"objective/rlhf_reward": -1.3588581085205078,
|
| 188 |
+
"objective/scores": -1.35894775390625,
|
| 189 |
+
"policy/approxkl_avg": 0.0,
|
| 190 |
+
"policy/clipfrac_avg": 0.0,
|
| 191 |
+
"step": 8,
|
| 192 |
+
"timer/active_model_forward": 1.0782428979873657,
|
| 193 |
+
"timer/calc_advantages": 33.10707092285156,
|
| 194 |
+
"timer/calc_loss": 1.0924396514892578,
|
| 195 |
+
"timer/generate": 29.794893264770508,
|
| 196 |
+
"timer/get_reward": 0.7108417749404907,
|
| 197 |
+
"timer/model_forward": 1.0906702280044556,
|
| 198 |
+
"timer/ref_model_forward": 1.0941966772079468,
|
| 199 |
+
"timer/training_step": 37.46529769897461,
|
| 200 |
+
"val/num_eos_tokens": 0.0,
|
| 201 |
+
"val/ratio": 1.0
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.0014259402293387202,
|
| 205 |
+
"grad_norm": 1.58626687607466e-06,
|
| 206 |
+
"learning_rate": 0.002998573918554904,
|
| 207 |
+
"loss": -0.0,
|
| 208 |
+
"loss/policy_avg": -5.851325113326311e-08,
|
| 209 |
+
"objective/entropy": 5.8357086181640625,
|
| 210 |
+
"objective/kl": 0.0,
|
| 211 |
+
"objective/rlhf_reward": -1.3656387329101562,
|
| 212 |
+
"objective/scores": -1.36566162109375,
|
| 213 |
+
"policy/approxkl_avg": 0.0,
|
| 214 |
+
"policy/clipfrac_avg": 0.0,
|
| 215 |
+
"step": 9,
|
| 216 |
+
"timer/active_model_forward": 0.9783480167388916,
|
| 217 |
+
"timer/calc_advantages": 32.70989990234375,
|
| 218 |
+
"timer/calc_loss": 0.9892486333847046,
|
| 219 |
+
"timer/generate": 29.658161163330078,
|
| 220 |
+
"timer/get_reward": 0.6437245011329651,
|
| 221 |
+
"timer/model_forward": 0.9874842166900635,
|
| 222 |
+
"timer/ref_model_forward": 0.9964737892150879,
|
| 223 |
+
"timer/training_step": 36.70344924926758,
|
| 224 |
+
"val/num_eos_tokens": 0.0,
|
| 225 |
+
"val/ratio": 1.0
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.001584378032598578,
|
| 229 |
+
"grad_norm": 1.8057213537758798e-06,
|
| 230 |
+
"learning_rate": 0.002998415465061005,
|
| 231 |
+
"loss": -0.0,
|
| 232 |
+
"loss/policy_avg": -4.391768015921116e-08,
|
| 233 |
+
"objective/entropy": 37.01044464111328,
|
| 234 |
+
"objective/kl": 0.0,
|
| 235 |
+
"objective/rlhf_reward": -1.1269941329956055,
|
| 236 |
+
"objective/scores": -1.126983642578125,
|
| 237 |
+
"policy/approxkl_avg": 0.0,
|
| 238 |
+
"policy/clipfrac_avg": 0.0,
|
| 239 |
+
"step": 10,
|
| 240 |
+
"timer/active_model_forward": 0.7927595973014832,
|
| 241 |
+
"timer/calc_advantages": 31.501224517822266,
|
| 242 |
+
"timer/calc_loss": 0.8029042482376099,
|
| 243 |
+
"timer/generate": 28.97046661376953,
|
| 244 |
+
"timer/get_reward": 0.5210747718811035,
|
| 245 |
+
"timer/model_forward": 0.8011468052864075,
|
| 246 |
+
"timer/ref_model_forward": 0.8100461363792419,
|
| 247 |
+
"timer/training_step": 34.83835983276367,
|
| 248 |
+
"val/num_eos_tokens": 0.0,
|
| 249 |
+
"val/ratio": 1.0
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.0017428158358584358,
|
| 253 |
+
"grad_norm": 1.3606485254058498e-06,
|
| 254 |
+
"learning_rate": 0.002998257011567105,
|
| 255 |
+
"loss": -0.0,
|
| 256 |
+
"loss/policy_avg": -6.2282197177410126e-09,
|
| 257 |
+
"objective/entropy": 82.50379943847656,
|
| 258 |
+
"objective/kl": 0.0,
|
| 259 |
+
"objective/rlhf_reward": -0.20352506637573242,
|
| 260 |
+
"objective/scores": -0.20351409912109375,
|
| 261 |
+
"policy/approxkl_avg": 0.0,
|
| 262 |
+
"policy/clipfrac_avg": 0.0,
|
| 263 |
+
"step": 11,
|
| 264 |
+
"timer/active_model_forward": 0.8447611331939697,
|
| 265 |
+
"timer/calc_advantages": 31.68113899230957,
|
| 266 |
