Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +139 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- checkpoint-117/README.md +202 -0
- checkpoint-117/adapter_config.json +34 -0
- checkpoint-117/adapter_model.safetensors +3 -0
- checkpoint-117/optimizer.pt +3 -0
- checkpoint-117/rng_state_0.pth +3 -0
- checkpoint-117/rng_state_1.pth +3 -0
- checkpoint-117/scheduler.pt +3 -0
- checkpoint-117/special_tokens_map.json +23 -0
- checkpoint-117/tokenizer.json +0 -0
- checkpoint-117/tokenizer_config.json +194 -0
- checkpoint-117/trainer_state.json +872 -0
- checkpoint-117/training_args.bin +3 -0
- checkpoint-156/README.md +202 -0
- checkpoint-156/adapter_config.json +34 -0
- checkpoint-156/adapter_model.safetensors +3 -0
- checkpoint-156/optimizer.pt +3 -0
- checkpoint-156/rng_state_0.pth +3 -0
- checkpoint-156/rng_state_1.pth +3 -0
- checkpoint-156/scheduler.pt +3 -0
- checkpoint-156/special_tokens_map.json +23 -0
- checkpoint-156/tokenizer.json +0 -0
- checkpoint-156/tokenizer_config.json +194 -0
- checkpoint-156/trainer_state.json +1153 -0
- checkpoint-156/training_args.bin +3 -0
- checkpoint-39/README.md +202 -0
- checkpoint-39/adapter_config.json +34 -0
- checkpoint-39/adapter_model.safetensors +3 -0
- checkpoint-39/optimizer.pt +3 -0
- checkpoint-39/rng_state_0.pth +3 -0
- checkpoint-39/rng_state_1.pth +3 -0
- checkpoint-39/scheduler.pt +3 -0
- checkpoint-39/special_tokens_map.json +23 -0
- checkpoint-39/tokenizer.json +0 -0
- checkpoint-39/tokenizer_config.json +194 -0
- checkpoint-39/trainer_state.json +310 -0
- checkpoint-39/training_args.bin +3 -0
- checkpoint-78/README.md +202 -0
- checkpoint-78/adapter_config.json +34 -0
- checkpoint-78/adapter_model.safetensors +3 -0
- checkpoint-78/optimizer.pt +3 -0
- checkpoint-78/rng_state_0.pth +3 -0
- checkpoint-78/rng_state_1.pth +3 -0
- checkpoint-78/scheduler.pt +3 -0
- checkpoint-78/special_tokens_map.json +23 -0
- checkpoint-78/tokenizer.json +0 -0
- checkpoint-78/tokenizer_config.json +194 -0
- checkpoint-78/trainer_state.json +591 -0
README.md
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 7 |
+
model-index:
|
| 8 |
+
- name: outputs/axolotl-qlora-out-code-ir-dscoder
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
+
<details><summary>See axolotl config</summary>
|
| 17 |
+
|
| 18 |
+
axolotl version: `0.4.0`
|
| 19 |
+
```yaml
|
| 20 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 21 |
+
model_type: LlamaForCausalLM
|
| 22 |
+
tokenizer_type: LlamaTokenizerFast
|
| 23 |
+
|
| 24 |
+
load_in_8bit: true
|
| 25 |
+
load_in_4bit: false
|
| 26 |
+
strict: false
|
| 27 |
+
|
| 28 |
+
datasets:
|
| 29 |
+
- path: vdaita/editpackft_inst_code
|
| 30 |
+
type: oasst
|
| 31 |
+
dataset_prepared_path:
|
| 32 |
+
val_set_size: 0.05
|
| 33 |
+
output_dir: ./outputs/axolotl-qlora-out-code-ir-dscoder
|
| 34 |
+
|
| 35 |
+
adapter: lora
|
| 36 |
+
lora_model_dir:
|
| 37 |
+
|
| 38 |
+
sequence_len: 2048
|
| 39 |
+
sample_packing: true
|
| 40 |
+
eval_sample_packing: false
|
| 41 |
+
pad_to_sequence_len: true
|
| 42 |
+
|
| 43 |
+
lora_r: 32
|
| 44 |
+
lora_alpha: 16
|
| 45 |
+
lora_dropout: 0.05
|
| 46 |
+
lora_target_modules:
|
| 47 |
+
- q_proj
|
| 48 |
+
- v_proj
|
| 49 |
+
- k_proj
|
| 50 |
+
- o_proj
|
| 51 |
+
- gate_proj
|
| 52 |
+
- down_proj
|
| 53 |
+
- up_proj
|
| 54 |
+
lora_target_linear: true
|
| 55 |
+
lora_fan_in_fan_out:
|
| 56 |
+
|
| 57 |
+
wandb_project: huggingface
|
| 58 |
+
wandb_log_model: axolotl-qlora-code-dscoder
|
| 59 |
+
|
| 60 |
+
gradient_accumulation_steps: 4
|
| 61 |
+
micro_batch_size: 2
|
| 62 |
+
num_epochs: 2
|
| 63 |
+
optimizer: paged_adamw_32bit
|
| 64 |
+
lr_scheduler: cosine
|
| 65 |
+
learning_rate: 0.0002
|
| 66 |
+
|
| 67 |
+
train_on_inputs: false
|
| 68 |
+
group_by_length: false
|
| 69 |
+
bf16: auto
|
| 70 |
+
fp16:
|
| 71 |
+
tf32: false
|
| 72 |
+
|
| 73 |
+
gradient_checkpointing: true
|
| 74 |
+
logging_steps: 1
|
| 75 |
+
flash_attention: true
|
| 76 |
+
|
| 77 |
+
warmup_steps: 20
|
| 78 |
+
evals_per_epoch: 2
|
| 79 |
+
saves_per_epoch: 2
|
| 80 |
+
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
</details><br>
|
| 84 |
+
|
| 85 |
+
# outputs/axolotl-qlora-out-code-ir-dscoder
|
| 86 |
+
|
| 87 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the None dataset.
|
| 88 |
+
It achieves the following results on the evaluation set:
|
| 89 |
+
- Loss: 0.1829
|
| 90 |
+
|
| 91 |
+
## Model description
|
| 92 |
+
|
| 93 |
+
More information needed
|
| 94 |
+
|
| 95 |
+
## Intended uses & limitations
|
| 96 |
+
|
| 97 |
+
More information needed
|
| 98 |
+
|
| 99 |
+
## Training and evaluation data
|
| 100 |
+
|
| 101 |
+
More information needed
|
| 102 |
+
|
| 103 |
+
## Training procedure
|
| 104 |
+
|
| 105 |
+
### Training hyperparameters
|
| 106 |
+
|
| 107 |
+
The following hyperparameters were used during training:
|
| 108 |
+
- learning_rate: 0.0002
|
| 109 |
+
- train_batch_size: 2
|
| 110 |
+
- eval_batch_size: 2
|
| 111 |
+
- seed: 42
|
| 112 |
+
- distributed_type: multi-GPU
|
| 113 |
+
- num_devices: 2
|
| 114 |
+
- gradient_accumulation_steps: 4
|
| 115 |
+
- total_train_batch_size: 16
|
| 116 |
+
- total_eval_batch_size: 4
|
| 117 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 118 |
+
- lr_scheduler_type: cosine
|
| 119 |
+
- lr_scheduler_warmup_steps: 20
|
| 120 |
+
- num_epochs: 2
|
| 121 |
+
|
| 122 |
+
### Training results
|
| 123 |
+
|
| 124 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 125 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 126 |
+
| 0.6574 | 0.01 | 1 | 0.7462 |
|
| 127 |
+
| 0.1778 | 0.5 | 39 | 0.2123 |
|
| 128 |
+
| 0.2121 | 1.0 | 78 | 0.1900 |
|
| 129 |
+
| 0.2512 | 1.47 | 117 | 0.1842 |
|
| 130 |
+
| 0.2024 | 1.97 | 156 | 0.1829 |
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
### Framework versions
|
| 134 |
+
|
| 135 |
+
- PEFT 0.10.0
|
| 136 |
+
- Transformers 4.40.0.dev0
|
| 137 |
+
- Pytorch 2.3.0+cu121
|
| 138 |
+
- Datasets 2.15.0
|
| 139 |
+
- Tokenizers 0.15.0
|
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": null,
|
| 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": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a37f4f9a125964017e08e3838e57040c7e85959632143719ab63c786aa204f4c
|
| 3 |
+
size 319977674
|
checkpoint-117/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-117/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": null,
|
| 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": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-117/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0734de419125b0c74038b4c19a05a1a89bb64df161ad6f8d90d40fb41296e19e
|
| 3 |
+
size 319876032
|
checkpoint-117/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:813b9430419f25ddbb393f851e7e2dfbe17974e96112200eca51d881001df6a7
|
| 3 |
+
size 639908602
|
checkpoint-117/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2304235bfd2ea453f5599567a68c09c9056833e48ed0f472f426e14ec84c002
|
| 3 |
+
size 14512
|
checkpoint-117/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f925dd9070b2af9f2c5b25c25d695d707608ae4e41544b1cbb596fe532b100
|
| 3 |
+
size 14512
|
checkpoint-117/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc753365e75ee095f8322f242dc1057cf030ff435cb7f234e53ffdb10bc1357a
|
| 3 |
+
size 1064
|
checkpoint-117/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 |
+
}
|
checkpoint-117/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-117/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"32000": {
|
| 6 |
+
"content": "õ",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"32001": {
|
| 14 |
+
"content": "÷",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"32002": {
|
| 22 |
+
"content": "Á",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32003": {
|
| 30 |
+
"content": "ý",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32004": {
|
| 38 |
+
"content": "À",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32005": {
|
| 46 |
+
"content": "ÿ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32006": {
|
| 54 |
+
"content": "ø",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32007": {
|
| 62 |
+
"content": "ú",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32008": {
|
| 70 |
+
"content": "þ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32009": {
|
| 78 |
+
"content": "ü",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32010": {
|
| 86 |
+
"content": "ù",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32011": {
|
| 94 |
+
"content": "ö",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32012": {
|
| 102 |
+
"content": "û",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32013": {
|
| 110 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32014": {
|
| 118 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32015": {
|
| 126 |
+
"content": "<｜fim▁hole｜>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32016": {
|
| 134 |
+
"content": "<｜fim▁begin｜>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32017": {
|
| 142 |
+
"content": "<｜fim▁end｜>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32018": {
|
| 150 |
+
"content": "<pad>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32019": {
|
| 158 |
+
"content": "<|User|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32020": {
|
| 166 |
+
"content": "<|Assistant|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32021": {
|
| 174 |
+
"content": "<|EOT|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 183 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<|EOT|>",
|
| 186 |
+
"legacy": true,
|
| 187 |
+
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
+
"sp_model_kwargs": {},
|
| 190 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
+
"unk_token": null,
|
| 192 |
+
"use_default_system_prompt": false,
|
| 193 |
+
"use_fast": true
|
| 194 |
+
}
|
checkpoint-117/trainer_state.json
ADDED
|
@@ -0,0 +1,872 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.4696485623003195,
|
| 5 |
+
"eval_steps": 39,
|
| 6 |
+
"global_step": 117,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.06435385346412659,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.6574,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"eval_loss": 0.7461566925048828,
|
| 21 |
+
"eval_runtime": 151.7973,
|
| 22 |
+
"eval_samples_per_second": 1.482,
|
| 23 |
+
