Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Area/adapter_model.safetensors +3 -0
- Area/checkpoint-200/adapter_model.safetensors +3 -0
- Area/checkpoint-250/adapter_model.safetensors +3 -0
- Area/checkpoint-300/adapter_model.safetensors +3 -0
- Area/checkpoint-550/adapter_model.safetensors +3 -0
- Area_SFT/README.md +62 -0
- Area_SFT/adapter_config.json +34 -0
- Area_SFT/added_tokens.json +3 -0
- Area_SFT/all_results.json +8 -0
- Area_SFT/checkpoint-50/README.md +202 -0
- Area_SFT/checkpoint-50/adapter_config.json +34 -0
- Area_SFT/checkpoint-50/added_tokens.json +3 -0
- Area_SFT/checkpoint-50/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-50/tokenizer.json +0 -0
- Area_SFT/checkpoint-50/tokenizer_config.json +59 -0
- Area_SFT/config.json +27 -0
- Area_SFT/generation_config.json +6 -0
- Area_SFT/model.safetensors.index.json +298 -0
- Area_SFT/special_tokens_map.json +36 -0
- Area_SFT/tokenizer.json +0 -0
- Area_SFT/tokenizer_config.json +59 -0
- Area_SFT/train_results.json +8 -0
- Area_SFT/trainer_log.jsonl +49 -0
- Area_SFT/trainer_state.json +912 -0
- Area_SFT/training_loss.png +0 -0
- Area_SFT/training_rewards_accuracies.png +0 -0
- Power/checkpoint-150/optimizer.pt +3 -0
- Power/checkpoint-200/adapter_model.safetensors +3 -0
- Power/checkpoint-450/adapter_model.safetensors +3 -0
- Power/checkpoint-50/adapter_model.safetensors +3 -0
- Power/checkpoint-500/optimizer.pt +3 -0
- Power/checkpoint-550/adapter_model.safetensors +3 -0
- Power/dpo/checkpoint-100/adapter_model.safetensors +3 -0
- Power/dpo/checkpoint-200/optimizer.pt +3 -0
- Power_Area_Time/.ipynb_checkpoints/trainer_log-checkpoint.jsonl +47 -0
- Power_Area_Time/checkpoint-200/adapter_config.json +34 -0
- Power_Area_Time/checkpoint-200/special_tokens_map.json +23 -0
- Power_Area_Time/checkpoint-200/tokenizer.json +0 -0
- Power_Area_Time/checkpoint-200/tokenizer_config.json +196 -0
- Power_Area_Time/checkpoint-200/trainer_state.json +333 -0
- Power_Area_Time/checkpoint-250/README.md +202 -0
- Power_Area_Time/checkpoint-250/adapter_config.json +34 -0
- Power_Area_Time/checkpoint-250/special_tokens_map.json +23 -0
- Power_Area_Time/checkpoint-250/tokenizer.json +0 -0
- Power_Area_Time/checkpoint-250/tokenizer_config.json +196 -0
- Power_Area_Time/checkpoint-250/trainer_state.json +408 -0
- Power_Area_Time/checkpoint-300/README.md +202 -0
- Power_Area_Time/checkpoint-300/adapter_config.json +34 -0
- Power_Area_Time/checkpoint-300/special_tokens_map.json +23 -0
- Power_Area_Time/checkpoint-300/tokenizer.json +0 -0
Area/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b73e6974aedd91139db9a6295fe14101c4ca32bc798f6e67c627c7e322a518f9
|
| 3 |
+
size 80013120
|
Area/checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7c2deb8bc989e65ec4ffb3492fc266b33c94913942107cf48dfa65816c873bc
|
| 3 |
+
size 80013120
|
Area/checkpoint-250/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e9a9badb43da693228b208a879c566291cf6c5e30c5ea38a3a0bb0c9a5a4bc6
|
| 3 |
+
size 80013120
|
Area/checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4355147d5c3bf3bcb8286e0b3943b469c4416efe25de0a3188e49275f6cc4cf
|
| 3 |
+
size 80013120
|
Area/checkpoint-550/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27c61a775d69091273fadc943a6c7ad0cb41119c102949e5aa28dfa1f03022d9
|
| 3 |
+
size 80013120
|
Area_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: Area_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 |
+
# Area_SFT
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ishorn5/RTLCoder-v1.1](https://huggingface.co/ishorn5/RTLCoder-v1.1) on the area 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
|
Area_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 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.502092050209207,
|
| 3 |
+
"total_flos": 2.1306294447112192e+18,
|
| 4 |
+
"train_loss": 0.1631378454381022,
|
| 5 |
+
"train_runtime": 3724.909,
|
| 6 |
+
"train_samples_per_second": 10.245,
|
| 7 |
+
"train_steps_per_second": 0.156
|
| 8 |
+
}
|
Area_SFT/checkpoint-50/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
|
Area_SFT/checkpoint-50/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 |
+
"gate_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-50/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-50/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 |
+
}
|
Area_SFT/checkpoint-50/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-50/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 |
+
}
|
Area_SFT/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"sliding_window": 4096,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.45.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32001
|
| 27 |
+
}
|
Area_SFT/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.45.2"
|
| 6 |
+
}
|
Area_SFT/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14483480576
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
Area_SFT/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 |
+
}
|
Area_SFT/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/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": "left",
|
| 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 |
+
}
|
Area_SFT/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.502092050209207,
|
| 3 |
+
"total_flos": 2.1306294447112192e+18,
|
| 4 |
+
"train_loss": 0.1631378454381022,
|
| 5 |
+
"train_runtime": 3724.909,
|
| 6 |
+
"train_samples_per_second": 10.245,
|
| 7 |
+
"train_steps_per_second": 0.156
|
| 8 |
+
}
|
Area_SFT/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 110, "total_steps": 580, "loss": 0.5908, "accuracy": 0.8374999761581421, "learning_rate": 4.878569458453592e-06, "epoch": 3.7698744769874475, "percentage": 18.97, "elapsed_time": "0:01:18", "remaining_time": "0:05:35"}
|
| 2 |
+
{"current_steps": 120, "total_steps": 580, "loss": 0.5783, "accuracy": 0.8999999761581421, "learning_rate": 4.827968782785062e-06, "epoch": 4.104602510460251, "percentage": 20.69, "elapsed_time": "0:02:30", "remaining_time": "0:09:38"}
|
| 3 |
+
{"current_steps": 130, "total_steps": 580, "loss": 0.5338, "accuracy": 0.8999999761581421, "learning_rate": 4.7689385491773934e-06, "epoch": 4.439330543933054, "percentage": 22.41, "elapsed_time": "0:03:46", "remaining_time": "0:13:04"}
|
| 4 |
+
{"current_steps": 140, "total_steps": 580, "loss": 0.5215, "accuracy": 0.824999988079071, "learning_rate": 4.70169250567482e-06, "epoch": 4.7740585774058575, "percentage": 24.14, "elapsed_time": "0:04:58", "remaining_time": "0:15:38"}
|
| 5 |
+
{"current_steps": 150, "total_steps": 580, "loss": 0.5019, "accuracy": 0.8500000238418579, "learning_rate": 4.626474149709127e-06, "epoch": 5.108786610878661, "percentage": 25.86, "elapsed_time": "0:06:19", "remaining_time": "0:18:07"}
|
| 6 |
+
{"current_steps": 160, "total_steps": 580, "loss": 0.4586, "accuracy": 0.824999988079071, "learning_rate": 4.54355584639723e-06, "epoch": 5.443514644351464, "percentage": 27.59, "elapsed_time": "0:07:35", "remaining_time": "0:19:55"}
|
| 7 |
+
{"current_steps": 170, "total_steps": 580, "loss": 0.4442, "accuracy": 0.887499988079071, "learning_rate": 4.45323784230908e-06, "epoch": 5.7782426778242675, "percentage": 29.31, "elapsed_time": "0:08:56", "remaining_time": "0:21:33"}
|
| 8 |
+
{"current_steps": 180, "total_steps": 580, "loss": 0.4355, "accuracy": 0.8999999761581421, "learning_rate": 4.355847178277025e-06, "epoch": 6.112970711297071, "percentage": 31.03, "elapsed_time": "0:10:11", "remaining_time": "0:22:39"}
|
| 9 |
+
{"current_steps": 190, "total_steps": 580, "loss": 0.3719, "accuracy": 0.925000011920929, "learning_rate": 4.2517365051833564e-06, "epoch": 6.447698744769874, "percentage": 32.76, "elapsed_time": "0:11:29", "remaining_time": "0:23:34"}
|
| 10 |
+
{"current_steps": 200, "total_steps": 580, "loss": 0.3829, "accuracy": 0.9375, "learning_rate": 4.141282807014034e-06, "epoch": 6.7824267782426775, "percentage": 34.48, "elapsed_time": "0:12:44", "remaining_time": "0:24:12"}
|
| 11 |
+
{"current_steps": 210, "total_steps": 580, "loss": 0.3522, "accuracy": 0.925000011920929, "learning_rate": 4.024886035802432e-06, "epoch": 7.117154811715481, "percentage": 36.21, "elapsed_time": "0:14:06", "remaining_time": "0:24:50"}
|
| 12 |
+
{"current_steps": 220, "total_steps": 580, "loss": 0.3219, "accuracy": 0.8999999761581421, "learning_rate": 3.9029676634059565e-06, "epoch": 7.451882845188284, "percentage": 37.93, "elapsed_time": "0:15:21", "remaining_time": "0:25:08"}
|
| 13 |
+
{"current_steps": 230, "total_steps": 580, "loss": 0.3041, "accuracy": 0.9125000238418579, "learning_rate": 3.7759691553595214e-06, "epoch": 7.786610878661088, "percentage": 39.66, "elapsed_time": "0:16:46", "remaining_time": "0:25:31"}
|
| 14 |
+
{"current_steps": 240, "total_steps": 580, "loss": 0.3065, "accuracy": 0.9125000238418579, "learning_rate": 3.6443503723320837e-06, "epoch": 8.121338912133892, "percentage": 41.38, "elapsed_time": "0:18:01", "remaining_time": "0:25:31"}
|
| 15 |
+
{"current_steps": 250, "total_steps": 580, "loss": 0.2498, "accuracy": 0.9750000238418579, "learning_rate": 3.508587904974522e-06, "epoch": 8.456066945606695, "percentage": 43.1, "elapsed_time": "0:19:23", "remaining_time": "0:25:35"}
|
| 16 |
+
{"current_steps": 260, "total_steps": 580, "loss": 0.2532, "accuracy": 0.925000011920929, "learning_rate": 3.3691733481883693e-06, "epoch": 8.790794979079498, "percentage": 44.83, "elapsed_time": "0:20:41", "remaining_time": "0:25:28"}
|
| 17 |
+
{"current_steps": 270, "total_steps": 580, "loss": 0.2314, "accuracy": 0.9750000238418579, "learning_rate": 3.226611521064278e-06, "epoch": 9.125523012552302, "percentage": 46.55, "elapsed_time": "0:21:51", "remaining_time": "0:25:06"}
|
| 18 |
+
{"current_steps": 280, "total_steps": 580, "loss": 0.2142, "accuracy": 0.9624999761581421, "learning_rate": 3.0814186389357765e-06, "epoch": 9.460251046025105, "percentage": 48.28, "elapsed_time": "0:23:10", "remaining_time": "0:24:49"}
|
| 19 |
+
{"current_steps": 290, "total_steps": 580, "loss": 0.1881, "accuracy": 1.0, "learning_rate": 2.9341204441673267e-06, "epoch": 9.794979079497908, "percentage": 50.0, "elapsed_time": "0:24:25", "remaining_time": "0:24:25"}
|
| 20 |
+
{"current_steps": 300, "total_steps": 580, "loss": 0.1798, "accuracy": 0.9624999761581421, "learning_rate": 2.785250302445062e-06, "epoch": 10.129707112970712, "percentage": 51.72, "elapsed_time": "0:25:46", "remaining_time": "0:24:02"}
|
| 21 |
+
{"current_steps": 310, "total_steps": 580, "loss": 0.1558, "accuracy": 0.987500011920929, "learning_rate": 2.6353472714635443e-06, "epoch": 10.464435146443515, "percentage": 53.45, "elapsed_time": "0:27:07", "remaining_time": "0:23:37"}