+
"timer/calc_loss": 0.8556842803955078,
|
| 267 |
+
"timer/generate": 29.030838012695312,
|
| 268 |
+
"timer/get_reward": 0.5556706786155701,
|
| 269 |
+
"timer/model_forward": 0.853936493396759,
|
| 270 |
+
"timer/ref_model_forward": 0.8623838424682617,
|
| 271 |
+
"timer/training_step": 35.189205169677734,
|
| 272 |
+
"val/num_eos_tokens": 0.0,
|
| 273 |
+
"val/ratio": 1.0
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.0019012536391182935,
|
| 277 |
+
"grad_norm": 1.5168055824688054e-06,
|
| 278 |
+
"learning_rate": 0.0029980985580732055,
|
| 279 |
+
"loss": -0.0,
|
| 280 |
+
"loss/policy_avg": -5.324545782059431e-08,
|
| 281 |
+
"objective/entropy": 43.37924575805664,
|
| 282 |
+
"objective/kl": 0.0,
|
| 283 |
+
"objective/rlhf_reward": -1.273842453956604,
|
| 284 |
+
"objective/scores": -1.2738037109375,
|
| 285 |
+
"policy/approxkl_avg": 0.0,
|
| 286 |
+
"policy/clipfrac_avg": 0.0,
|
| 287 |
+
"step": 12,
|
| 288 |
+
"timer/active_model_forward": 0.6771436929702759,
|
| 289 |
+
"timer/calc_advantages": 30.566415786743164,
|
| 290 |
+
"timer/calc_loss": 0.6872404217720032,
|
| 291 |
+
"timer/generate": 28.381263732910156,
|
| 292 |
+
"timer/get_reward": 0.4441335201263428,
|
| 293 |
+
"timer/model_forward": 0.6854845881462097,
|
| 294 |
+
"timer/ref_model_forward": 0.6946568489074707,
|
| 295 |
+
"timer/training_step": 33.479454040527344,
|
| 296 |
+
"val/num_eos_tokens": 0.0,
|
| 297 |
+
"val/ratio": 1.0
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0020596914423781513,
|
| 301 |
+
"grad_norm": 9.032095817929076e-07,
|
| 302 |
+
"learning_rate": 0.0029979401045793063,
|
| 303 |
+
"loss": -0.0,
|
| 304 |
+
"loss/policy_avg": -5.2401446737349033e-08,
|
| 305 |
+
"objective/entropy": 43.8469123840332,
|
| 306 |
+
"objective/kl": 0.0,
|
| 307 |
+
"objective/rlhf_reward": -1.2306889295578003,
|
| 308 |
+
"objective/scores": -1.230804443359375,
|
| 309 |
+
"policy/approxkl_avg": 0.0,
|
| 310 |
+
"policy/clipfrac_avg": 0.0,
|
| 311 |
+
"step": 13,
|
| 312 |
+
"timer/active_model_forward": 0.8871802091598511,
|
| 313 |
+
"timer/calc_advantages": 31.831775665283203,
|
| 314 |
+
"timer/calc_loss": 0.8963775634765625,
|
| 315 |
+
"timer/generate": 29.063201904296875,
|
| 316 |
+
"timer/get_reward": 0.5812451839447021,
|
| 317 |
+
"timer/model_forward": 0.8946273326873779,
|
| 318 |
+
"timer/ref_model_forward": 0.9052593111991882,
|
| 319 |
+
"timer/training_step": 35.49396514892578,
|
| 320 |
+
"val/num_eos_tokens": 0.0,
|
| 321 |
+
"val/ratio": 1.0
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.002218129245638009,
|
| 325 |
+
"grad_norm": 1.8163491404266097e-06,
|
| 326 |
+
"learning_rate": 0.0029977816510854067,
|
| 327 |
+
"loss": -0.0,
|
| 328 |
+
"loss/policy_avg": -6.629852578043938e-08,
|
| 329 |
+
"objective/entropy": 46.85642623901367,
|
| 330 |
+
"objective/kl": 0.0,
|
| 331 |
+
"objective/rlhf_reward": -1.4318056106567383,
|
| 332 |
+
"objective/scores": -1.431884765625,
|
| 333 |
+
"policy/approxkl_avg": 0.0,
|
| 334 |
+
"policy/clipfrac_avg": 0.0,
|
| 335 |
+
"step": 14,
|
| 336 |
+
"timer/active_model_forward": 0.7645549774169922,
|
| 337 |
+
"timer/calc_advantages": 31.06265640258789,
|
| 338 |
+
"timer/calc_loss": 0.775362491607666,
|
| 339 |
+
"timer/generate": 28.632740020751953,
|
| 340 |
+
"timer/get_reward": 0.5032914876937866,
|
| 341 |
+
"timer/model_forward": 0.7736347317695618,
|
| 342 |
+
"timer/ref_model_forward": 0.7821637988090515,
|
| 343 |
+
"timer/training_step": 34.282867431640625,
|
| 344 |
+