"eval_steps_per_second": 0.376,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 0.062134526669979095,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.6897,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 0.06962593644857407,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 0.6974,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 0.0730314701795578,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 0.7454,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 0.07659862190485,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 0.6962,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08,
|
| 56 |
+
"grad_norm": 0.07314729690551758,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.6602,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09,
|
| 63 |
+
"grad_norm": 0.0892895832657814,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.6594,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1,
|
| 70 |
+
"grad_norm": 0.11520648747682571,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.7406,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12,
|
| 77 |
+
"grad_norm": 0.1333557516336441,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.663,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13,
|
| 84 |
+
"grad_norm": 0.14017663896083832,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.6185,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"grad_norm": 0.1453818678855896,
|
| 92 |
+
"learning_rate": 0.00011000000000000002,
|
| 93 |
+
"loss": 0.602,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"grad_norm": 0.14279265701770782,
|
| 99 |
+
"learning_rate": 0.00012,
|
| 100 |
+
"loss": 0.6151,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17,
|
| 105 |
+
"grad_norm": 0.11934962123632431,
|
| 106 |
+
"learning_rate": 0.00013000000000000002,
|
| 107 |
+
"loss": 0.5085,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18,
|
| 112 |
+
"grad_norm": 0.11375121772289276,
|
| 113 |
+
"learning_rate": 0.00014,
|
| 114 |
+
"loss": 0.4823,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19,
|
| 119 |
+
"grad_norm": 0.09707039594650269,
|
| 120 |
+
"learning_rate": 0.00015000000000000001,
|
| 121 |
+
"loss": 0.4281,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2,
|
| 126 |
+
"grad_norm": 0.11333765089511871,
|
| 127 |
+
"learning_rate": 0.00016,
|
| 128 |
+
"loss": 0.4417,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"grad_norm": 0.09926053136587143,
|
| 134 |
+
"learning_rate": 0.00017,
|
| 135 |
+
"loss": 0.3654,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23,
|
| 140 |
+
"grad_norm": 0.1027929037809372,
|
| 141 |
+
"learning_rate": 0.00018,
|
| 142 |
+
"loss": 0.3748,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24,
|
| 147 |
+
"grad_norm": 0.09768980741500854,
|
| 148 |
+
"learning_rate": 0.00019,
|
| 149 |
+
"loss": 0.3306,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26,
|
| 154 |
+
"grad_norm": 0.08072198927402496,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 0.355,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27,
|
| 161 |
+
"grad_norm": 0.06444709748029709,
|
| 162 |
+
"learning_rate": 0.00019997332081116373,
|
| 163 |
+
"loss": 0.3152,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28,
|
| 168 |
+
"grad_norm": 0.0576409213244915,
|
| 169 |
+
"learning_rate": 0.00019989329748023725,
|
| 170 |
+
"loss": 0.2674,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.29,
|
| 175 |
+
"grad_norm": 0.08624427020549774,
|
| 176 |
+
"learning_rate": 0.0001997599727063717,
|
| 177 |
+
"loss": 0.2807,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.31,
|
| 182 |
+
"grad_norm": 0.08828990906476974,
|
| 183 |
+
"learning_rate": 0.00019957341762950344,
|
| 184 |
+
"loss": 0.2736,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32,
|
| 189 |
+
"grad_norm": 0.0641990676522255,
|
| 190 |
+
"learning_rate": 0.00019933373179239502,
|
| 191 |
+
"loss": 0.2427,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33,
|
| 196 |
+
"grad_norm": 0.05487390235066414,
|
| 197 |
+
"learning_rate": 0.0001990410430875205,
|
| 198 |
+
"loss": 0.2737,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.35,
|
| 203 |
+
"grad_norm": 0.0666637197136879,
|
| 204 |
+
"learning_rate": 0.00019869550768882455,
|
| 205 |
+
"loss": 0.2806,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36,
|
| 210 |
+
"grad_norm": 0.053027719259262085,
|
| 211 |
+
"learning_rate": 0.0001982973099683902,
|
| 212 |
+
"loss": 0.2664,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37,
|
| 217 |
+
"grad_norm": 0.055217448621988297,
|
| 218 |
+
"learning_rate": 0.0001978466623980609,
|
| 219 |
+
"loss": 0.309,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38,
|
| 224 |
+
"grad_norm": 0.05493360385298729,
|
| 225 |
+
"learning_rate": 0.0001973438054360693,
|
| 226 |
+
"loss": 0.2318,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4,
|
| 231 |
+
"grad_norm": 0.0376153439283371,
|
| 232 |
+
"learning_rate": 0.00019678900739873226,
|
| 233 |
+
"loss": 0.2049,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41,
|
| 238 |
+
"grad_norm": 0.03811287507414818,
|
| 239 |
+
"learning_rate": 0.00019618256431728194,
|
| 240 |
+
"loss": 0.2771,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42,
|
| 245 |
+
"grad_norm": 0.04185184836387634,
|
| 246 |
+
"learning_rate": 0.000195524799779908,
|
| 247 |
+
"loss": 0.1843,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43,
|
| 252 |
+
"grad_norm": 0.04743755981326103,
|
| 253 |
+
"learning_rate": 0.0001948160647590966,
|
| 254 |
+
"loss": 0.2414,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"grad_norm": 0.03343382850289345,
|
| 260 |
+
"learning_rate": 0.00019405673742435678,
|
| 261 |
+
"loss": 0.2007,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46,
|
| 266 |
+
"grad_norm": 0.03178093209862709,
|
| 267 |
+
"learning_rate": 0.00019324722294043558,
|
| 268 |
+
"loss": 0.1898,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47,
|
| 273 |
+
"grad_norm": 0.03482227399945259,
|
| 274 |
+
"learning_rate": 0.0001923879532511287,
|
| 275 |
+
"loss": 0.2657,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.49,
|
| 280 |
+
"grad_norm": 0.03727172687649727,
|
| 281 |
+
"learning_rate": 0.0001914793868488021,
|
| 282 |
+
"loss": 0.2185,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"grad_norm": 0.0382206104695797,
|
| 288 |
+
"learning_rate": 0.00019052200852974819,
|
| 289 |
+
"loss": 0.1778,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5,
|
| 294 |
+
"eval_loss": 0.2122737020254135,
|
| 295 |
+
"eval_runtime": 154.5774,
|
| 296 |
+
"eval_samples_per_second": 1.456,
|
| 297 |
+
"eval_steps_per_second": 0.369,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.51,
|
| 302 |
+
"grad_norm": 0.03256627917289734,
|
| 303 |
+
"learning_rate": 0.00018951632913550626,
|
| 304 |
+
"loss": 0.2528,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.52,
|
| 309 |
+
"grad_norm": 0.032382771372795105,
|
| 310 |
+
"learning_rate": 0.00018846288528028555,
|
| 311 |
+
"loss": 0.2165,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.54,
|
| 316 |
+
"grad_norm": 0.030948858708143234,
|
| 317 |
+
"learning_rate": 0.00018736223906463696,
|
| 318 |
+
"loss": 0.1754,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.55,
|
| 323 |
+
"grad_norm": 0.041598908603191376,
|
| 324 |
+
"learning_rate": 0.00018621497777552507,
|
| 325 |
+
"loss": 0.2676,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.56,
|
| 330 |
+
"grad_norm": 0.03000044636428356,
|
| 331 |
+
"learning_rate": 0.00018502171357296144,
|
| 332 |
+
"loss": 0.1501,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.58,
|
| 337 |
+
"grad_norm": 0.03305242955684662,
|
| 338 |
+
"learning_rate": 0.00018378308316336584,
|
| 339 |
+
"loss": 0.1937,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.59,
|
| 344 |
+
"grad_norm": 0.02798221819102764,
|
| 345 |
+
"learning_rate": 0.00018249974745983023,
|
| 346 |
+
"loss": 0.2241,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.6,
|
| 351 |
+
"grad_norm": 0.03340066224336624,
|
| 352 |
+
"learning_rate": 0.00018117239122946615,
|
| 353 |
+
"loss": 0.2078,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.61,
|
| 358 |
+
"grad_norm": 0.032081808894872665,
|
| 359 |
+
"learning_rate": 0.000179801722728024,
|
| 360 |
+
"loss": 0.2061,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.63,
|
| 365 |
+
"grad_norm": 0.033740073442459106,
|
| 366 |
+
"learning_rate": 0.00017838847332197938,
|
| 367 |
+
"loss": 0.2411,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.64,
|
| 372 |
+
"grad_norm": 0.02972455322742462,
|
| 373 |
+
"learning_rate": 0.00017693339709828792,
|
| 374 |
+
"loss": 0.2346,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.65,
|
| 379 |
+
"grad_norm": 0.03134370595216751,
|
| 380 |
+
"learning_rate": 0.0001754372704620164,
|
| 381 |
+
"loss": 0.2573,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.66,
|
| 386 |
+
"grad_norm": 0.035204820334911346,
|
| 387 |
+
"learning_rate": 0.00017390089172206592,
|
| 388 |
+
"loss": 0.2596,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.68,
|
| 393 |
+
"grad_norm": 0.027202850207686424,
|
| 394 |
+
"learning_rate": 0.00017232508066520702,
|
| 395 |
+
"loss": 0.1738,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.69,
|
| 400 |
+
"grad_norm": 0.02930806204676628,
|
| 401 |
+
"learning_rate": 0.00017071067811865476,
|
| 402 |
+
"loss": 0.2178,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7,
|
| 407 |
+
"grad_norm": 0.03558573126792908,
|
| 408 |
+
"learning_rate": 0.00016905854550141716,
|
| 409 |
+
"loss": 0.2677,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.72,
|
| 414 |
+
"grad_norm": 0.03179259970784187,
|
| 415 |
+
"learning_rate": 0.00016736956436465573,
|
| 416 |
+
"loss": 0.1704,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.73,
|
| 421 |
+
"grad_norm": 0.0318523608148098,
|
| 422 |
+
"learning_rate": 0.00016564463592130428,
|
| 423 |
+
"loss": 0.2117,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.74,
|
| 428 |
+
"grad_norm": 0.034657321870326996,
|
| 429 |
+
"learning_rate": 0.00016388468056519612,
|
| 430 |
+
"loss": 0.206,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.75,
|
| 435 |
+
"grad_norm": 0.032808613032102585,
|
| 436 |
+
"learning_rate": 0.00016209063737995715,
|
| 437 |
+
"loss": 0.2235,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.77,
|
| 442 |
+
"grad_norm": 0.029593750834465027,
|
| 443 |
+
"learning_rate": 0.00016026346363792567,
|
| 444 |
+
"loss": 0.1976,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.78,
|
| 449 |
+
"grad_norm": 0.033486686646938324,
|
| 450 |
+
"learning_rate": 0.00015840413428936767,
|
| 451 |
+
"loss": 0.184,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.79,
|
| 456 |
+
"grad_norm": 0.029341375455260277,
|
| 457 |
+
"learning_rate": 0.0001565136414422592,
|
| 458 |
+