|
| 22 |
+
{"current_steps": 320, "total_steps": 580, "loss": 0.1538, "accuracy": 0.9750000238418579, "learning_rate": 2.4849541490017868e-06, "epoch": 10.799163179916318, "percentage": 55.17, "elapsed_time": "0:28:28", "remaining_time": "0:23:08"}
|
| 23 |
+
{"current_steps": 330, "total_steps": 580, "loss": 0.1373, "accuracy": 0.9750000238418579, "learning_rate": 2.3346155074564712e-06, "epoch": 11.133891213389122, "percentage": 56.9, "elapsed_time": "0:29:46", "remaining_time": "0:22:33"}
|
| 24 |
+
{"current_steps": 340, "total_steps": 580, "loss": 0.1257, "accuracy": 0.9624999761581421, "learning_rate": 2.184875721949277e-06, "epoch": 11.468619246861925, "percentage": 58.62, "elapsed_time": "0:31:01", "remaining_time": "0:21:54"}
|
| 25 |
+
{"current_steps": 350, "total_steps": 580, "loss": 0.1184, "accuracy": 0.987500011920929, "learning_rate": 2.0362769991485514e-06, "epoch": 11.803347280334728, "percentage": 60.34, "elapsed_time": "0:32:21", "remaining_time": "0:21:16"}
|
| 26 |
+
{"current_steps": 360, "total_steps": 580, "loss": 0.1106, "accuracy": 0.987500011920929, "learning_rate": 1.8893574139429226e-06, "epoch": 12.138075313807532, "percentage": 62.07, "elapsed_time": "0:33:37", "remaining_time": "0:20:33"}
|
| 27 |
+
{"current_steps": 370, "total_steps": 580, "loss": 0.0907, "accuracy": 0.9750000238418579, "learning_rate": 1.744648961076068e-06, "epoch": 12.472803347280335, "percentage": 63.79, "elapsed_time": "0:34:56", "remaining_time": "0:19:50"}
|
| 28 |
+
{"current_steps": 380, "total_steps": 580, "loss": 0.0923, "accuracy": 1.0, "learning_rate": 1.602675628797636e-06, "epoch": 12.807531380753138, "percentage": 65.52, "elapsed_time": "0:36:17", "remaining_time": "0:19:06"}
|
| 29 |
+
{"current_steps": 390, "total_steps": 580, "loss": 0.0876, "accuracy": 0.9624999761581421, "learning_rate": 1.4639515015056205e-06, "epoch": 13.142259414225942, "percentage": 67.24, "elapsed_time": "0:37:36", "remaining_time": "0:18:19"}
|
| 30 |
+
{"current_steps": 400, "total_steps": 580, "loss": 0.0662, "accuracy": 1.0, "learning_rate": 1.328978898250525e-06, "epoch": 13.476987447698745, "percentage": 68.97, "elapsed_time": "0:38:56", "remaining_time": "0:17:31"}
|
| 31 |
+
{"current_steps": 410, "total_steps": 580, "loss": 0.0808, "accuracy": 0.987500011920929, "learning_rate": 1.198246553841744e-06, "epoch": 13.811715481171548, "percentage": 70.69, "elapsed_time": "0:40:12", "remaining_time": "0:16:40"}
|
| 32 |
+
{"current_steps": 420, "total_steps": 580, "loss": 0.0651, "accuracy": 1.0, "learning_rate": 1.0722278491423998e-06, "epoch": 14.146443514644352, "percentage": 72.41, "elapsed_time": "0:41:32", "remaining_time": "0:15:49"}
|
| 33 |
+
{"current_steps": 430, "total_steps": 580, "loss": 0.0609, "accuracy": 1.0, "learning_rate": 9.513790969606926e-07, "epoch": 14.481171548117155, "percentage": 74.14, "elapsed_time": "0:42:48", "remaining_time": "0:14:55"}
|
| 34 |
+
{"current_steps": 440, "total_steps": 580, "loss": 0.0624, "accuracy": 1.0, "learning_rate": 8.361378897445643e-07, "epoch": 14.815899581589958, "percentage": 75.86, "elapsed_time": "0:44:05", "remaining_time": "0:14:01"}
|
| 35 |
+
{"current_steps": 450, "total_steps": 580, "loss": 0.0513, "accuracy": 1.0, "learning_rate": 7.269215150626391e-07, "epoch": 15.150627615062762, "percentage": 77.59, "elapsed_time": "0:45:17", "remaining_time": "0:13:05"}
|
| 36 |
+
{"current_steps": 460, "total_steps": 580, "loss": 0.0588, "accuracy": 0.987500011920929, "learning_rate": 6.241254446089942e-07, "epoch": 15.485355648535565, "percentage": 79.31, "elapsed_time": "0:46:31", "remaining_time": "0:12:08"}
|
| 37 |
+
{"current_steps": 470, "total_steps": 580, "loss": 0.0484, "accuracy": 1.0, "learning_rate": 5.281219022030423e-07, "epoch": 15.820083682008368, "percentage": 81.03, "elapsed_time": "0:47:50", "remaining_time": "0:11:11"}
|
| 38 |
+
{"current_steps": 480, "total_steps": 580, "loss": 0.0443, "accuracy": 1.0, "learning_rate": 4.392585159698087e-07, "epoch": 16.15481171548117, "percentage": 82.76, "elapsed_time": "0:49:06", "remaining_time": "0:10:13"}
|
| 39 |
+
{"current_steps": 490, "total_steps": 580, "loss": 0.0483, "accuracy": 1.0, "learning_rate": 3.578570595810274e-07, "epoch": 16.489539748953973, "percentage": 84.48, "elapsed_time": "0:50:20", "remaining_time": "0:09:14"}
|
| 40 |
+
{"current_steps": 500, "total_steps": 580, "loss": 0.0468, "accuracy": 1.0, "learning_rate": 2.8421228711503127e-07, "epoch": 16.824267782426777, "percentage": 86.21, "elapsed_time": "0:51:36", "remaining_time": "0:08:15"}
|
| 41 |
+
{"current_steps": 510, "total_steps": 580, "loss": 0.0398, "accuracy": 1.0, "learning_rate": 2.1859086575439225e-07, "epoch": 17.15899581589958, "percentage": 87.93, "elapsed_time": "0:52:54", "remaining_time": "0:07:15"}
|
| 42 |
+
{"current_steps": 520, "total_steps": 580, "loss": 0.0436, "accuracy": 1.0, "learning_rate": 1.6123041018599766e-07, "epoch": 17.493723849372383, "percentage": 89.66, "elapsed_time": "0:54:14", "remaining_time": "0:06:15"}
|
| 43 |
+
{"current_steps": 530, "total_steps": 580, "loss": 0.0477, "accuracy": 1.0, "learning_rate": 1.1233862220001168e-07, "epoch": 17.828451882845187, "percentage": 91.38, "elapsed_time": "0:55:34", "remaining_time": "0:05:14"}
|
| 44 |
+
{"current_steps": 540, "total_steps": 580, "loss": 0.0408, "accuracy": 1.0, "learning_rate": 7.209253860320897e-08, "epoch": 18.16317991631799, "percentage": 93.1, "elapsed_time": "0:56:54", "remaining_time": "0:04:12"}
|
| 45 |
+
{"current_steps": 550, "total_steps": 580, "loss": 0.0423, "accuracy": 1.0, "learning_rate": 4.063789016999331e-08, "epoch": 18.497907949790793, "percentage": 94.83, "elapsed_time": "0:58:10", "remaining_time": "0:03:10"}
|
| 46 |
+
{"current_steps": 560, "total_steps": 580, "loss": 0.04, "accuracy": 1.0, "learning_rate": 1.808857395232788e-08, "epoch": 18.8326359832636, "percentage": 96.55, "elapsed_time": "0:59:27", "remaining_time": "0:02:07"}
|
| 47 |
+
{"current_steps": 570, "total_steps": 580, "loss": 0.041, "accuracy": 1.0, "learning_rate": 4.526240859345499e-09, "epoch": 19.1673640167364, "percentage": 98.28, "elapsed_time": "1:00:47", "remaining_time": "0:01:03"}
|
| 48 |
+
{"current_steps": 580, "total_steps": 580, "loss": 0.0408, "accuracy": 0.987500011920929, "learning_rate": 0.0, "epoch": 19.502092050209207, "percentage": 100.0, "elapsed_time": "1:02:03", "remaining_time": "0:00:00"}
|
| 49 |
+
{"current_steps": 580, "total_steps": 580, "epoch": 19.502092050209207, "percentage": 100.0, "elapsed_time": "1:02:04", "remaining_time": "0:00:00"}
|
Area_SFT/trainer_state.json
ADDED
|
@@ -0,0 +1,912 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.502092050209207,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 580,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.443514644351464,
|
| 238 |
+
"grad_norm": 4.364648818969727,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": -2.408982992172241,
|
| 241 |
+
"logits/rejected": -2.4170727729797363,
|
| 242 |
+
"logps/chosen": -81.3556900024414,
|
| 243 |
+
"logps/rejected": -86.85897064208984,
|
| 244 |
+
"loss": 0.4586,
|
| 245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 246 |
+
"rewards/chosen": -0.23941104114055634,
|
| 247 |
+
"rewards/margins": 0.675674319267273,
|
| 248 |
+
"rewards/rejected": -0.9150853157043457,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.7782426778242675,
|
| 253 |
+
"grad_norm": 5.241800308227539,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": -2.4194908142089844,
|
| 256 |
+
"logits/rejected": -2.4498963356018066,
|
| 257 |
+
"logps/chosen": -62.32392120361328,
|
| 258 |
+
"logps/rejected": -76.39479064941406,
|
| 259 |
+
"loss": 0.4442,
|
| 260 |
+
"rewards/accuracies": 0.887499988079071,
|
| 261 |
+
"rewards/chosen": -0.26662638783454895,
|
| 262 |
+
"rewards/margins": 0.6662653088569641,
|
| 263 |
+
"rewards/rejected": -0.9328916668891907,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.112970711297071,
|
| 268 |
+
"grad_norm": 4.73954439163208,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": -2.4365036487579346,
|
| 271 |
+
"logits/rejected": -2.435439348220825,
|
| 272 |
+
"logps/chosen": -73.06513977050781,
|
| 273 |
+
"logps/rejected": -81.04569244384766,
|
| 274 |
+
"loss": 0.4355,
|
| 275 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 276 |
+
"rewards/chosen": -0.37924182415008545,
|
| 277 |
+
"rewards/margins": 0.7773979902267456,
|
| 278 |
+
"rewards/rejected": -1.156639814376831,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.447698744769874,
|
| 283 |
+
"grad_norm": 5.250921726226807,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": -2.387922525405884,
|
| 286 |
+
"logits/rejected": -2.3835678100585938,
|
| 287 |
+
"logps/chosen": -64.85784912109375,
|
| 288 |
+
"logps/rejected": -90.08439636230469,
|
| 289 |
+
"loss": 0.3719,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.42228370904922485,
|
| 292 |
+
"rewards/margins": 1.0562283992767334,
|
| 293 |
+
"rewards/rejected": -1.478512167930603,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.7824267782426775,
|
| 298 |
+
"grad_norm": 5.088508129119873,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": -2.376319169998169,
|
| 301 |
+
"logits/rejected": -2.3985953330993652,
|
| 302 |
+
"logps/chosen": -70.64585876464844,
|
| 303 |
+
"logps/rejected": -89.17048645019531,
|
| 304 |
+
"loss": 0.3829,
|
| 305 |
+
"rewards/accuracies": 0.9375,
|
| 306 |
+
"rewards/chosen": -0.5233972072601318,
|
| 307 |
+
"rewards/margins": 1.1063960790634155,
|
| 308 |
+
"rewards/rejected": -1.629793405532837,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.117154811715481,
|
| 313 |
+
"grad_norm": 4.6062092781066895,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": -2.371851682662964,
|
| 316 |
+
"logits/rejected": -2.3844287395477295,
|
| 317 |
+
"logps/chosen": -74.63328552246094,
|
| 318 |
+
"logps/rejected": -97.81452178955078,
|
| 319 |
+
"loss": 0.3522,
|
| 320 |
+
"rewards/accuracies": 0.925000011920929,
|
| 321 |
+
"rewards/chosen": -0.6278538703918457,
|
| 322 |
+
"rewards/margins": 1.2317354679107666,
|
| 323 |
+
"rewards/rejected": -1.8595889806747437,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.451882845188284,
|
| 328 |
+
"grad_norm": 5.105669021606445,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": -2.4011385440826416,
|
| 331 |
+
"logits/rejected": -2.4039382934570312,
|
| 332 |
+
"logps/chosen": -75.92952728271484,
|
| 333 |
+
"logps/rejected": -78.41490936279297,
|
| 334 |
+
"loss": 0.3219,
|
| 335 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 336 |
+
"rewards/chosen": -0.39645594358444214,
|