"val/num_eos_tokens": 0.0,
|
| 345 |
+
"val/ratio": 1.0
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.002376567048897867,
|
| 349 |
+
"grad_norm": 1.1021771797459223e-06,
|
| 350 |
+
"learning_rate": 0.002997623197591507,
|
| 351 |
+
"loss": -0.0,
|
| 352 |
+
"loss/policy_avg": -4.4819898903369904e-08,
|
| 353 |
+
"objective/entropy": 83.53251647949219,
|
| 354 |
+
"objective/kl": 0.0,
|
| 355 |
+
"objective/rlhf_reward": -0.6715226173400879,
|
| 356 |
+
"objective/scores": -0.671539306640625,
|
| 357 |
+
"policy/approxkl_avg": 0.0,
|
| 358 |
+
"policy/clipfrac_avg": 0.0,
|
| 359 |
+
"step": 15,
|
| 360 |
+
"timer/active_model_forward": 1.1367318630218506,
|
| 361 |
+
"timer/calc_advantages": 33.59859848022461,
|
| 362 |
+
"timer/calc_loss": 1.2175476551055908,
|
| 363 |
+
"timer/generate": 30.091690063476562,
|
| 364 |
+
"timer/get_reward": 0.7473501563072205,
|
| 365 |
+
"timer/model_forward": 1.2155828475952148,
|
| 366 |
+
"timer/ref_model_forward": 1.1532230377197266,
|
| 367 |
+
"timer/training_step": 38.26678466796875,
|
| 368 |
+
"val/num_eos_tokens": 0.0,
|
| 369 |
+
"val/ratio": 1.0
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.002535004852157725,
|
| 373 |
+
"grad_norm": 1.2331845482549397e-06,
|
| 374 |
+
"learning_rate": 0.0029974647440976073,
|
| 375 |
+
"loss": -0.0,
|
| 376 |
+
"loss/policy_avg": -1.6909325495362282e-08,
|
| 377 |
+
"objective/entropy": 119.47362518310547,
|
| 378 |
+
"objective/kl": 0.0,
|
| 379 |
+
"objective/rlhf_reward": -0.5125551223754883,
|
| 380 |
+
"objective/scores": -0.5126724243164062,
|
| 381 |
+
"policy/approxkl_avg": 0.0,
|
| 382 |
+
"policy/clipfrac_avg": 0.0,
|
| 383 |
+
"step": 16,
|
| 384 |
+
"timer/active_model_forward": 0.9046459197998047,
|
| 385 |
+
"timer/calc_advantages": 32.02373123168945,
|
| 386 |
+
"timer/calc_loss": 0.914932906627655,
|
| 387 |
+
"timer/generate": 29.190690994262695,
|
| 388 |
+
"timer/get_reward": 0.5946121215820312,
|
| 389 |
+
"timer/model_forward": 0.9131810665130615,
|
| 390 |
+
"timer/ref_model_forward": 0.922136127948761,
|
| 391 |
+
"timer/training_step": 35.75535202026367,
|
| 392 |
+
"val/num_eos_tokens": 0.0,
|
| 393 |
+
"val/ratio": 1.0
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.0026934426554175825,
|
| 397 |
+
"grad_norm": 2.2155286387715023e-06,
|
| 398 |
+
"learning_rate": 0.002997306290603708,
|
| 399 |
+
"loss": -0.0,
|
| 400 |
+
"loss/policy_avg": -4.8712536226958036e-08,
|
| 401 |
+
"objective/entropy": 121.45540618896484,
|
| 402 |
+
"objective/kl": 0.0,
|
| 403 |
+
"objective/rlhf_reward": -1.4430209398269653,
|
| 404 |
+
"objective/scores": -1.443115234375,
|
| 405 |
+
"policy/approxkl_avg": 0.0,
|
| 406 |
+
"policy/clipfrac_avg": 0.0,
|
| 407 |
+
"step": 17,
|
| 408 |
+
"timer/active_model_forward": 0.7191606163978577,
|
| 409 |
+
"timer/calc_advantages": 31.075271606445312,
|
| 410 |
+
"timer/calc_loss": 0.7287229895591736,
|
| 411 |
+
"timer/generate": 28.78363037109375,
|
| 412 |
+
"timer/get_reward": 0.4706084430217743,
|
| 413 |
+
"timer/model_forward": 0.7269375324249268,
|
| 414 |
+
"timer/ref_model_forward": 0.737448513507843,
|
| 415 |
+
"timer/training_step": 34.119632720947266,
|
| 416 |
+
"val/num_eos_tokens": 0.0,
|
| 417 |
+
"val/ratio": 1.0
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0028518804586774404,
|
| 421 |
+
"grad_norm": 8.308816177304834e-07,
|
| 422 |
+
"learning_rate": 0.0029971478371098085,
|
| 423 |
+
"loss": -0.0,
|
| 424 |
+
"loss/policy_avg": -1.1129304766654968e-07,
|
| 425 |
+