"loss": 0.2114,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.81,
|
| 463 |
+
"grad_norm": 0.03653452917933464,
|
| 464 |
+
"learning_rate": 0.00015459299383291345,
|
| 465 |
+
"loss": 0.2183,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.82,
|
| 470 |
+
"grad_norm": 0.03146987408399582,
|
| 471 |
+
"learning_rate": 0.0001526432162877356,
|
| 472 |
+
"loss": 0.2444,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.83,
|
| 477 |
+
"grad_norm": 0.03224271163344383,
|
| 478 |
+
"learning_rate": 0.00015066534917639195,
|
| 479 |
+
"loss": 0.2157,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.84,
|
| 484 |
+
"grad_norm": 0.028182610869407654,
|
| 485 |
+
"learning_rate": 0.00014866044785668563,
|
| 486 |
+
"loss": 0.16,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.86,
|
| 491 |
+
"grad_norm": 0.03271663188934326,
|
| 492 |
+
"learning_rate": 0.0001466295821114348,
|
| 493 |
+
"loss": 0.2102,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.87,
|
| 498 |
+
"grad_norm": 0.032980792224407196,
|
| 499 |
+
"learning_rate": 0.00014457383557765386,
|
| 500 |
+
"loss": 0.2605,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.88,
|
| 505 |
+
"grad_norm": 0.03456718847155571,
|
| 506 |
+
"learning_rate": 0.0001424943051683422,
|
| 507 |
+
"loss": 0.212,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.89,
|
| 512 |
+
"grad_norm": 0.036501459777355194,
|
| 513 |
+
"learning_rate": 0.00014039210048718949,
|
| 514 |
+
"loss": 0.1798,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.91,
|
| 519 |
+
"grad_norm": 0.033730726689100266,
|
| 520 |
+
"learning_rate": 0.000138268343236509,
|
| 521 |
+
"loss": 0.2018,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.92,
|
| 526 |
+
"grad_norm": 0.03012872487306595,
|
| 527 |
+
"learning_rate": 0.00013612416661871533,
|
| 528 |
+
"loss": 0.2309,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.93,
|
| 533 |
+
"grad_norm": 0.032879915088415146,
|
| 534 |
+
"learning_rate": 0.00013396071473166613,
|
| 535 |
+
"loss": 0.1912,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.95,
|
| 540 |
+
"grad_norm": 0.02916533872485161,
|
| 541 |
+
"learning_rate": 0.00013177914195819016,
|
| 542 |
+
"loss": 0.2313,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.96,
|
| 547 |
+
"grad_norm": 0.032934658229351044,
|
| 548 |
+
"learning_rate": 0.00012958061235012706,
|
| 549 |
+
"loss": 0.2118,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.97,
|
| 554 |
+
"grad_norm": 0.03474392369389534,
|
| 555 |
+
"learning_rate": 0.0001273662990072083,
|
| 556 |
+
"loss": 0.1465,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.98,
|
| 561 |
+
"grad_norm": 0.033331647515296936,
|
| 562 |
+
"learning_rate": 0.0001251373834511103,
|
| 563 |
+
"loss": 0.2207,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.0,
|
| 568 |
+
"grad_norm": 0.030515702441334724,
|
| 569 |
+
"learning_rate": 0.0001228950549950134,
|
| 570 |
+
"loss": 0.2121,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.0,
|
| 575 |
+
"eval_loss": 0.19000689685344696,
|
| 576 |
+
"eval_runtime": 153.8331,
|
| 577 |
+
"eval_samples_per_second": 1.463,
|
| 578 |
+
"eval_steps_per_second": 0.371,
|
| 579 |
+
"step": 78
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.01,
|
| 583 |
+
"grad_norm": 0.03746604546904564,
|
| 584 |
+
"learning_rate": 0.00012064051010900397,
|
| 585 |
+
"loss": 0.1755,
|
| 586 |
+
"step": 79
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.02,
|
| 590 |
+
"grad_norm": 0.032529812306165695,
|
| 591 |
+
"learning_rate": 0.00011837495178165706,
|
| 592 |
+
"loss": 0.2279,
|
| 593 |
+
"step": 80
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.01,
|
| 597 |
+
"grad_norm": 0.02698327600955963,
|
| 598 |
+
"learning_rate": 0.00011609958887814129,
|
| 599 |
+
"loss": 0.1718,
|
| 600 |
+
"step": 81
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.02,
|
| 604 |
+
"grad_norm": 0.030606260523200035,
|
| 605 |
+
"learning_rate": 0.00011381563549518823,
|
| 606 |
+
"loss": 0.2253,
|
| 607 |
+
"step": 82
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.04,
|
| 611 |
+
"grad_norm": 0.03295598179101944,
|
| 612 |
+
"learning_rate": 0.00011152431031326978,
|
| 613 |
+
"loss": 0.1592,
|
| 614 |
+
"step": 83
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.05,
|
| 618 |
+
"grad_norm": 0.04062403365969658,
|
| 619 |
+
"learning_rate": 0.00010922683594633021,
|
| 620 |
+
"loss": 0.2458,
|
| 621 |
+
"step": 84
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.06,
|
| 625 |
+
"grad_norm": 0.04118546470999718,
|
| 626 |
+
"learning_rate": 0.00010692443828941918,
|
| 627 |
+
"loss": 0.1938,
|
| 628 |
+
"step": 85
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.07,
|
| 632 |
+
"grad_norm": 0.03897158056497574,
|
| 633 |
+
"learning_rate": 0.00010461834586457398,
|
| 634 |
+
"loss": 0.1816,
|
| 635 |
+
"step": 86
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.09,
|
| 639 |
+
"grad_norm": 0.031059524044394493,
|
| 640 |
+
"learning_rate": 0.00010230978916530012,
|
| 641 |
+
"loss": 0.2024,
|
| 642 |
+
"step": 87
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.1,
|
| 646 |
+
"grad_norm": 0.0294091384857893,
|
| 647 |
+
"learning_rate": 0.0001,
|
| 648 |
+
"loss": 0.199,
|
| 649 |
+
"step": 88
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.11,
|
| 653 |
+
"grad_norm": 0.03456791117787361,
|
| 654 |
+
"learning_rate": 9.76902108346999e-05,
|
| 655 |
+
"loss": 0.2616,
|
| 656 |
+
"step": 89
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.12,
|
| 660 |
+
"grad_norm": 0.03276889771223068,
|
| 661 |
+
"learning_rate": 9.538165413542607e-05,
|
| 662 |
+
"loss": 0.2115,
|
| 663 |
+
"step": 90
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.14,
|
| 667 |
+
"grad_norm": 0.03038157895207405,
|
| 668 |
+
"learning_rate": 9.307556171058085e-05,
|
| 669 |
+
"loss": 0.1721,
|
| 670 |
+
"step": 91
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.15,
|
| 674 |
+
"grad_norm": 0.02885863371193409,
|
| 675 |
+
"learning_rate": 9.077316405366981e-05,
|
| 676 |
+
"loss": 0.2199,
|
| 677 |
+
"step": 92
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.16,
|
| 681 |
+
"grad_norm": 0.03282390534877777,
|
| 682 |
+
"learning_rate": 8.847568968673026e-05,
|
| 683 |
+
"loss": 0.1885,
|
| 684 |
+
"step": 93
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.18,
|
| 688 |
+
"grad_norm": 0.03559669107198715,
|
| 689 |
+
"learning_rate": 8.61843645048118e-05,
|
| 690 |
+
"loss": 0.2253,
|
| 691 |
+
"step": 94
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.19,
|
| 695 |
+
"grad_norm": 0.027744270861148834,
|
| 696 |
+
"learning_rate": 8.39004111218587e-05,
|
| 697 |
+
"loss": 0.1825,
|
| 698 |
+
"step": 95
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.2,
|
| 702 |
+
"grad_norm": 0.035874996334314346,
|
| 703 |
+
"learning_rate": 8.162504821834295e-05,
|
| 704 |
+
"loss": 0.1983,
|
| 705 |
+
"step": 96
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.21,
|
| 709 |
+
"grad_norm": 0.03325138986110687,
|
| 710 |
+
"learning_rate": 7.935948989099605e-05,
|
| 711 |
+
"loss": 0.1812,
|
| 712 |
+
"step": 97
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.23,
|
| 716 |
+
"grad_norm": 0.028679154813289642,
|
| 717 |
+
"learning_rate": 7.710494500498662e-05,
|
| 718 |
+
"loss": 0.1875,
|
| 719 |
+
"step": 98
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.24,
|
| 723 |
+
"grad_norm": 0.036103084683418274,
|
| 724 |
+
"learning_rate": 7.486261654888973e-05,
|
| 725 |
+
"loss": 0.2025,
|
| 726 |
+
"step": 99
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.25,
|
| 730 |
+
"grad_norm": 0.0321945995092392,
|
| 731 |
+
"learning_rate": 7.263370099279172e-05,
|
| 732 |
+
"loss": 0.2342,
|
| 733 |
+
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.27,
|
| 737 |
+
"grad_norm": 0.0304876621812582,
|
| 738 |
+
"learning_rate": 7.041938764987297e-05,
|
| 739 |
+
"loss": 0.1642,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.28,
|
| 744 |
+
"grad_norm": 0.03619467467069626,
|
| 745 |
+
"learning_rate": 6.822085804180984e-05,
|
| 746 |
+
"loss": 0.187,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.29,
|
| 751 |
+
"grad_norm": 0.03597356379032135,
|
| 752 |
+
"learning_rate": 6.603928526833387e-05,
|
| 753 |
+
"loss": 0.1343,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3,
|
| 758 |
+
"grad_norm": 0.036540765315294266,
|
| 759 |
+
"learning_rate": 6.387583338128471e-05,
|
| 760 |
+
"loss": 0.2062,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.32,
|
| 765 |
+
"grad_norm": 0.03327038511633873,
|
| 766 |
+
"learning_rate": 6.173165676349103e-05,
|
| 767 |
+
"loss": 0.22,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.33,
|
| 772 |
+
"grad_norm": 0.03374246507883072,
|
| 773 |
+
"learning_rate": 5.960789951281052e-05,
|
| 774 |
+
"loss": 0.1765,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.34,
|
| 779 |
+
"grad_norm": 0.032783444970846176,
|
| 780 |
+
"learning_rate": 5.750569483165784e-05,
|
| 781 |
+
"loss": 0.2397,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.35,
|
| 786 |
+
"grad_norm": 0.03667570650577545,
|
| 787 |
+
"learning_rate": 5.542616442234618e-05,
|
| 788 |
+
"loss": 0.1841,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.37,
|
| 793 |
+
"grad_norm": 0.029467754065990448,
|
| 794 |
+
"learning_rate": 5.337041788856518e-05,
|
| 795 |
+
"loss": 0.2282,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.38,
|
| 800 |
+
"grad_norm": 0.03702455386519432,
|
| 801 |
+
"learning_rate": 5.1339552143314384e-05,
|
| 802 |
+
"loss": 0.2601,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.39,
|
| 807 |
+
"grad_norm": 0.033595018088817596,
|
| 808 |
+
"learning_rate": 4.933465082360807e-05,
|
| 809 |
+
"loss": 0.2077,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.41,
|
| 814 |
+
"grad_norm": 0.03349510580301285,
|
| 815 |
+
"learning_rate": 4.735678371226441e-05,
|
| 816 |
+
"loss": 0.1686,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.42,
|
| 821 |
+
"grad_norm": 0.03149344027042389,
|
| 822 |
+
"learning_rate": 4.540700616708658e-05,
|
| 823 |
+
"loss": 0.2075,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.43,
|
| 828 |
+
"grad_norm": 0.035017482936382294,
|
| 829 |
+
"learning_rate": 4.3486358557740814e-05,
|
| 830 |
+
"loss": 0.1462,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.44,
|
| 835 |
+
"grad_norm": 0.029670318588614464,
|
| 836 |
+
"learning_rate": 4.159586571063236e-05,
|
| 837 |
+
"loss": 0.1602,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.46,
|
| 842 |
+
"grad_norm": 0.037266362458467484,
|
| 843 |
