Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Power_Time_SFT/checkpoint-400/README.md +202 -0
- Power_Time_SFT/checkpoint-400/adapter_config.json +34 -0
- Power_Time_SFT/checkpoint-400/added_tokens.json +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_0.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_1.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_2.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_3.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_4.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_5.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_6.pth +3 -0
- Power_Time_SFT/checkpoint-400/rng_state_7.pth +3 -0
- Power_Time_SFT/checkpoint-400/scheduler.pt +3 -0
- Power_Time_SFT/checkpoint-400/special_tokens_map.json +36 -0
- Power_Time_SFT/checkpoint-400/tokenizer.json +0 -0
- Power_Time_SFT/checkpoint-400/tokenizer.model +3 -0
- Power_Time_SFT/checkpoint-400/tokenizer_config.json +59 -0
- Power_Time_SFT/checkpoint-400/trainer_state.json +633 -0
- Power_Time_SFT/checkpoint-400/training_args.bin +3 -0
- Power_Time_SFT/checkpoint-500/README.md +202 -0
- Power_Time_SFT/checkpoint-500/adapter_config.json +34 -0
- Power_Time_SFT/checkpoint-500/added_tokens.json +3 -0
- Power_Time_SFT/checkpoint-500/rng_state_4.pth +3 -0
- Power_Time_SFT/checkpoint-500/rng_state_5.pth +3 -0
- Power_Time_SFT/checkpoint-500/rng_state_7.pth +3 -0
- Power_Time_SFT/checkpoint-500/special_tokens_map.json +36 -0
- Power_Time_SFT/checkpoint-500/tokenizer.json +0 -0
- Power_Time_SFT/checkpoint-500/tokenizer_config.json +59 -0
- Power_Time_SFT/checkpoint-500/trainer_state.json +783 -0
- Power_Time_SFT/checkpoint-540/README.md +202 -0
- Power_Time_SFT/checkpoint-540/adapter_config.json +34 -0
- Power_Time_SFT/checkpoint-540/added_tokens.json +3 -0
- Power_Time_SFT/checkpoint-540/special_tokens_map.json +36 -0
- Power_Time_SFT/checkpoint-540/tokenizer.json +0 -0
- Power_Time_SFT/checkpoint-540/tokenizer_config.json +59 -0
- Power_Time_SFT/checkpoint-540/trainer_state.json +843 -0
- Time_SFT/README.md +62 -0
- Time_SFT/adapter_config.json +34 -0
- Time_SFT/added_tokens.json +3 -0
- Time_SFT/all_results.json +8 -0
- Time_SFT/checkpoint-100/README.md +202 -0
- Time_SFT/checkpoint-100/adapter_config.json +34 -0
- Time_SFT/checkpoint-100/added_tokens.json +3 -0
- Time_SFT/checkpoint-100/special_tokens_map.json +36 -0
- Time_SFT/checkpoint-100/tokenizer.json +0 -0
- Time_SFT/checkpoint-100/tokenizer_config.json +59 -0
- Time_SFT/checkpoint-100/trainer_state.json +183 -0
- Time_SFT/checkpoint-200/README.md +202 -0
- Time_SFT/checkpoint-200/adapter_config.json +34 -0
- Time_SFT/checkpoint-200/added_tokens.json +3 -0
- Time_SFT/checkpoint-200/special_tokens_map.json +36 -0
Power_Time_SFT/checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 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 0.12.0
|
Power_Time_SFT/checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Time_SFT/checkpoint-400/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Power_Time_SFT/checkpoint-400/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07d994b317c4df888a1a1aabc0c532e81f1fa34c18c8313cb2feadca3bb37194
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f5b05860618aa49c7f5d8c366d6ee73cf8b3b0d0adc17d9313b72621630d0aa
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7262faf861e984775b4fd85bc76a11b0b8b04037690e8a08a58cf9ff5328a042
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9479cad91150e2e266d17eb95fe678579a770f6df6b53496cf72067b186b094d
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:435cb6cf559e0ce3fe0d4582cac16ea40b48b7a64589952402a4c399cafbfc00
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f51001b0d8dc5792180c3a9705ccbfa66b61d46d7639afb6f7abf409629ed74f
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1e87084f11088fdce293e1fbbb05e35f5c7385b00e2f9ba195bf61cb36f757d
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d32e9bdd65145ae509e6c6ef4f6ea9d842f94a34c34a0d7d2ab6c248d3f2121
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56d28ffb6027f5e1e5c39e331ccc5af5bd59576b529e2c08ae15b4349ce86568
|
| 3 |
+
size 1064
|
Power_Time_SFT/checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Power_Time_SFT/checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Time_SFT/checkpoint-400/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
Power_Time_SFT/checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Power_Time_SFT/checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.479638009049774,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36199095022624433,
|
| 13 |
+
"grad_norm": 4.351782321929932,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": -2.3496108055114746,
|
| 16 |
+
"logits/rejected": -2.354576349258423,
|
| 17 |
+
"logps/chosen": -86.63139343261719,
|
| 18 |
+
"logps/rejected": -76.90333557128906,
|
| 19 |
+
"loss": 0.6923,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": -0.00019822348258458078,
|
| 22 |
+
"rewards/margins": -0.002337233629077673,
|
| 23 |
+
"rewards/rejected": 0.00213901000097394,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7239819004524887,
|
| 28 |
+
"grad_norm": 3.8085336685180664,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": -2.3482470512390137,
|
| 31 |
+
"logits/rejected": -2.3420329093933105,
|
| 32 |
+
"logps/chosen": -73.18113708496094,
|
| 33 |
+
"logps/rejected": -72.52565002441406,
|
| 34 |
+
"loss": 0.6943,
|
| 35 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 36 |
+
"rewards/chosen": 0.00011640912998700514,
|
| 37 |
+
"rewards/margins": -0.002153881825506687,
|
| 38 |
+
"rewards/rejected": 0.002270291093736887,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.085972850678733,
|
| 43 |
+
"grad_norm": 5.329021453857422,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": -2.3689351081848145,
|
| 46 |
+
"logits/rejected": -2.3885178565979004,
|
| 47 |
+
"logps/chosen": -72.15180969238281,
|
| 48 |
+
"logps/rejected": -74.70518493652344,
|
| 49 |
+
"loss": 0.6924,
|
| 50 |
+
"rewards/accuracies": 0.5625,
|
| 51 |
+
"rewards/chosen": 0.0020837264601141214,
|
| 52 |
+
"rewards/margins": 0.00603193324059248,
|
| 53 |
+
"rewards/rejected": -0.0039482079446315765,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4479638009049773,
|
| 58 |
+
"grad_norm": 3.671722888946533,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": -2.3091399669647217,
|
| 61 |
+
"logits/rejected": -2.3273236751556396,
|
| 62 |
+
"logps/chosen": -69.45216369628906,
|
| 63 |
+
"logps/rejected": -260.0699157714844,
|
| 64 |
+
"loss": 0.6899,
|
| 65 |
+
"rewards/accuracies": 0.550000011920929,
|
| 66 |
+
"rewards/chosen": -0.0094170942902565,
|
| 67 |
+
"rewards/margins": 0.14604035019874573,
|
| 68 |
+
"rewards/rejected": -0.15545745193958282,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8099547511312217,
|
| 73 |
+
"grad_norm": 4.172375679016113,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": -2.31831693649292,
|
| 76 |
+
"logits/rejected": -2.335618495941162,
|
| 77 |
+
"logps/chosen": -72.82856750488281,
|
| 78 |
+
"logps/rejected": -90.61243438720703,
|
| 79 |
+
"loss": 0.6865,
|
| 80 |
+
"rewards/accuracies": 0.625,
|
| 81 |
+
"rewards/chosen": -0.01846747286617756,
|
| 82 |
+
"rewards/margins": 0.015672579407691956,
|
| 83 |
+
"rewards/rejected": -0.034140050411224365,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.171945701357466,
|
| 88 |
+
"grad_norm": 4.386168479919434,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": -2.3203041553497314,
|
| 91 |
+
"logits/rejected": -2.3315658569335938,
|
| 92 |
+
"logps/chosen": -67.68244934082031,
|
| 93 |
+
"logps/rejected": -86.2356185913086,
|
| 94 |
+
"loss": 0.6775,
|
| 95 |
+
"rewards/accuracies": 0.637499988079071,
|
| 96 |
+
"rewards/chosen": -0.03993881493806839,
|
| 97 |
+
"rewards/margins": 0.027381544932723045,
|
| 98 |
+
"rewards/rejected": -0.06732036173343658,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5339366515837103,
|
| 103 |
+
"grad_norm": 4.38440465927124,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": -2.3607311248779297,
|
| 106 |
+
"logits/rejected": -2.3799984455108643,
|
| 107 |
+
"logps/chosen": -72.8117904663086,
|
| 108 |
+
"logps/rejected": -79.02535247802734,
|
| 109 |
+
"loss": 0.6636,
|
| 110 |
+
"rewards/accuracies": 0.6875,
|
| 111 |
+
"rewards/chosen": -0.06544635444879532,
|
| 112 |
+
"rewards/margins": 0.069185271859169,
|
| 113 |
+
"rewards/rejected": -0.13463163375854492,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8959276018099547,
|
| 118 |
+
"grad_norm": 4.333106517791748,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": -2.392198324203491,
|
| 121 |
+
"logits/rejected": -2.3854451179504395,
|
| 122 |
+
"logps/chosen": -64.03775787353516,
|
| 123 |
+
"logps/rejected": -71.01383972167969,
|
| 124 |
+
"loss": 0.6473,
|
| 125 |
+
"rewards/accuracies": 0.75,
|
| 126 |
+
"rewards/chosen": -0.09924488514661789,
|
| 127 |
+
"rewards/margins": 0.1070803552865982,
|
| 128 |
+
"rewards/rejected": -0.2063252478837967,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.257918552036199,
|
| 133 |
+
"grad_norm": 4.575820446014404,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": -2.3316967487335205,
|
| 136 |
+
"logits/rejected": -2.3399548530578613,
|
| 137 |
+
"logps/chosen": -66.9199447631836,
|
| 138 |
+
"logps/rejected": -67.97264099121094,
|
| 139 |
+
"loss": 0.6292,
|
| 140 |
+
"rewards/accuracies": 0.675000011920929,
|
| 141 |
+
"rewards/chosen": -0.1342274248600006,
|
| 142 |
+
"rewards/margins": 0.1109505444765091,
|
| 143 |
+
"rewards/rejected": -0.2451779842376709,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6199095022624435,
|
| 148 |
+
"grad_norm": 4.666302680969238,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": -2.3398795127868652,
|
| 151 |
+
"logits/rejected": -2.3582355976104736,
|
| 152 |
+
"logps/chosen": -76.05484771728516,
|
| 153 |
+
"logps/rejected": -78.4997787475586,
|
| 154 |
+
"loss": 0.6015,
|
| 155 |
+
"rewards/accuracies": 0.75,
|
| 156 |
+
"rewards/chosen": -0.15528908371925354,
|
| 157 |
+
"rewards/margins": 0.17627069354057312,
|
| 158 |
+
"rewards/rejected": -0.33155977725982666,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.981900452488688,
|
| 163 |
+
"grad_norm": 4.472248554229736,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": -2.3747470378875732,
|
| 166 |
+
"logits/rejected": -2.3589282035827637,
|
| 167 |
+
"logps/chosen": -75.08245086669922,
|
| 168 |
+
"logps/rejected": -88.42532348632812,
|
| 169 |
+
"loss": 0.582,
|
| 170 |
+
"rewards/accuracies": 0.762499988079071,
|
| 171 |
+
"rewards/chosen": -0.22706560790538788,
|
| 172 |
+
"rewards/margins": 0.2718750834465027,
|
| 173 |
+
"rewards/rejected": -0.49894070625305176,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.343891402714932,
|
| 178 |
+
"grad_norm": 4.420746326446533,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": -2.3004438877105713,
|
| 181 |
+
"logits/rejected": -2.33561635017395,
|
| 182 |
+
"logps/chosen": -92.03379821777344,
|
| 183 |
+
"logps/rejected": -84.3415298461914,
|
| 184 |
+
"loss": 0.5537,
|
| 185 |
+
"rewards/accuracies": 0.75,
|
| 186 |
+
"rewards/chosen": -0.2706041932106018,
|
| 187 |
+
"rewards/margins": 0.2943420112133026,
|
| 188 |
+
"rewards/rejected": -0.564946174621582,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.705882352941177,
|
| 193 |
+
"grad_norm": 4.54348611831665,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": -2.4000728130340576,
|
| 196 |
+
"logits/rejected": -2.3912758827209473,
|
| 197 |
+
"logps/chosen": -70.9849624633789,
|
| 198 |
+
"logps/rejected": -79.27720642089844,
|
| 199 |
+
"loss": 0.5306,
|
| 200 |
+
"rewards/accuracies": 0.800000011920929,
|
| 201 |
+
"rewards/chosen": -0.2949373126029968,
|
| 202 |
+
"rewards/margins": 0.4063098430633545,
|
| 203 |
+
"rewards/rejected": -0.7012470960617065,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.067873303167421,
|
| 208 |
+
"grad_norm": 4.43679141998291,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": -2.3637630939483643,
|
| 211 |
+
"logits/rejected": -2.3869171142578125,
|
| 212 |
+
"logps/chosen": -63.164039611816406,
|
| 213 |
+
"logps/rejected": -78.0440673828125,
|
| 214 |
+
"loss": 0.5028,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.2740551233291626,
|
| 217 |
+
"rewards/margins": 0.5061118006706238,