"objective/entropy": 96.97429656982422,
|
| 426 |
+
"objective/kl": 0.0,
|
| 427 |
+
"objective/rlhf_reward": -2.8110389709472656,
|
| 428 |
+
"objective/scores": -2.811279296875,
|
| 429 |
+
"policy/approxkl_avg": 0.0,
|
| 430 |
+
"policy/clipfrac_avg": 0.0,
|
| 431 |
+
"step": 18,
|
| 432 |
+
"timer/active_model_forward": 0.8409894704818726,
|
| 433 |
+
"timer/calc_advantages": 31.73868179321289,
|
| 434 |
+
"timer/calc_loss": 0.8524103164672852,
|
| 435 |
+
"timer/generate": 29.05769920349121,
|
| 436 |
+
"timer/get_reward": 0.5517525672912598,
|
| 437 |
+
"timer/model_forward": 0.8506196737289429,
|
| 438 |
+
"timer/ref_model_forward": 0.8585314154624939,
|
| 439 |
+
"timer/training_step": 35.25176239013672,
|
| 440 |
+
"val/num_eos_tokens": 0.0,
|
| 441 |
+
"val/ratio": 1.0
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.0030103182619372983,
|
| 445 |
+
"grad_norm": 3.799691228323354e-07,
|
| 446 |
+
"learning_rate": 0.002996989383615909,
|
| 447 |
+
"loss": -0.0,
|
| 448 |
+
"loss/policy_avg": -9.569339454174042e-08,
|
| 449 |
+
"objective/entropy": 85.54360961914062,
|
| 450 |
+
"objective/kl": 0.0,
|
| 451 |
+
"objective/rlhf_reward": -2.591951370239258,
|
| 452 |
+
"objective/scores": -2.591796875,
|
| 453 |
+
"policy/approxkl_avg": 0.0,
|
| 454 |
+
"policy/clipfrac_avg": 0.0,
|
| 455 |
+
"step": 19,
|
| 456 |
+
"timer/active_model_forward": 0.8125832080841064,
|
| 457 |
+
"timer/calc_advantages": 31.4530029296875,
|
| 458 |
+
"timer/calc_loss": 0.8229714632034302,
|
| 459 |
+
"timer/generate": 28.860492706298828,
|
| 460 |
+
"timer/get_reward": 0.5346251130104065,
|
| 461 |
+
"timer/model_forward": 0.8212224245071411,
|
| 462 |
+
"timer/ref_model_forward": 0.8305649757385254,
|
| 463 |
+
"timer/training_step": 34.838218688964844,
|
| 464 |
+
"val/num_eos_tokens": 0.0,
|
| 465 |
+
"val/ratio": 1.0
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.003168756065197156,
|
| 469 |
+
"grad_norm": 3.7777222132717725e-06,
|
| 470 |
+
"learning_rate": 0.002996830930122009,
|
| 471 |
+
"loss": -0.0,
|
| 472 |
+
"loss/policy_avg": -7.898779585957527e-08,
|
| 473 |
+
"objective/entropy": 78.87588500976562,
|
| 474 |
+
"objective/kl": 0.0,
|
| 475 |
+
"objective/rlhf_reward": -2.1325230598449707,
|
| 476 |
+
"objective/scores": -2.13275146484375,
|
| 477 |
+
"policy/approxkl_avg": 0.0,
|
| 478 |
+
"policy/clipfrac_avg": 0.0,
|
| 479 |
+
"step": 20,
|
| 480 |
+
"timer/active_model_forward": 1.0649389028549194,
|
| 481 |
+
"timer/calc_advantages": 33.12159729003906,
|
| 482 |
+
"timer/calc_loss": 1.0808004140853882,
|
| 483 |
+
"timer/generate": 29.827653884887695,
|
| 484 |
+
"timer/get_reward": 0.7013706564903259,
|
| 485 |
+
"timer/model_forward": 1.0790588855743408,
|
| 486 |
+
"timer/ref_model_forward": 1.0825612545013428,
|
| 487 |
+
"timer/training_step": 37.4581413269043,
|
| 488 |
+
"val/num_eos_tokens": 0.0,
|
| 489 |
+
"val/ratio": 1.0
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.0033271938684570138,
|
| 493 |
+
"grad_norm": 2.958485652015952e-07,
|
| 494 |
+
"learning_rate": 0.00299667247662811,
|
| 495 |
+
"loss": -0.0,
|
| 496 |
+
"loss/policy_avg": -6.577465683221817e-08,
|
| 497 |
+
"objective/entropy": 26.52663803100586,
|
| 498 |
+
"objective/kl": 0.0,
|
| 499 |
+
"objective/rlhf_reward": -1.5283641815185547,
|
| 500 |
+
"objective/scores": -1.52838134765625,
|
| 501 |
+
"policy/approxkl_avg": 0.0,
|
| 502 |
+
"policy/clipfrac_avg": 0.0,
|
| 503 |
+
"step": 21,
|
| 504 |
+
"timer/active_model_forward": 0.8408429622650146,
|