+
"learning_rate": 3.973653636207437e-05,
|
| 844 |
+
"loss": 0.1798,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.47,
|
| 849 |
+
"grad_norm": 0.03251258283853531,
|
| 850 |
+
"learning_rate": 3.7909362620042865e-05,
|
| 851 |
+
"loss": 0.2512,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.47,
|
| 856 |
+
"eval_loss": 0.18417498469352722,
|
| 857 |
+
"eval_runtime": 155.2041,
|
| 858 |
+
"eval_samples_per_second": 1.45,
|
| 859 |
+
"eval_steps_per_second": 0.367,
|
| 860 |
+
"step": 117
|
| 861 |
+
}
|
| 862 |
+
],
|
| 863 |
+
"logging_steps": 1,
|
| 864 |
+
"max_steps": 156,
|
| 865 |
+
"num_input_tokens_seen": 0,
|
| 866 |
+
"num_train_epochs": 2,
|
| 867 |
+
"save_steps": 39,
|
| 868 |
+
"total_flos": 1.5385293522940723e+17,
|
| 869 |
+
"train_batch_size": 2,
|
| 870 |
+
"trial_name": null,
|
| 871 |
+
"trial_params": null
|
| 872 |
+
}
|
checkpoint-117/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a36fbc0a6f934d44efc86171559fa23366edb0ce2bd813321dd96ee628e581
|
| 3 |
+
size 5816
|
checkpoint-156/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-156/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": null,
|
| 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": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-156/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fb4c83788eaa1383631dcfc20456f19c724f49293a692f80fdc494dc9eb1fb5
|
| 3 |
+
size 319876032
|
checkpoint-156/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8723eab393f883e62a0a226ad5b975dffdf9e5aa2a9aa93725b1d630ac7162
|
| 3 |
+
size 639908602
|
checkpoint-156/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb5f4d3520c3e16efd97d14e349ff1f633d03118094d6d114f67777e6f1ec5a
|
| 3 |
+
size 14512
|
checkpoint-156/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2519d6595bffbd44de4304aaa4e4ad7c7c8126595e444097a19d02a3795a19f7
|
| 3 |
+
size 14512
|
checkpoint-156/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f29957f67a1104eb7e1e9c865e3a858f808178d1ef723e4f73e2ac1579011a4d
|
| 3 |
+
size 1064
|
checkpoint-156/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 |
+
}
|
checkpoint-156/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-156/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"32000": {
|
| 6 |
+
"content": "õ",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"32001": {
|
| 14 |
+
"content": "÷",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"32002": {
|
| 22 |
+
"content": "Á",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32003": {
|
| 30 |
+
"content": "ý",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32004": {
|
| 38 |
+
"content": "À",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32005": {
|
| 46 |
+
"content": "ÿ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32006": {
|
| 54 |
+
"content": "ø",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32007": {
|
| 62 |
+
"content": "ú",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32008": {
|
| 70 |
+
"content": "þ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32009": {
|
| 78 |
+
"content": "ü",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32010": {
|
| 86 |
+
"content": "ù",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32011": {
|
| 94 |
+
"content": "ö",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32012": {
|
| 102 |
+
"content": "û",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32013": {
|
| 110 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32014": {
|
| 118 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32015": {
|
| 126 |
+
"content": "<｜fim▁hole｜>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32016": {
|
| 134 |
+
"content": "<｜fim▁begin｜>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32017": {
|
| 142 |
+
"content": "<｜fim▁end｜>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32018": {
|
| 150 |
+
"content": "<pad>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32019": {
|
| 158 |
+
"content": "<|User|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32020": {
|
| 166 |
+
"content": "<|Assistant|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32021": {
|
| 174 |
+
"content": "<|EOT|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 183 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<|EOT|>",
|
| 186 |
+
"legacy": true,
|
| 187 |
+
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
+
"sp_model_kwargs": {},
|
| 190 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
+
"unk_token": null,
|
| 192 |
+
"use_default_system_prompt": false,
|
| 193 |
+
"use_fast": true
|
| 194 |
+
}
|
checkpoint-156/trainer_state.json
ADDED
|
@@ -0,0 +1,1153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9680511182108626,
|
| 5 |
+
"eval_steps": 39,
|
| 6 |
+
"global_step": 156,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.06435385346412659,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.6574,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"eval_loss": 0.7461566925048828,
|
| 21 |
+
"eval_runtime": 151.7973,
|
| 22 |
+
"eval_samples_per_second": 1.482,
|
| 23 |
+
"eval_steps_per_second": 0.376,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 0.062134526669979095,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.6897,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 0.06962593644857407,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 0.6974,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 0.0730314701795578,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 0.7454,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 0.07659862190485,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 0.6962,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08,
|
| 56 |
+
"grad_norm": 0.07314729690551758,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.6602,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09,
|
| 63 |
+
"grad_norm": 0.0892895832657814,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.6594,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1,
|
| 70 |
+
"grad_norm": 0.11520648747682571,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.7406,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12,
|
| 77 |
+
"grad_norm": 0.1333557516336441,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.663,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13,
|
| 84 |
+
"grad_norm": 0.14017663896083832,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.6185,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"grad_norm": 0.1453818678855896,
|
| 92 |
+
"learning_rate": 0.00011000000000000002,
|
| 93 |
+
"loss": 0.602,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"grad_norm": 0.14279265701770782,
|
| 99 |
+
"learning_rate": 0.00012,
|
| 100 |
+
"loss": 0.6151,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17,
|
| 105 |
+
"grad_norm": 0.11934962123632431,
|
| 106 |
+
"learning_rate": 0.00013000000000000002,
|
| 107 |
+
"loss": 0.5085,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18,
|
| 112 |
+
"grad_norm": 0.11375121772289276,
|
| 113 |
+
"learning_rate": 0.00014,
|
| 114 |
+
"loss": 0.4823,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19,
|
| 119 |
+
"grad_norm": 0.09707039594650269,
|
| 120 |
+
"learning_rate": 0.00015000000000000001,
|
| 121 |
+
"loss": 0.4281,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2,
|
| 126 |
+
"grad_norm": 0.11333765089511871,
|
| 127 |
+
"learning_rate": 0.00016,
|
| 128 |
+
"loss": 0.4417,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"grad_norm": 0.09926053136587143,
|
| 134 |
+
"learning_rate": 0.00017,
|
| 135 |
+
"loss": 0.3654,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23,
|
| 140 |
+
"grad_norm": 0.1027929037809372,
|
| 141 |
+
"learning_rate": 0.00018,
|
| 142 |
+
"loss": 0.3748,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24,
|
| 147 |
+
"grad_norm": 0.09768980741500854,
|
| 148 |
+
"learning_rate": 0.00019,
|
| 149 |
+
"loss": 0.3306,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26,
|
| 154 |
+
"grad_norm": 0.08072198927402496,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 0.355,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27,
|
| 161 |
+
"grad_norm": 0.06444709748029709,
|
| 162 |
+
"learning_rate": 0.00019997332081116373,
|
| 163 |
+
"loss": 0.3152,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28,
|
| 168 |
+
"grad_norm": 0.0576409213244915,
|
| 169 |
+
"learning_rate": 0.00019989329748023725,
|
| 170 |
+
"loss": 0.2674,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.29,
|
| 175 |
+
"grad_norm": 0.08624427020549774,
|
| 176 |
+
"learning_rate": 0.0001997599727063717,
|
| 177 |
+
"loss": 0.2807,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.31,
|
| 182 |
+
"grad_norm": 0.08828990906476974,
|
| 183 |
+
"learning_rate": 0.00019957341762950344,
|
| 184 |
+
"loss": 0.2736,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32,
|
| 189 |
+
"grad_norm": 0.0641990676522255,
|
| 190 |
+
"learning_rate": 0.00019933373179239502,
|
| 191 |
+
"loss": 0.2427,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33,
|
| 196 |
+
"grad_norm": 0.05487390235066414,
|
| 197 |
+
"learning_rate": 0.0001990410430875205,
|
| 198 |
+
"loss": 0.2737,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.35,
|
| 203 |
+
"grad_norm": 0.0666637197136879,
|
| 204 |
+
"learning_rate": 0.00019869550768882455,
|
| 205 |
+
"loss": 0.2806,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36,
|
| 210 |
+
"grad_norm": 0.053027719259262085,
|
| 211 |
+
"learning_rate": 0.0001982973099683902,
|
| 212 |
+
"loss": 0.2664,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37,
|
| 217 |
+
"grad_norm": 0.055217448621988297,
|
| 218 |
+
"learning_rate": 0.0001978466623980609,
|
| 219 |
+
"loss": 0.309,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38,
|
| 224 |
+
"grad_norm": 0.05493360385298729,
|
| 225 |
+
"learning_rate": 0.0001973438054360693,
|
| 226 |
+
"loss": 0.2318,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4,
|
| 231 |
+
"grad_norm": 0.0376153439283371,
|
| 232 |
+
"learning_rate": 0.00019678900739873226,
|
| 233 |
+
"loss": 0.2049,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41,
|
| 238 |
+
"grad_norm": 0.03811287507414818,
|
| 239 |
+
"learning_rate": 0.00019618256431728194,
|
| 240 |
+
"loss": 0.2771,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42,
|
| 245 |
+
"grad_norm": 0.04185184836387634,
|
| 246 |
+
"learning_rate": 0.000195524799779908,
|
| 247 |
+
"loss": 0.1843,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43,
|
| 252 |
+
"grad_norm": 0.04743755981326103,
|
| 253 |
+