|
| 218 |
+
"rewards/rejected": -0.7801669836044312,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.429864253393665,
|
| 223 |
+
"grad_norm": 4.934199810028076,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": -2.342858076095581,
|
| 226 |
+
"logits/rejected": -2.3417344093322754,
|
| 227 |
+
"logps/chosen": -80.54903411865234,
|
| 228 |
+
"logps/rejected": -79.4267807006836,
|
| 229 |
+
"loss": 0.4663,
|
| 230 |
+
"rewards/accuracies": 0.8125,
|
| 231 |
+
"rewards/chosen": -0.3702576756477356,
|
| 232 |
+
"rewards/margins": 0.5886551141738892,
|
| 233 |
+
"rewards/rejected": -0.95891273021698,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.791855203619909,
|
| 238 |
+
"grad_norm": 5.551158905029297,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": -2.36419415473938,
|
| 241 |
+
"logits/rejected": -2.388049364089966,
|
| 242 |
+
"logps/chosen": -69.40000915527344,
|
| 243 |
+
"logps/rejected": -91.36970520019531,
|
| 244 |
+
"loss": 0.4636,
|
| 245 |
+
"rewards/accuracies": 0.875,
|
| 246 |
+
"rewards/chosen": -0.42509594559669495,
|
| 247 |
+
"rewards/margins": 0.7187294363975525,
|
| 248 |
+
"rewards/rejected": -1.1438252925872803,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.153846153846154,
|
| 253 |
+
"grad_norm": 4.6863555908203125,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": -2.3798611164093018,
|
| 256 |
+
"logits/rejected": -2.388327121734619,
|
| 257 |
+
"logps/chosen": -84.27762603759766,
|
| 258 |
+
"logps/rejected": -95.46641540527344,
|
| 259 |
+
"loss": 0.4245,
|
| 260 |
+
"rewards/accuracies": 0.949999988079071,
|
| 261 |
+
"rewards/chosen": -0.4049956202507019,
|
| 262 |
+
"rewards/margins": 0.965179443359375,
|
| 263 |
+
"rewards/rejected": -1.3701750040054321,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.515837104072398,
|
| 268 |
+
"grad_norm": 5.001020431518555,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": -2.376713991165161,
|
| 271 |
+
"logits/rejected": -2.413689374923706,
|
| 272 |
+
"logps/chosen": -75.96709442138672,
|
| 273 |
+
"logps/rejected": -88.12495422363281,
|
| 274 |
+
"loss": 0.449,
|
| 275 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 276 |
+
"rewards/chosen": -0.3547631800174713,
|
| 277 |
+
"rewards/margins": 0.8548161387443542,
|
| 278 |
+
"rewards/rejected": -1.2095792293548584,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.877828054298643,
|
| 283 |
+
"grad_norm": 5.340312957763672,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": -2.385936737060547,
|
| 286 |
+
"logits/rejected": -2.4080803394317627,
|
| 287 |
+
"logps/chosen": -66.79461669921875,
|
| 288 |
+
"logps/rejected": -85.04891204833984,
|
| 289 |
+
"loss": 0.3764,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.4008978307247162,
|
| 292 |
+
"rewards/margins": 0.8593969345092773,
|
| 293 |
+
"rewards/rejected": -1.2602946758270264,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.239819004524887,
|
| 298 |
+
"grad_norm": 4.7585883140563965,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": -2.4034409523010254,
|
| 301 |
+
"logits/rejected": -2.425673246383667,
|
| 302 |
+
"logps/chosen": -78.95824432373047,
|
| 303 |
+
"logps/rejected": -92.42652893066406,
|
| 304 |
+
"loss": 0.3362,
|
| 305 |
+
"rewards/accuracies": 0.949999988079071,
|
| 306 |
+
"rewards/chosen": -0.5016047358512878,
|
| 307 |
+
"rewards/margins": 1.3585138320922852,
|
| 308 |
+
"rewards/rejected": -1.8601186275482178,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.601809954751131,
|
| 313 |
+
"grad_norm": 5.299131870269775,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": -2.405515193939209,
|
| 316 |
+
"logits/rejected": -2.4070794582366943,
|
| 317 |
+
"logps/chosen": -70.76835632324219,
|
| 318 |
+
"logps/rejected": -94.3203353881836,
|
| 319 |
+
"loss": 0.317,
|
| 320 |
+
"rewards/accuracies": 0.987500011920929,
|
| 321 |
+
"rewards/chosen": -0.7332154512405396,
|
| 322 |
+
"rewards/margins": 1.352203130722046,
|
| 323 |
+
"rewards/rejected": -2.085418701171875,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.963800904977376,
|
| 328 |
+
"grad_norm": 6.385330677032471,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": -2.3782029151916504,
|
| 331 |
+
"logits/rejected": -2.3890140056610107,
|
| 332 |
+
"logps/chosen": -74.07151794433594,
|
| 333 |
+
"logps/rejected": -97.96099853515625,
|
| 334 |
+
"loss": 0.3338,
|
| 335 |
+
"rewards/accuracies": 0.875,
|
| 336 |
+
"rewards/chosen": -0.8589820861816406,
|
| 337 |
+
"rewards/margins": 1.498375415802002,
|
| 338 |
+
"rewards/rejected": -2.3573575019836426,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.32579185520362,
|
| 343 |
+
"grad_norm": 5.3784027099609375,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": -2.411106586456299,
|
| 346 |
+
"logits/rejected": -2.4102063179016113,
|
| 347 |
+
"logps/chosen": -78.97357940673828,
|
| 348 |
+
"logps/rejected": -104.22176361083984,
|
| 349 |
+
"loss": 0.2894,
|
| 350 |
+
"rewards/accuracies": 0.9375,
|
| 351 |
+
"rewards/chosen": -0.850872814655304,
|
| 352 |
+
"rewards/margins": 1.5754810571670532,
|
| 353 |
+
"rewards/rejected": -2.426353931427002,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.687782805429864,
|
| 358 |
+
"grad_norm": 5.306555271148682,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": -2.3758366107940674,
|
| 361 |
+
"logits/rejected": -2.393923282623291,
|
| 362 |
+
"logps/chosen": -75.22766876220703,
|
| 363 |
+
"logps/rejected": -105.24629211425781,
|
| 364 |
+
"loss": 0.2666,
|
| 365 |
+
"rewards/accuracies": 0.949999988079071,
|
| 366 |
+
"rewards/chosen": -0.6813958287239075,
|
| 367 |
+
"rewards/margins": 1.697392225265503,
|
| 368 |
+
"rewards/rejected": -2.3787879943847656,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.049773755656108,
|
| 373 |
+
"grad_norm": 5.835656642913818,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": -2.345181465148926,
|
| 376 |
+
"logits/rejected": -2.3525192737579346,
|
| 377 |
+
"logps/chosen": -99.5466537475586,
|
| 378 |
+
"logps/rejected": -115.3326644897461,
|
| 379 |
+
"loss": 0.2556,
|
| 380 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 381 |
+
"rewards/chosen": -1.1117511987686157,
|
| 382 |
+
"rewards/margins": 1.774484634399414,
|
| 383 |
+
"rewards/rejected": -2.8862357139587402,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.411764705882353,
|
| 388 |
+
"grad_norm": 5.279304504394531,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": -2.3707776069641113,
|
| 391 |
+
"logits/rejected": -2.3579325675964355,
|
| 392 |
+
"logps/chosen": -107.48176574707031,
|
| 393 |
+
"logps/rejected": -119.63212585449219,
|
| 394 |
+
"loss": 0.223,
|
| 395 |
+
"rewards/accuracies": 1.0,
|
| 396 |
+
"rewards/chosen": -1.34574556350708,
|
| 397 |
+
"rewards/margins": 2.105149745941162,
|
| 398 |
+
"rewards/rejected": -3.450894832611084,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.773755656108598,
|
| 403 |
+
"grad_norm": 6.106879711151123,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": -2.367492198944092,
|
| 406 |
+
"logits/rejected": -2.3800530433654785,
|
| 407 |
+
"logps/chosen": -94.10942077636719,
|
| 408 |
+
"logps/rejected": -108.04286193847656,
|
| 409 |
+
"loss": 0.2108,
|
| 410 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 411 |
+
"rewards/chosen": -1.319504976272583,
|
| 412 |
+
"rewards/margins": 2.0621278285980225,
|
| 413 |
+
"rewards/rejected": -3.3816330432891846,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.135746606334841,
|
| 418 |
+
"grad_norm": 4.824020862579346,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": -2.29042649269104,
|
| 421 |
+
"logits/rejected": -2.2942726612091064,
|
| 422 |
+
"logps/chosen": -88.15667724609375,
|
| 423 |
+
"logps/rejected": -116.263671875,
|
| 424 |
+
"loss": 0.2067,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.352482795715332,
|
| 427 |
+
"rewards/margins": 2.1809113025665283,
|
| 428 |
+
"rewards/rejected": -3.5333938598632812,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.497737556561086,
|
| 433 |
+
"grad_norm": 5.073860168457031,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": -2.319164276123047,
|
| 436 |
+
"logits/rejected": -2.327695846557617,
|
| 437 |
+
"logps/chosen": -89.06367492675781,
|
| 438 |
+
"logps/rejected": -113.19393157958984,
|
| 439 |
+
"loss": 0.1791,
|
| 440 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 441 |
+
"rewards/chosen": -1.4301341772079468,
|
| 442 |
+
"rewards/margins": 2.2849090099334717,
|
| 443 |
+
"rewards/rejected": -3.715043306350708,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.85972850678733,
|
| 448 |
+
"grad_norm": 6.990862846374512,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": -2.322035551071167,
|
| 451 |
+
"logits/rejected": -2.343055248260498,
|
| 452 |
+
"logps/chosen": -79.6242904663086,
|
| 453 |
+
"logps/rejected": -117.89810943603516,
|
| 454 |
+
"loss": 0.173,
|
| 455 |
+
"rewards/accuracies": 0.949999988079071,
|
| 456 |
+
"rewards/chosen": -1.5006747245788574,
|
| 457 |
+
"rewards/margins": 2.6087098121643066,
|
| 458 |
+
"rewards/rejected": -4.109384059906006,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.221719457013574,
|
| 463 |
+
"grad_norm": 4.418057918548584,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": -2.313563585281372,
|
| 466 |
+
"logits/rejected": -2.3379547595977783,
|
| 467 |
+
"logps/chosen": -96.51193237304688,
|
| 468 |
+
"logps/rejected": -128.72109985351562,
|
| 469 |
+
"loss": 0.1525,
|
| 470 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 471 |
+
"rewards/chosen": -1.7700340747833252,
|
| 472 |
+
"rewards/margins": 2.5669429302215576,
|
| 473 |
+
"rewards/rejected": -4.336977005004883,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.583710407239819,
|
| 478 |
+
"grad_norm": 5.5379638671875,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": -2.3077690601348877,
|
| 481 |
+
"logits/rejected": -2.3094325065612793,
|
| 482 |
+
"logps/chosen": -97.48485565185547,
|
| 483 |
+
"logps/rejected": -120.9418716430664,
|
| 484 |
+
"loss": 0.1367,
|
| 485 |
+
"rewards/accuracies": 0.987500011920929,
|
| 486 |
+
"rewards/chosen": -1.6908330917358398,
|
| 487 |
+
"rewards/margins": 2.76543927192688,
|
| 488 |
+
"rewards/rejected": -4.456272602081299,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.945701357466064,
|
| 493 |
+
"grad_norm": 8.315099716186523,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": -2.2925028800964355,
|
| 496 |
+
"logits/rejected": -2.31669545173645,
|
| 497 |
+
"logps/chosen": -88.35062408447266,
|
| 498 |
+
"logps/rejected": -125.6523208618164,
|
| 499 |
+
"loss": 0.1436,
|
| 500 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 501 |
+
"rewards/chosen": -2.12321400642395,
|
| 502 |
+
"rewards/margins": 2.9592180252075195,
|
| 503 |
+
"rewards/rejected": -5.082431316375732,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.307692307692308,
|
| 508 |
+
"grad_norm": 5.883168697357178,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": -2.2664735317230225,
|
| 511 |
+
"logits/rejected": -2.3047263622283936,
|
| 512 |
+
"logps/chosen": -87.54987335205078,
|
| 513 |
+
"logps/rejected": -120.87919616699219,
|
| 514 |
+
"loss": 0.1185,
|
| 515 |
+
"rewards/accuracies": 0.987500011920929,
|
| 516 |
+
"rewards/chosen": -1.9975258111953735,
|
| 517 |
+
"rewards/margins": 3.0641627311706543,
|
| 518 |
+
"rewards/rejected": -5.061688423156738,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.669683257918551,
|
| 523 |
+
"grad_norm": 4.8013458251953125,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": -2.2390546798706055,
|
| 526 |
+
"logits/rejected": -2.233534097671509,
|
| 527 |
+
"logps/chosen": -102.70186614990234,
|
| 528 |
+
"logps/rejected": -136.1205291748047,
|
| 529 |
+
"loss": 0.111,
|
| 530 |
+
"rewards/accuracies": 0.987500011920929,
|
| 531 |
+
"rewards/chosen": -2.10892915725708,
|
| 532 |
+
"rewards/margins": 3.2926182746887207,
|
| 533 |
+
"rewards/rejected": -5.401547431945801,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 13.031674208144796,
|
| 538 |
+
"grad_norm": 4.820348739624023,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": -2.2781853675842285,
|
| 541 |
+
"logits/rejected": -2.3037526607513428,
|
| 542 |
+
"logps/chosen": -94.27687072753906,
|
| 543 |
+
"logps/rejected": -143.52162170410156,
|
| 544 |
+