| 505 |
+
"timer/calc_advantages": 31.583477020263672,
|
| 506 |
+
"timer/calc_loss": 0.8517074584960938,
|
| 507 |
+
"timer/generate": 28.94709014892578,
|
| 508 |
+
"timer/get_reward": 0.5524436235427856,
|
| 509 |
+
"timer/model_forward": 0.8499797582626343,
|
| 510 |
+
"timer/ref_model_forward": 0.859445333480835,
|
| 511 |
+
"timer/training_step": 35.0816535949707,
|
| 512 |
+
"val/num_eos_tokens": 0.0,
|
| 513 |
+
"val/ratio": 1.0
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.0034856316717168717,
|
| 517 |
+
"grad_norm": 2.1688055085178348e-07,
|
| 518 |
+
"learning_rate": 0.0029965140231342103,
|
| 519 |
+
"loss": -0.0,
|
| 520 |
+
"loss/policy_avg": -7.275957614183426e-08,
|
| 521 |
+
"objective/entropy": 5.097399711608887,
|
| 522 |
+
"objective/kl": 0.0,
|
| 523 |
+
"objective/rlhf_reward": -1.3907923698425293,
|
| 524 |
+
"objective/scores": -1.390869140625,
|
| 525 |
+
"policy/approxkl_avg": 0.0,
|
| 526 |
+
"policy/clipfrac_avg": 0.0,
|
| 527 |
+
"step": 22,
|
| 528 |
+
"timer/active_model_forward": 0.7821312546730042,
|
| 529 |
+
"timer/calc_advantages": 31.17966079711914,
|
| 530 |
+
"timer/calc_loss": 0.7932944297790527,
|
| 531 |
+
"timer/generate": 28.714157104492188,
|
| 532 |
+
"timer/get_reward": 0.5111904144287109,
|
| 533 |
+
"timer/model_forward": 0.7915641069412231,
|
| 534 |
+
"timer/ref_model_forward": 0.8004368543624878,
|
| 535 |
+
"timer/training_step": 34.46521759033203,
|
| 536 |
+
"val/num_eos_tokens": 0.0,
|
| 537 |
+
"val/ratio": 1.0
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.0036440694749767296,
|
| 541 |
+
"grad_norm": 1.0821660367810182e-07,
|
| 542 |
+
"learning_rate": 0.0029963555696403106,
|
| 543 |
+
"loss": -0.0,
|
| 544 |
+
"loss/policy_avg": -5.2619725465774536e-08,
|
| 545 |
+
"objective/entropy": 0.7932516932487488,
|
| 546 |
+
"objective/kl": 0.0,
|
| 547 |
+
"objective/rlhf_reward": -1.3286209106445312,
|
| 548 |
+
"objective/scores": -1.3287353515625,
|
| 549 |
+
"policy/approxkl_avg": 0.0,
|
| 550 |
+
"policy/clipfrac_avg": 0.0,
|
| 551 |
+
"step": 23,
|
| 552 |
+
"timer/active_model_forward": 0.7814183235168457,
|
| 553 |
+
"timer/calc_advantages": 31.230453491210938,
|
| 554 |
+
"timer/calc_loss": 0.7906038761138916,
|
| 555 |
+
"timer/generate": 28.76888656616211,
|
| 556 |
+
"timer/get_reward": 0.511726438999176,
|
| 557 |
+
"timer/model_forward": 0.7888429164886475,
|
| 558 |
+
"timer/ref_model_forward": 0.7980221509933472,
|
| 559 |
+
"timer/training_step": 34.51930236816406,
|
| 560 |
+
"val/num_eos_tokens": 0.0,
|
| 561 |
+
"val/ratio": 1.0
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.003802507278236587,
|
| 565 |
+
"grad_norm": 7.358872267104744e-08,
|
| 566 |
+
"learning_rate": 0.0029961971161464114,
|
| 567 |
+
"loss": -0.0,
|
| 568 |
+
"loss/policy_avg": -4.1211023926734924e-08,
|
| 569 |
+
"objective/entropy": 0.42043036222457886,
|
| 570 |
+
"objective/kl": 0.0,
|
| 571 |
+
"objective/rlhf_reward": -1.3438358306884766,
|
| 572 |
+
"objective/scores": -1.34381103515625,
|
| 573 |
+
"policy/approxkl_avg": 0.0,
|
| 574 |
+
"policy/clipfrac_avg": 0.0,
|
| 575 |
+
"step": 24,
|
| 576 |
+
"timer/active_model_forward": 1.0947436094284058,
|
| 577 |
+
"timer/calc_advantages": 33.27772903442383,
|
| 578 |
+
"timer/calc_loss": 1.1070483922958374,
|
| 579 |
+
"timer/generate": 29.915428161621094,
|
| 580 |
+
"timer/get_reward": 0.7210176587104797,
|
| 581 |
+
"timer/model_forward": 1.1053131818771362,
|
| 582 |
+
"timer/ref_model_forward": 1.1129379272460938,
|
| 583 |
+