| 337 |
+
"rewards/margins": 1.2095177173614502,
|
| 338 |
+
"rewards/rejected": -1.6059738397598267,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.786610878661088,
|
| 343 |
+
"grad_norm": 6.292915344238281,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": -2.3707780838012695,
|
| 346 |
+
"logits/rejected": -2.377169609069824,
|
| 347 |
+
"logps/chosen": -88.07064056396484,
|
| 348 |
+
"logps/rejected": -108.6225814819336,
|
| 349 |
+
"loss": 0.3041,
|
| 350 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 351 |
+
"rewards/chosen": -0.9827474355697632,
|
| 352 |
+
"rewards/margins": 1.3651618957519531,
|
| 353 |
+
"rewards/rejected": -2.3479092121124268,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.121338912133892,
|
| 358 |
+
"grad_norm": 5.0669097900390625,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": -2.3608062267303467,
|
| 361 |
+
"logits/rejected": -2.3792402744293213,
|
| 362 |
+
"logps/chosen": -72.83047485351562,
|
| 363 |
+
"logps/rejected": -91.09341430664062,
|
| 364 |
+
"loss": 0.3065,
|
| 365 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 366 |
+
"rewards/chosen": -0.9334943890571594,
|
| 367 |
+
"rewards/margins": 1.3210034370422363,
|
| 368 |
+
"rewards/rejected": -2.25449800491333,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.456066945606695,
|
| 373 |
+
"grad_norm": 5.0598931312561035,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": -2.324855327606201,
|
| 376 |
+
"logits/rejected": -2.364541530609131,
|
| 377 |
+
"logps/chosen": -90.57644653320312,
|
| 378 |
+
"logps/rejected": -106.41752624511719,
|
| 379 |
+
"loss": 0.2498,
|
| 380 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 381 |
+
"rewards/chosen": -0.8531273007392883,
|
| 382 |
+
"rewards/margins": 1.8315904140472412,
|
| 383 |
+
"rewards/rejected": -2.684717893600464,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.790794979079498,
|
| 388 |
+
"grad_norm": 6.120776653289795,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": -2.3436760902404785,
|
| 391 |
+
"logits/rejected": -2.3720099925994873,
|
| 392 |
+
"logps/chosen": -86.95789337158203,
|
| 393 |
+
"logps/rejected": -102.34903717041016,
|
| 394 |
+
"loss": 0.2532,
|
| 395 |
+
"rewards/accuracies": 0.925000011920929,
|
| 396 |
+
"rewards/chosen": -1.1573801040649414,
|
| 397 |
+
"rewards/margins": 1.7690637111663818,
|
| 398 |
+
"rewards/rejected": -2.9264438152313232,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.125523012552302,
|
| 403 |
+
"grad_norm": 4.666015625,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": -2.3132309913635254,
|
| 406 |
+
"logits/rejected": -2.309297800064087,
|
| 407 |
+
"logps/chosen": -78.139404296875,
|
| 408 |
+
"logps/rejected": -99.09760284423828,
|
| 409 |
+
"loss": 0.2314,
|
| 410 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 411 |
+
"rewards/chosen": -1.0649818181991577,
|
| 412 |
+
"rewards/margins": 1.8774713277816772,
|
| 413 |
+
"rewards/rejected": -2.942453384399414,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.460251046025105,
|
| 418 |
+
"grad_norm": 8.85567855834961,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": -2.3629987239837646,
|
| 421 |
+
"logits/rejected": -2.385927200317383,
|
| 422 |
+
"logps/chosen": -91.09283447265625,
|
| 423 |
+
"logps/rejected": -102.37603759765625,
|
| 424 |
+
"loss": 0.2142,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.5404099225997925,
|
| 427 |
+
"rewards/margins": 2.121422290802002,
|
| 428 |
+
"rewards/rejected": -3.661832094192505,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.794979079497908,
|
| 433 |
+
"grad_norm": 5.228074550628662,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": -2.356905221939087,
|
| 436 |
+
"logits/rejected": -2.3635311126708984,
|
| 437 |
+
"logps/chosen": -91.65778350830078,
|
| 438 |
+
"logps/rejected": -117.89949035644531,
|
| 439 |
+
"loss": 0.1881,
|
| 440 |
+
"rewards/accuracies": 1.0,
|
| 441 |
+
"rewards/chosen": -1.6620346307754517,
|
| 442 |
+
"rewards/margins": 2.1766200065612793,
|
| 443 |
+
"rewards/rejected": -3.8386547565460205,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.129707112970712,
|
| 448 |
+
"grad_norm": 5.115809440612793,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": -2.2903695106506348,
|
| 451 |
+
"logits/rejected": -2.2926692962646484,
|
| 452 |
+
"logps/chosen": -104.5173110961914,
|
| 453 |
+
"logps/rejected": -123.13216400146484,
|
| 454 |
+
"loss": 0.1798,
|
| 455 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 456 |
+
"rewards/chosen": -1.7224146127700806,
|
| 457 |
+
"rewards/margins": 2.3892369270324707,
|
| 458 |
+
"rewards/rejected": -4.111651420593262,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.464435146443515,
|
| 463 |
+
"grad_norm": 5.882064342498779,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": -2.2836384773254395,
|
| 466 |
+
"logits/rejected": -2.2969231605529785,
|
| 467 |
+
"logps/chosen": -88.8235855102539,
|
| 468 |
+
"logps/rejected": -119.67433166503906,
|
| 469 |
+
"loss": 0.1558,
|
| 470 |
+
"rewards/accuracies": 0.987500011920929,
|
| 471 |
+
"rewards/chosen": -1.6937462091445923,
|
| 472 |
+
"rewards/margins": 2.4059743881225586,
|
| 473 |
+
"rewards/rejected": -4.0997209548950195,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.799163179916318,
|
| 478 |
+
"grad_norm": 6.9003376960754395,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": -2.289567232131958,
|
| 481 |
+
"logits/rejected": -2.3216423988342285,
|
| 482 |
+
"logps/chosen": -90.58432006835938,
|
| 483 |
+
"logps/rejected": -118.13006591796875,
|
| 484 |
+
"loss": 0.1538,
|
| 485 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 486 |
+
"rewards/chosen": -1.6574989557266235,
|
| 487 |
+
"rewards/margins": 2.9354054927825928,
|
| 488 |
+
"rewards/rejected": -4.592904567718506,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.133891213389122,
|
| 493 |
+
"grad_norm": 4.916522979736328,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": -2.2699310779571533,
|
| 496 |
+
"logits/rejected": -2.3001017570495605,
|
| 497 |
+
"logps/chosen": -100.2576675415039,
|
| 498 |
+
"logps/rejected": -133.8759307861328,
|
| 499 |
+
"loss": 0.1373,
|
| 500 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 501 |
+
"rewards/chosen": -2.174388885498047,
|
| 502 |
+
"rewards/margins": 3.038696050643921,
|
| 503 |
+
"rewards/rejected": -5.213086128234863,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.468619246861925,
|
| 508 |
+
"grad_norm": 6.739722728729248,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": -2.2740581035614014,
|
| 511 |
+
"logits/rejected": -2.315854549407959,
|
| 512 |
+
"logps/chosen": -83.28224182128906,
|
| 513 |
+
"logps/rejected": -107.7516098022461,
|
| 514 |
+
"loss": 0.1257,
|
| 515 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 516 |
+
"rewards/chosen": -1.777440071105957,
|
| 517 |
+
"rewards/margins": 2.704913377761841,
|
| 518 |
+
"rewards/rejected": -4.482353687286377,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.803347280334728,
|
| 523 |
+
"grad_norm": 4.988001823425293,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": -2.2616047859191895,
|
| 526 |
+
"logits/rejected": -2.2596449851989746,
|
| 527 |
+
"logps/chosen": -107.07649230957031,
|
| 528 |
+
"logps/rejected": -139.80697631835938,
|
| 529 |
+
"loss": 0.1184,
|
| 530 |
+
"rewards/accuracies": 0.987500011920929,
|
| 531 |
+
"rewards/chosen": -2.618734359741211,
|
| 532 |
+
"rewards/margins": 3.291966199874878,
|
| 533 |
+
"rewards/rejected": -5.910700798034668,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.138075313807532,
|
| 538 |
+
"grad_norm": 4.956677436828613,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": -2.233889102935791,
|
| 541 |
+
"logits/rejected": -2.2601330280303955,
|
| 542 |
+
"logps/chosen": -95.82877349853516,
|
| 543 |
+
"logps/rejected": -138.9019775390625,
|
| 544 |
+
"loss": 0.1106,
|
| 545 |
+
"rewards/accuracies": 0.987500011920929,
|
| 546 |
+
"rewards/chosen": -2.5194194316864014,
|
| 547 |
+
"rewards/margins": 3.470710039138794,
|
| 548 |
+
"rewards/rejected": -5.990128993988037,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.472803347280335,
|
| 553 |
+
"grad_norm": 4.895273208618164,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": -2.2324471473693848,
|
| 556 |
+
"logits/rejected": -2.233158588409424,
|
| 557 |
+
"logps/chosen": -117.90779113769531,
|
| 558 |
+
"logps/rejected": -141.53753662109375,
|
| 559 |
+
"loss": 0.0907,
|
| 560 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 561 |
+
"rewards/chosen": -2.7019529342651367,
|
| 562 |
+
"rewards/margins": 3.4567368030548096,
|
| 563 |
+
"rewards/rejected": -6.158689975738525,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.807531380753138,
|
| 568 |
+
"grad_norm": 5.789585590362549,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": -2.2296676635742188,
|
| 571 |
+
"logits/rejected": -2.2535061836242676,
|
| 572 |
+
"logps/chosen": -117.69709777832031,
|
| 573 |
+
"logps/rejected": -150.61538696289062,
|
| 574 |
+
"loss": 0.0923,
|
| 575 |
+
"rewards/accuracies": 1.0,
|
| 576 |
+
"rewards/chosen": -3.4674232006073,
|
| 577 |
+
"rewards/margins": 3.8480961322784424,
|
| 578 |
+
"rewards/rejected": -7.3155198097229,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.142259414225942,
|
| 583 |
+
"grad_norm": 4.082385540008545,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": -2.232024908065796,
|
| 586 |
+
"logits/rejected": -2.235680103302002,
|
| 587 |
+
"logps/chosen": -96.60597229003906,
|
| 588 |
+
"logps/rejected": -130.7404022216797,
|
| 589 |
+
"loss": 0.0876,
|
| 590 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 591 |
+
"rewards/chosen": -2.816174268722534,
|
| 592 |
+
"rewards/margins": 3.2225749492645264,
|
| 593 |
+
"rewards/rejected": -6.038748741149902,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.476987447698745,
|
| 598 |
+
"grad_norm": 4.423525333404541,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": -2.2275261878967285,
|
| 601 |
+
"logits/rejected": -2.2222421169281006,
|
| 602 |
+
"logps/chosen": -107.16130065917969,
|
| 603 |
+
"logps/rejected": -148.48500061035156,
|
| 604 |
+
"loss": 0.0662,
|
| 605 |
+
"rewards/accuracies": 1.0,
|
| 606 |
+
"rewards/chosen": -3.10858154296875,
|
| 607 |
+
"rewards/margins": 3.9508070945739746,
|
| 608 |
+
"rewards/rejected": -7.059388637542725,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.811715481171548,
|
| 613 |
+
"grad_norm": 3.721898078918457,
|
| 614 |
+
"learning_rate": 1.198246553841744e-06,
|
| 615 |
+
"logits/chosen": -2.2333359718322754,
|
| 616 |
+
"logits/rejected": -2.2442851066589355,