"loss": 0.1133,
|
| 545 |
+
"rewards/accuracies": 0.987500011920929,
|
| 546 |
+
"rewards/chosen": -2.185966730117798,
|
| 547 |
+
"rewards/margins": 3.149972438812256,
|
| 548 |
+
"rewards/rejected": -5.335939884185791,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.393665158371041,
|
| 553 |
+
"grad_norm": 4.292584419250488,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": -2.260101079940796,
|
| 556 |
+
"logits/rejected": -2.270853042602539,
|
| 557 |
+
"logps/chosen": -112.0027847290039,
|
| 558 |
+
"logps/rejected": -155.92738342285156,
|
| 559 |
+
"loss": 0.0866,
|
| 560 |
+
"rewards/accuracies": 1.0,
|
| 561 |
+
"rewards/chosen": -2.6447501182556152,
|
| 562 |
+
"rewards/margins": 3.6627235412597656,
|
| 563 |
+
"rewards/rejected": -6.307473659515381,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.755656108597286,
|
| 568 |
+
"grad_norm": 4.569724082946777,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": -2.2924914360046387,
|
| 571 |
+
"logits/rejected": -2.3221309185028076,
|
| 572 |
+
"logps/chosen": -104.69401550292969,
|
| 573 |
+
"logps/rejected": -138.05264282226562,
|
| 574 |
+
"loss": 0.0953,
|
| 575 |
+
"rewards/accuracies": 0.987500011920929,
|
| 576 |
+
"rewards/chosen": -2.8196561336517334,
|
| 577 |
+
"rewards/margins": 3.5180962085723877,
|
| 578 |
+
"rewards/rejected": -6.337752342224121,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.117647058823529,
|
| 583 |
+
"grad_norm": 4.538058280944824,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": -2.2493948936462402,
|
| 586 |
+
"logits/rejected": -2.2872321605682373,
|
| 587 |
+
"logps/chosen": -102.8060531616211,
|
| 588 |
+
"logps/rejected": -135.58599853515625,
|
| 589 |
+
"loss": 0.0879,
|
| 590 |
+
"rewards/accuracies": 0.987500011920929,
|
| 591 |
+
"rewards/chosen": -2.9318606853485107,
|
| 592 |
+
"rewards/margins": 3.4618797302246094,
|
| 593 |
+
"rewards/rejected": -6.393740177154541,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.479638009049774,
|
| 598 |
+
"grad_norm": 4.173523426055908,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": -2.246553659439087,
|
| 601 |
+
"logits/rejected": -2.2457058429718018,
|
| 602 |
+
"logps/chosen": -109.64227294921875,
|
| 603 |
+
"logps/rejected": -147.6108856201172,
|
| 604 |
+
"loss": 0.0783,
|
| 605 |
+
"rewards/accuracies": 0.987500011920929,
|
| 606 |
+
"rewards/chosen": -2.916919708251953,
|
| 607 |
+
"rewards/margins": 3.4423089027404785,
|
| 608 |
+
"rewards/rejected": -6.359227657318115,
|
| 609 |
+
"step": 400
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 10,
|
| 613 |
+
"max_steps": 540,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 20,
|
| 616 |
+
"save_steps": 100,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 1.4780471294474322e+18,
|
| 630 |
+
"train_batch_size": 1,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
Power_Time_SFT/checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e50105b8507db6fa7203d9222c5383f7882ce3ab89ab4c08bf6b529a525993e
|
| 3 |
+
size 5368
|
Power_Time_SFT/checkpoint-500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 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 0.12.0
|
Power_Time_SFT/checkpoint-500/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Time_SFT/checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Power_Time_SFT/checkpoint-500/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45f7f10857a0bfbb73af85f384029b8392fbfefbee0de21b050fba883244c2c4
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-500/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632333e189d17bf4deb60a342ba16da53e8056c7cac6295fad33eda84d4104a4
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-500/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cc09b08b3c4e19867b731c6c4acc49dd500202da095249952fda571d4a7ab4d
|
| 3 |
+
size 15984
|
Power_Time_SFT/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Power_Time_SFT/checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Time_SFT/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Power_Time_SFT/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.099547511312217,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36199095022624433,
|
| 13 |
+
"grad_norm": 4.351782321929932,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": -2.3496108055114746,
|
| 16 |
+
"logits/rejected": -2.354576349258423,
|
| 17 |
+
"logps/chosen": -86.63139343261719,
|
| 18 |
+
"logps/rejected": -76.90333557128906,
|
| 19 |
+
"loss": 0.6923,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": -0.00019822348258458078,
|
| 22 |
+
"rewards/margins": -0.002337233629077673,
|
| 23 |
+
"rewards/rejected": 0.00213901000097394,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7239819004524887,
|
| 28 |
+
"grad_norm": 3.8085336685180664,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": -2.3482470512390137,
|
| 31 |
+
"logits/rejected": -2.3420329093933105,
|
| 32 |
+
"logps/chosen": -73.18113708496094,
|
| 33 |
+
"logps/rejected": -72.52565002441406,
|
| 34 |
+
"loss": 0.6943,
|
| 35 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 36 |
+
"rewards/chosen": 0.00011640912998700514,
|
| 37 |
+
"rewards/margins": -0.002153881825506687,
|
| 38 |
+
"rewards/rejected": 0.002270291093736887,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.085972850678733,
|
| 43 |
+
"grad_norm": 5.329021453857422,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": -2.3689351081848145,
|
| 46 |
+
"logits/rejected": -2.3885178565979004,
|
| 47 |
+
"logps/chosen": -72.15180969238281,
|
| 48 |
+
"logps/rejected": -74.70518493652344,
|
| 49 |
+
"loss": 0.6924,
|
| 50 |
+
"rewards/accuracies": 0.5625,
|
| 51 |
+
"rewards/chosen": 0.0020837264601141214,
|
| 52 |
+
"rewards/margins": 0.00603193324059248,
|
| 53 |
+
"rewards/rejected": -0.0039482079446315765,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4479638009049773,
|
| 58 |
+
"grad_norm": 3.671722888946533,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": -2.3091399669647217,
|
| 61 |
+
"logits/rejected": -2.3273236751556396,
|
| 62 |
+
"logps/chosen": -69.45216369628906,
|
| 63 |
+
"logps/rejected": -260.0699157714844,
|
| 64 |
+
"loss": 0.6899,
|
| 65 |
+
"rewards/accuracies": 0.550000011920929,
|
| 66 |
+
"rewards/chosen": -0.0094170942902565,
|
| 67 |
+
"rewards/margins": 0.14604035019874573,
|
| 68 |
+
"rewards/rejected": -0.15545745193958282,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8099547511312217,
|
| 73 |
+
"grad_norm": 4.172375679016113,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": -2.31831693649292,
|
| 76 |
+
"logits/rejected": -2.335618495941162,
|
| 77 |
+
"logps/chosen": -72.82856750488281,
|
| 78 |
+
"logps/rejected": -90.61243438720703,
|
| 79 |
+
"loss": 0.6865,
|
| 80 |
+
"rewards/accuracies": 0.625,
|
| 81 |
+
"rewards/chosen": -0.01846747286617756,
|
| 82 |
+
"rewards/margins": 0.015672579407691956,
|
| 83 |
+
"rewards/rejected": -0.034140050411224365,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.171945701357466,
|
| 88 |
+
"grad_norm": 4.386168479919434,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": -2.3203041553497314,
|
| 91 |
+
"logits/rejected": -2.3315658569335938,
|
| 92 |
+
"logps/chosen": -67.68244934082031,
|
| 93 |
+
"logps/rejected": -86.2356185913086,
|
| 94 |
+
"loss": 0.6775,
|
| 95 |
+
"rewards/accuracies": 0.637499988079071,
|
| 96 |
+
"rewards/chosen": -0.03993881493806839,
|
| 97 |
+
"rewards/margins": 0.027381544932723045,
|
| 98 |
+
"rewards/rejected": -0.06732036173343658,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5339366515837103,
|
| 103 |
+
"grad_norm": 4.38440465927124,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": -2.3607311248779297,
|
| 106 |
+
"logits/rejected": -2.3799984455108643,
|
| 107 |
+
"logps/chosen": -72.8117904663086,
|
| 108 |
+
"logps/rejected": -79.02535247802734,
|
| 109 |
+
"loss": 0.6636,
|
| 110 |
+
"rewards/accuracies": 0.6875,
|
| 111 |
+
"rewards/chosen": -0.06544635444879532,
|
| 112 |
+
"rewards/margins": 0.069185271859169,
|
| 113 |
+
"rewards/rejected": -0.13463163375854492,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8959276018099547,
|
| 118 |
+
"grad_norm": 4.333106517791748,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": -2.392198324203491,
|
| 121 |
+
"logits/rejected": -2.3854451179504395,
|
| 122 |
+
"logps/chosen": -64.03775787353516,
|
| 123 |
+
"logps/rejected": -71.01383972167969,
|
| 124 |
+
"loss": 0.6473,
|
| 125 |
+
"rewards/accuracies": 0.75,
|
| 126 |
+
"rewards/chosen": -0.09924488514661789,
|
| 127 |
+
"rewards/margins": 0.1070803552865982,
|
| 128 |
+
"rewards/rejected": -0.2063252478837967,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.257918552036199,
|
| 133 |
+
"grad_norm": 4.575820446014404,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": -2.3316967487335205,
|
| 136 |
+
"logits/rejected": -2.3399548530578613,
|
| 137 |
+
"logps/chosen": -66.9199447631836,
|
| 138 |
+
"logps/rejected": -67.97264099121094,
|
| 139 |
+
"loss": 0.6292,
|
| 140 |
+
"rewards/accuracies": 0.675000011920929,
|
| 141 |
+
"rewards/chosen": -0.1342274248600006,
|
| 142 |
+
"rewards/margins": 0.1109505444765091,
|
| 143 |
+
"rewards/rejected": -0.2451779842376709,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6199095022624435,
|
| 148 |
+
"grad_norm": 4.666302680969238,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": -2.3398795127868652,
|
| 151 |
+
"logits/rejected": -2.3582355976104736,
|
| 152 |
+
"logps/chosen": -76.05484771728516,
|
| 153 |
+
"logps/rejected": -78.4997787475586,
|
| 154 |
+
"loss": 0.6015,
|
| 155 |
+
"rewards/accuracies": 0.75,
|
| 156 |
+
"rewards/chosen": -0.15528908371925354,
|
| 157 |
+
"rewards/margins": 0.17627069354057312,
|
| 158 |
+
"rewards/rejected": -0.33155977725982666,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.981900452488688,
|
| 163 |
+
"grad_norm": 4.472248554229736,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": -2.3747470378875732,
|
| 166 |
+
"logits/rejected": -2.3589282035827637,
|
| 167 |
+
"logps/chosen": -75.08245086669922,
|
| 168 |
+
"logps/rejected": -88.42532348632812,
|
| 169 |
+
"loss": 0.582,
|
| 170 |
+
"rewards/accuracies": 0.762499988079071,
|
| 171 |
+
"rewards/chosen": -0.22706560790538788,
|
| 172 |
+
"rewards/margins": 0.2718750834465027,
|
| 173 |
+
"rewards/rejected": -0.49894070625305176,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.343891402714932,
|
| 178 |
+
"grad_norm": 4.420746326446533,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": -2.3004438877105713,
|
| 181 |
+
"logits/rejected": -2.33561635017395,
|
| 182 |
+
"logps/chosen": -92.03379821777344,
|
| 183 |
+
"logps/rejected": -84.3415298461914,
|
| 184 |
+
"loss": 0.5537,
|
| 185 |
+
"rewards/accuracies": 0.75,
|
| 186 |
+
"rewards/chosen": -0.2706041932106018,
|
| 187 |
+
"rewards/margins": 0.2943420112133026,
|
| 188 |
+
"rewards/rejected": -0.564946174621582,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.705882352941177,
|
| 193 |
+
"grad_norm": 4.54348611831665,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": -2.4000728130340576,
|
| 196 |
+
"logits/rejected": -2.3912758827209473,
|
| 197 |
+
"logps/chosen": -70.9849624633789,
|
| 198 |
+
"logps/rejected": -79.27720642089844,
|
| 199 |
+
"loss": 0.5306,
|
| 200 |
+
"rewards/accuracies": 0.800000011920929,
|
| 201 |
+
"rewards/chosen": -0.2949373126029968,
|
| 202 |
+
"rewards/margins": 0.4063098430633545,
|
| 203 |
+
"rewards/rejected": -0.7012470960617065,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.067873303167421,
|
| 208 |
+
"grad_norm": 4.43679141998291,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": -2.3637630939483643,
|
| 211 |
+
"logits/rejected": -2.3869171142578125,
|
| 212 |
+
"logps/chosen": -63.164039611816406,
|
| 213 |
+
"logps/rejected": -78.0440673828125,
|
| 214 |
+
"loss": 0.5028,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.2740551233291626,
|
| 217 |
+
"rewards/margins": 0.5061118006706238,
|
| 218 |
+
"rewards/rejected": -0.7801669836044312,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.429864253393665,
|
| 223 |
+
"grad_norm": 4.934199810028076,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": -2.342858076095581,
|
| 226 |
+
"logits/rejected": -2.3417344093322754,
|
| 227 |
+
"logps/chosen": -80.54903411865234,
|
| 228 |
+
