Upload folder using huggingface_hub
Browse files- 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 +405 -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 +597 -0
- checkpoint-24/training_args.bin +3 -0
- checkpoint-8/README.md +202 -0
- checkpoint-8/adapter_config.json +34 -0
- checkpoint-8/adapter_model.safetensors +3 -0
- checkpoint-8/added_tokens.json +3 -0
- checkpoint-8/optimizer.pt +3 -0
- checkpoint-8/rng_state.pth +3 -0
- checkpoint-8/scheduler.pt +3 -0
- checkpoint-8/special_tokens_map.json +30 -0
- checkpoint-8/tokenizer.json +0 -0
- checkpoint-8/tokenizer.model +3 -0
- checkpoint-8/tokenizer_config.json +52 -0
- checkpoint-8/trainer_state.json +213 -0
- checkpoint-8/training_args.bin +3 -0
- runs/May03_18-30-59_2efa04e46d11/events.out.tfevents.1714761060.2efa04e46d11 +3 -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 |
+
"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-16/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe7c35d3f185f2db4b749d9872b0c3a63ae1ec60e65181a376d28337e5c00efe
|
| 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 sha256:1a3c979c6b74e88cfd018a78fb7e6dcc069b3866f42a8ede2fd8782ed4b9563a
|
| 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 sha256:0a49594e520a54ab954ef807a8bb22682aca7855a71a2d7de76c15b6f4e7b5dd
|
| 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 +1,405 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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 |
+
"logging_steps": 1,
|
| 397 |
+
"max_steps": 18933,
|
| 398 |
+
"num_input_tokens_seen": 0,
|
| 399 |
+
"num_train_epochs": 3,
|
| 400 |
+
"save_steps": 8,
|
| 401 |
+
"total_flos": 8202719718014976.0,
|
| 402 |
+
"train_batch_size": 4,
|
| 403 |
+
"trial_name": null,
|
| 404 |
+
"trial_params": null
|
| 405 |
+
}
|
checkpoint-16/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-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 |
+
"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-24/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea0cc735ff7e8fd3fe492f096b63ce3d17edad05be64861712cc5c17149e3812
|
| 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 sha256:2d2a92867974ac6a4766ea63cfd663ffdae821f95e72e1044e3e77d0cc2d96d6
|
| 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 sha256:7fb33e813715a283626fa102bc98947d275f989309cd7b46edd7a34c8cc9c036
|
| 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 +1,597 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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 |
+
"logging_steps": 1,
|
| 589 |
+
"max_steps": 18933,
|
| 590 |
+
"num_input_tokens_seen": 0,
|
| 591 |
+
"num_train_epochs": 3,
|
| 592 |
+
"save_steps": 8,
|
| 593 |
+
"total_flos": 1.2330858923163648e+16,
|
| 594 |
+
"train_batch_size": 4,
|
| 595 |
+
"trial_name": null,
|
| 596 |
+
"trial_params": null
|
| 597 |
+
}
|
checkpoint-24/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-8/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-8/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-8/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f403687f6dad53355584cf4049ca95a48e3a5a81cde650a7a730dacf463031b0
|
| 3 |
+
size 167832240
|
checkpoint-8/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-8/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca4fc371814ed79a5f135cd5d32cc3853ae9f7f0bc46f99e96003250f7458674
|
| 3 |
+
size 335812858
|
checkpoint-8/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d53129727ce62fb59f1778b850873a7bd4b84b764819ed4551328ba6d04343
|
| 3 |
+
size 14244
|
checkpoint-8/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c6fdb7cdf920ef05732bf13f956b9ee39c74fecc1a767e6021b622d5fbec1df
|
| 3 |
+
size 1064
|
checkpoint-8/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-8/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-8/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-8/trainer_state.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0012675024260788625,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8,
|
| 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 |
+
"logging_steps": 1,
|
| 205 |
+
"max_steps": 18933,
|
| 206 |
+
"num_input_tokens_seen": 0,
|
| 207 |
+
"num_train_epochs": 3,
|
| 208 |
+
"save_steps": 8,
|
| 209 |
+
"total_flos": 4025485044940800.0,
|
| 210 |
+
"train_batch_size": 4,
|
| 211 |
+
"trial_name": null,
|
| 212 |
+
"trial_params": null
|
| 213 |
+
}
|
checkpoint-8/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dee1690a11bb3358d66a6ba11dd88327a96654a51c9007c2a9830994ea29f7c
|
| 3 |
+
size 5240
|
runs/May03_18-30-59_2efa04e46d11/events.out.tfevents.1714761060.2efa04e46d11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89bfec4a8424b547e2ea0c673671d468c94d90a59049f88a31308dbdae5183fe
|
| 3 |
+
size 36776
|