|
| 617 |
+
"logps/chosen": -104.8399429321289,
|
| 618 |
+
"logps/rejected": -137.98049926757812,
|
| 619 |
+
"loss": 0.0808,
|
| 620 |
+
"rewards/accuracies": 0.987500011920929,
|
| 621 |
+
"rewards/chosen": -3.3306171894073486,
|
| 622 |
+
"rewards/margins": 3.471170425415039,
|
| 623 |
+
"rewards/rejected": -6.80178689956665,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 14.146443514644352,
|
| 628 |
+
"grad_norm": 4.411396026611328,
|
| 629 |
+
"learning_rate": 1.0722278491423998e-06,
|
| 630 |
+
"logits/chosen": -2.2033934593200684,
|
| 631 |
+
"logits/rejected": -2.206735610961914,
|
| 632 |
+
"logps/chosen": -122.04057312011719,
|
| 633 |
+
"logps/rejected": -139.2510528564453,
|
| 634 |
+
"loss": 0.0651,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/chosen": -3.4570648670196533,
|
| 637 |
+
"rewards/margins": 3.5551300048828125,
|
| 638 |
+
"rewards/rejected": -7.012194633483887,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.481171548117155,
|
| 643 |
+
"grad_norm": 4.514885902404785,
|
| 644 |
+
"learning_rate": 9.513790969606926e-07,
|
| 645 |
+
"logits/chosen": -2.1915841102600098,
|
| 646 |
+
"logits/rejected": -2.23836088180542,
|
| 647 |
+
"logps/chosen": -111.24171447753906,
|
| 648 |
+
"logps/rejected": -159.8766326904297,
|
| 649 |
+
"loss": 0.0609,
|
| 650 |
+
"rewards/accuracies": 1.0,
|
| 651 |
+
"rewards/chosen": -3.719008207321167,
|
| 652 |
+
"rewards/margins": 4.095301628112793,
|
| 653 |
+
"rewards/rejected": -7.814309597015381,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.815899581589958,
|
| 658 |
+
"grad_norm": 6.274470329284668,
|
| 659 |
+
"learning_rate": 8.361378897445643e-07,
|
| 660 |
+
"logits/chosen": -2.2278056144714355,
|
| 661 |
+
"logits/rejected": -2.2360167503356934,
|
| 662 |
+
"logps/chosen": -95.31124877929688,
|
| 663 |
+
"logps/rejected": -136.5842742919922,
|
| 664 |
+
"loss": 0.0624,
|
| 665 |
+
"rewards/accuracies": 1.0,
|
| 666 |
+
"rewards/chosen": -3.1528682708740234,
|
| 667 |
+
"rewards/margins": 4.095580577850342,
|
| 668 |
+
"rewards/rejected": -7.248448848724365,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 15.150627615062762,
|
| 673 |
+
"grad_norm": 4.49701452255249,
|
| 674 |
+
"learning_rate": 7.269215150626391e-07,
|
| 675 |
+
"logits/chosen": -2.196305513381958,
|
| 676 |
+
"logits/rejected": -2.2363815307617188,
|
| 677 |
+
"logps/chosen": -101.97003173828125,
|
| 678 |
+
"logps/rejected": -151.15646362304688,
|
| 679 |
+
"loss": 0.0513,
|
| 680 |
+
"rewards/accuracies": 1.0,
|
| 681 |
+
"rewards/chosen": -3.562624454498291,
|
| 682 |
+
"rewards/margins": 4.104978084564209,
|
| 683 |
+
"rewards/rejected": -7.667603492736816,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 15.485355648535565,
|
| 688 |
+
"grad_norm": 4.746140956878662,
|
| 689 |
+
"learning_rate": 6.241254446089942e-07,
|
| 690 |
+
"logits/chosen": -2.1973156929016113,
|
| 691 |
+
"logits/rejected": -2.217236042022705,
|
| 692 |
+
"logps/chosen": -108.36579895019531,
|
| 693 |
+
"logps/rejected": -146.45358276367188,
|
| 694 |
+
"loss": 0.0588,
|
| 695 |
+
"rewards/accuracies": 0.987500011920929,
|
| 696 |
+
"rewards/chosen": -3.8717312812805176,
|
| 697 |
+
"rewards/margins": 3.9130451679229736,
|
| 698 |
+
"rewards/rejected": -7.784776210784912,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 15.820083682008368,
|
| 703 |
+
"grad_norm": 2.910703182220459,
|
| 704 |
+
"learning_rate": 5.281219022030423e-07,
|
| 705 |
+
"logits/chosen": -2.1933655738830566,
|
| 706 |
+
"logits/rejected": -2.193134307861328,
|
| 707 |
+
"logps/chosen": -125.05366516113281,
|
| 708 |
+
"logps/rejected": -158.47085571289062,
|
| 709 |
+
"loss": 0.0484,
|
| 710 |
+
"rewards/accuracies": 1.0,
|
| 711 |
+
"rewards/chosen": -3.9004642963409424,
|
| 712 |
+
"rewards/margins": 4.252579689025879,
|
| 713 |
+
"rewards/rejected": -8.153043746948242,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 16.15481171548117,
|
| 718 |
+
"grad_norm": 2.814772367477417,
|
| 719 |
+
"learning_rate": 4.392585159698087e-07,
|
| 720 |
+
"logits/chosen": -2.1886072158813477,
|
| 721 |
+
"logits/rejected": -2.1937201023101807,
|
| 722 |
+
"logps/chosen": -113.6917724609375,
|
| 723 |
+
"logps/rejected": -160.83851623535156,
|
| 724 |
+
"loss": 0.0443,
|
| 725 |
+
"rewards/accuracies": 1.0,
|
| 726 |
+
"rewards/chosen": -3.779496669769287,
|
| 727 |
+
"rewards/margins": 4.261423587799072,
|
| 728 |
+
"rewards/rejected": -8.04092025756836,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 16.489539748953973,
|
| 733 |
+
"grad_norm": 3.579289197921753,
|
| 734 |
+
"learning_rate": 3.578570595810274e-07,
|
| 735 |
+
"logits/chosen": -2.19553542137146,
|
| 736 |
+
"logits/rejected": -2.1956517696380615,
|
| 737 |
+
"logps/chosen": -110.0953140258789,
|
| 738 |
+
"logps/rejected": -165.99652099609375,
|
| 739 |
+
"loss": 0.0483,
|
| 740 |
+
"rewards/accuracies": 1.0,
|
| 741 |
+
"rewards/chosen": -3.7303287982940674,
|
| 742 |
+
"rewards/margins": 4.63196325302124,
|
| 743 |
+
"rewards/rejected": -8.36229133605957,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 16.824267782426777,
|
| 748 |
+
"grad_norm": 4.428997039794922,
|
| 749 |
+
"learning_rate": 2.8421228711503127e-07,
|
| 750 |
+
"logits/chosen": -2.1704812049865723,
|
| 751 |
+
"logits/rejected": -2.183809280395508,
|
| 752 |
+
"logps/chosen": -99.66941833496094,
|
| 753 |
+
"logps/rejected": -152.3459930419922,
|
| 754 |
+
"loss": 0.0468,
|
| 755 |
+
"rewards/accuracies": 1.0,
|
| 756 |
+
"rewards/chosen": -3.7393298149108887,
|
| 757 |
+
"rewards/margins": 4.549952030181885,
|
| 758 |
+
"rewards/rejected": -8.289281845092773,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 17.15899581589958,
|
| 763 |
+
"grad_norm": 3.5141501426696777,
|
| 764 |
+
"learning_rate": 2.1859086575439225e-07,
|
| 765 |
+
"logits/chosen": -2.114220380783081,
|
| 766 |
+
"logits/rejected": -2.1453700065612793,
|
| 767 |
+
"logps/chosen": -119.66983795166016,
|
| 768 |
+
"logps/rejected": -161.91326904296875,
|
| 769 |
+
"loss": 0.0398,
|
| 770 |
+
"rewards/accuracies": 1.0,
|
| 771 |
+
"rewards/chosen": -4.162126064300537,
|
| 772 |
+
"rewards/margins": 4.615090370178223,
|
| 773 |
+
"rewards/rejected": -8.777216911315918,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 17.493723849372383,
|
| 778 |
+
"grad_norm": 3.1655192375183105,
|
| 779 |
+
"learning_rate": 1.6123041018599766e-07,
|
| 780 |
+
"logits/chosen": -2.1598916053771973,
|
| 781 |
+
"logits/rejected": -2.151259660720825,
|
| 782 |
+
"logps/chosen": -112.63690185546875,
|
| 783 |
+
"logps/rejected": -166.2643280029297,
|
| 784 |
+
"loss": 0.0436,
|
| 785 |
+
"rewards/accuracies": 1.0,
|
| 786 |
+
"rewards/chosen": -3.9895179271698,
|
| 787 |
+
"rewards/margins": 4.71376895904541,
|
| 788 |
+
"rewards/rejected": -8.703287124633789,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 17.828451882845187,
|
| 793 |
+
"grad_norm": 3.882448673248291,
|
| 794 |
+
"learning_rate": 1.1233862220001168e-07,
|
| 795 |
+
"logits/chosen": -2.1259069442749023,
|
| 796 |
+
"logits/rejected": -2.1679906845092773,
|
| 797 |
+
"logps/chosen": -125.42464447021484,
|
| 798 |
+
"logps/rejected": -172.642822265625,
|
| 799 |
+
"loss": 0.0477,
|
| 800 |
+
"rewards/accuracies": 1.0,
|
| 801 |
+
"rewards/chosen": -4.517868995666504,
|
| 802 |
+
"rewards/margins": 4.534079551696777,
|
| 803 |
+
"rewards/rejected": -9.051949501037598,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 18.16317991631799,
|
| 808 |
+
"grad_norm": 4.275852203369141,
|
| 809 |
+
"learning_rate": 7.209253860320897e-08,
|
| 810 |
+
"logits/chosen": -2.1740193367004395,
|
| 811 |
+
"logits/rejected": -2.1897895336151123,
|
| 812 |
+
"logps/chosen": -133.6866455078125,
|
| 813 |
+
"logps/rejected": -160.42288208007812,
|
| 814 |
+
"loss": 0.0408,
|
| 815 |
+
"rewards/accuracies": 1.0,
|
| 816 |
+
"rewards/chosen": -4.688433647155762,
|
| 817 |
+
"rewards/margins": 4.159676551818848,
|
| 818 |
+
"rewards/rejected": -8.848111152648926,
|
| 819 |
+
"step": 540
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 18.497907949790793,
|
| 823 |
+
"grad_norm": 3.586958646774292,
|
| 824 |
+
"learning_rate": 4.063789016999331e-08,
|
| 825 |
+
"logits/chosen": -2.157022476196289,
|
| 826 |
+
"logits/rejected": -2.179140567779541,
|
| 827 |
+
"logps/chosen": -122.80704498291016,
|
| 828 |
+
"logps/rejected": -170.018798828125,
|
| 829 |
+
"loss": 0.0423,
|
| 830 |
+
"rewards/accuracies": 1.0,
|
| 831 |
+
"rewards/chosen": -4.441340923309326,
|
| 832 |
+
"rewards/margins": 4.718876838684082,
|
| 833 |
+
"rewards/rejected": -9.16021728515625,
|
| 834 |
+
"step": 550
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 18.8326359832636,
|
| 838 |
+
"grad_norm": 2.9948108196258545,
|
| 839 |
+
"learning_rate": 1.808857395232788e-08,
|
| 840 |
+
"logits/chosen": -2.1356325149536133,
|
| 841 |
+
"logits/rejected": -2.1427738666534424,
|
| 842 |
+
"logps/chosen": -112.40225982666016,
|
| 843 |
+
"logps/rejected": -166.0186767578125,
|
| 844 |
+
"loss": 0.04,
|
| 845 |
+
"rewards/accuracies": 1.0,
|
| 846 |
+
"rewards/chosen": -4.3510541915893555,
|
| 847 |
+
"rewards/margins": 4.859889030456543,
|
| 848 |
+
"rewards/rejected": -9.210943222045898,
|
| 849 |
+
"step": 560
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 19.1673640167364,
|
| 853 |
+
"grad_norm": 3.9700310230255127,
|
| 854 |
+
"learning_rate": 4.526240859345499e-09,
|
| 855 |
+
"logits/chosen": -2.1602721214294434,
|
| 856 |
+
"logits/rejected": -2.168781042098999,
|
| 857 |
+
"logps/chosen": -125.03184509277344,
|
| 858 |
+
"logps/rejected": -174.86129760742188,
|
| 859 |
+
"loss": 0.041,
|
| 860 |
+
"rewards/accuracies": 1.0,
|
| 861 |
+
"rewards/chosen": -4.168228626251221,
|
| 862 |
+
"rewards/margins": 4.846875190734863,
|
| 863 |
+
"rewards/rejected": -9.015104293823242,
|
| 864 |
+
"step": 570
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 19.502092050209207,
|
| 868 |
+
"grad_norm": 3.226668119430542,
|
| 869 |
+
"learning_rate": 0.0,
|
| 870 |
+
"logits/chosen": -2.183656692504883,
|
| 871 |
+
"logits/rejected": -2.190368175506592,
|
| 872 |
+
"logps/chosen": -107.56755065917969,
|
| 873 |
+
"logps/rejected": -153.33026123046875,
|
| 874 |
+
"loss": 0.0408,
|
| 875 |
+
"rewards/accuracies": 0.987500011920929,
|
| 876 |
+
"rewards/chosen": -4.3311662673950195,
|
| 877 |
+
"rewards/margins": 4.147943019866943,
|
| 878 |
+
"rewards/rejected": -8.479108810424805,
|
| 879 |
+
"step": 580
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 19.502092050209207,
|
| 883 |
+
"step": 580,
|
| 884 |
+
"total_flos": 2.1306294447112192e+18,
|
| 885 |
+
"train_loss": 0.1631378454381022,