"learning_rate": 0.0001948160647590966,
|
| 254 |
+
"loss": 0.2414,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"grad_norm": 0.03343382850289345,
|
| 260 |
+
"learning_rate": 0.00019405673742435678,
|
| 261 |
+
"loss": 0.2007,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46,
|
| 266 |
+
"grad_norm": 0.03178093209862709,
|
| 267 |
+
"learning_rate": 0.00019324722294043558,
|
| 268 |
+
"loss": 0.1898,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47,
|
| 273 |
+
"grad_norm": 0.03482227399945259,
|
| 274 |
+
"learning_rate": 0.0001923879532511287,
|
| 275 |
+
"loss": 0.2657,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.49,
|
| 280 |
+
"grad_norm": 0.03727172687649727,
|
| 281 |
+
"learning_rate": 0.0001914793868488021,
|
| 282 |
+
"loss": 0.2185,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"grad_norm": 0.0382206104695797,
|
| 288 |
+
"learning_rate": 0.00019052200852974819,
|
| 289 |
+
"loss": 0.1778,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5,
|
| 294 |
+
"eval_loss": 0.2122737020254135,
|
| 295 |
+
"eval_runtime": 154.5774,
|
| 296 |
+
"eval_samples_per_second": 1.456,
|
| 297 |
+
"eval_steps_per_second": 0.369,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.51,
|
| 302 |
+
"grad_norm": 0.03256627917289734,
|
| 303 |
+
"learning_rate": 0.00018951632913550626,
|
| 304 |
+
"loss": 0.2528,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.52,
|
| 309 |
+
"grad_norm": 0.032382771372795105,
|
| 310 |
+
"learning_rate": 0.00018846288528028555,
|
| 311 |
+
"loss": 0.2165,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.54,
|
| 316 |
+
"grad_norm": 0.030948858708143234,
|
| 317 |
+
"learning_rate": 0.00018736223906463696,
|
| 318 |
+
"loss": 0.1754,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.55,
|
| 323 |
+
"grad_norm": 0.041598908603191376,
|
| 324 |
+
"learning_rate": 0.00018621497777552507,
|
| 325 |
+
"loss": 0.2676,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.56,
|
| 330 |
+
"grad_norm": 0.03000044636428356,
|
| 331 |
+
"learning_rate": 0.00018502171357296144,
|
| 332 |
+
"loss": 0.1501,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.58,
|
| 337 |
+
"grad_norm": 0.03305242955684662,
|
| 338 |
+
"learning_rate": 0.00018378308316336584,
|
| 339 |
+
"loss": 0.1937,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.59,
|
| 344 |
+
"grad_norm": 0.02798221819102764,
|
| 345 |
+
"learning_rate": 0.00018249974745983023,
|
| 346 |
+
"loss": 0.2241,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.6,
|
| 351 |
+
"grad_norm": 0.03340066224336624,
|
| 352 |
+
"learning_rate": 0.00018117239122946615,
|
| 353 |
+
"loss": 0.2078,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.61,
|
| 358 |
+
"grad_norm": 0.032081808894872665,
|
| 359 |
+
"learning_rate": 0.000179801722728024,
|
| 360 |
+
"loss": 0.2061,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.63,
|
| 365 |
+
"grad_norm": 0.033740073442459106,
|
| 366 |
+
"learning_rate": 0.00017838847332197938,
|
| 367 |
+
"loss": 0.2411,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.64,
|
| 372 |
+
"grad_norm": 0.02972455322742462,
|
| 373 |
+
"learning_rate": 0.00017693339709828792,
|
| 374 |
+
"loss": 0.2346,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.65,
|
| 379 |
+
"grad_norm": 0.03134370595216751,
|
| 380 |
+
"learning_rate": 0.0001754372704620164,
|
| 381 |
+
"loss": 0.2573,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.66,
|
| 386 |
+
"grad_norm": 0.035204820334911346,
|
| 387 |
+
"learning_rate": 0.00017390089172206592,
|
| 388 |
+
"loss": 0.2596,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.68,
|
| 393 |
+
"grad_norm": 0.027202850207686424,
|
| 394 |
+
"learning_rate": 0.00017232508066520702,
|
| 395 |
+
"loss": 0.1738,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.69,
|
| 400 |
+
"grad_norm": 0.02930806204676628,
|
| 401 |
+
"learning_rate": 0.00017071067811865476,
|
| 402 |
+
"loss": 0.2178,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7,
|
| 407 |
+
"grad_norm": 0.03558573126792908,
|
| 408 |
+
"learning_rate": 0.00016905854550141716,
|
| 409 |
+
"loss": 0.2677,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.72,
|
| 414 |
+
"grad_norm": 0.03179259970784187,
|
| 415 |
+
"learning_rate": 0.00016736956436465573,
|
| 416 |
+
"loss": 0.1704,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.73,
|
| 421 |
+
"grad_norm": 0.0318523608148098,
|
| 422 |
+
"learning_rate": 0.00016564463592130428,
|
| 423 |
+
"loss": 0.2117,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.74,
|
| 428 |
+
"grad_norm": 0.034657321870326996,
|
| 429 |
+
"learning_rate": 0.00016388468056519612,
|
| 430 |
+
"loss": 0.206,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.75,
|
| 435 |
+
"grad_norm": 0.032808613032102585,
|
| 436 |
+
"learning_rate": 0.00016209063737995715,
|
| 437 |
+
"loss": 0.2235,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.77,
|
| 442 |
+
"grad_norm": 0.029593750834465027,
|
| 443 |
+
"learning_rate": 0.00016026346363792567,
|
| 444 |
+
"loss": 0.1976,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.78,
|
| 449 |
+
"grad_norm": 0.033486686646938324,
|
| 450 |
+
"learning_rate": 0.00015840413428936767,
|
| 451 |
+
"loss": 0.184,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.79,
|
| 456 |
+
"grad_norm": 0.029341375455260277,
|
| 457 |
+
"learning_rate": 0.0001565136414422592,
|
| 458 |
+
"loss": 0.2114,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.81,
|
| 463 |
+
"grad_norm": 0.03653452917933464,
|
| 464 |
+
"learning_rate": 0.00015459299383291345,
|
| 465 |
+
"loss": 0.2183,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.82,
|
| 470 |
+
"grad_norm": 0.03146987408399582,
|
| 471 |
+
"learning_rate": 0.0001526432162877356,
|
| 472 |
+
"loss": 0.2444,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.83,
|
| 477 |
+
"grad_norm": 0.03224271163344383,
|
| 478 |
+
"learning_rate": 0.00015066534917639195,
|
| 479 |
+
"loss": 0.2157,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.84,
|
| 484 |
+
"grad_norm": 0.028182610869407654,
|
| 485 |
+
"learning_rate": 0.00014866044785668563,
|
| 486 |
+
"loss": 0.16,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.86,
|
| 491 |
+
"grad_norm": 0.03271663188934326,
|
| 492 |
+
"learning_rate": 0.0001466295821114348,
|
| 493 |
+
"loss": 0.2102,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.87,
|
| 498 |
+
"grad_norm": 0.032980792224407196,
|
| 499 |
+
"learning_rate": 0.00014457383557765386,
|
| 500 |
+
"loss": 0.2605,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.88,
|
| 505 |
+
"grad_norm": 0.03456718847155571,
|
| 506 |
+
"learning_rate": 0.0001424943051683422,
|
| 507 |
+
"loss": 0.212,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.89,
|
| 512 |
+
"grad_norm": 0.036501459777355194,
|
| 513 |
+
"learning_rate": 0.00014039210048718949,
|
| 514 |
+
"loss": 0.1798,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.91,
|
| 519 |
+
"grad_norm": 0.033730726689100266,
|
| 520 |
+
"learning_rate": 0.000138268343236509,
|
| 521 |
+
"loss": 0.2018,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.92,
|
| 526 |
+
"grad_norm": 0.03012872487306595,
|
| 527 |
+
"learning_rate": 0.00013612416661871533,
|
| 528 |
+
"loss": 0.2309,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.93,
|
| 533 |
+
"grad_norm": 0.032879915088415146,
|
| 534 |
+
"learning_rate": 0.00013396071473166613,
|
| 535 |
+
"loss": 0.1912,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.95,
|
| 540 |
+
"grad_norm": 0.02916533872485161,
|
| 541 |
+
"learning_rate": 0.00013177914195819016,
|
| 542 |
+
"loss": 0.2313,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.96,
|
| 547 |
+
"grad_norm": 0.032934658229351044,
|
| 548 |
+
"learning_rate": 0.00012958061235012706,
|
| 549 |
+
"loss": 0.2118,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.97,
|
| 554 |
+
"grad_norm": 0.03474392369389534,
|
| 555 |
+
"learning_rate": 0.0001273662990072083,
|
| 556 |
+
"loss": 0.1465,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.98,
|
| 561 |
+
"grad_norm": 0.033331647515296936,
|
| 562 |
+
"learning_rate": 0.0001251373834511103,
|
| 563 |
+
"loss": 0.2207,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.0,
|
| 568 |
+
"grad_norm": 0.030515702441334724,
|
| 569 |
+
"learning_rate": 0.0001228950549950134,
|
| 570 |
+
"loss": 0.2121,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.0,
|
| 575 |
+
"eval_loss": 0.19000689685344696,
|
| 576 |
+
"eval_runtime": 153.8331,
|
| 577 |
+
"eval_samples_per_second": 1.463,
|
| 578 |
+
"eval_steps_per_second": 0.371,
|
| 579 |
+
"step": 78
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.01,
|
| 583 |
+
"grad_norm": 0.03746604546904564,
|
| 584 |
+
"learning_rate": 0.00012064051010900397,
|
| 585 |
+
"loss": 0.1755,
|
| 586 |
+
"step": 79
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.02,
|
| 590 |
+
"grad_norm": 0.032529812306165695,
|
| 591 |
+
"learning_rate": 0.00011837495178165706,
|
| 592 |
+
"loss": 0.2279,
|
| 593 |
+
"step": 80
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.01,
|
| 597 |
+
"grad_norm": 0.02698327600955963,
|
| 598 |
+
"learning_rate": 0.00011609958887814129,
|
| 599 |
+
"loss": 0.1718,
|
| 600 |
+
"step": 81
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.02,
|
| 604 |
+
"grad_norm": 0.030606260523200035,
|
| 605 |
+
"learning_rate": 0.00011381563549518823,
|
| 606 |
+
"loss": 0.2253,
|
| 607 |
+
"step": 82
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.04,
|
| 611 |
+
"grad_norm": 0.03295598179101944,
|
| 612 |
+
"learning_rate": 0.00011152431031326978,
|
| 613 |
+
"loss": 0.1592,
|
| 614 |
+
"step": 83
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.05,
|
| 618 |
+
"grad_norm": 0.04062403365969658,
|
| 619 |
+
"learning_rate": 0.00010922683594633021,
|
| 620 |
+
"loss": 0.2458,
|
| 621 |
+
"step": 84
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.06,
|
| 625 |
+
"grad_norm": 0.04118546470999718,
|
| 626 |
+
"learning_rate": 0.00010692443828941918,
|
| 627 |
+
"loss": 0.1938,
|
| 628 |
+
"step": 85
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.07,
|
| 632 |
+
"grad_norm": 0.03897158056497574,
|
| 633 |
+
"learning_rate": 0.00010461834586457398,
|
| 634 |
+
"loss": 0.1816,
|
| 635 |
+
"step": 86
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.09,
|
| 639 |
+
"grad_norm": 0.031059524044394493,
|
| 640 |
+
"learning_rate": 0.00010230978916530012,
|
| 641 |
+
"loss": 0.2024,
|
| 642 |
+
"step": 87
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.1,
|
| 646 |
+
"grad_norm": 0.0294091384857893,
|
| 647 |
+
"learning_rate": 0.0001,