"logps/rejected": -79.4267807006836,
|
| 229 |
+
"loss": 0.4663,
|
| 230 |
+
"rewards/accuracies": 0.8125,
|
| 231 |
+
"rewards/chosen": -0.3702576756477356,
|
| 232 |
+
"rewards/margins": 0.5886551141738892,
|
| 233 |
+
"rewards/rejected": -0.95891273021698,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.791855203619909,
|
| 238 |
+
"grad_norm": 5.551158905029297,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": -2.36419415473938,
|
| 241 |
+
"logits/rejected": -2.388049364089966,
|
| 242 |
+
"logps/chosen": -69.40000915527344,
|
| 243 |
+
"logps/rejected": -91.36970520019531,
|
| 244 |
+
"loss": 0.4636,
|
| 245 |
+
"rewards/accuracies": 0.875,
|
| 246 |
+
"rewards/chosen": -0.42509594559669495,
|
| 247 |
+
"rewards/margins": 0.7187294363975525,
|
| 248 |
+
"rewards/rejected": -1.1438252925872803,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.153846153846154,
|
| 253 |
+
"grad_norm": 4.6863555908203125,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": -2.3798611164093018,
|
| 256 |
+
"logits/rejected": -2.388327121734619,
|
| 257 |
+
"logps/chosen": -84.27762603759766,
|
| 258 |
+
"logps/rejected": -95.46641540527344,
|
| 259 |
+
"loss": 0.4245,
|
| 260 |
+
"rewards/accuracies": 0.949999988079071,
|
| 261 |
+
"rewards/chosen": -0.4049956202507019,
|
| 262 |
+
"rewards/margins": 0.965179443359375,
|
| 263 |
+
"rewards/rejected": -1.3701750040054321,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.515837104072398,
|
| 268 |
+
"grad_norm": 5.001020431518555,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": -2.376713991165161,
|
| 271 |
+
"logits/rejected": -2.413689374923706,
|
| 272 |
+
"logps/chosen": -75.96709442138672,
|
| 273 |
+
"logps/rejected": -88.12495422363281,
|
| 274 |
+
"loss": 0.449,
|
| 275 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 276 |
+
"rewards/chosen": -0.3547631800174713,
|
| 277 |
+
"rewards/margins": 0.8548161387443542,
|
| 278 |
+
"rewards/rejected": -1.2095792293548584,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.877828054298643,
|
| 283 |
+
"grad_norm": 5.340312957763672,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": -2.385936737060547,
|
| 286 |
+
"logits/rejected": -2.4080803394317627,
|
| 287 |
+
"logps/chosen": -66.79461669921875,
|
| 288 |
+
"logps/rejected": -85.04891204833984,
|
| 289 |
+
"loss": 0.3764,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.4008978307247162,
|
| 292 |
+
"rewards/margins": 0.8593969345092773,
|
| 293 |
+
"rewards/rejected": -1.2602946758270264,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.239819004524887,
|
| 298 |
+
"grad_norm": 4.7585883140563965,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": -2.4034409523010254,
|
| 301 |
+
"logits/rejected": -2.425673246383667,
|
| 302 |
+
"logps/chosen": -78.95824432373047,
|
| 303 |
+
"logps/rejected": -92.42652893066406,
|
| 304 |
+
"loss": 0.3362,
|
| 305 |
+
"rewards/accuracies": 0.949999988079071,
|
| 306 |
+
"rewards/chosen": -0.5016047358512878,
|
| 307 |
+
"rewards/margins": 1.3585138320922852,
|
| 308 |
+
"rewards/rejected": -1.8601186275482178,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.601809954751131,
|
| 313 |
+
"grad_norm": 5.299131870269775,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": -2.405515193939209,
|
| 316 |
+
"logits/rejected": -2.4070794582366943,
|
| 317 |
+
"logps/chosen": -70.76835632324219,
|
| 318 |
+
"logps/rejected": -94.3203353881836,
|
| 319 |
+
"loss": 0.317,
|
| 320 |
+
"rewards/accuracies": 0.987500011920929,
|
| 321 |
+
"rewards/chosen": -0.7332154512405396,
|
| 322 |
+
"rewards/margins": 1.352203130722046,
|
| 323 |
+
"rewards/rejected": -2.085418701171875,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.963800904977376,
|
| 328 |
+
"grad_norm": 6.385330677032471,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": -2.3782029151916504,
|
| 331 |
+
"logits/rejected": -2.3890140056610107,
|
| 332 |
+
"logps/chosen": -74.07151794433594,
|
| 333 |
+
"logps/rejected": -97.96099853515625,
|
| 334 |
+
"loss": 0.3338,
|
| 335 |
+
"rewards/accuracies": 0.875,
|
| 336 |
+
"rewards/chosen": -0.8589820861816406,
|
| 337 |
+
"rewards/margins": 1.498375415802002,
|
| 338 |
+
"rewards/rejected": -2.3573575019836426,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.32579185520362,
|
| 343 |
+
"grad_norm": 5.3784027099609375,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": -2.411106586456299,
|
| 346 |
+
"logits/rejected": -2.4102063179016113,
|
| 347 |
+
"logps/chosen": -78.97357940673828,
|
| 348 |
+
"logps/rejected": -104.22176361083984,
|
| 349 |
+
"loss": 0.2894,
|
| 350 |
+
"rewards/accuracies": 0.9375,
|
| 351 |
+
"rewards/chosen": -0.850872814655304,
|
| 352 |
+
"rewards/margins": 1.5754810571670532,
|
| 353 |
+
"rewards/rejected": -2.426353931427002,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.687782805429864,
|
| 358 |
+
"grad_norm": 5.306555271148682,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": -2.3758366107940674,
|
| 361 |
+
"logits/rejected": -2.393923282623291,
|
| 362 |
+
"logps/chosen": -75.22766876220703,
|
| 363 |
+
"logps/rejected": -105.24629211425781,
|
| 364 |
+
"loss": 0.2666,
|
| 365 |
+
"rewards/accuracies": 0.949999988079071,
|
| 366 |
+
"rewards/chosen": -0.6813958287239075,
|
| 367 |
+
"rewards/margins": 1.697392225265503,
|
| 368 |
+
"rewards/rejected": -2.3787879943847656,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.049773755656108,
|
| 373 |
+
"grad_norm": 5.835656642913818,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": -2.345181465148926,
|
| 376 |
+
"logits/rejected": -2.3525192737579346,
|
| 377 |
+
"logps/chosen": -99.5466537475586,
|
| 378 |
+
"logps/rejected": -115.3326644897461,
|
| 379 |
+
"loss": 0.2556,
|
| 380 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 381 |
+
"rewards/chosen": -1.1117511987686157,
|
| 382 |
+
"rewards/margins": 1.774484634399414,
|
| 383 |
+
"rewards/rejected": -2.8862357139587402,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.411764705882353,
|
| 388 |
+
"grad_norm": 5.279304504394531,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": -2.3707776069641113,
|
| 391 |
+
"logits/rejected": -2.3579325675964355,
|
| 392 |
+
"logps/chosen": -107.48176574707031,
|
| 393 |
+
"logps/rejected": -119.63212585449219,
|
| 394 |
+
"loss": 0.223,
|
| 395 |
+
"rewards/accuracies": 1.0,
|
| 396 |
+
"rewards/chosen": -1.34574556350708,
|
| 397 |
+
"rewards/margins": 2.105149745941162,
|
| 398 |
+
"rewards/rejected": -3.450894832611084,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.773755656108598,
|
| 403 |
+
"grad_norm": 6.106879711151123,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": -2.367492198944092,
|
| 406 |
+
"logits/rejected": -2.3800530433654785,
|
| 407 |
+
"logps/chosen": -94.10942077636719,
|
| 408 |
+
"logps/rejected": -108.04286193847656,
|
| 409 |
+
"loss": 0.2108,
|
| 410 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 411 |
+
"rewards/chosen": -1.319504976272583,
|
| 412 |
+
"rewards/margins": 2.0621278285980225,
|
| 413 |
+
"rewards/rejected": -3.3816330432891846,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.135746606334841,
|
| 418 |
+
"grad_norm": 4.824020862579346,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": -2.29042649269104,
|
| 421 |
+
"logits/rejected": -2.2942726612091064,
|
| 422 |
+
"logps/chosen": -88.15667724609375,
|
| 423 |
+
"logps/rejected": -116.263671875,
|
| 424 |
+
"loss": 0.2067,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.352482795715332,
|
| 427 |
+
"rewards/margins": 2.1809113025665283,
|
| 428 |
+
"rewards/rejected": -3.5333938598632812,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.497737556561086,
|
| 433 |
+
"grad_norm": 5.073860168457031,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": -2.319164276123047,
|
| 436 |
+
"logits/rejected": -2.327695846557617,
|
| 437 |
+
"logps/chosen": -89.06367492675781,
|
| 438 |
+
"logps/rejected": -113.19393157958984,
|
| 439 |
+
"loss": 0.1791,
|
| 440 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 441 |
+
"rewards/chosen": -1.4301341772079468,
|
| 442 |
+
"rewards/margins": 2.2849090099334717,
|
| 443 |
+
"rewards/rejected": -3.715043306350708,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.85972850678733,
|
| 448 |
+
"grad_norm": 6.990862846374512,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": -2.322035551071167,
|
| 451 |
+
"logits/rejected": -2.343055248260498,
|
| 452 |
+
"logps/chosen": -79.6242904663086,
|
| 453 |
+
"logps/rejected": -117.89810943603516,
|
| 454 |
+
"loss": 0.173,
|
| 455 |
+
"rewards/accuracies": 0.949999988079071,
|
| 456 |
+
"rewards/chosen": -1.5006747245788574,
|
| 457 |
+
"rewards/margins": 2.6087098121643066,
|
| 458 |
+
"rewards/rejected": -4.109384059906006,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.221719457013574,
|
| 463 |
+
"grad_norm": 4.418057918548584,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": -2.313563585281372,
|
| 466 |
+
"logits/rejected": -2.3379547595977783,
|
| 467 |
+
"logps/chosen": -96.51193237304688,
|
| 468 |
+
"logps/rejected": -128.72109985351562,
|
| 469 |
+
"loss": 0.1525,
|
| 470 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 471 |
+
"rewards/chosen": -1.7700340747833252,
|
| 472 |
+
"rewards/margins": 2.5669429302215576,
|
| 473 |
+
"rewards/rejected": -4.336977005004883,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.583710407239819,
|
| 478 |
+
"grad_norm": 5.5379638671875,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": -2.3077690601348877,
|
| 481 |
+
"logits/rejected": -2.3094325065612793,
|
| 482 |
+
"logps/chosen": -97.48485565185547,
|
| 483 |
+
"logps/rejected": -120.9418716430664,
|
| 484 |
+
"loss": 0.1367,
|
| 485 |
+
"rewards/accuracies": 0.987500011920929,
|
| 486 |
+
"rewards/chosen": -1.6908330917358398,
|
| 487 |
+
"rewards/margins": 2.76543927192688,
|
| 488 |
+
"rewards/rejected": -4.456272602081299,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.945701357466064,
|
| 493 |
+
"grad_norm": 8.315099716186523,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": -2.2925028800964355,
|
| 496 |
+
"logits/rejected": -2.31669545173645,
|
| 497 |
+
"logps/chosen": -88.35062408447266,
|
| 498 |
+
"logps/rejected": -125.6523208618164,
|
| 499 |
+
"loss": 0.1436,
|
| 500 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 501 |
+
"rewards/chosen": -2.12321400642395,
|
| 502 |
+
"rewards/margins": 2.9592180252075195,
|
| 503 |
+
"rewards/rejected": -5.082431316375732,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.307692307692308,
|
| 508 |
+
"grad_norm": 5.883168697357178,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": -2.2664735317230225,
|
| 511 |
+
"logits/rejected": -2.3047263622283936,
|
| 512 |
+
"logps/chosen": -87.54987335205078,
|
| 513 |
+
"logps/rejected": -120.87919616699219,
|
| 514 |
+
"loss": 0.1185,
|
| 515 |
+
"rewards/accuracies": 0.987500011920929,
|
| 516 |
+
"rewards/chosen": -1.9975258111953735,
|
| 517 |
+
"rewards/margins": 3.0641627311706543,
|
| 518 |
+
"rewards/rejected": -5.061688423156738,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.669683257918551,
|
| 523 |
+
"grad_norm": 4.8013458251953125,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": -2.2390546798706055,
|
| 526 |
+
"logits/rejected": -2.233534097671509,
|
| 527 |
+
"logps/chosen": -102.70186614990234,
|
| 528 |
+
"logps/rejected": -136.1205291748047,
|
| 529 |
+
"loss": 0.111,
|
| 530 |
+
"rewards/accuracies": 0.987500011920929,
|
| 531 |
+
"rewards/chosen": -2.10892915725708,
|
| 532 |
+
"rewards/margins": 3.2926182746887207,
|
| 533 |
+
"rewards/rejected": -5.401547431945801,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 13.031674208144796,
|
| 538 |
+
"grad_norm": 4.820348739624023,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": -2.2781853675842285,
|
| 541 |
+
"logits/rejected": -2.3037526607513428,
|
| 542 |
+
"logps/chosen": -94.27687072753906,
|
| 543 |
+
"logps/rejected": -143.52162170410156,
|
| 544 |
+
"loss": 0.1133,
|
| 545 |
+
"rewards/accuracies": 0.987500011920929,
|
| 546 |
+
"rewards/chosen": -2.185966730117798,
|
| 547 |
+
"rewards/margins": 3.149972438812256,
|
| 548 |
+
"rewards/rejected": -5.335939884185791,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.393665158371041,
|
| 553 |
+
"grad_norm": 4.292584419250488,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": -2.260101079940796,