|
| 886 |
+
"train_runtime": 3724.909,
|
| 887 |
+
"train_samples_per_second": 10.245,
|
| 888 |
+
"train_steps_per_second": 0.156
|
| 889 |
+
}
|
| 890 |
+
],
|
| 891 |
+
"logging_steps": 10,
|
| 892 |
+
"max_steps": 580,
|
| 893 |
+
"num_input_tokens_seen": 0,
|
| 894 |
+
"num_train_epochs": 20,
|
| 895 |
+
"save_steps": 50,
|
| 896 |
+
"stateful_callbacks": {
|
| 897 |
+
"TrainerControl": {
|
| 898 |
+
"args": {
|
| 899 |
+
"should_epoch_stop": false,
|
| 900 |
+
"should_evaluate": false,
|
| 901 |
+
"should_log": false,
|
| 902 |
+
"should_save": true,
|
| 903 |
+
"should_training_stop": true
|
| 904 |
+
},
|
| 905 |
+
"attributes": {}
|
| 906 |
+
}
|
| 907 |
+
},
|
| 908 |
+
"total_flos": 2.1306294447112192e+18,
|
| 909 |
+
"train_batch_size": 1,
|
| 910 |
+
"trial_name": null,
|
| 911 |
+
"trial_params": null
|
| 912 |
+
}
|
Area_SFT/training_loss.png
ADDED
|
Area_SFT/training_rewards_accuracies.png
ADDED
|
Power/checkpoint-150/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ab3eed5206a949bc24f9c53e328ab2e3a9b77a8ab0755bf26079dfc712d0d40
|
| 3 |
+
size 160284754
|
Power/checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1182f1bb7b761762aa5777d371231e213bfcc03d3bff0592c03acb4e11aa1be
|
| 3 |
+
size 80013120
|
Power/checkpoint-450/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc1849def1c6d097904ffc6b36c74dbd85a7985f2ded2d3561b5b77622f864cd
|
| 3 |
+
size 80013120
|
Power/checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d41d504463e4903aa14fbc4ffee0bcacba6d3d41c800280b850274b217f80b94
|
| 3 |
+
size 80013120
|
Power/checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95734e88ba764dd02f9b440b4d7c6464d19423a01f1c791ee722fb2dbfa2eb06
|
| 3 |
+
size 160284754
|
Power/checkpoint-550/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c262021924e982d654eaedd71f92e0c085faf471e47b86e4f8fe92ae248ceb63
|
| 3 |
+
size 80013120
|
Power/dpo/checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:131505d3334cd72d2c76250efb9fa6c0e5385e519e217f795ba07e38439499e8
|
| 3 |
+
size 80013120
|
Power/dpo/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae06af10b837cb5d4e6572f13eaf0f043c19aaa94206a8e8b6b0ac9eed8a79f2
|
| 3 |
+
size 160284754
|
Power_Area_Time/.ipynb_checkpoints/trainer_log-checkpoint.jsonl
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 580, "loss": 0.693, "accuracy": 0.4000000059604645, "learning_rate": 8.620689655172415e-07, "epoch": 0.3448275862068966, "percentage": 1.72, "elapsed_time": "0:01:12", "remaining_time": "1:08:25"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 580, "loss": 0.6929, "accuracy": 0.512499988079071, "learning_rate": 1.724137931034483e-06, "epoch": 0.6896551724137931, "percentage": 3.45, "elapsed_time": "0:02:19", "remaining_time": "1:05:15"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 580, "loss": 0.6935, "accuracy": 0.574999988079071, "learning_rate": 2.5862068965517246e-06, "epoch": 1.0344827586206897, "percentage": 5.17, "elapsed_time": "0:03:35", "remaining_time": "1:05:54"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 580, "loss": 0.6923, "accuracy": 0.5625, "learning_rate": 3.448275862068966e-06, "epoch": 1.3793103448275863, "percentage": 6.9, "elapsed_time": "0:04:51", "remaining_time": "1:05:35"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 580, "loss": 0.6954, "accuracy": 0.625, "learning_rate": 4.310344827586207e-06, "epoch": 1.7241379310344827, "percentage": 8.62, "elapsed_time": "0:06:01", "remaining_time": "1:03:56"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 580, "loss": 0.6938, "accuracy": 0.5874999761581421, "learning_rate": 4.999818897894192e-06, "epoch": 2.0689655172413794, "percentage": 10.34, "elapsed_time": "0:07:23", "remaining_time": "1:03:59"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 580, "loss": 0.6905, "accuracy": 0.637499988079071, "learning_rate": 4.9934830787948756e-06, "epoch": 2.413793103448276, "percentage": 12.07, "elapsed_time": "0:08:32", "remaining_time": "1:02:13"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 580, "loss": 0.6942, "accuracy": 0.4749999940395355, "learning_rate": 4.978118375700895e-06, "epoch": 2.7586206896551726, "percentage": 13.79, "elapsed_time": "0:09:43", "remaining_time": "1:00:48"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 580, "loss": 0.6919, "accuracy": 0.550000011920929, "learning_rate": 4.953780424089803e-06, "epoch": 3.103448275862069, "percentage": 15.52, "elapsed_time": "0:10:55", "remaining_time": "0:59:28"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 580, "loss": 0.6905, "accuracy": 0.4749999940395355, "learning_rate": 4.920557351506409e-06, "epoch": 3.4482758620689653, "percentage": 17.24, "elapsed_time": "0:12:14", "remaining_time": "0:58:45"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 580, "loss": 0.6899, "accuracy": 0.5874999761581421, "learning_rate": 4.878569458453592e-06, "epoch": 3.793103448275862, "percentage": 18.97, "elapsed_time": "0:13:29", "remaining_time": "0:57:37"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 580, "loss": 0.6878, "accuracy": 0.4749999940395355, "learning_rate": 4.827968782785062e-06, "epoch": 4.137931034482759, "percentage": 20.69, "elapsed_time": "0:14:43", "remaining_time": "0:56:28"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 580, "loss": 0.6857, "accuracy": 0.625, "learning_rate": 4.7689385491773934e-06, "epoch": 4.482758620689655, "percentage": 22.41, "elapsed_time": "0:15:52", "remaining_time": "0:54:58"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 580, "loss": 0.6804, "accuracy": 0.6625000238418579, "learning_rate": 4.70169250567482e-06, "epoch": 4.827586206896552, "percentage": 24.14, "elapsed_time": "0:17:05", "remaining_time": "0:53:43"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 580, "loss": 0.6803, "accuracy": 0.637499988079071, "learning_rate": 4.626474149709127e-06, "epoch": 5.172413793103448, "percentage": 25.86, "elapsed_time": "0:18:22", "remaining_time": "0:52:40"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 580, "loss": 0.6748, "accuracy": 0.6625000238418579, "learning_rate": 4.54355584639723e-06, "epoch": 5.517241379310345, "percentage": 27.59, "elapsed_time": "0:19:39", "remaining_time": "0:51:36"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 580, "loss": 0.6706, "accuracy": 0.7250000238418579, "learning_rate": 4.45323784230908e-06, "epoch": 5.862068965517241, "percentage": 29.31, "elapsed_time": "0:20:49", "remaining_time": "0:50:13"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 580, "loss": 0.6661, "accuracy": 0.7250000238418579, "learning_rate": 4.355847178277025e-06, "epoch": 6.206896551724138, "percentage": 31.03, "elapsed_time": "0:21:57", "remaining_time": "0:48:46"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 580, "loss": 0.6573, "accuracy": 0.7124999761581421, "learning_rate": 4.2517365051833564e-06, "epoch": 6.551724137931035, "percentage": 32.76, "elapsed_time": "0:23:11", "remaining_time": "0:47:36"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 580, "loss": 0.6595, "accuracy": 0.574999988079071, "learning_rate": 4.141282807014034e-06, "epoch": 6.896551724137931, "percentage": 34.48, "elapsed_time": "0:24:23", "remaining_time": "0:46:20"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 580, "loss": 0.6498, "accuracy": 0.737500011920929, "learning_rate": 4.024886035802432e-06, "epoch": 7.241379310344827, "percentage": 36.21, "elapsed_time": "0:25:34", "remaining_time": "0:45:03"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 580, "loss": 0.6457, "accuracy": 0.699999988079071, "learning_rate": 3.9029676634059565e-06, "epoch": 7.586206896551724, "percentage": 37.93, "elapsed_time": "0:26:48", "remaining_time": "0:43:51"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 580, "loss": 0.6391, "accuracy": 0.6875, "learning_rate": 3.7759691553595214e-06, "epoch": 7.931034482758621, "percentage": 39.66, "elapsed_time": "0:27:57", "remaining_time": "0:42:32"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 580, "loss": 0.6322, "accuracy": 0.675000011920929, "learning_rate": 3.6443503723320837e-06, "epoch": 8.275862068965518, "percentage": 41.38, "elapsed_time": "0:29:08", "remaining_time": "0:41:16"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 580, "loss": 0.6217, "accuracy": 0.7749999761581421, "learning_rate": 3.508587904974522e-06, "epoch": 8.620689655172415, "percentage": 43.1, "elapsed_time": "0:30:22", "remaining_time": "0:40:06"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 580, "loss": 0.6273, "accuracy": 0.762499988079071, "learning_rate": 3.3691733481883693e-06, "epoch": 8.96551724137931, "percentage": 44.83, "elapsed_time": "0:31:32", "remaining_time": "0:38:49"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 580, "loss": 0.6077, "accuracy": 0.75, "learning_rate": 3.226611521064278e-06, "epoch": 9.310344827586206, "percentage": 46.55, "elapsed_time": "0:32:49", "remaining_time": "0:37:40"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 580, "loss": 0.6161, "accuracy": 0.7875000238418579, "learning_rate": 3.0814186389357765e-06, "epoch": 9.655172413793103, "percentage": 48.28, "elapsed_time": "0:34:01", "remaining_time": "0:36:26"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 580, "loss": 0.605, "accuracy": 0.75, "learning_rate": 2.9341204441673267e-06, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:35:11", "remaining_time": "0:35:11"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 580, "loss": 0.6044, "accuracy": 0.7749999761581421, "learning_rate": 2.785250302445062e-06, "epoch": 10.344827586206897, "percentage": 51.72, "elapsed_time": "0:36:27", "remaining_time": "0:34:02"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 580, "loss": 0.589, "accuracy": 0.7875000238418579, "learning_rate": 2.6353472714635443e-06, "epoch": 10.689655172413794, "percentage": 53.45, "elapsed_time": "0:37:40", "remaining_time": "0:32:48"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 580, "loss": 0.5912, "accuracy": 0.737500011920929, "learning_rate": 2.4849541490017868e-06, "epoch": 11.03448275862069, "percentage": 55.17, "elapsed_time": "0:38:51", "remaining_time": "0:31:34"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 580, "loss": 0.5903, "accuracy": 0.7875000238418579, "learning_rate": 2.3346155074564712e-06, "epoch": 11.379310344827585, "percentage": 56.9, "elapsed_time": "0:40:05", "remaining_time": "0:30:22"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 580, "loss": 0.5773, "accuracy": 0.8374999761581421, "learning_rate": 2.184875721949277e-06, "epoch": 11.724137931034482, "percentage": 58.62, "elapsed_time": "0:41:23", "remaining_time": "0:29:12"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 