"timer/training_step": 37.71331024169922,
|
| 584 |
+
"val/num_eos_tokens": 0.0,
|
| 585 |
+
"val/ratio": 1.0
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0039609450814964454,
|
| 589 |
+
"grad_norm": 2.472104299044986e-08,
|
| 590 |
+
"learning_rate": 0.0029960386626525118,
|
| 591 |
+
"loss": -0.0,
|
| 592 |
+
"loss/policy_avg": -5.727633833885193e-08,
|
| 593 |
+
"objective/entropy": 0.012148905545473099,
|
| 594 |
+
"objective/kl": 0.0,
|
| 595 |
+
"objective/rlhf_reward": -0.9438667297363281,
|
| 596 |
+
"objective/scores": -0.943817138671875,
|
| 597 |
+
"policy/approxkl_avg": 0.0,
|
| 598 |
+
"policy/clipfrac_avg": 0.0,
|
| 599 |
+
"step": 25,
|
| 600 |
+
"timer/active_model_forward": 0.8634592890739441,
|
| 601 |
+
"timer/calc_advantages": 31.91621971130371,
|
| 602 |
+
"timer/calc_loss": 0.8720701932907104,
|
| 603 |
+
"timer/generate": 29.20632553100586,
|
| 604 |
+
"timer/get_reward": 0.5676878094673157,
|
| 605 |
+
"timer/model_forward": 0.8703302145004272,
|
| 606 |
+
"timer/ref_model_forward": 0.8802404999732971,
|
| 607 |
+
"timer/training_step": 35.50330352783203,
|
| 608 |
+
"val/num_eos_tokens": 0.0,
|
| 609 |
+
"val/ratio": 1.0
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.0041193828847563025,
|
| 613 |
+
"grad_norm": 7.710570848473708e-09,
|
| 614 |
+
"learning_rate": 0.002995880209158612,
|
| 615 |
+
"loss": -0.0,
|
| 616 |
+
"loss/policy_avg": -5.185938789509237e-08,
|
| 617 |
+
"objective/entropy": 0.004173352383077145,
|
| 618 |
+
"objective/kl": 0.0,
|
| 619 |
+
"objective/rlhf_reward": -1.0292143821716309,
|
| 620 |
+
"objective/scores": -1.02923583984375,
|
| 621 |
+
"policy/approxkl_avg": 0.0,
|
| 622 |
+
"policy/clipfrac_avg": 0.0,
|
| 623 |
+
"step": 26,
|
| 624 |
+
"timer/active_model_forward": 1.1470246315002441,
|
| 625 |
+
"timer/calc_advantages": 33.62145233154297,
|
| 626 |
+
"timer/calc_loss": 1.1597700119018555,
|
| 627 |
+
"timer/generate": 30.103939056396484,
|
| 628 |
+
"timer/get_reward": 0.7558026313781738,
|
| 629 |
+
"timer/model_forward": 1.1580355167388916,
|
| 630 |
+
"timer/ref_model_forward": 1.1651380062103271,
|
| 631 |
+
"timer/training_step": 38.25925064086914,
|
| 632 |
+
"val/num_eos_tokens": 0.0,
|
| 633 |
+
"val/ratio": 1.0
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.00427782068801616,
|
| 637 |
+
"grad_norm": 3.3511178276768305e-09,
|
| 638 |
+
"learning_rate": 0.0029957217556647125,
|
| 639 |
+
"loss": -0.0,
|
| 640 |
+
"loss/policy_avg": -5.727633833885193e-08,
|
| 641 |
+
"objective/entropy": 0.0016420490574091673,
|
| 642 |
+
"objective/kl": 0.0,
|
| 643 |
+
"objective/rlhf_reward": -1.0198352336883545,
|
| 644 |
+
"objective/scores": -1.0199356079101562,
|
| 645 |
+
"policy/approxkl_avg": 0.0,
|
| 646 |
+
"policy/clipfrac_avg": 0.0,
|
| 647 |
+
"step": 27,
|
| 648 |
+
"timer/active_model_forward": 0.8805452585220337,
|
| 649 |
+
"timer/calc_advantages": 31.86100196838379,
|
| 650 |
+
"timer/calc_loss": 0.8916431665420532,
|
| 651 |
+
"timer/generate": 29.115583419799805,
|
| 652 |
+
"timer/get_reward": 0.5775084495544434,
|
| 653 |
+
"timer/model_forward": 0.8899136185646057,
|
| 654 |
+
"timer/ref_model_forward": 0.8984355926513672,
|
| 655 |
+
"timer/training_step": 35.50636291503906,
|
| 656 |
+
"val/num_eos_tokens": 0.0,
|
| 657 |
+
"val/ratio": 1.0
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.004436258491276018,
|
| 661 |
+
"grad_norm": 1.413538508465706e-09,
|
| 662 |
+
"learning_rate": 0.0029955633021708132,
|
| 663 |
+
"loss": -0.0,
|
| 664 |
+