|
| 648 |
+
"loss": 0.199,
|
| 649 |
+
"step": 88
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.11,
|
| 653 |
+
"grad_norm": 0.03456791117787361,
|
| 654 |
+
"learning_rate": 9.76902108346999e-05,
|
| 655 |
+
"loss": 0.2616,
|
| 656 |
+
"step": 89
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.12,
|
| 660 |
+
"grad_norm": 0.03276889771223068,
|
| 661 |
+
"learning_rate": 9.538165413542607e-05,
|
| 662 |
+
"loss": 0.2115,
|
| 663 |
+
"step": 90
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.14,
|
| 667 |
+
"grad_norm": 0.03038157895207405,
|
| 668 |
+
"learning_rate": 9.307556171058085e-05,
|
| 669 |
+
"loss": 0.1721,
|
| 670 |
+
"step": 91
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.15,
|
| 674 |
+
"grad_norm": 0.02885863371193409,
|
| 675 |
+
"learning_rate": 9.077316405366981e-05,
|
| 676 |
+
"loss": 0.2199,
|
| 677 |
+
"step": 92
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.16,
|
| 681 |
+
"grad_norm": 0.03282390534877777,
|
| 682 |
+
"learning_rate": 8.847568968673026e-05,
|
| 683 |
+
"loss": 0.1885,
|
| 684 |
+
"step": 93
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.18,
|
| 688 |
+
"grad_norm": 0.03559669107198715,
|
| 689 |
+
"learning_rate": 8.61843645048118e-05,
|
| 690 |
+
"loss": 0.2253,
|
| 691 |
+
"step": 94
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.19,
|
| 695 |
+
"grad_norm": 0.027744270861148834,
|
| 696 |
+
"learning_rate": 8.39004111218587e-05,
|
| 697 |
+
"loss": 0.1825,
|
| 698 |
+
"step": 95
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.2,
|
| 702 |
+
"grad_norm": 0.035874996334314346,
|
| 703 |
+
"learning_rate": 8.162504821834295e-05,
|
| 704 |
+
"loss": 0.1983,
|
| 705 |
+
"step": 96
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.21,
|
| 709 |
+
"grad_norm": 0.03325138986110687,
|
| 710 |
+
"learning_rate": 7.935948989099605e-05,
|
| 711 |
+
"loss": 0.1812,
|
| 712 |
+
"step": 97
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.23,
|
| 716 |
+
"grad_norm": 0.028679154813289642,
|
| 717 |
+
"learning_rate": 7.710494500498662e-05,
|
| 718 |
+
"loss": 0.1875,
|
| 719 |
+
"step": 98
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.24,
|
| 723 |
+
"grad_norm": 0.036103084683418274,
|
| 724 |
+
"learning_rate": 7.486261654888973e-05,
|
| 725 |
+
"loss": 0.2025,
|
| 726 |
+
"step": 99
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.25,
|
| 730 |
+
"grad_norm": 0.0321945995092392,
|
| 731 |
+
"learning_rate": 7.263370099279172e-05,
|
| 732 |
+
"loss": 0.2342,
|
| 733 |
+
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.27,
|
| 737 |
+
"grad_norm": 0.0304876621812582,
|
| 738 |
+
"learning_rate": 7.041938764987297e-05,
|
| 739 |
+
"loss": 0.1642,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.28,
|
| 744 |
+
"grad_norm": 0.03619467467069626,
|
| 745 |
+
"learning_rate": 6.822085804180984e-05,
|
| 746 |
+
"loss": 0.187,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.29,
|
| 751 |
+
"grad_norm": 0.03597356379032135,
|
| 752 |
+
"learning_rate": 6.603928526833387e-05,
|
| 753 |
+
"loss": 0.1343,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3,
|
| 758 |
+
"grad_norm": 0.036540765315294266,
|
| 759 |
+
"learning_rate": 6.387583338128471e-05,
|
| 760 |
+
"loss": 0.2062,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.32,
|
| 765 |
+
"grad_norm": 0.03327038511633873,
|
| 766 |
+
"learning_rate": 6.173165676349103e-05,
|
| 767 |
+
"loss": 0.22,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.33,
|
| 772 |
+
"grad_norm": 0.03374246507883072,
|
| 773 |
+
"learning_rate": 5.960789951281052e-05,
|
| 774 |
+
"loss": 0.1765,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.34,
|
| 779 |
+
"grad_norm": 0.032783444970846176,
|
| 780 |
+
"learning_rate": 5.750569483165784e-05,
|
| 781 |
+
"loss": 0.2397,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.35,
|
| 786 |
+
"grad_norm": 0.03667570650577545,
|
| 787 |
+
"learning_rate": 5.542616442234618e-05,
|
| 788 |
+
"loss": 0.1841,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.37,
|
| 793 |
+
"grad_norm": 0.029467754065990448,
|
| 794 |
+
"learning_rate": 5.337041788856518e-05,
|
| 795 |
+
"loss": 0.2282,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.38,
|
| 800 |
+
"grad_norm": 0.03702455386519432,
|
| 801 |
+
"learning_rate": 5.1339552143314384e-05,
|
| 802 |
+
"loss": 0.2601,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.39,
|
| 807 |
+
"grad_norm": 0.033595018088817596,
|
| 808 |
+
"learning_rate": 4.933465082360807e-05,
|
| 809 |
+
"loss": 0.2077,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.41,
|
| 814 |
+
"grad_norm": 0.03349510580301285,
|
| 815 |
+
"learning_rate": 4.735678371226441e-05,
|
| 816 |
+
"loss": 0.1686,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.42,
|
| 821 |
+
"grad_norm": 0.03149344027042389,
|
| 822 |
+
"learning_rate": 4.540700616708658e-05,
|
| 823 |
+
"loss": 0.2075,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.43,
|
| 828 |
+
"grad_norm": 0.035017482936382294,
|
| 829 |
+
"learning_rate": 4.3486358557740814e-05,
|
| 830 |
+
"loss": 0.1462,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.44,
|
| 835 |
+
"grad_norm": 0.029670318588614464,
|
| 836 |
+
"learning_rate": 4.159586571063236e-05,
|
| 837 |
+
"loss": 0.1602,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.46,
|
| 842 |
+
"grad_norm": 0.037266362458467484,
|
| 843 |
+
"learning_rate": 3.973653636207437e-05,
|
| 844 |
+
"loss": 0.1798,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.47,
|
| 849 |
+
"grad_norm": 0.03251258283853531,
|
| 850 |
+
"learning_rate": 3.7909362620042865e-05,
|
| 851 |
+
"loss": 0.2512,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.47,
|
| 856 |
+
"eval_loss": 0.18417498469352722,
|
| 857 |
+
"eval_runtime": 155.2041,
|
| 858 |
+
"eval_samples_per_second": 1.45,
|
| 859 |
+
"eval_steps_per_second": 0.367,
|
| 860 |
+
"step": 117
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.48,
|
| 864 |
+
"grad_norm": 0.03466426581144333,
|
| 865 |
+
"learning_rate": 3.6115319434803894e-05,
|
| 866 |
+
"loss": 0.2053,
|
| 867 |
+
"step": 118
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.5,
|
| 871 |
+
"grad_norm": 0.03304358944296837,
|
| 872 |
+
"learning_rate": 3.435536407869575e-05,
|
| 873 |
+
"loss": 0.2136,
|
| 874 |
+
"step": 119
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.51,
|
| 878 |
+
"grad_norm": 0.03283797577023506,
|
| 879 |
+
"learning_rate": 3.263043563534428e-05,
|
| 880 |
+
"loss": 0.2349,
|
| 881 |
+
"step": 120
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.52,
|
| 885 |
+
"grad_norm": 0.028859762474894524,
|
| 886 |
+
"learning_rate": 3.094145449858285e-05,
|
| 887 |
+
"loss": 0.1776,
|
| 888 |
+
"step": 121
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.53,
|
| 892 |
+
"grad_norm": 0.030209610238671303,
|
| 893 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 894 |
+
"loss": 0.1851,
|
| 895 |
+
"step": 122
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.55,
|
| 899 |
+
"grad_norm": 0.037758719176054,
|
| 900 |
+
"learning_rate": 2.7674919334793035e-05,
|
| 901 |
+
"loss": 0.1706,
|
| 902 |
+
"step": 123
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.56,
|
| 906 |
+
"grad_norm": 0.032276131212711334,
|
| 907 |
+
"learning_rate": 2.6099108277934103e-05,
|
| 908 |
+
"loss": 0.2028,
|
| 909 |
+
"step": 124
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.57,
|
| 913 |
+
"grad_norm": 0.029737072065472603,
|
| 914 |
+
"learning_rate": 2.456272953798361e-05,
|
| 915 |
+
"loss": 0.173,
|
| 916 |
+
"step": 125
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.58,
|
| 920 |
+
"grad_norm": 0.03279801830649376,
|
| 921 |
+
"learning_rate": 2.3066602901712108e-05,
|
| 922 |
+
"loss": 0.2188,
|
| 923 |
+
"step": 126
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.6,
|
| 927 |
+
"grad_norm": 0.031686633825302124,
|
| 928 |
+
"learning_rate": 2.1611526678020654e-05,
|
| 929 |
+
"loss": 0.1929,
|
| 930 |
+
"step": 127
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.61,
|
| 934 |
+
"grad_norm": 0.035397134721279144,
|
| 935 |
+
"learning_rate": 2.0198277271976052e-05,
|
| 936 |
+
"loss": 0.2417,
|
| 937 |
+
"step": 128
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.62,
|
| 941 |
+
"grad_norm": 0.033016614615917206,
|
| 942 |
+
"learning_rate": 1.882760877053388e-05,
|
| 943 |
+
"loss": 0.1898,
|
| 944 |
+
"step": 129
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.64,
|
| 948 |
+
"grad_norm": 0.03705607354640961,
|
| 949 |
+
"learning_rate": 1.750025254016978e-05,
|
| 950 |
+
"loss": 0.1865,
|
| 951 |
+
"step": 130
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.65,
|
| 955 |
+
"grad_norm": 0.032849811017513275,
|
| 956 |
+
"learning_rate": 1.621691683663418e-05,
|
| 957 |
+
"loss": 0.1761,
|
| 958 |
+
"step": 131
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.66,
|
| 962 |
+
"grad_norm": 0.03138056769967079,
|
| 963 |
+
"learning_rate": 1.4978286427038601e-05,
|
| 964 |
+
"loss": 0.1846,
|
| 965 |
+
"step": 132
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.67,
|
| 969 |
+
"grad_norm": 0.034144606441259384,
|
| 970 |
+
"learning_rate": 1.3785022224474942e-05,
|
| 971 |
+
"loss": 0.2515,
|
| 972 |
+
"step": 133
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.69,
|
| 976 |
+
"grad_norm": 0.030318470671772957,
|
| 977 |
+
"learning_rate": 1.2637760935363053e-05,
|
| 978 |
+
"loss": 0.1868,
|
| 979 |
+
"step": 134
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.7,
|
| 983 |
+
"grad_norm": 0.03535514324903488,
|
| 984 |
+
"learning_rate": 1.1537114719714481e-05,
|
| 985 |
+
"loss": 0.2123,
|
| 986 |
+
"step": 135
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.71,
|
| 990 |
+
"grad_norm": 0.03618015721440315,
|
| 991 |
+
"learning_rate": 1.0483670864493778e-05,
|
| 992 |
+
"loss": 0.2316,
|
| 993 |
+
"step": 136
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.73,
|
| 997 |
+
"grad_norm": 0.035231318324804306,
|
| 998 |
+
"learning_rate": 9.477991470251791e-06,
|
| 999 |
+
"loss": 0.174,
|
| 1000 |
+
"step": 137
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.74,
|
| 1004 |
+
"grad_norm": 0.02953380160033703,
|
| 1005 |
+
"learning_rate": 8.520613151197898e-06,
|
| 1006 |
+
"loss": 0.1941,
|
| 1007 |
+
"step": 138
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.75,
|
| 1011 |
+
"grad_norm": 0.032863788306713104,
|
| 1012 |
+
"learning_rate": 7.612046748871327e-06,
|
| 1013 |
+
"loss": 0.1972,
|
| 1014 |
+
"step": 139
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.76,
|
| 1018 |
+
"grad_norm": 0.03691845387220383,