580, "loss": 0.5738, "accuracy": 0.8374999761581421, "learning_rate": 2.0362769991485514e-06, "epoch": 12.068965517241379, "percentage": 60.34, "elapsed_time": "0:42:32", "remaining_time": "0:27:57"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 580, "loss": 0.5678, "accuracy": 0.8125, "learning_rate": 1.8893574139429226e-06, "epoch": 12.413793103448276, "percentage": 62.07, "elapsed_time": "0:43:44", "remaining_time": "0:26:43"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 580, "loss": 0.5739, "accuracy": 0.7875000238418579, "learning_rate": 1.744648961076068e-06, "epoch": 12.758620689655173, "percentage": 63.79, "elapsed_time": "0:44:55", "remaining_time": "0:25:29"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 580, "loss": 0.5856, "accuracy": 0.75, "learning_rate": 1.602675628797636e-06, "epoch": 13.10344827586207, "percentage": 65.52, "elapsed_time": "0:46:02", "remaining_time": "0:24:13"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 580, "loss": 0.5641, "accuracy": 0.824999988079071, "learning_rate": 1.4639515015056205e-06, "epoch": 13.448275862068966, "percentage": 67.24, "elapsed_time": "0:47:14", "remaining_time": "0:23:00"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 580, "loss": 0.5611, "accuracy": 0.824999988079071, "learning_rate": 1.328978898250525e-06, "epoch": 13.793103448275861, "percentage": 68.97, "elapsed_time": "0:48:29", "remaining_time": "0:21:49"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 580, "loss": 0.558, "accuracy": 0.762499988079071, "learning_rate": 1.198246553841744e-06, "epoch": 14.137931034482758, "percentage": 70.69, "elapsed_time": "0:49:39", "remaining_time": "0:20:35"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 580, "loss": 0.551, "accuracy": 0.824999988079071, "learning_rate": 1.0722278491423998e-06, "epoch": 14.482758620689655, "percentage": 72.41, "elapsed_time": "0:50:47", "remaining_time": "0:19:20"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 580, "loss": 0.5586, "accuracy": 0.699999988079071, "learning_rate": 9.513790969606926e-07, "epoch": 14.827586206896552, "percentage": 74.14, "elapsed_time": "0:52:08", "remaining_time": "0:18:11"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 580, "loss": 0.5532, "accuracy": 0.800000011920929, "learning_rate": 8.361378897445643e-07, "epoch": 15.172413793103448, "percentage": 75.86, "elapsed_time": "0:53:18", "remaining_time": "0:16:57"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 580, "loss": 0.5493, "accuracy": 0.862500011920929, "learning_rate": 7.269215150626391e-07, "epoch": 15.517241379310345, "percentage": 77.59, "elapsed_time": "0:54:34", "remaining_time": "0:15:45"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 580, "loss": 0.5519, "accuracy": 0.762499988079071, "learning_rate": 6.241254446089942e-07, "epoch": 15.862068965517242, "percentage": 79.31, "elapsed_time": "0:55:44", "remaining_time": "0:14:32"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 580, "loss": 0.5514, "accuracy": 0.824999988079071, "learning_rate": 5.281219022030423e-07, "epoch": 16.20689655172414, "percentage": 81.03, "elapsed_time": "0:57:01", "remaining_time": "0:13:20"}
|
Power_Area_Time/checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 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 |
+
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area_Time/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area_Time/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area_Time/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% 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 + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area_Time/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.896551724137931,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3448275862068966,
|
| 13 |
+
"grad_norm": 0.5030671954154968,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.8564815521240234,
|
| 16 |
+
"logits/rejected": 1.8255866765975952,
|
| 17 |
+
"logps/chosen": -95.54290008544922,
|
| 18 |
+
"logps/rejected": -79.79582214355469,
|
| 19 |
+
"loss": 0.693,
|
| 20 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 21 |
+
"rewards/chosen": -0.0028573228046298027,
|
| 22 |
+
"rewards/margins": 0.0005112116923555732,
|
| 23 |
+
"rewards/rejected": -0.0033685355447232723,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6896551724137931,
|
| 28 |
+
"grad_norm": 0.45081979036331177,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.781947374343872,
|
| 31 |
+
"logits/rejected": 1.6911979913711548,
|
| 32 |
+
"logps/chosen": -104.20463562011719,
|
| 33 |
+
"logps/rejected": -78.91150665283203,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": 0.00018558502779342234,
|
| 37 |
+
"rewards/margins": -0.002152198925614357,
|
| 38 |
+
"rewards/rejected": 0.0023377849720418453,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0344827586206897,
|
| 43 |
+
"grad_norm": 0.41456305980682373,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.7937275171279907,
|
| 46 |
+
"logits/rejected": 1.729128122329712,
|
| 47 |
+
"logps/chosen": -90.21867370605469,
|
| 48 |
+
"logps/rejected": -71.69265747070312,
|
| 49 |
+
"loss": 0.6935,
|
| 50 |
+
"rewards/accuracies": 0.574999988079071,
|
| 51 |
+
"rewards/chosen": 0.003012509550899267,
|
| 52 |
+
"rewards/margins": 0.009945740923285484,
|
| 53 |
+
"rewards/rejected": -0.006933231838047504,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3793103448275863,
|
| 58 |
+
"grad_norm": 0.45128729939460754,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.864363670349121,
|
| 61 |
+
"logits/rejected": 1.9002879858016968,
|
| 62 |
+
"logps/chosen": -87.1126480102539,
|
| 63 |
+
"logps/rejected": -77.18392181396484,
|
| 64 |
+
"loss": 0.6923,
|
| 65 |
+
"rewards/accuracies": 0.5625,
|
| 66 |
+
"rewards/chosen": 0.0013037443859502673,
|
| 67 |
+
"rewards/margins": 0.006342612206935883,
|
| 68 |
+
"rewards/rejected": -0.005038867238909006,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.7241379310344827,
|
| 73 |
+
"grad_norm": 0.4960842728614807,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.7825076580047607,
|
| 76 |
+
"logits/rejected": 1.829602837562561,
|
| 77 |
+
"logps/chosen": -78.63069915771484,
|
| 78 |
+
"logps/rejected": -91.36685180664062,
|
| 79 |
+
"loss": 0.6954,
|
| 80 |
+
"rewards/accuracies": 0.625,
|
| 81 |
+
"rewards/chosen": 0.009792634285986423,
|
| 82 |
+
"rewards/margins": 0.014146638102829456,
|
| 83 |
+
"rewards/rejected": -0.0043540047481656075,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0689655172413794,
|
| 88 |
+
"grad_norm": 0.5404626727104187,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.8061244487762451,
|
| 91 |
+
"logits/rejected": 1.7855304479599,
|
| 92 |
+
"logps/chosen": -90.69072723388672,
|
| 93 |
+
"logps/rejected": -72.0459213256836,
|
| 94 |
+
"loss": 0.6938,
|
| 95 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 96 |
+
"rewards/chosen": 0.002143201883882284,
|
| 97 |
+
"rewards/margins": 0.005239076912403107,
|
| 98 |
+
"rewards/rejected": -0.0030958750285208225,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.413793103448276,
|
| 103 |
+
"grad_norm": 0.5091063380241394,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.6158870458602905,
|
| 106 |
+
"logits/rejected": 1.696754813194275,
|
| 107 |
+
"logps/chosen": -76.28319549560547,
|
| 108 |
+
"logps/rejected": -77.81846618652344,
|
| 109 |
+
"loss": 0.6905,
|
| 110 |
+
"rewards/accuracies": 0.637499988079071,
|
| 111 |
+
"rewards/chosen": 1.5049334251671098e-05,
|
| 112 |
+
"rewards/margins": 0.007967600598931313,
|
| 113 |
+
"rewards/rejected": -0.00795255322009325,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.7586206896551726,
|
| 118 |
+
"grad_norm": 0.6066665053367615,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.6109062433242798,
|
| 121 |
+
"logits/rejected": 1.7185981273651123,
|
| 122 |
+
"logps/chosen": -84.615966796875,
|
| 123 |
+
"logps/rejected": -96.0793228149414,
|
| 124 |
+
"loss": 0.6942,
|
| 125 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 126 |
+
"rewards/chosen": -0.000627221364993602,
|
| 127 |
+
"rewards/margins": 0.0009560534963384271,
|
| 128 |
+
"rewards/rejected": -0.0015832759672775865,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.103448275862069,
|
| 133 |
+
"grad_norm": 0.5341666340827942,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.8657306432724,
|
| 136 |
+
"logits/rejected": 1.8894052505493164,
|
| 137 |
+
"logps/chosen": -87.67496490478516,
|
| 138 |
+
"logps/rejected": -77.41777038574219,
|
| 139 |
+
"loss": 0.6919,
|
| 140 |
+
"rewards/accuracies": 0.550000011920929,
|
| 141 |
+
"rewards/chosen": -0.004135184455662966,
|
| 142 |
+
"rewards/margins": 0.011894735507667065,
|
| 143 |
+
"rewards/rejected": -0.016029920428991318,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.4482758620689653,
|
| 148 |
+
"grad_norm": 0.5891664028167725,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.8143476247787476,
|
| 151 |
+
"logits/rejected": 1.8618648052215576,
|
| 152 |
+
"logps/chosen": -82.7096176147461,
|
| 153 |
+
"logps/rejected": -80.64532470703125,
|
| 154 |
+
"loss": 0.6905,
|
| 155 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 156 |
+
"rewards/chosen": -0.014110831543803215,
|
| 157 |
+
"rewards/margins": -0.007867741398513317,
|
| 158 |
+
"rewards/rejected": -0.0062430910766124725,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.793103448275862,
|
| 163 |
+
"grad_norm": 0.5773605704307556,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.7850589752197266,
|
| 166 |
+
"logits/rejected": 1.76922607421875,
|
| 167 |
+
"logps/chosen": -87.4909896850586,
|
| 168 |
+
"logps/rejected": -90.67459869384766,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 171 |
+
"rewards/chosen": 0.0026252653915435076,
|
| 172 |
+
"rewards/margins": 0.014214910566806793,
|
| 173 |
+
"rewards/rejected": -0.011589646339416504,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.137931034482759,
|
| 178 |
+
"grad_norm": 0.6582341194152832,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7467533349990845,
|
| 181 |
+
"logits/rejected": 1.8858740329742432,
|
| 182 |
+
"logps/chosen": -69.12274169921875,
|
| 183 |
+
"logps/rejected": -94.86824035644531,
|
| 184 |
+
"loss": 0.6878,
|
| 185 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 186 |
+
"rewards/chosen": -0.009279675781726837,
|
| 187 |
+
"rewards/margins": 0.0035783485509455204,
|
| 188 |
+
"rewards/rejected": -0.012858022935688496,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.482758620689655,
|
| 193 |
+