"loss/policy_avg": -5.634501576423645e-08,
|
| 665 |
+
"objective/entropy": 0.0007059703930281103,
|
| 666 |
+
"objective/kl": 0.0,
|
| 667 |
+
"objective/rlhf_reward": -0.7993221282958984,
|
| 668 |
+
"objective/scores": -0.79931640625,
|
| 669 |
+
"policy/approxkl_avg": 0.0,
|
| 670 |
+
"policy/clipfrac_avg": 0.0,
|
| 671 |
+
"step": 28,
|
| 672 |
+
"timer/active_model_forward": 1.1332266330718994,
|
| 673 |
+
"timer/calc_advantages": 33.521759033203125,
|
| 674 |
+
"timer/calc_loss": 1.1450132131576538,
|
| 675 |
+
"timer/generate": 30.048032760620117,
|
| 676 |
+
"timer/get_reward": 0.7485961318016052,
|
| 677 |
+
"timer/model_forward": 1.1432639360427856,
|
| 678 |
+
"timer/ref_model_forward": 1.1509253978729248,
|
| 679 |
+
"timer/training_step": 38.09806442260742,
|
| 680 |
+
"val/num_eos_tokens": 0.0,
|
| 681 |
+
"val/ratio": 1.0
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.004594696294535876,
|
| 685 |
+
"grad_norm": 5.78209535806451e-10,
|
| 686 |
+
"learning_rate": 0.0029954048486769136,
|
| 687 |
+
"loss": -0.0,
|
| 688 |
+
"loss/policy_avg": -4.7963112592697144e-08,
|
| 689 |
+
"objective/entropy": 0.00033563331817276776,
|
| 690 |
+
"objective/kl": 0.0,
|
| 691 |
+
"objective/rlhf_reward": -0.8303084373474121,
|
| 692 |
+
"objective/scores": -0.8302459716796875,
|
| 693 |
+
"policy/approxkl_avg": 0.0,
|
| 694 |
+
"policy/clipfrac_avg": 0.0,
|
| 695 |
+
"step": 29,
|
| 696 |
+
"timer/active_model_forward": 0.5042444467544556,
|
| 697 |
+
"timer/calc_advantages": 29.47503662109375,
|
| 698 |
+
"timer/calc_loss": 0.5117393136024475,
|
| 699 |
+
"timer/generate": 27.804088592529297,
|
| 700 |
+
"timer/get_reward": 0.32876861095428467,
|
| 701 |
+
"timer/model_forward": 0.5100182294845581,
|
| 702 |
+
"timer/ref_model_forward": 0.5201169848442078,
|
| 703 |
+
"timer/training_step": 31.75719451904297,
|
| 704 |
+
"val/num_eos_tokens": 0.0,
|
| 705 |
+
"val/ratio": 1.0
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.004753134097795734,
|
| 709 |
+
"grad_norm": 1.9897845870975317e-10,
|
| 710 |
+
"learning_rate": 0.002995246395183014,
|
| 711 |
+
"loss": -0.0,
|
| 712 |
+
"loss/policy_avg": -3.341119736433029e-08,
|
| 713 |
+
"objective/entropy": 0.00016836810391396284,
|
| 714 |
+
"objective/kl": 0.0,
|
| 715 |
+
"objective/rlhf_reward": -1.0440139770507812,
|
| 716 |
+
"objective/scores": -1.0440673828125,
|
| 717 |
+
"policy/approxkl_avg": 0.0,
|
| 718 |
+
"policy/clipfrac_avg": 0.0,
|
| 719 |
+
"step": 30,
|
| 720 |
+
"timer/active_model_forward": 0.8818363547325134,
|
| 721 |
+
"timer/calc_advantages": 31.895645141601562,
|
| 722 |
+
"timer/calc_loss": 0.8967288732528687,
|
| 723 |
+
"timer/generate": 29.129695892333984,
|
| 724 |
+
"timer/get_reward": 0.5798584222793579,
|
| 725 |
+
"timer/model_forward": 0.8949993848800659,
|
| 726 |
+
"timer/ref_model_forward": 0.8993439674377441,
|
| 727 |
+
"timer/training_step": 35.555747985839844,
|
| 728 |
+
"val/num_eos_tokens": 0.0,
|
| 729 |
+
"val/ratio": 1.0
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.004911571901055592,
|
| 733 |
+
"grad_norm": 1.4891138322425945e-10,
|
| 734 |
+
"learning_rate": 0.0029950879416891143,
|
| 735 |
+
"loss": -0.0,
|
| 736 |
+
"loss/policy_avg": -5.029141902923584e-08,
|
| 737 |
+
"objective/entropy": 8.117404649965465e-05,
|
| 738 |
+
"objective/kl": 0.0,
|
| 739 |
+
"objective/rlhf_reward": -1.2238502502441406,
|
| 740 |
+
"objective/scores": -1.22381591796875,
|
| 741 |
+
"policy/approxkl_avg": 0.0,
|
| 742 |
+
"policy/clipfrac_avg": 0.0,