|
| 556 |
+
"logits/rejected": -2.270853042602539,
|
| 557 |
+
"logps/chosen": -112.0027847290039,
|
| 558 |
+
"logps/rejected": -155.92738342285156,
|
| 559 |
+
"loss": 0.0866,
|
| 560 |
+
"rewards/accuracies": 1.0,
|
| 561 |
+
"rewards/chosen": -2.6447501182556152,
|
| 562 |
+
"rewards/margins": 3.6627235412597656,
|
| 563 |
+
"rewards/rejected": -6.307473659515381,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.755656108597286,
|
| 568 |
+
"grad_norm": 4.569724082946777,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": -2.2924914360046387,
|
| 571 |
+
"logits/rejected": -2.3221309185028076,
|
| 572 |
+
"logps/chosen": -104.69401550292969,
|
| 573 |
+
"logps/rejected": -138.05264282226562,
|
| 574 |
+
"loss": 0.0953,
|
| 575 |
+
"rewards/accuracies": 0.987500011920929,
|
| 576 |
+
"rewards/chosen": -2.8196561336517334,
|
| 577 |
+
"rewards/margins": 3.5180962085723877,
|
| 578 |
+
"rewards/rejected": -6.337752342224121,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.117647058823529,
|
| 583 |
+
"grad_norm": 4.538058280944824,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": -2.2493948936462402,
|
| 586 |
+
"logits/rejected": -2.2872321605682373,
|
| 587 |
+
"logps/chosen": -102.8060531616211,
|
| 588 |
+
"logps/rejected": -135.58599853515625,
|
| 589 |
+
"loss": 0.0879,
|
| 590 |
+
"rewards/accuracies": 0.987500011920929,
|
| 591 |
+
"rewards/chosen": -2.9318606853485107,
|
| 592 |
+
"rewards/margins": 3.4618797302246094,
|
| 593 |
+
"rewards/rejected": -6.393740177154541,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.479638009049774,
|
| 598 |
+
"grad_norm": 4.173523426055908,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": -2.246553659439087,
|
| 601 |
+
"logits/rejected": -2.2457058429718018,
|
| 602 |
+
"logps/chosen": -109.64227294921875,
|
| 603 |
+
"logps/rejected": -147.6108856201172,
|
| 604 |
+
"loss": 0.0783,
|
| 605 |
+
"rewards/accuracies": 0.987500011920929,
|
| 606 |
+
"rewards/chosen": -2.916919708251953,
|
| 607 |
+
"rewards/margins": 3.4423089027404785,
|
| 608 |
+
"rewards/rejected": -6.359227657318115,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 14.841628959276019,
|
| 613 |
+
"grad_norm": 4.715793132781982,
|
| 614 |
+
"learning_rate": 8.319828944714508e-07,
|
| 615 |
+
"logits/chosen": -2.241994857788086,
|
| 616 |
+
"logits/rejected": -2.2265496253967285,
|
| 617 |
+
"logps/chosen": -106.87748718261719,
|
| 618 |
+
"logps/rejected": -134.00021362304688,
|
| 619 |
+
"loss": 0.0818,
|
| 620 |
+
"rewards/accuracies": 1.0,
|
| 621 |
+
"rewards/chosen": -2.9697346687316895,
|
| 622 |
+
"rewards/margins": 3.2734649181365967,
|
| 623 |
+
"rewards/rejected": -6.243198871612549,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 15.203619909502262,
|
| 628 |
+
"grad_norm": 3.8070931434631348,
|
| 629 |
+
"learning_rate": 7.151756636052529e-07,
|
| 630 |
+
"logits/chosen": -2.2427737712860107,
|
| 631 |
+
"logits/rejected": -2.287010908126831,
|
| 632 |
+
"logps/chosen": -93.37985229492188,
|
| 633 |
+
"logps/rejected": -145.51707458496094,
|
| 634 |
+
"loss": 0.08,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/chosen": -2.7174670696258545,
|
| 637 |
+
"rewards/margins": 3.7303779125213623,
|
| 638 |
+
"rewards/rejected": -6.447844505310059,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 15.565610859728507,
|
| 643 |
+
"grad_norm": 3.25356125831604,
|
| 644 |
+
"learning_rate": 6.058238413897052e-07,
|
| 645 |
+
"logits/chosen": -2.2657885551452637,
|
| 646 |
+
"logits/rejected": -2.259291887283325,
|
| 647 |
+
"logps/chosen": -101.24921417236328,
|
| 648 |
+
"logps/rejected": -136.51953125,
|
| 649 |
+
"loss": 0.0697,
|
| 650 |
+
"rewards/accuracies": 1.0,
|
| 651 |
+
"rewards/chosen": -3.116041421890259,
|
| 652 |
+
"rewards/margins": 3.617115020751953,
|
| 653 |
+
"rewards/rejected": -6.733156681060791,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.927601809954751,
|
| 658 |
+
"grad_norm": 4.29131555557251,
|
| 659 |
+
"learning_rate": 5.043842024802675e-07,
|
| 660 |
+
"logits/chosen": -2.2412171363830566,
|
| 661 |
+
"logits/rejected": -2.2466728687286377,
|
| 662 |
+
"logps/chosen": -98.49857330322266,
|
| 663 |
+
"logps/rejected": -143.11204528808594,
|
| 664 |
+
"loss": 0.0643,
|
| 665 |
+
"rewards/accuracies": 1.0,
|
| 666 |
+
"rewards/chosen": -3.198906421661377,
|
| 667 |
+
"rewards/margins": 3.8427040576934814,
|
| 668 |
+
"rewards/rejected": -7.041609764099121,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.289592760180994,
|
| 673 |
+
"grad_norm": 4.5554375648498535,
|
| 674 |
+
"learning_rate": 4.1128047146765936e-07,
|
| 675 |
+
"logits/chosen": -2.2196035385131836,
|
| 676 |
+
"logits/rejected": -2.243433952331543,
|
| 677 |
+
"logps/chosen": -121.4827651977539,
|
| 678 |
+
"logps/rejected": -141.68087768554688,
|
| 679 |
+
"loss": 0.0693,
|
| 680 |
+
"rewards/accuracies": 1.0,
|
| 681 |
+
"rewards/chosen": -3.3067448139190674,
|
| 682 |
+
"rewards/margins": 4.059030532836914,
|
| 683 |
+
"rewards/rejected": -7.365775108337402,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 16.65158371040724,
|
| 688 |
+
"grad_norm": 4.047634124755859,
|
| 689 |
+
"learning_rate": 3.269015529333805e-07,
|
| 690 |
+
"logits/chosen": -2.2159605026245117,
|
| 691 |
+
"logits/rejected": -2.2447285652160645,
|
| 692 |
+
"logps/chosen": -102.39476013183594,
|
| 693 |
+
"logps/rejected": -162.81443786621094,
|
| 694 |
+
"loss": 0.0608,
|
| 695 |
+
"rewards/accuracies": 1.0,
|
| 696 |
+
"rewards/chosen": -3.4078800678253174,
|
| 697 |
+
"rewards/margins": 4.151500701904297,
|
| 698 |
+
"rewards/rejected": -7.55938196182251,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 17.013574660633484,
|
| 703 |
+
"grad_norm": 3.6768975257873535,
|
| 704 |
+
"learning_rate": 2.515999069522676e-07,
|
| 705 |
+
"logits/chosen": -2.222931385040283,
|
| 706 |
+
"logits/rejected": -2.2669026851654053,
|
| 707 |
+
"logps/chosen": -99.30271911621094,
|
| 708 |
+
"logps/rejected": -134.9786376953125,
|
| 709 |
+
"loss": 0.0617,
|
| 710 |
+
"rewards/accuracies": 1.0,
|
| 711 |
+
"rewards/chosen": -3.145139217376709,
|
| 712 |
+
"rewards/margins": 3.7978076934814453,
|
| 713 |
+
"rewards/rejected": -6.9429473876953125,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 17.375565610859727,
|
| 718 |
+
"grad_norm": 6.302717208862305,
|
| 719 |
+
"learning_rate": 1.8569007682777417e-07,
|
| 720 |
+
"logits/chosen": -2.2295079231262207,
|
| 721 |
+
"logits/rejected": -2.2286057472229004,
|
| 722 |
+
"logps/chosen": -107.6258544921875,
|
| 723 |
+
"logps/rejected": -135.12925720214844,
|
| 724 |
+
"loss": 0.0602,
|
| 725 |
+
"rewards/accuracies": 0.987500011920929,
|
| 726 |
+
"rewards/chosen": -3.210822343826294,
|
| 727 |
+
"rewards/margins": 3.5960655212402344,
|
| 728 |
+
"rewards/rejected": -6.806887626647949,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 17.737556561085974,
|
| 733 |
+
"grad_norm": 3.749708414077759,
|
| 734 |
+
"learning_rate": 1.2944737520980883e-07,
|
| 735 |
+
"logits/chosen": -2.199395179748535,
|
| 736 |
+
"logits/rejected": -2.2533044815063477,
|
| 737 |
+
"logps/chosen": -103.281005859375,
|
| 738 |
+
"logps/rejected": -147.35745239257812,
|
| 739 |
+
"loss": 0.0585,
|
| 740 |
+
"rewards/accuracies": 1.0,
|
| 741 |
+
"rewards/chosen": -3.2957870960235596,
|
| 742 |
+
"rewards/margins": 4.124021053314209,
|
| 743 |
+
"rewards/rejected": -7.419807434082031,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 18.099547511312217,
|
| 748 |
+
"grad_norm": 3.7229220867156982,
|
| 749 |
+
"learning_rate": 8.310673408334496e-08,
|
| 750 |
+
"logits/chosen": -2.174075126647949,
|
| 751 |
+
"logits/rejected": -2.1925175189971924,
|
| 752 |
+
"logps/chosen": -110.58296203613281,
|
| 753 |
+
"logps/rejected": -148.13821411132812,
|
| 754 |
+
"loss": 0.0617,
|
| 755 |
+
"rewards/accuracies": 1.0,
|
| 756 |
+
"rewards/chosen": -3.2307941913604736,
|
| 757 |
+
"rewards/margins": 3.874736785888672,
|
| 758 |
+
"rewards/rejected": -7.10552978515625,
|
| 759 |
+
"step": 500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 10,
|
| 763 |
+
"max_steps": 540,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 20,
|
| 766 |
+
"save_steps": 100,
|
| 767 |
+
"stateful_callbacks": {
|
| 768 |
+
"TrainerControl": {
|
| 769 |
+
"args": {
|
| 770 |
+
"should_epoch_stop": false,
|
| 771 |
+
"should_evaluate": false,
|
| 772 |
+
"should_log": false,
|
| 773 |
+
"should_save": true,
|
| 774 |
+
"should_training_stop": false
|
| 775 |
+
},
|
| 776 |
+
"attributes": {}
|
| 777 |
+
}
|
| 778 |
+
},
|
| 779 |
+
"total_flos": 1.8479927931636285e+18,
|
| 780 |
+
"train_batch_size": 1,
|
| 781 |
+
"trial_name": null,
|
| 782 |
+
"trial_params": null
|
| 783 |
+
}
|
Power_Time_SFT/checkpoint-540/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 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 0.12.0
|
Power_Time_SFT/checkpoint-540/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Time_SFT/checkpoint-540/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Power_Time_SFT/checkpoint-540/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Power_Time_SFT/checkpoint-540/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Time_SFT/checkpoint-540/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Power_Time_SFT/checkpoint-540/trainer_state.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.547511312217196,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 540,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36199095022624433,
|
| 13 |
+
"grad_norm": 4.351782321929932,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": -2.3496108055114746,
|
| 16 |
+
"logits/rejected": -2.354576349258423,
|
| 17 |
+
"logps/chosen": -86.63139343261719,
|
| 18 |
+
"logps/rejected": -76.90333557128906,
|
| 19 |
+
"loss": 0.6923,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": -0.00019822348258458078,
|
| 22 |
+
"rewards/margins": -0.002337233629077673,
|
| 23 |
+
"rewards/rejected": 0.00213901000097394,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7239819004524887,
|
| 28 |
+
"grad_norm": 3.8085336685180664,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": -2.3482470512390137,
|
| 31 |
+
"logits/rejected": -2.3420329093933105,
|
| 32 |
+
"logps/chosen": -73.18113708496094,
|
| 33 |
+
"logps/rejected": -72.52565002441406,
|
| 34 |
+
"loss": 0.6943,
|
| 35 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 36 |
+
"rewards/chosen": 0.00011640912998700514,
|
| 37 |
+
"rewards/margins": -0.002153881825506687,
|
| 38 |
+
"rewards/rejected": 0.002270291093736887,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.085972850678733,
|
| 43 |
+
"grad_norm": 5.329021453857422,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": -2.3689351081848145,
|
| 46 |
+
"logits/rejected": -2.3885178565979004,
|
| 47 |
+
"logps/chosen": -72.15180969238281,
|
| 48 |
+
"logps/rejected": -74.70518493652344,
|
| 49 |
+
"loss": 0.6924,
|
| 50 |
+
"rewards/accuracies": 0.5625,
|
| 51 |
+
"rewards/chosen": 0.0020837264601141214,
|
| 52 |
+
"rewards/margins": 0.00603193324059248,
|
| 53 |
+
"rewards/rejected": -0.0039482079446315765,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4479638009049773,
|
| 58 |
+
"grad_norm": 3.671722888946533,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": -2.3091399669647217,
|
| 61 |
+
"logits/rejected": -2.3273236751556396,
|
| 62 |
+
"logps/chosen": -69.45216369628906,
|
| 63 |
+
"logps/rejected": -260.0699157714844,
|
| 64 |
+
"loss": 0.6899,
|
| 65 |
+
"rewards/accuracies": 0.550000011920929,
|
| 66 |
+
"rewards/chosen": -0.0094170942902565,
|
| 67 |
+
"rewards/margins": 0.14604035019874573,
|
| 68 |
+
"rewards/rejected": -0.15545745193958282,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8099547511312217,
|
| 73 |
+
"grad_norm": 4.172375679016113,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": -2.31831693649292,
|
| 76 |
+
"logits/rejected": -2.335618495941162,
|
| 77 |
+
"logps/chosen": -72.82856750488281,
|
| 78 |
+
"logps/rejected": -90.61243438720703,
|
| 79 |
+
"loss": 0.6865,
|
| 80 |
+
"rewards/accuracies": 0.625,
|
| 81 |
+
"rewards/chosen": -0.01846747286617756,
|
| 82 |
+
"rewards/margins": 0.015672579407691956,
|
| 83 |
+
"rewards/rejected": -0.034140050411224365,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.171945701357466,
|
| 88 |
+