"grad_norm": 0.7790700793266296,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.8058643341064453,
|
| 196 |
+
"logits/rejected": 1.866713523864746,
|
| 197 |
+
"logps/chosen": -79.86953735351562,
|
| 198 |
+
"logps/rejected": -76.4103012084961,
|
| 199 |
+
"loss": 0.6857,
|
| 200 |
+
"rewards/accuracies": 0.625,
|
| 201 |
+
"rewards/chosen": 0.00016659722314216197,
|
| 202 |
+
"rewards/margins": 0.023889193311333656,
|
| 203 |
+
"rewards/rejected": -0.02372259460389614,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.827586206896552,
|
| 208 |
+
"grad_norm": 0.7933465242385864,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.7705074548721313,
|
| 211 |
+
"logits/rejected": 1.7728191614151,
|
| 212 |
+
"logps/chosen": -86.46583557128906,
|
| 213 |
+
"logps/rejected": -75.83828735351562,
|
| 214 |
+
"loss": 0.6804,
|
| 215 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 216 |
+
"rewards/chosen": -0.0001745700865285471,
|
| 217 |
+
"rewards/margins": 0.029326915740966797,
|
| 218 |
+
"rewards/rejected": -0.02950148656964302,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.172413793103448,
|
| 223 |
+
"grad_norm": 0.7435988187789917,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.740312933921814,
|
| 226 |
+
"logits/rejected": 1.7526963949203491,
|
| 227 |
+
"logps/chosen": -100.93019104003906,
|
| 228 |
+
"logps/rejected": -90.39695739746094,
|
| 229 |
+
"loss": 0.6803,
|
| 230 |
+
"rewards/accuracies": 0.637499988079071,
|
| 231 |
+
"rewards/chosen": -0.013870477676391602,
|
| 232 |
+
"rewards/margins": 0.03614342585206032,
|
| 233 |
+
"rewards/rejected": -0.05001390725374222,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.517241379310345,
|
| 238 |
+
"grad_norm": 0.8416279554367065,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.7618926763534546,
|
| 241 |
+
"logits/rejected": 1.8320789337158203,
|
| 242 |
+
"logps/chosen": -71.05604553222656,
|
| 243 |
+
"logps/rejected": -82.77362060546875,
|
| 244 |
+
"loss": 0.6748,
|
| 245 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 246 |
+
"rewards/chosen": -0.028952527791261673,
|
| 247 |
+
"rewards/margins": 0.03283882141113281,
|
| 248 |
+
"rewards/rejected": -0.061791349202394485,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.862068965517241,
|
| 253 |
+
"grad_norm": 0.9731557965278625,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.7541310787200928,
|
| 256 |
+
"logits/rejected": 1.845503807067871,
|
| 257 |
+
"logps/chosen": -79.18022155761719,
|
| 258 |
+
"logps/rejected": -89.36749267578125,
|
| 259 |
+
"loss": 0.6706,
|
| 260 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 261 |
+
"rewards/chosen": -0.02990702912211418,
|
| 262 |
+
"rewards/margins": 0.05189533159136772,
|
| 263 |
+
"rewards/rejected": -0.0818023532629013,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.206896551724138,
|
| 268 |
+
"grad_norm": 0.8338156938552856,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.7501287460327148,
|
| 271 |
+
"logits/rejected": 1.7370710372924805,
|
| 272 |
+
"logps/chosen": -91.2562484741211,
|
| 273 |
+
"logps/rejected": -80.88179779052734,
|
| 274 |
+
"loss": 0.6661,
|
| 275 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 276 |
+
"rewards/chosen": -0.03045990690588951,
|
| 277 |
+
"rewards/margins": 0.08234542608261108,
|
| 278 |
+
"rewards/rejected": -0.1128053292632103,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.551724137931035,
|
| 283 |
+
"grad_norm": 0.8057475686073303,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.8594491481781006,
|
| 286 |
+
"logits/rejected": 1.9256786108016968,
|
| 287 |
+
"logps/chosen": -74.18313598632812,
|
| 288 |
+
"logps/rejected": -84.37249755859375,
|
| 289 |
+
"loss": 0.6573,
|
| 290 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 291 |
+
"rewards/chosen": -0.05836126208305359,
|
| 292 |
+
"rewards/margins": 0.06953532248735428,
|
| 293 |
+
"rewards/rejected": -0.12789657711982727,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.896551724137931,
|
| 298 |
+
"grad_norm": 0.957699716091156,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.696286916732788,
|
| 301 |
+
"logits/rejected": 1.782080888748169,
|
| 302 |
+
"logps/chosen": -83.79094696044922,
|
| 303 |
+
"logps/rejected": -79.17488861083984,
|
| 304 |
+
"loss": 0.6595,
|
| 305 |
+
"rewards/accuracies": 0.574999988079071,
|
| 306 |
+
"rewards/chosen": -0.08588370680809021,
|
| 307 |
+
"rewards/margins": 0.062126852571964264,
|
| 308 |
+
"rewards/rejected": -0.14801056683063507,
|
| 309 |
+
"step": 200
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 10,
|
| 313 |
+
"max_steps": 580,
|
| 314 |
+
"num_input_tokens_seen": 0,
|
| 315 |
+
"num_train_epochs": 20,
|
| 316 |
+
"save_steps": 50,
|
| 317 |
+
"stateful_callbacks": {
|
| 318 |
+
"TrainerControl": {
|
| 319 |
+
"args": {
|
| 320 |
+
"should_epoch_stop": false,
|
| 321 |
+
"should_evaluate": false,
|
| 322 |
+
"should_log": false,
|
| 323 |
+
"should_save": true,
|
| 324 |
+
"should_training_stop": false
|
| 325 |
+
},
|
| 326 |
+
"attributes": {}
|
| 327 |
+
}
|
| 328 |
+
},
|
| 329 |
+
"total_flos": 6.756175928193188e+17,
|
| 330 |
+
"train_batch_size": 1,
|
| 331 |
+
"trial_name": null,
|
| 332 |
+
"trial_params": null
|
| 333 |
+
}
|
Power_Area_Time/checkpoint-250/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 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_Area_Time/checkpoint-250/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 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 |
+
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area_Time/checkpoint-250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area_Time/checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area_Time/checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% 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 + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area_Time/checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.620689655172415,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3448275862068966,
|
| 13 |
+
"grad_norm": 0.5030671954154968,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.8564815521240234,
|
| 16 |
+
"logits/rejected": 1.8255866765975952,
|
| 17 |
+
"logps/chosen": -95.54290008544922,
|
| 18 |
+
"logps/rejected": -79.79582214355469,
|
| 19 |
+
"loss": 0.693,
|
| 20 |
+
"rewards/accuracies": 0.4000000059604645,
|
| 21 |
+
"rewards/chosen": -0.0028573228046298027,
|
| 22 |
+
"rewards/margins": 0.0005112116923555732,
|
| 23 |
+
"rewards/rejected": -0.0033685355447232723,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6896551724137931,
|
| 28 |
+
"grad_norm": 0.45081979036331177,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.781947374343872,
|
| 31 |
+
"logits/rejected": 1.6911979913711548,
|
| 32 |
+
"logps/chosen": -104.20463562011719,
|
| 33 |
+
"logps/rejected": -78.91150665283203,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": 0.00018558502779342234,
|
| 37 |
+
"rewards/margins": -0.002152198925614357,
|
| 38 |
+
"rewards/rejected": 0.0023377849720418453,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0344827586206897,
|
| 43 |
+
"grad_norm": 0.41456305980682373,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.7937275171279907,
|
| 46 |
+
"logits/rejected": 1.729128122329712,
|
| 47 |
+
"logps/chosen": -90.21867370605469,
|
| 48 |
+
"logps/rejected": -71.69265747070312,
|
| 49 |
+
"loss": 0.6935,
|
| 50 |
+
"rewards/accuracies": 0.574999988079071,
|
| 51 |
+
"rewards/chosen": 0.003012509550899267,
|
| 52 |
+
"rewards/margins": 0.009945740923285484,
|
| 53 |
+
"rewards/rejected": -0.006933231838047504,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3793103448275863,
|
| 58 |
+
"grad_norm": 0.45128729939460754,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.864363670349121,
|
| 61 |
+
"logits/rejected": 1.9002879858016968,
|
| 62 |
+
"logps/chosen": -87.1126480102539,
|
| 63 |
+
"logps/rejected": -77.18392181396484,
|
| 64 |
+
"loss": 0.6923,
|
| 65 |
+
"rewards/accuracies": 0.5625,
|
| 66 |
+
"rewards/chosen": 0.0013037443859502673,
|
| 67 |
+
"rewards/margins": 0.006342612206935883,
|
| 68 |
+
"rewards/rejected": -0.005038867238909006,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.7241379310344827,
|
| 73 |
+
"grad_norm": 0.4960842728614807,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.7825076580047607,
|
| 76 |
+
"logits/rejected": 1.829602837562561,
|
| 77 |
+
"logps/chosen": -78.63069915771484,
|
| 78 |
+
"logps/rejected": -91.36685180664062,
|
| 79 |
+
"loss": 0.6954,
|
| 80 |
+
"rewards/accuracies": 0.625,
|
| 81 |
+
"rewards/chosen": 0.009792634285986423,
|
| 82 |
+
"rewards/margins": 0.014146638102829456,
|
| 83 |
+
"rewards/rejected": -0.0043540047481656075,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0689655172413794,
|
| 88 |
+
"grad_norm": 0.5404626727104187,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.8061244487762451,
|
| 91 |
+
"logits/rejected": 1.7855304479599,
|
| 92 |
+
"logps/chosen": -90.69072723388672,
|
| 93 |
+
"logps/rejected": -72.0459213256836,
|
| 94 |
+
"loss": 0.6938,
|
| 95 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 96 |
+
"rewards/chosen": 0.002143201883882284,
|
| 97 |
+
"rewards/margins": 0.005239076912403107,
|
| 98 |
+
"rewards/rejected": -0.0030958750285208225,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.413793103448276,
|
| 103 |
+
"grad_norm": 0.5091063380241394,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.6158870458602905,
|
| 106 |
+
"logits/rejected": 1.696754813194275,
|
| 107 |
+
"logps/chosen": -76.28319549560547,
|
| 108 |
+
"logps/rejected": -77.81846618652344,
|
| 109 |
+
"loss": 0.6905,
|
| 110 |
+
"rewards/accuracies": 0.637499988079071,
|
| 111 |
+
"rewards/chosen": 1.5049334251671098e-05,
|
| 112 |
+
"rewards/margins": 0.007967600598931313,
|
| 113 |
+
"rewards/rejected": -0.00795255322009325,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.7586206896551726,
|
| 118 |
+
"grad_norm": 0.6066665053367615,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.6109062433242798,
|
| 121 |
+
"logits/rejected": 1.7185981273651123,
|
| 122 |
+
"logps/chosen": -84.615966796875,
|
| 123 |
+
"logps/rejected": -96.0793228149414,
|
| 124 |
+
"loss": 0.6942,
|
| 125 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 126 |
+
"rewards/chosen": -0.000627221364993602,
|
| 127 |
+
"rewards/margins": 0.0009560534963384271,
|
| 128 |
+
"rewards/rejected": -0.0015832759672775865,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.103448275862069,
|
| 133 |
+
"grad_norm": 0.5341666340827942,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.8657306432724,