|
| 743 |
+
"step": 31,
|
| 744 |
+
"timer/active_model_forward": 0.9351563453674316,
|
| 745 |
+
"timer/calc_advantages": 32.229801177978516,
|
| 746 |
+
"timer/calc_loss": 0.946864128112793,
|
| 747 |
+
"timer/generate": 29.3177490234375,
|
| 748 |
+
"timer/get_reward": 0.6167161464691162,
|
| 749 |
+
"timer/model_forward": 0.9451220035552979,
|
| 750 |
+
"timer/ref_model_forward": 0.9523330330848694,
|
| 751 |
+
"timer/training_step": 36.09205627441406,
|
| 752 |
+
"val/num_eos_tokens": 0.0,
|
| 753 |
+
"val/ratio": 1.0
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.00507000970431545,
|
| 757 |
+
"grad_norm": 8.760232816928948e-11,
|
| 758 |
+
"learning_rate": 0.0029949294881952146,
|
| 759 |
+
"loss": -0.0,
|
| 760 |
+
"loss/policy_avg": -4.237517714500427e-08,
|
| 761 |
+
"objective/entropy": 6.1035148974042386e-05,
|
| 762 |
+
"objective/kl": 0.0,
|
| 763 |
+
"objective/rlhf_reward": -1.0421943664550781,
|
| 764 |
+
"objective/scores": -1.042266845703125,
|
| 765 |
+
"policy/approxkl_avg": 0.0,
|
| 766 |
+
"policy/clipfrac_avg": 0.0,
|
| 767 |
+
"step": 32,
|
| 768 |
+
"timer/active_model_forward": 0.829505205154419,
|
| 769 |
+
"timer/calc_advantages": 31.583553314208984,
|
| 770 |
+
"timer/calc_loss": 0.8393364548683167,
|
| 771 |
+
"timer/generate": 28.969213485717773,
|
| 772 |
+
"timer/get_reward": 0.5460556745529175,
|
| 773 |
+
"timer/model_forward": 0.8376072645187378,
|
| 774 |
+
"timer/ref_model_forward": 0.8457875847816467,
|
| 775 |
+
"timer/training_step": 35.03805160522461,
|
| 776 |
+
"val/num_eos_tokens": 0.0,
|
| 777 |
+
"val/ratio": 1.0
|
| 778 |
+
}
|
| 779 |
+
],
|
| 780 |
+
"logging_steps": 1,
|
| 781 |
+
"max_steps": 18933,
|
| 782 |
+
"num_input_tokens_seen": 0,
|
| 783 |
+
"num_train_epochs": 3,
|
| 784 |
+
"save_steps": 8,
|
| 785 |
+
"total_flos": 1.6683704308432896e+16,
|
| 786 |
+
"train_batch_size": 4,
|
| 787 |
+
"trial_name": null,
|
| 788 |
+
"trial_params": null
|
| 789 |
+
}
|
checkpoint-32/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dee1690a11bb3358d66a6ba11dd88327a96654a51c9007c2a9830994ea29f7c
|
| 3 |
+
size 5240
|
checkpoint-40/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-40/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-40/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70044cab9467765af41352e7fd5443ea240d3eadc40c02253a075926bcc45196
|
| 3 |
+
size 167832240
|
checkpoint-40/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-40/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9289c8203209cfb2eb8074550b768f63d949e47a1cb7688216b5d8295e490344
|
| 3 |
+
size 335812858
|
checkpoint-40/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:261c4e49ac26581fa11ec8d056defd925ad6868f506fcb838fdead487c42a1ff
|
| 3 |
+
size 14244
|
checkpoint-40/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5edd5b0bd0a1e427c19238b01ec197fb6618bc62ad31251d7cae4fcc55b11eee
|
| 3 |
+
size 1064
|
checkpoint-40/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-40/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-40/tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 41 |
+
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "</s>",
|
| 43 |
+
"legacy": true,
|
| 44 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
+
"padding_side": "left",
|
| 47 |
+
"sp_model_kwargs": {},
|
| 48 |
+
"spaces_between_special_tokens": false,
|
| 49 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 50 |
+
"unk_token": "<unk>",
|
| 51 |
+
"use_default_system_prompt": false
|
| 52 |
+
}
|