"grad_norm": 4.386168479919434,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": -2.3203041553497314,
|
| 91 |
+
"logits/rejected": -2.3315658569335938,
|
| 92 |
+
"logps/chosen": -67.68244934082031,
|
| 93 |
+
"logps/rejected": -86.2356185913086,
|
| 94 |
+
"loss": 0.6775,
|
| 95 |
+
"rewards/accuracies": 0.637499988079071,
|
| 96 |
+
"rewards/chosen": -0.03993881493806839,
|
| 97 |
+
"rewards/margins": 0.027381544932723045,
|
| 98 |
+
"rewards/rejected": -0.06732036173343658,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5339366515837103,
|
| 103 |
+
"grad_norm": 4.38440465927124,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": -2.3607311248779297,
|
| 106 |
+
"logits/rejected": -2.3799984455108643,
|
| 107 |
+
"logps/chosen": -72.8117904663086,
|
| 108 |
+
"logps/rejected": -79.02535247802734,
|
| 109 |
+
"loss": 0.6636,
|
| 110 |
+
"rewards/accuracies": 0.6875,
|
| 111 |
+
"rewards/chosen": -0.06544635444879532,
|
| 112 |
+
"rewards/margins": 0.069185271859169,
|
| 113 |
+
"rewards/rejected": -0.13463163375854492,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8959276018099547,
|
| 118 |
+
"grad_norm": 4.333106517791748,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": -2.392198324203491,
|
| 121 |
+
"logits/rejected": -2.3854451179504395,
|
| 122 |
+
"logps/chosen": -64.03775787353516,
|
| 123 |
+
"logps/rejected": -71.01383972167969,
|
| 124 |
+
"loss": 0.6473,
|
| 125 |
+
"rewards/accuracies": 0.75,
|
| 126 |
+
"rewards/chosen": -0.09924488514661789,
|
| 127 |
+
"rewards/margins": 0.1070803552865982,
|
| 128 |
+
"rewards/rejected": -0.2063252478837967,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.257918552036199,
|
| 133 |
+
"grad_norm": 4.575820446014404,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": -2.3316967487335205,
|
| 136 |
+
"logits/rejected": -2.3399548530578613,
|
| 137 |
+
"logps/chosen": -66.9199447631836,
|
| 138 |
+
"logps/rejected": -67.97264099121094,
|
| 139 |
+
"loss": 0.6292,
|
| 140 |
+
"rewards/accuracies": 0.675000011920929,
|
| 141 |
+
"rewards/chosen": -0.1342274248600006,
|
| 142 |
+
"rewards/margins": 0.1109505444765091,
|
| 143 |
+
"rewards/rejected": -0.2451779842376709,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6199095022624435,
|
| 148 |
+
"grad_norm": 4.666302680969238,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": -2.3398795127868652,
|
| 151 |
+
"logits/rejected": -2.3582355976104736,
|
| 152 |
+
"logps/chosen": -76.05484771728516,
|
| 153 |
+
"logps/rejected": -78.4997787475586,
|
| 154 |
+
"loss": 0.6015,
|
| 155 |
+
"rewards/accuracies": 0.75,
|
| 156 |
+
"rewards/chosen": -0.15528908371925354,
|
| 157 |
+
"rewards/margins": 0.17627069354057312,
|
| 158 |
+
"rewards/rejected": -0.33155977725982666,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.981900452488688,
|
| 163 |
+
"grad_norm": 4.472248554229736,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": -2.3747470378875732,
|
| 166 |
+
"logits/rejected": -2.3589282035827637,
|
| 167 |
+
"logps/chosen": -75.08245086669922,
|
| 168 |
+
"logps/rejected": -88.42532348632812,
|
| 169 |
+
"loss": 0.582,
|
| 170 |
+
"rewards/accuracies": 0.762499988079071,
|
| 171 |
+
"rewards/chosen": -0.22706560790538788,
|
| 172 |
+
"rewards/margins": 0.2718750834465027,
|
| 173 |
+
"rewards/rejected": -0.49894070625305176,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.343891402714932,
|
| 178 |
+
"grad_norm": 4.420746326446533,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": -2.3004438877105713,
|
| 181 |
+
"logits/rejected": -2.33561635017395,
|
| 182 |
+
"logps/chosen": -92.03379821777344,
|
| 183 |
+
"logps/rejected": -84.3415298461914,
|
| 184 |
+
"loss": 0.5537,
|
| 185 |
+
"rewards/accuracies": 0.75,
|
| 186 |
+
"rewards/chosen": -0.2706041932106018,
|
| 187 |
+
"rewards/margins": 0.2943420112133026,
|
| 188 |
+
"rewards/rejected": -0.564946174621582,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.705882352941177,
|
| 193 |
+
"grad_norm": 4.54348611831665,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": -2.4000728130340576,
|
| 196 |
+
"logits/rejected": -2.3912758827209473,
|
| 197 |
+
"logps/chosen": -70.9849624633789,
|
| 198 |
+
"logps/rejected": -79.27720642089844,
|
| 199 |
+
"loss": 0.5306,
|
| 200 |
+
"rewards/accuracies": 0.800000011920929,
|
| 201 |
+
"rewards/chosen": -0.2949373126029968,
|
| 202 |
+
"rewards/margins": 0.4063098430633545,
|
| 203 |
+
"rewards/rejected": -0.7012470960617065,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.067873303167421,
|
| 208 |
+
"grad_norm": 4.43679141998291,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": -2.3637630939483643,
|
| 211 |
+
"logits/rejected": -2.3869171142578125,
|
| 212 |
+
"logps/chosen": -63.164039611816406,
|
| 213 |
+
"logps/rejected": -78.0440673828125,
|
| 214 |
+
"loss": 0.5028,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.2740551233291626,
|
| 217 |
+
"rewards/margins": 0.5061118006706238,
|
| 218 |
+
"rewards/rejected": -0.7801669836044312,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.429864253393665,
|
| 223 |
+
"grad_norm": 4.934199810028076,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": -2.342858076095581,
|
| 226 |
+
"logits/rejected": -2.3417344093322754,
|
| 227 |
+
"logps/chosen": -80.54903411865234,
|
| 228 |
+
"logps/rejected": -79.4267807006836,
|
| 229 |
+
"loss": 0.4663,
|
| 230 |
+
"rewards/accuracies": 0.8125,
|
| 231 |
+
"rewards/chosen": -0.3702576756477356,
|
| 232 |
+
"rewards/margins": 0.5886551141738892,
|
| 233 |
+
"rewards/rejected": -0.95891273021698,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.791855203619909,
|
| 238 |
+
"grad_norm": 5.551158905029297,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": -2.36419415473938,
|
| 241 |
+
"logits/rejected": -2.388049364089966,
|
| 242 |
+
"logps/chosen": -69.40000915527344,
|
| 243 |
+
"logps/rejected": -91.36970520019531,
|
| 244 |
+
"loss": 0.4636,
|
| 245 |
+
"rewards/accuracies": 0.875,
|
| 246 |
+
"rewards/chosen": -0.42509594559669495,
|
| 247 |
+
"rewards/margins": 0.7187294363975525,
|
| 248 |
+
"rewards/rejected": -1.1438252925872803,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.153846153846154,
|
| 253 |
+
"grad_norm": 4.6863555908203125,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": -2.3798611164093018,
|
| 256 |
+
"logits/rejected": -2.388327121734619,
|
| 257 |
+
"logps/chosen": -84.27762603759766,
|
| 258 |
+
"logps/rejected": -95.46641540527344,
|
| 259 |
+
"loss": 0.4245,
|
| 260 |
+
"rewards/accuracies": 0.949999988079071,
|
| 261 |
+
"rewards/chosen": -0.4049956202507019,
|
| 262 |
+
"rewards/margins": 0.965179443359375,
|
| 263 |
+
"rewards/rejected": -1.3701750040054321,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.515837104072398,
|
| 268 |
+
"grad_norm": 5.001020431518555,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": -2.376713991165161,
|
| 271 |
+
"logits/rejected": -2.413689374923706,
|
| 272 |
+
"logps/chosen": -75.96709442138672,
|
| 273 |
+
"logps/rejected": -88.12495422363281,
|
| 274 |
+
"loss": 0.449,
|
| 275 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 276 |
+
"rewards/chosen": -0.3547631800174713,
|
| 277 |
+
"rewards/margins": 0.8548161387443542,
|
| 278 |
+
"rewards/rejected": -1.2095792293548584,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.877828054298643,
|
| 283 |
+
"grad_norm": 5.340312957763672,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": -2.385936737060547,
|
| 286 |
+
"logits/rejected": -2.4080803394317627,
|
| 287 |
+
"logps/chosen": -66.79461669921875,
|
| 288 |
+
"logps/rejected": -85.04891204833984,
|
| 289 |
+
"loss": 0.3764,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.4008978307247162,
|
| 292 |
+
"rewards/margins": 0.8593969345092773,
|
| 293 |
+
"rewards/rejected": -1.2602946758270264,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.239819004524887,
|
| 298 |
+
"grad_norm": 4.7585883140563965,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": -2.4034409523010254,
|
| 301 |
+
"logits/rejected": -2.425673246383667,
|
| 302 |
+
"logps/chosen": -78.95824432373047,
|
| 303 |
+
"logps/rejected": -92.42652893066406,
|
| 304 |
+
"loss": 0.3362,
|
| 305 |
+
"rewards/accuracies": 0.949999988079071,
|
| 306 |
+
"rewards/chosen": -0.5016047358512878,
|
| 307 |
+
"rewards/margins": 1.3585138320922852,
|
| 308 |
+
"rewards/rejected": -1.8601186275482178,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.601809954751131,
|
| 313 |
+
"grad_norm": 5.299131870269775,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": -2.405515193939209,
|
| 316 |
+
"logits/rejected": -2.4070794582366943,
|
| 317 |
+
"logps/chosen": -70.76835632324219,
|
| 318 |
+
"logps/rejected": -94.3203353881836,
|
| 319 |
+
"loss": 0.317,
|
| 320 |
+
"rewards/accuracies": 0.987500011920929,
|
| 321 |
+
"rewards/chosen": -0.7332154512405396,
|
| 322 |
+
"rewards/margins": 1.352203130722046,
|
| 323 |
+
"rewards/rejected": -2.085418701171875,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.963800904977376,
|
| 328 |
+
"grad_norm": 6.385330677032471,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": -2.3782029151916504,
|
| 331 |
+
"logits/rejected": -2.3890140056610107,
|
| 332 |
+
"logps/chosen": -74.07151794433594,
|
| 333 |
+
"logps/rejected": -97.96099853515625,
|
| 334 |
+
"loss": 0.3338,
|
| 335 |
+
"rewards/accuracies": 0.875,
|
| 336 |
+
"rewards/chosen": -0.8589820861816406,
|
| 337 |
+
"rewards/margins": 1.498375415802002,
|
| 338 |
+
"rewards/rejected": -2.3573575019836426,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.32579185520362,
|
| 343 |
+
"grad_norm": 5.3784027099609375,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": -2.411106586456299,
|
| 346 |
+
"logits/rejected": -2.4102063179016113,
|
| 347 |
+
"logps/chosen": -78.97357940673828,
|
| 348 |
+
"logps/rejected": -104.22176361083984,
|
| 349 |
+
"loss": 0.2894,
|
| 350 |
+
"rewards/accuracies": 0.9375,
|
| 351 |
+
"rewards/chosen": -0.850872814655304,
|
| 352 |
+
"rewards/margins": 1.5754810571670532,
|
| 353 |
+
"rewards/rejected": -2.426353931427002,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.687782805429864,
|
| 358 |
+
"grad_norm": 5.306555271148682,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": -2.3758366107940674,
|
| 361 |
+
"logits/rejected": -2.393923282623291,
|
| 362 |
+
"logps/chosen": -75.22766876220703,
|
| 363 |
+
"logps/rejected": -105.24629211425781,
|
| 364 |
+
"loss": 0.2666,
|
| 365 |
+
"rewards/accuracies": 0.949999988079071,
|
| 366 |
+
"rewards/chosen": -0.6813958287239075,
|
| 367 |
+
"rewards/margins": 1.697392225265503,
|
| 368 |
+
"rewards/rejected": -2.3787879943847656,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.049773755656108,
|
| 373 |
+
"grad_norm": 5.835656642913818,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": -2.345181465148926,
|
| 376 |
+
"logits/rejected": -2.3525192737579346,
|
| 377 |
+
"logps/chosen": -99.5466537475586,
|
| 378 |
+
"logps/rejected": -115.3326644897461,
|
| 379 |
+
"loss": 0.2556,
|
| 380 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 381 |
+
"rewards/chosen": -1.1117511987686157,
|
| 382 |
+
"rewards/margins": 1.774484634399414,
|
| 383 |
+
"rewards/rejected": -2.8862357139587402,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.411764705882353,
|
| 388 |
+
"grad_norm": 5.279304504394531,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": -2.3707776069641113,
|
| 391 |
+
"logits/rejected": -2.3579325675964355,
|
| 392 |
+
"logps/chosen": -107.48176574707031,
|
| 393 |
+
"logps/rejected": -119.63212585449219,
|
| 394 |
+
"loss": 0.223,
|
| 395 |
+
"rewards/accuracies": 1.0,
|
| 396 |
+
"rewards/chosen": -1.34574556350708,
|
| 397 |
+
"rewards/margins": 2.105149745941162,
|
| 398 |
+
"rewards/rejected": -3.450894832611084,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.773755656108598,
|
| 403 |
+
"grad_norm": 6.106879711151123,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": -2.367492198944092,
|
| 406 |
+
"logits/rejected": -2.3800530433654785,
|
| 407 |
+
"logps/chosen": -94.10942077636719,
|
| 408 |
+
"logps/rejected": -108.04286193847656,
|
| 409 |
+
"loss": 0.2108,
|
| 410 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 411 |
+
"rewards/chosen": -1.319504976272583,
|
| 412 |
+
"rewards/margins": 2.0621278285980225,
|
| 413 |
+