|
| 136 |
+
"logits/rejected": 1.8894052505493164,
|
| 137 |
+
"logps/chosen": -87.67496490478516,
|
| 138 |
+
"logps/rejected": -77.41777038574219,
|
| 139 |
+
"loss": 0.6919,
|
| 140 |
+
"rewards/accuracies": 0.550000011920929,
|
| 141 |
+
"rewards/chosen": -0.004135184455662966,
|
| 142 |
+
"rewards/margins": 0.011894735507667065,
|
| 143 |
+
"rewards/rejected": -0.016029920428991318,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.4482758620689653,
|
| 148 |
+
"grad_norm": 0.5891664028167725,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.8143476247787476,
|
| 151 |
+
"logits/rejected": 1.8618648052215576,
|
| 152 |
+
"logps/chosen": -82.7096176147461,
|
| 153 |
+
"logps/rejected": -80.64532470703125,
|
| 154 |
+
"loss": 0.6905,
|
| 155 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 156 |
+
"rewards/chosen": -0.014110831543803215,
|
| 157 |
+
"rewards/margins": -0.007867741398513317,
|
| 158 |
+
"rewards/rejected": -0.0062430910766124725,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.793103448275862,
|
| 163 |
+
"grad_norm": 0.5773605704307556,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.7850589752197266,
|
| 166 |
+
"logits/rejected": 1.76922607421875,
|
| 167 |
+
"logps/chosen": -87.4909896850586,
|
| 168 |
+
"logps/rejected": -90.67459869384766,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 171 |
+
"rewards/chosen": 0.0026252653915435076,
|
| 172 |
+
"rewards/margins": 0.014214910566806793,
|
| 173 |
+
"rewards/rejected": -0.011589646339416504,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.137931034482759,
|
| 178 |
+
"grad_norm": 0.6582341194152832,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7467533349990845,
|
| 181 |
+
"logits/rejected": 1.8858740329742432,
|
| 182 |
+
"logps/chosen": -69.12274169921875,
|
| 183 |
+
"logps/rejected": -94.86824035644531,
|
| 184 |
+
"loss": 0.6878,
|
| 185 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 186 |
+
"rewards/chosen": -0.009279675781726837,
|
| 187 |
+
"rewards/margins": 0.0035783485509455204,
|
| 188 |
+
"rewards/rejected": -0.012858022935688496,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.482758620689655,
|
| 193 |
+
"grad_norm": 0.7790700793266296,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.8058643341064453,
|
| 196 |
+
"logits/rejected": 1.866713523864746,
|
| 197 |
+
"logps/chosen": -79.86953735351562,
|
| 198 |
+
"logps/rejected": -76.4103012084961,
|
| 199 |
+
"loss": 0.6857,
|
| 200 |
+
"rewards/accuracies": 0.625,
|
| 201 |
+
"rewards/chosen": 0.00016659722314216197,
|
| 202 |
+
"rewards/margins": 0.023889193311333656,
|
| 203 |
+
"rewards/rejected": -0.02372259460389614,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.827586206896552,
|
| 208 |
+
"grad_norm": 0.7933465242385864,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.7705074548721313,
|
| 211 |
+
"logits/rejected": 1.7728191614151,
|
| 212 |
+
"logps/chosen": -86.46583557128906,
|
| 213 |
+
"logps/rejected": -75.83828735351562,
|
| 214 |
+
"loss": 0.6804,
|
| 215 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 216 |
+
"rewards/chosen": -0.0001745700865285471,
|
| 217 |
+
"rewards/margins": 0.029326915740966797,
|
| 218 |
+
"rewards/rejected": -0.02950148656964302,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.172413793103448,
|
| 223 |
+
"grad_norm": 0.7435988187789917,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.740312933921814,
|
| 226 |
+
"logits/rejected": 1.7526963949203491,
|
| 227 |
+
"logps/chosen": -100.93019104003906,
|
| 228 |
+
"logps/rejected": -90.39695739746094,
|
| 229 |
+
"loss": 0.6803,
|
| 230 |
+
"rewards/accuracies": 0.637499988079071,
|
| 231 |
+
"rewards/chosen": -0.013870477676391602,
|
| 232 |
+
"rewards/margins": 0.03614342585206032,
|
| 233 |
+
"rewards/rejected": -0.05001390725374222,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.517241379310345,
|
| 238 |
+
"grad_norm": 0.8416279554367065,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.7618926763534546,
|
| 241 |
+
"logits/rejected": 1.8320789337158203,
|
| 242 |
+
"logps/chosen": -71.05604553222656,
|
| 243 |
+
"logps/rejected": -82.77362060546875,
|
| 244 |
+
"loss": 0.6748,
|
| 245 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 246 |
+
"rewards/chosen": -0.028952527791261673,
|
| 247 |
+
"rewards/margins": 0.03283882141113281,
|
| 248 |
+
"rewards/rejected": -0.061791349202394485,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.862068965517241,
|
| 253 |
+
"grad_norm": 0.9731557965278625,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.7541310787200928,
|
| 256 |
+
"logits/rejected": 1.845503807067871,
|
| 257 |
+
"logps/chosen": -79.18022155761719,
|
| 258 |
+
"logps/rejected": -89.36749267578125,
|
| 259 |
+
"loss": 0.6706,
|
| 260 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 261 |
+
"rewards/chosen": -0.02990702912211418,
|
| 262 |
+
"rewards/margins": 0.05189533159136772,
|
| 263 |
+
"rewards/rejected": -0.0818023532629013,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.206896551724138,
|
| 268 |
+
"grad_norm": 0.8338156938552856,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.7501287460327148,
|
| 271 |
+
"logits/rejected": 1.7370710372924805,
|
| 272 |
+
"logps/chosen": -91.2562484741211,
|
| 273 |
+
"logps/rejected": -80.88179779052734,
|
| 274 |
+
"loss": 0.6661,
|
| 275 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 276 |
+
"rewards/chosen": -0.03045990690588951,
|
| 277 |
+
"rewards/margins": 0.08234542608261108,
|
| 278 |
+
"rewards/rejected": -0.1128053292632103,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.551724137931035,
|
| 283 |
+
"grad_norm": 0.8057475686073303,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.8594491481781006,
|
| 286 |
+
"logits/rejected": 1.9256786108016968,
|
| 287 |
+
"logps/chosen": -74.18313598632812,
|
| 288 |
+
"logps/rejected": -84.37249755859375,
|
| 289 |
+
"loss": 0.6573,
|
| 290 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 291 |
+
"rewards/chosen": -0.05836126208305359,
|
| 292 |
+
"rewards/margins": 0.06953532248735428,
|
| 293 |
+
"rewards/rejected": -0.12789657711982727,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.896551724137931,
|
| 298 |
+
"grad_norm": 0.957699716091156,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.696286916732788,
|
| 301 |
+
"logits/rejected": 1.782080888748169,
|
| 302 |
+
"logps/chosen": -83.79094696044922,
|
| 303 |
+
"logps/rejected": -79.17488861083984,
|
| 304 |
+
"loss": 0.6595,
|
| 305 |
+
"rewards/accuracies": 0.574999988079071,
|
| 306 |
+
"rewards/chosen": -0.08588370680809021,
|
| 307 |
+
"rewards/margins": 0.062126852571964264,
|
| 308 |
+
"rewards/rejected": -0.14801056683063507,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.241379310344827,
|
| 313 |
+
"grad_norm": 0.8981906771659851,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.8213344812393188,
|
| 316 |
+
"logits/rejected": 1.9113010168075562,
|
| 317 |
+
"logps/chosen": -67.83535766601562,
|
| 318 |
+
"logps/rejected": -80.57597351074219,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.737500011920929,
|
| 321 |
+
"rewards/chosen": -0.05136314034461975,
|
| 322 |
+
"rewards/margins": 0.10948891937732697,
|
| 323 |
+
"rewards/rejected": -0.16085204482078552,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.586206896551724,
|
| 328 |
+
"grad_norm": 1.0450000762939453,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.8091751337051392,
|
| 331 |
+
"logits/rejected": 1.705392599105835,
|
| 332 |
+
"logps/chosen": -98.79942321777344,
|
| 333 |
+
"logps/rejected": -79.21489715576172,
|
| 334 |
+
"loss": 0.6457,
|
| 335 |
+
"rewards/accuracies": 0.699999988079071,
|
| 336 |
+
"rewards/chosen": -0.09070365875959396,
|
| 337 |
+
"rewards/margins": 0.12246594578027725,
|
| 338 |
+
"rewards/rejected": -0.21316960453987122,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.931034482758621,
|
| 343 |
+
"grad_norm": 0.9624446034431458,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8079789876937866,
|
| 346 |
+
"logits/rejected": 1.8931957483291626,
|
| 347 |
+
"logps/chosen": -77.8460922241211,
|
| 348 |
+
"logps/rejected": -76.8448715209961,
|
| 349 |
+
"loss": 0.6391,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.09181363880634308,
|
| 352 |
+
"rewards/margins": 0.09949400275945663,
|
| 353 |
+
"rewards/rejected": -0.19130763411521912,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.275862068965518,
|
| 358 |
+
"grad_norm": 0.9608933925628662,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7896497249603271,
|
| 361 |
+
"logits/rejected": 1.8757597208023071,
|
| 362 |
+
"logps/chosen": -79.89161682128906,
|
| 363 |
+
"logps/rejected": -88.79243469238281,
|
| 364 |
+
"loss": 0.6322,
|
| 365 |
+
"rewards/accuracies": 0.675000011920929,
|
| 366 |
+
"rewards/chosen": -0.10905975103378296,
|
| 367 |
+
"rewards/margins": 0.12515850365161896,
|
| 368 |
+
"rewards/rejected": -0.23421823978424072,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.620689655172415,
|
| 373 |
+
"grad_norm": 0.9355646967887878,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.860887885093689,
|
| 376 |
+
"logits/rejected": 1.9076162576675415,
|
| 377 |
+
"logps/chosen": -85.80632781982422,
|
| 378 |
+
"logps/rejected": -104.0634765625,
|
| 379 |
+
"loss": 0.6217,
|
| 380 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 381 |
+
"rewards/chosen": -0.11484359204769135,
|
| 382 |
+
"rewards/margins": 0.1558837592601776,
|
| 383 |
+
"rewards/rejected": -0.27072733640670776,
|
| 384 |
+
"step": 250
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 10,
|
| 388 |
+
"max_steps": 580,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 20,
|
| 391 |
+
"save_steps": 50,
|
| 392 |
+
"stateful_callbacks": {
|
| 393 |
+
"TrainerControl": {
|
| 394 |
+
"args": {
|
| 395 |
+
"should_epoch_stop": false,
|
| 396 |
+
"should_evaluate": false,
|
| 397 |
+
"should_log": false,
|
| 398 |
+
"should_save": true,
|
| 399 |
+
"should_training_stop": false
|
| 400 |
+
},
|
| 401 |
+
"attributes": {}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"total_flos": 8.455537871237939e+17,
|
| 405 |
+
"train_batch_size": 1,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
Power_Area_Time/checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 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_Area_Time/checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 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 |
+
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area_Time/checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area_Time/checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|