|
| 1019 |
+
"learning_rate": 6.75277705956443e-06,
|
| 1020 |
+
"loss": 0.2058,
|
| 1021 |
+
"step": 140
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.78,
|
| 1025 |
+
"grad_norm": 0.037353359162807465,
|
| 1026 |
+
"learning_rate": 5.943262575643238e-06,
|
| 1027 |
+
"loss": 0.2278,
|
| 1028 |
+
"step": 141
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.79,
|
| 1032 |
+
"grad_norm": 0.030703024938702583,
|
| 1033 |
+
"learning_rate": 5.183935240903414e-06,
|
| 1034 |
+
"loss": 0.1926,
|
| 1035 |
+
"step": 142
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.8,
|
| 1039 |
+
"grad_norm": 0.0352725051343441,
|
| 1040 |
+
"learning_rate": 4.475200220092002e-06,
|
| 1041 |
+
"loss": 0.181,
|
| 1042 |
+
"step": 143
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.81,
|
| 1046 |
+
"grad_norm": 0.03681638464331627,
|
| 1047 |
+
"learning_rate": 3.817435682718096e-06,
|
| 1048 |
+
"loss": 0.1915,
|
| 1049 |
+
"step": 144
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.83,
|
| 1053 |
+
"grad_norm": 0.03503178432583809,
|
| 1054 |
+
"learning_rate": 3.2109926012677484e-06,
|
| 1055 |
+
"loss": 0.1815,
|
| 1056 |
+
"step": 145
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.84,
|
| 1060 |
+
"grad_norm": 0.03486161679029465,
|
| 1061 |
+
"learning_rate": 2.656194563930714e-06,
|
| 1062 |
+
"loss": 0.1607,
|
| 1063 |
+
"step": 146
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.85,
|
| 1067 |
+
"grad_norm": 0.03625166788697243,
|
| 1068 |
+
"learning_rate": 2.1533376019391094e-06,
|
| 1069 |
+
"loss": 0.2287,
|
| 1070 |
+
"step": 147
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.87,
|
| 1074 |
+
"grad_norm": 0.03178601339459419,
|
| 1075 |
+
"learning_rate": 1.7026900316098215e-06,
|
| 1076 |
+
"loss": 0.152,
|
| 1077 |
+
"step": 148
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.88,
|
| 1081 |
+
"grad_norm": 0.03327329456806183,
|
| 1082 |
+
"learning_rate": 1.3044923111754427e-06,
|
| 1083 |
+
"loss": 0.2323,
|
| 1084 |
+
"step": 149
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.89,
|
| 1088 |
+
"grad_norm": 0.037077613174915314,
|
| 1089 |
+
"learning_rate": 9.589569124794916e-07,
|
| 1090 |
+
"loss": 0.2673,
|
| 1091 |
+
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9,
|
| 1095 |
+
"grad_norm": 0.029201308265328407,
|
| 1096 |
+
"learning_rate": 6.662682076050031e-07,
|
| 1097 |
+
"loss": 0.1671,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.92,
|
| 1102 |
+
"grad_norm": 0.03882408142089844,
|
| 1103 |
+
"learning_rate": 4.2658237049655323e-07,
|
| 1104 |
+
"loss": 0.2322,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.93,
|
| 1109 |
+
"grad_norm": 0.036668822169303894,
|
| 1110 |
+
"learning_rate": 2.400272936283088e-07,
|
| 1111 |
+
"loss": 0.2091,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.94,
|
| 1116 |
+
"grad_norm": 0.03214651718735695,
|
| 1117 |
+
"learning_rate": 1.0670251976275803e-07,
|
| 1118 |
+
"loss": 0.176,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.96,
|
| 1123 |
+
"grad_norm": 0.03298597037792206,
|
| 1124 |
+
"learning_rate": 2.667918883627607e-08,
|
| 1125 |
+
"loss": 0.2042,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.97,
|
| 1130 |
+
"grad_norm": 0.03144283965229988,
|
| 1131 |
+
"learning_rate": 0.0,
|
| 1132 |
+
"loss": 0.2024,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.97,
|
| 1137 |
+
"eval_loss": 0.18294647336006165,
|
| 1138 |
+
"eval_runtime": 156.1361,
|
| 1139 |
+
"eval_samples_per_second": 1.441,
|
| 1140 |
+
"eval_steps_per_second": 0.365,
|
| 1141 |
+
"step": 156
|
| 1142 |
+
}
|
| 1143 |
+
],
|
| 1144 |
+
"logging_steps": 1,
|
| 1145 |
+
"max_steps": 156,
|
| 1146 |
+
"num_input_tokens_seen": 0,
|
| 1147 |
+
"num_train_epochs": 2,
|
| 1148 |
+
"save_steps": 39,
|
| 1149 |
+
"total_flos": 2.0513724697254298e+17,
|
| 1150 |
+
"train_batch_size": 2,
|
| 1151 |
+
"trial_name": null,
|
| 1152 |
+
"trial_params": null
|
| 1153 |
+
}
|
checkpoint-156/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a36fbc0a6f934d44efc86171559fa23366edb0ce2bd813321dd96ee628e581
|
| 3 |
+
size 5816
|
checkpoint-39/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-39/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": null,
|
| 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": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-39/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92605911f348de1bb354902ca1d04dfdbf710cb9b6f5b17be7a28229592c1cd0
|
| 3 |
+
size 319876032
|
checkpoint-39/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2033c7bf0d49d662ce438cdc8315f5930a850c4c2ee1d654914528330de762
|
| 3 |
+
size 639908602
|
checkpoint-39/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57c9a922328594ea5313c25531fd85176f94f125d6bdad998ec687bd125b019e
|
| 3 |
+
size 14512
|
checkpoint-39/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80c8ca6bd685f730d3890f9c5dbc8c2e10eafe1adc3895b0478c4ae9b5e3dc19
|
| 3 |
+
size 14512
|
checkpoint-39/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:310df81de3faaeaf9f3b736e0b5570d44c732bd5955a4634392f06d4d9e27a0f
|
| 3 |
+
size 1064
|
checkpoint-39/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 |
+
}
|
checkpoint-39/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-39/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"32000": {
|
| 6 |
+
"content": "õ",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"32001": {
|
| 14 |
+
"content": "÷",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"32002": {
|
| 22 |
+
"content": "Á",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32003": {
|
| 30 |
+
"content": "ý",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32004": {
|
| 38 |
+
"content": "À",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32005": {
|
| 46 |
+
"content": "ÿ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32006": {
|
| 54 |
+
"content": "ø",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32007": {
|
| 62 |
+
"content": "ú",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32008": {
|
| 70 |
+
"content": "þ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32009": {
|
| 78 |
+
"content": "ü",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32010": {
|
| 86 |
+
"content": "ù",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32011": {
|
| 94 |
+
"content": "ö",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32012": {
|
| 102 |
+
"content": "û",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32013": {
|
| 110 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32014": {
|
| 118 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32015": {
|
| 126 |
+
"content": "<｜fim▁hole｜>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32016": {
|
| 134 |
+
"content": "<｜fim▁begin｜>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32017": {
|
| 142 |
+
"content": "<｜fim▁end｜>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32018": {
|
| 150 |
+
"content": "<pad>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32019": {
|
| 158 |
+
"content": "<|User|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32020": {
|
| 166 |
+
"content": "<|Assistant|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32021": {
|
| 174 |
+
"content": "<|EOT|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 183 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<|EOT|>",
|
| 186 |
+
"legacy": true,
|
| 187 |
+
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
+
"sp_model_kwargs": {},
|
| 190 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
+
"unk_token": null,
|
| 192 |
+
"use_default_system_prompt": false,
|
| 193 |
+
"use_fast": true
|
| 194 |
+
}
|
checkpoint-39/trainer_state.json
ADDED
|
@@ -0,0 +1,310 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4984025559105431,
|
| 5 |
+
"eval_steps": 39,
|
| 6 |
+
"global_step": 39,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.06435385346412659,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.6574,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"eval_loss": 0.7461566925048828,
|
| 21 |
+
"eval_runtime": 151.7973,
|
| 22 |
+
"eval_samples_per_second": 1.482,
|
| 23 |
+
"eval_steps_per_second": 0.376,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 0.062134526669979095,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.6897,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 0.06962593644857407,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 0.6974,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 0.0730314701795578,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 0.7454,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 0.07659862190485,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 0.6962,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08,
|
| 56 |
+
"grad_norm": 0.07314729690551758,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.6602,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09,
|
| 63 |
+
"grad_norm": 0.0892895832657814,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.6594,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1,
|
| 70 |
+
"grad_norm": 0.11520648747682571,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.7406,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12,
|
| 77 |
+
"grad_norm": 0.1333557516336441,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.663,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13,
|
| 84 |
+
"grad_norm": 0.14017663896083832,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.6185,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"grad_norm": 0.1453818678855896,
|
| 92 |
+
"learning_rate": 0.00011000000000000002,
|
| 93 |
+
"loss": 0.602,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"grad_norm": 0.14279265701770782,
|
| 99 |
+
"learning_rate": 0.00012,
|
| 100 |
+
"loss": 0.6151,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17,
|
| 105 |
+
"grad_norm": 0.11934962123632431,
|
| 106 |
+
"learning_rate": 0.00013000000000000002,
|
| 107 |
+
"loss": 0.5085,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18,
|
| 112 |
+
"grad_norm": 0.11375121772289276,
|
| 113 |
+
"learning_rate": 0.00014,
|
| 114 |
+
"loss": 0.4823,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19,
|
| 119 |
+
"grad_norm": 0.09707039594650269,
|
| 120 |
+
"learning_rate": 0.00015000000000000001,
|
| 121 |
+
"loss": 0.4281,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2,
|
| 126 |
+
"grad_norm": 0.11333765089511871,
|
| 127 |
+
"learning_rate": 0.00016,
|
| 128 |
+
"loss": 0.4417,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"grad_norm": 0.09926053136587143,