"rewards/rejected": -3.3816330432891846,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.135746606334841,
|
| 418 |
+
"grad_norm": 4.824020862579346,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": -2.29042649269104,
|
| 421 |
+
"logits/rejected": -2.2942726612091064,
|
| 422 |
+
"logps/chosen": -88.15667724609375,
|
| 423 |
+
"logps/rejected": -116.263671875,
|
| 424 |
+
"loss": 0.2067,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.352482795715332,
|
| 427 |
+
"rewards/margins": 2.1809113025665283,
|
| 428 |
+
"rewards/rejected": -3.5333938598632812,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.497737556561086,
|
| 433 |
+
"grad_norm": 5.073860168457031,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": -2.319164276123047,
|
| 436 |
+
"logits/rejected": -2.327695846557617,
|
| 437 |
+
"logps/chosen": -89.06367492675781,
|
| 438 |
+
"logps/rejected": -113.19393157958984,
|
| 439 |
+
"loss": 0.1791,
|
| 440 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 441 |
+
"rewards/chosen": -1.4301341772079468,
|
| 442 |
+
"rewards/margins": 2.2849090099334717,
|
| 443 |
+
"rewards/rejected": -3.715043306350708,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.85972850678733,
|
| 448 |
+
"grad_norm": 6.990862846374512,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": -2.322035551071167,
|
| 451 |
+
"logits/rejected": -2.343055248260498,
|
| 452 |
+
"logps/chosen": -79.6242904663086,
|
| 453 |
+
"logps/rejected": -117.89810943603516,
|
| 454 |
+
"loss": 0.173,
|
| 455 |
+
"rewards/accuracies": 0.949999988079071,
|
| 456 |
+
"rewards/chosen": -1.5006747245788574,
|
| 457 |
+
"rewards/margins": 2.6087098121643066,
|
| 458 |
+
"rewards/rejected": -4.109384059906006,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.221719457013574,
|
| 463 |
+
"grad_norm": 4.418057918548584,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": -2.313563585281372,
|
| 466 |
+
"logits/rejected": -2.3379547595977783,
|
| 467 |
+
"logps/chosen": -96.51193237304688,
|
| 468 |
+
"logps/rejected": -128.72109985351562,
|
| 469 |
+
"loss": 0.1525,
|
| 470 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 471 |
+
"rewards/chosen": -1.7700340747833252,
|
| 472 |
+
"rewards/margins": 2.5669429302215576,
|
| 473 |
+
"rewards/rejected": -4.336977005004883,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.583710407239819,
|
| 478 |
+
"grad_norm": 5.5379638671875,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": -2.3077690601348877,
|
| 481 |
+
"logits/rejected": -2.3094325065612793,
|
| 482 |
+
"logps/chosen": -97.48485565185547,
|
| 483 |
+
"logps/rejected": -120.9418716430664,
|
| 484 |
+
"loss": 0.1367,
|
| 485 |
+
"rewards/accuracies": 0.987500011920929,
|
| 486 |
+
"rewards/chosen": -1.6908330917358398,
|
| 487 |
+
"rewards/margins": 2.76543927192688,
|
| 488 |
+
"rewards/rejected": -4.456272602081299,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.945701357466064,
|
| 493 |
+
"grad_norm": 8.315099716186523,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": -2.2925028800964355,
|
| 496 |
+
"logits/rejected": -2.31669545173645,
|
| 497 |
+
"logps/chosen": -88.35062408447266,
|
| 498 |
+
"logps/rejected": -125.6523208618164,
|
| 499 |
+
"loss": 0.1436,
|
| 500 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 501 |
+
"rewards/chosen": -2.12321400642395,
|
| 502 |
+
"rewards/margins": 2.9592180252075195,
|
| 503 |
+
"rewards/rejected": -5.082431316375732,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.307692307692308,
|
| 508 |
+
"grad_norm": 5.883168697357178,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": -2.2664735317230225,
|
| 511 |
+
"logits/rejected": -2.3047263622283936,
|
| 512 |
+
"logps/chosen": -87.54987335205078,
|
| 513 |
+
"logps/rejected": -120.87919616699219,
|
| 514 |
+
"loss": 0.1185,
|
| 515 |
+
"rewards/accuracies": 0.987500011920929,
|
| 516 |
+
"rewards/chosen": -1.9975258111953735,
|
| 517 |
+
"rewards/margins": 3.0641627311706543,
|
| 518 |
+
"rewards/rejected": -5.061688423156738,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.669683257918551,
|
| 523 |
+
"grad_norm": 4.8013458251953125,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": -2.2390546798706055,
|
| 526 |
+
"logits/rejected": -2.233534097671509,
|
| 527 |
+
"logps/chosen": -102.70186614990234,
|
| 528 |
+
"logps/rejected": -136.1205291748047,
|
| 529 |
+
"loss": 0.111,
|
| 530 |
+
"rewards/accuracies": 0.987500011920929,
|
| 531 |
+
"rewards/chosen": -2.10892915725708,
|
| 532 |
+
"rewards/margins": 3.2926182746887207,
|
| 533 |
+
"rewards/rejected": -5.401547431945801,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 13.031674208144796,
|
| 538 |
+
"grad_norm": 4.820348739624023,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": -2.2781853675842285,
|
| 541 |
+
"logits/rejected": -2.3037526607513428,
|
| 542 |
+
"logps/chosen": -94.27687072753906,
|
| 543 |
+
"logps/rejected": -143.52162170410156,
|
| 544 |
+
"loss": 0.1133,
|
| 545 |
+
"rewards/accuracies": 0.987500011920929,
|
| 546 |
+
"rewards/chosen": -2.185966730117798,
|
| 547 |
+
"rewards/margins": 3.149972438812256,
|
| 548 |
+
"rewards/rejected": -5.335939884185791,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.393665158371041,
|
| 553 |
+
"grad_norm": 4.292584419250488,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": -2.260101079940796,
|
| 556 |
+
"logits/rejected": -2.270853042602539,
|
| 557 |
+
"logps/chosen": -112.0027847290039,
|
| 558 |
+
"logps/rejected": -155.92738342285156,
|
| 559 |
+
"loss": 0.0866,
|
| 560 |
+
"rewards/accuracies": 1.0,
|
| 561 |
+
"rewards/chosen": -2.6447501182556152,
|
| 562 |
+
"rewards/margins": 3.6627235412597656,
|
| 563 |
+
"rewards/rejected": -6.307473659515381,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.755656108597286,
|
| 568 |
+
"grad_norm": 4.569724082946777,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": -2.2924914360046387,
|
| 571 |
+
"logits/rejected": -2.3221309185028076,
|
| 572 |
+
"logps/chosen": -104.69401550292969,
|
| 573 |
+
"logps/rejected": -138.05264282226562,
|
| 574 |
+
"loss": 0.0953,
|
| 575 |
+
"rewards/accuracies": 0.987500011920929,
|
| 576 |
+
"rewards/chosen": -2.8196561336517334,
|
| 577 |
+
"rewards/margins": 3.5180962085723877,
|
| 578 |
+
"rewards/rejected": -6.337752342224121,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.117647058823529,
|
| 583 |
+
"grad_norm": 4.538058280944824,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": -2.2493948936462402,
|
| 586 |
+
"logits/rejected": -2.2872321605682373,
|
| 587 |
+
"logps/chosen": -102.8060531616211,
|
| 588 |
+
"logps/rejected": -135.58599853515625,
|
| 589 |
+
"loss": 0.0879,
|
| 590 |
+
"rewards/accuracies": 0.987500011920929,
|
| 591 |
+
"rewards/chosen": -2.9318606853485107,
|
| 592 |
+
"rewards/margins": 3.4618797302246094,
|
| 593 |
+
"rewards/rejected": -6.393740177154541,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.479638009049774,
|
| 598 |
+
"grad_norm": 4.173523426055908,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": -2.246553659439087,
|
| 601 |
+
"logits/rejected": -2.2457058429718018,
|
| 602 |
+
"logps/chosen": -109.64227294921875,
|
| 603 |
+
"logps/rejected": -147.6108856201172,
|
| 604 |
+
"loss": 0.0783,
|
| 605 |
+
"rewards/accuracies": 0.987500011920929,
|
| 606 |
+
"rewards/chosen": -2.916919708251953,
|
| 607 |
+
"rewards/margins": 3.4423089027404785,
|
| 608 |
+
"rewards/rejected": -6.359227657318115,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 14.841628959276019,
|
| 613 |
+
"grad_norm": 4.715793132781982,
|
| 614 |
+
"learning_rate": 8.319828944714508e-07,
|
| 615 |
+
"logits/chosen": -2.241994857788086,
|
| 616 |
+
"logits/rejected": -2.2265496253967285,
|
| 617 |
+
"logps/chosen": -106.87748718261719,
|
| 618 |
+
"logps/rejected": -134.00021362304688,
|
| 619 |
+
"loss": 0.0818,
|
| 620 |
+
"rewards/accuracies": 1.0,
|
| 621 |
+
"rewards/chosen": -2.9697346687316895,
|
| 622 |
+
"rewards/margins": 3.2734649181365967,
|
| 623 |
+
"rewards/rejected": -6.243198871612549,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 15.203619909502262,
|
| 628 |
+
"grad_norm": 3.8070931434631348,
|
| 629 |
+
"learning_rate": 7.151756636052529e-07,
|
| 630 |
+
"logits/chosen": -2.2427737712860107,
|
| 631 |
+
"logits/rejected": -2.287010908126831,
|
| 632 |
+
"logps/chosen": -93.37985229492188,
|
| 633 |
+
"logps/rejected": -145.51707458496094,
|
| 634 |
+
"loss": 0.08,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/chosen": -2.7174670696258545,
|
| 637 |
+
"rewards/margins": 3.7303779125213623,
|
| 638 |
+
"rewards/rejected": -6.447844505310059,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 15.565610859728507,
|
| 643 |
+
"grad_norm": 3.25356125831604,
|
| 644 |
+
"learning_rate": 6.058238413897052e-07,
|
| 645 |
+
"logits/chosen": -2.2657885551452637,
|
| 646 |
+
"logits/rejected": -2.259291887283325,
|
| 647 |
+
"logps/chosen": -101.24921417236328,
|
| 648 |
+
"logps/rejected": -136.51953125,
|
| 649 |
+
"loss": 0.0697,
|
| 650 |
+
"rewards/accuracies": 1.0,
|
| 651 |
+
"rewards/chosen": -3.116041421890259,
|
| 652 |
+
"rewards/margins": 3.617115020751953,
|
| 653 |
+
"rewards/rejected": -6.733156681060791,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.927601809954751,
|
| 658 |
+
"grad_norm": 4.29131555557251,
|
| 659 |
+
"learning_rate": 5.043842024802675e-07,
|
| 660 |
+
"logits/chosen": -2.2412171363830566,
|
| 661 |
+
"logits/rejected": -2.2466728687286377,
|
| 662 |
+
"logps/chosen": -98.49857330322266,
|
| 663 |
+
"logps/rejected": -143.11204528808594,
|
| 664 |
+
"loss": 0.0643,
|
| 665 |
+
"rewards/accuracies": 1.0,
|
| 666 |
+
"rewards/chosen": -3.198906421661377,
|
| 667 |
+
"rewards/margins": 3.8427040576934814,
|
| 668 |
+
"rewards/rejected": -7.041609764099121,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.289592760180994,
|
| 673 |
+
"grad_norm": 4.5554375648498535,
|
| 674 |
+
"learning_rate": 4.1128047146765936e-07,
|
| 675 |
+
"logits/chosen": -2.2196035385131836,
|
| 676 |
+
"logits/rejected": -2.243433952331543,
|
| 677 |
+
"logps/chosen": -121.4827651977539,
|
| 678 |
+
"logps/rejected": -141.68087768554688,
|
| 679 |
+
"loss": 0.0693,
|
| 680 |
+
"rewards/accuracies": 1.0,
|
| 681 |
+
"rewards/chosen": -3.3067448139190674,
|
| 682 |
+
"rewards/margins": 4.059030532836914,
|
| 683 |
+
"rewards/rejected": -7.365775108337402,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 16.65158371040724,
|
| 688 |
+
"grad_norm": 4.047634124755859,
|
| 689 |
+
"learning_rate": 3.269015529333805e-07,
|
| 690 |
+
"logits/chosen": -2.2159605026245117,
|
| 691 |
+
"logits/rejected": -2.2447285652160645,
|
| 692 |
+
"logps/chosen": -102.39476013183594,
|
| 693 |
+
"logps/rejected": -162.81443786621094,
|
| 694 |
+
"loss": 0.0608,
|
| 695 |
+
"rewards/accuracies": 1.0,
|
| 696 |
+
"rewards/chosen": -3.4078800678253174,
|
| 697 |
+
"rewards/margins": 4.151500701904297,
|
| 698 |
+
"rewards/rejected": -7.55938196182251,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 17.013574660633484,
|
| 703 |
+
"grad_norm": 3.6768975257873535,
|
| 704 |
+
"learning_rate": 2.515999069522676e-07,
|
| 705 |
+
"logits/chosen": -2.222931385040283,
|
| 706 |
+
"logits/rejected": -2.2669026851654053,
|
| 707 |
+
"logps/chosen": -99.30271911621094,
|
| 708 |
+
"logps/rejected": -134.9786376953125,
|
| 709 |
+
"loss": 0.0617,
|
| 710 |
+
"rewards/accuracies": 1.0,
|
| 711 |
+
"rewards/chosen": -3.145139217376709,
|
| 712 |
+
"rewards/margins": 3.7978076934814453,
|
| 713 |
+
"rewards/rejected": -6.9429473876953125,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 17.375565610859727,
|
| 718 |
+
"grad_norm": 6.302717208862305,
|
| 719 |
+
"learning_rate": 1.8569007682777417e-07,
|
| 720 |
+
"logits/chosen": -2.2295079231262207,
|
| 721 |
+
"logits/rejected": -2.2286057472229004,
|
| 722 |
+
"logps/chosen": -107.6258544921875,
|
| 723 |
+
"logps/rejected": -135.12925720214844,
|
| 724 |
+
"loss": 0.0602,
|
| 725 |
+
"rewards/accuracies": 0.987500011920929,
|
| 726 |
+
"rewards/chosen": -3.210822343826294,
|
| 727 |
+
"rewards/margins": 3.5960655212402344,
|
| 728 |
+
"rewards/rejected": -6.806887626647949,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 17.737556561085974,
|
| 733 |
+
"grad_norm": 3.749708414077759,
|
| 734 |
+
"learning_rate": 1.2944737520980883e-07,
|
| 735 |
+
"logits/chosen": -2.199395179748535,
|
| 736 |
+
"logits/rejected": -2.2533044815063477,
|
| 737 |
+
"logps/chosen": -103.281005859375,
|
| 738 |
+
"logps/rejected": -147.35745239257812,
|
| 739 |
+
"loss": 0.0585,
|
| 740 |
+
"rewards/accuracies": 1.0,
|
| 741 |
+
"rewards/chosen": -3.2957870960235596,
|
| 742 |
+
"rewards/margins": 4.124021053314209,
|
| 743 |
+
"rewards/rejected": -7.419807434082031,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 18.099547511312217,
|
| 748 |
+
"grad_norm": 3.7229220867156982,
|
| 749 |
+
"learning_rate": 8.310673408334496e-08,
|
| 750 |
+
"logits/chosen": -2.174075126647949,
|
| 751 |
+
"logits/rejected": -2.1925175189971924,
|
| 752 |
+
"logps/chosen": -110.58296203613281,
|
| 753 |
+
"logps/rejected": -148.13821411132812,
|
| 754 |
+
"loss": 0.0617,
|
| 755 |
+
"rewards/accuracies": 1.0,
|
| 756 |
+
"rewards/chosen": -3.2307941913604736,
|
| 757 |
+
"rewards/margins": 3.874736785888672,
|
| 758 |
+
"rewards/rejected": -7.10552978515625,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 18.46153846153846,
|
| 763 |
+
"grad_norm": 3.482407331466675,
|
| 764 |
+
"learning_rate": 4.6861723431538273e-08,
|
| 765 |
+
"logits/chosen": -2.2031123638153076,
|
| 766 |
+
"logits/rejected": -2.2612881660461426,
|
| 767 |
+
"logps/chosen": -108.82826232910156,
|
| 768 |
+
"logps/rejected": -164.102294921875,
|
| 769 |
+
"loss": 0.0639,
|
| 770 |
+
"rewards/accuracies": 1.0,
|
| 771 |
+
"rewards/chosen": -3.6643009185791016,
|
| 772 |
+
"rewards/margins": 4.219679832458496,
|
| 773 |
+
"rewards/rejected": -7.883980751037598,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 18.823529411764707,
|
| 778 |
+
"grad_norm": 3.6187524795532227,
|
| 779 |
+
"learning_rate": 2.0863742672497244e-08,
|
| 780 |
+
"logits/chosen": -2.228766918182373,
|
| 781 |
+
"logits/rejected": -2.217647075653076,
|
| 782 |
+
"logps/chosen": -107.79327392578125,
|
| 783 |
+
"logps/rejected": -139.94277954101562,
|
| 784 |
+
"loss": 0.0534,
|
| 785 |
+
"rewards/accuracies": 0.987500011920929,
|
| 786 |
+
"rewards/chosen": -3.2466843128204346,
|
| 787 |
+
"rewards/margins": 3.7326819896698,
|
| 788 |
+
"rewards/rejected": -6.979366302490234,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 19.18552036199095,
|
| 793 |
+
"grad_norm": 4.491217613220215,
|
| 794 |
+
"learning_rate": 5.221388247169945e-09,
|
| 795 |
+
"logits/chosen": -2.194672107696533,
|
| 796 |
+
"logits/rejected": -2.229614734649658,
|
| 797 |
+
"logps/chosen": -97.34280395507812,
|
| 798 |
+
"logps/rejected": -144.13217163085938,
|
| 799 |
+
"loss": 0.0605,
|
| 800 |
+
"rewards/accuracies": 0.987500011920929,
|
| 801 |
+
"rewards/chosen": -2.943859815597534,
|
| 802 |
+
"rewards/margins": 3.916800022125244,
|
| 803 |
+
"rewards/rejected": -6.860659599304199,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 19.547511312217196,
|
| 808 |
+
"grad_norm": 5.3823065757751465,
|
| 809 |
+
"learning_rate": 0.0,
|
| 810 |
+
"logits/chosen": -2.2234930992126465,
|
| 811 |
+
"logits/rejected": -2.2182583808898926,
|
| 812 |
+
"logps/chosen": -111.52687072753906,
|
| 813 |
+
"logps/rejected": -151.66384887695312,
|
| 814 |
+
"loss": 0.0601,
|
| 815 |
+
"rewards/accuracies": 1.0,
|
| 816 |
+
"rewards/chosen": -3.98834228515625,
|
| 817 |
+
"rewards/margins": 3.9456241130828857,
|
| 818 |
+
"rewards/rejected": -7.93396520614624,
|
| 819 |
+
"step": 540
|
| 820 |
+
}
|
| 821 |
+
],
|
| 822 |
+
"logging_steps": 10,
|
| 823 |
+
"max_steps": 540,
|
| 824 |
+
"num_input_tokens_seen": 0,
|
| 825 |
+
"num_train_epochs": 20,
|
| 826 |
+
"save_steps": 100,
|
| 827 |
+
"stateful_callbacks": {
|
| 828 |
+
"TrainerControl": {
|
| 829 |
+
"args": {
|
| 830 |
+
"should_epoch_stop": false,
|
| 831 |
+
"should_evaluate": false,
|
| 832 |
+
"should_log": false,
|
| 833 |
+
"should_save": true,
|
| 834 |
+
"should_training_stop": true
|
| 835 |
+
},
|
| 836 |
+
"attributes": {}
|
| 837 |
+
}
|
| 838 |
+
},
|
| 839 |
+
"total_flos": 1.993357666398765e+18,
|
| 840 |
+
"train_batch_size": 1,
|
| 841 |
+
"trial_name": null,
|
| 842 |
+
"trial_params": null
|
| 843 |
+
}
|
Time_SFT/README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: other
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Time_SFT
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Time_SFT
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ishorn5/RTLCoder-v1.1](https://huggingface.co/ishorn5/RTLCoder-v1.1) on the time dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 20.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.12.0
|
| 59 |
+
- Transformers 4.45.2
|
| 60 |
+
- Pytorch 2.4.1+cu124
|
| 61 |
+
- Datasets 2.21.0
|
| 62 |
+
- Tokenizers 0.20.0
|
Time_SFT/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Time_SFT/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Time_SFT/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.37219730941704,
|
| 3 |
+
"total_flos": 1.981675043968516e+18,
|
| 4 |
+
"train_loss": 0.2879459043343862,
|
| 5 |
+
"train_runtime": 4187.4777,
|
| 6 |
+
"train_samples_per_second": 8.521,
|
| 7 |
+
"train_steps_per_second": 0.129
|
| 8 |
+
}
|
Time_SFT/checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 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 0.12.0
|
Time_SFT/checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Time_SFT/checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Time_SFT/checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Time_SFT/checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Time_SFT/checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Time_SFT/checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.587443946188341,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.35874439461883406,
|
| 13 |
+
"grad_norm": 5.573123455047607,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": -2.3576977252960205,
|
| 16 |
+
"logits/rejected": -2.3553850650787354,
|
| 17 |
+
"logps/chosen": -61.0846061706543,
|
| 18 |
+
"logps/rejected": -126.1152572631836,
|
| 19 |
+
"loss": 0.6942,
|
| 20 |
+
"rewards/accuracies": 0.36250001192092896,
|
| 21 |
+
"rewards/chosen": -0.0012381849810481071,
|
| 22 |
+
"rewards/margins": -0.010831715539097786,
|
| 23 |
+
"rewards/rejected": 0.009593529626727104,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7174887892376681,
|
| 28 |
+
"grad_norm": 3.8175244331359863,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": -2.3618054389953613,
|
| 31 |
+
"logits/rejected": -2.384873867034912,
|
| 32 |
+
"logps/chosen": -63.2865104675293,
|
| 33 |
+
"logps/rejected": -81.8724365234375,
|
| 34 |
+
"loss": 0.6925,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": -0.002874236088246107,
|
| 37 |
+
"rewards/margins": -0.003056168556213379,
|
| 38 |
+
"rewards/rejected": 0.00018193255527876318,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0762331838565022,
|
| 43 |
+
"grad_norm": 4.383662700653076,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": -2.3333091735839844,
|
| 46 |
+
"logits/rejected": -2.3545360565185547,
|
| 47 |
+
"logps/chosen": -76.02193450927734,
|
| 48 |
+
"logps/rejected": -88.19218444824219,
|
| 49 |
+
"loss": 0.6932,
|
| 50 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 51 |
+
"rewards/chosen": -0.008687756024301052,
|
| 52 |
+
"rewards/margins": -0.0016246589366346598,
|
| 53 |
+
"rewards/rejected": -0.007063096854835749,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4349775784753362,
|
| 58 |
+
"grad_norm": 4.095139503479004,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": -2.3483197689056396,
|
| 61 |
+
"logits/rejected": -2.363131523132324,
|
| 62 |
+
"logps/chosen": -66.08761596679688,
|
| 63 |
+
"logps/rejected": -78.22222900390625,
|
| 64 |
+
"loss": 0.6889,
|
| 65 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 66 |
+
"rewards/chosen": -0.014177674427628517,
|
| 67 |
+
"rewards/margins": 0.012472175993025303,
|
| 68 |
+
"rewards/rejected": -0.026649847626686096,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.7937219730941703,
|
| 73 |
+
"grad_norm": 4.034746170043945,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": -2.31459903717041,
|
| 76 |
+
"logits/rejected": -2.335706949234009,
|
| 77 |
+
"logps/chosen": -69.31814575195312,
|
| 78 |
+
"logps/rejected": -77.91527557373047,
|
| 79 |
+
"loss": 0.6823,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.04294499754905701,
|
| 82 |
+
"rewards/margins": 0.007987136952579021,
|
| 83 |
+
"rewards/rejected": -0.050932131707668304,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1524663677130045,
|
| 88 |
+
"grad_norm": 4.620233535766602,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": -2.364583969116211,
|
| 91 |
+
"logits/rejected": -2.3598217964172363,
|
| 92 |
+
"logps/chosen": -69.84207153320312,
|
| 93 |
+
"logps/rejected": -79.67817687988281,
|
| 94 |
+
"loss": 0.6717,
|
| 95 |
+
"rewards/accuracies": 0.699999988079071,
|
| 96 |
+
"rewards/chosen": -0.06739393621683121,
|
| 97 |
+
"rewards/margins": 0.050740111619234085,
|
| 98 |
+
"rewards/rejected": -0.118134044110775,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5112107623318387,
|
| 103 |
+
"grad_norm": 4.450082302093506,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": -2.298379421234131,
|
| 106 |
+
"logits/rejected": -2.3169469833374023,
|
| 107 |
+
"logps/chosen": -79.13768005371094,
|
| 108 |
+
"logps/rejected": -79.24192810058594,
|
| 109 |
+
"loss": 0.6499,
|
| 110 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 111 |
+
"rewards/chosen": -0.1282506138086319,
|
| 112 |
+
"rewards/margins": 0.08815944194793701,
|
| 113 |
+
"rewards/rejected": -0.21641004085540771,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8699551569506725,
|
| 118 |
+
"grad_norm": 4.7328877449035645,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": -2.3363795280456543,
|
| 121 |
+
"logits/rejected": -2.3331849575042725,
|
| 122 |
+
"logps/chosen": -77.52214050292969,
|
| 123 |
+
"logps/rejected": -86.90077209472656,
|
| 124 |
+
"loss": 0.6346,
|
| 125 |
+
"rewards/accuracies": 0.75,
|
| 126 |
+
"rewards/chosen": -0.22365322709083557,
|
| 127 |
+
"rewards/margins": 0.1937221735715866,
|
| 128 |
+
"rewards/rejected": -0.4173754155635834,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2286995515695067,
|
| 133 |
+
"grad_norm": 4.016219615936279,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": -2.30871844291687,
|
| 136 |
+
"logits/rejected": -2.3049044609069824,
|
| 137 |
+
"logps/chosen": -65.6957778930664,
|
| 138 |
+
"logps/rejected": -77.02860260009766,
|
| 139 |
+
"loss": 0.6004,
|
| 140 |
+
"rewards/accuracies": 0.762499988079071,
|
| 141 |
+
"rewards/chosen": -0.23905189335346222,
|
| 142 |
+
"rewards/margins": 0.2932591438293457,
|
| 143 |
+
"rewards/rejected": -0.5323110222816467,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.587443946188341,
|
| 148 |
+
"grad_norm": 4.553714752197266,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": -2.3068125247955322,
|
| 151 |
+
"logits/rejected": -2.294462203979492,
|
| 152 |
+
"logps/chosen": -85.46375274658203,
|
| 153 |
+
"logps/rejected": -79.72854614257812,
|
| 154 |
+
"loss": 0.5816,
|
| 155 |
+
"rewards/accuracies": 0.6875,
|
| 156 |
+
"rewards/chosen": -0.3506511151790619,
|
| 157 |
+
"rewards/margins": 0.2997886538505554,
|
| 158 |
+
"rewards/rejected": -0.6504397392272949,
|
| 159 |
+
"step": 100
|
| 160 |
+
}
|
| 161 |
+
],
|
| 162 |
+
"logging_steps": 10,
|
| 163 |
+
"max_steps": 540,
|
| 164 |
+
"num_input_tokens_seen": 0,
|
| 165 |
+
"num_train_epochs": 20,
|
| 166 |
+
"save_steps": 100,
|
| 167 |
+
"stateful_callbacks": {
|
| 168 |
+
"TrainerControl": {
|
| 169 |
+
"args": {
|
| 170 |
+
"should_epoch_stop": false,
|
| 171 |
+
"should_evaluate": false,
|
| 172 |
+
"should_log": false,
|
| 173 |
+
"should_save": true,
|
| 174 |
+
"should_training_stop": false
|
| 175 |
+
},
|
| 176 |
+
"attributes": {}
|
| 177 |
+
}
|
| 178 |
+
},
|
| 179 |
+
"total_flos": 3.648437622595912e+17,
|
| 180 |
+
"train_batch_size": 1,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
Time_SFT/checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 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 0.12.0
|
Time_SFT/checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Time_SFT/checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Time_SFT/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|