|
| 134 |
+
"learning_rate": 0.00017,
|
| 135 |
+
"loss": 0.3654,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23,
|
| 140 |
+
"grad_norm": 0.1027929037809372,
|
| 141 |
+
"learning_rate": 0.00018,
|
| 142 |
+
"loss": 0.3748,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24,
|
| 147 |
+
"grad_norm": 0.09768980741500854,
|
| 148 |
+
"learning_rate": 0.00019,
|
| 149 |
+
"loss": 0.3306,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26,
|
| 154 |
+
"grad_norm": 0.08072198927402496,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 0.355,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27,
|
| 161 |
+
"grad_norm": 0.06444709748029709,
|
| 162 |
+
"learning_rate": 0.00019997332081116373,
|
| 163 |
+
"loss": 0.3152,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28,
|
| 168 |
+
"grad_norm": 0.0576409213244915,
|
| 169 |
+
"learning_rate": 0.00019989329748023725,
|
| 170 |
+
"loss": 0.2674,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.29,
|
| 175 |
+
"grad_norm": 0.08624427020549774,
|
| 176 |
+
"learning_rate": 0.0001997599727063717,
|
| 177 |
+
"loss": 0.2807,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.31,
|
| 182 |
+
"grad_norm": 0.08828990906476974,
|
| 183 |
+
"learning_rate": 0.00019957341762950344,
|
| 184 |
+
"loss": 0.2736,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32,
|
| 189 |
+
"grad_norm": 0.0641990676522255,
|
| 190 |
+
"learning_rate": 0.00019933373179239502,
|
| 191 |
+
"loss": 0.2427,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33,
|
| 196 |
+
"grad_norm": 0.05487390235066414,
|
| 197 |
+
"learning_rate": 0.0001990410430875205,
|
| 198 |
+
"loss": 0.2737,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.35,
|
| 203 |
+
"grad_norm": 0.0666637197136879,
|
| 204 |
+
"learning_rate": 0.00019869550768882455,
|
| 205 |
+
"loss": 0.2806,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36,
|
| 210 |
+
"grad_norm": 0.053027719259262085,
|
| 211 |
+
"learning_rate": 0.0001982973099683902,
|
| 212 |
+
"loss": 0.2664,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37,
|
| 217 |
+
"grad_norm": 0.055217448621988297,
|
| 218 |
+
"learning_rate": 0.0001978466623980609,
|
| 219 |
+
"loss": 0.309,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38,
|
| 224 |
+
"grad_norm": 0.05493360385298729,
|
| 225 |
+
"learning_rate": 0.0001973438054360693,
|
| 226 |
+
"loss": 0.2318,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4,
|
| 231 |
+
"grad_norm": 0.0376153439283371,
|
| 232 |
+
"learning_rate": 0.00019678900739873226,
|
| 233 |
+
"loss": 0.2049,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41,
|
| 238 |
+
"grad_norm": 0.03811287507414818,
|
| 239 |
+
"learning_rate": 0.00019618256431728194,
|
| 240 |
+
"loss": 0.2771,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42,
|
| 245 |
+
"grad_norm": 0.04185184836387634,
|
| 246 |
+
"learning_rate": 0.000195524799779908,
|
| 247 |
+
"loss": 0.1843,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43,
|
| 252 |
+
"grad_norm": 0.04743755981326103,
|
| 253 |
+
"learning_rate": 0.0001948160647590966,
|
| 254 |
+
"loss": 0.2414,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"grad_norm": 0.03343382850289345,
|
| 260 |
+
"learning_rate": 0.00019405673742435678,
|
| 261 |
+
"loss": 0.2007,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46,
|
| 266 |
+
"grad_norm": 0.03178093209862709,
|
| 267 |
+
"learning_rate": 0.00019324722294043558,
|
| 268 |
+
"loss": 0.1898,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47,
|
| 273 |
+
"grad_norm": 0.03482227399945259,
|
| 274 |
+
"learning_rate": 0.0001923879532511287,
|
| 275 |
+
"loss": 0.2657,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.49,
|
| 280 |
+
"grad_norm": 0.03727172687649727,
|
| 281 |
+
"learning_rate": 0.0001914793868488021,
|
| 282 |
+
"loss": 0.2185,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"grad_norm": 0.0382206104695797,
|
| 288 |
+
"learning_rate": 0.00019052200852974819,
|
| 289 |
+
"loss": 0.1778,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5,
|
| 294 |
+
"eval_loss": 0.2122737020254135,
|
| 295 |
+
"eval_runtime": 154.5774,
|
| 296 |
+
"eval_samples_per_second": 1.456,
|
| 297 |
+
"eval_steps_per_second": 0.369,
|
| 298 |
+
"step": 39
|
| 299 |
+
}
|
| 300 |
+
],
|
| 301 |
+
"logging_steps": 1,
|
| 302 |
+
"max_steps": 156,
|
| 303 |
+
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 2,
|
| 305 |
+
"save_steps": 39,
|
| 306 |
+
"total_flos": 5.128431174313574e+16,
|
| 307 |
+
"train_batch_size": 2,
|
| 308 |
+
"trial_name": null,
|
| 309 |
+
"trial_params": null
|
| 310 |
+
}
|
checkpoint-39/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a36fbc0a6f934d44efc86171559fa23366edb0ce2bd813321dd96ee628e581
|
| 3 |
+
size 5816
|
checkpoint-78/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-78/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": null,
|
| 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": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-78/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a060bbca54adccf94cf0a00b2f5975fda72ce415add1466b988c3e89e4548061
|
| 3 |
+
size 319876032
|
checkpoint-78/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577532ca4efb77c05cad7856f82f0297d7c4df46b4a852b25c18ac34b8ec26d4
|
| 3 |
+
size 639908602
|
checkpoint-78/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:079929fe533dc1e2281102778d417dba1f697b636daec38d8186f746402a4073
|
| 3 |
+
size 14512
|
checkpoint-78/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87c50d142a081080291e1bad0ec01433d6217cc0d48f730866be3aae405ef2ad
|
| 3 |
+
size 14512
|
checkpoint-78/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ecbadddbc0d6aa74eff9bd3f8902a05613ee3063886c5ad794f1c2ceacc5c7
|
| 3 |
+
size 1064
|
checkpoint-78/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 |
+
}
|
checkpoint-78/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-78/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"32000": {
|
| 6 |
+
"content": "õ",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"32001": {
|
| 14 |
+
"content": "÷",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"32002": {
|
| 22 |
+
"content": "Á",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32003": {
|
| 30 |
+
"content": "ý",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32004": {
|
| 38 |
+
"content": "À",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32005": {
|
| 46 |
+
"content": "ÿ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32006": {
|
| 54 |
+
"content": "ø",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32007": {
|
| 62 |
+
"content": "ú",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32008": {
|
| 70 |
+
"content": "þ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32009": {
|
| 78 |
+
"content": "ü",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32010": {
|
| 86 |
+
"content": "ù",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32011": {
|
| 94 |
+
"content": "ö",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32012": {
|
| 102 |
+
"content": "û",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32013": {
|
| 110 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32014": {
|
| 118 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32015": {
|
| 126 |
+
"content": "<｜fim▁hole｜>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32016": {
|
| 134 |
+
"content": "<｜fim▁begin｜>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32017": {
|
| 142 |
+
"content": "<｜fim▁end｜>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32018": {
|
| 150 |
+
"content": "<pad>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32019": {
|
| 158 |
+
"content": "<|User|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32020": {
|
| 166 |
+
"content": "<|Assistant|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32021": {
|
| 174 |
+
"content": "<|EOT|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 183 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<|EOT|>",
|
| 186 |
+
"legacy": true,
|
| 187 |
+
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
+
"sp_model_kwargs": {},
|
| 190 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
+
"unk_token": null,
|
| 192 |
+
"use_default_system_prompt": false,
|
| 193 |
+
"use_fast": true
|
| 194 |
+
}
|
checkpoint-78/trainer_state.json
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9968051118210862,
|
| 5 |
+
"eval_steps": 39,
|
| 6 |
+
"global_step": 78,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.06435385346412659,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.6574,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"eval_loss": 0.7461566925048828,
|
| 21 |
+
"eval_runtime": 151.7973,
|
| 22 |
+
"eval_samples_per_second": 1.482,
|
| 23 |
+
"eval_steps_per_second": 0.376,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 0.062134526669979095,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.6897,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 0.06962593644857407,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 0.6974,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 0.0730314701795578,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 0.7454,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 0.07659862190485,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 0.6962,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08,
|
| 56 |
+
"grad_norm": 0.07314729690551758,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 0.6602,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09,
|
| 63 |
+
"grad_norm": 0.0892895832657814,
|
| 64 |
+
"learning_rate": 7e-05,
|
| 65 |
+
"loss": 0.6594,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1,
|
| 70 |
+
"grad_norm": 0.11520648747682571,
|
| 71 |
+
"learning_rate": 8e-05,
|
| 72 |
+
"loss": 0.7406,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12,
|
| 77 |
+
"grad_norm": 0.1333557516336441,
|
| 78 |
+
"learning_rate": 9e-05,
|
| 79 |
+
"loss": 0.663,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13,
|
| 84 |
+
"grad_norm": 0.14017663896083832,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.6185,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"grad_norm": 0.1453818678855896,
|
| 92 |
+
"learning_rate": 0.00011000000000000002,
|
| 93 |
+
"loss": 0.602,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"grad_norm": 0.14279265701770782,
|
| 99 |
+
"learning_rate": 0.00012,
|
| 100 |
+
"loss": 0.6151,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17,
|
| 105 |
+
"grad_norm": 0.11934962123632431,
|
| 106 |
+
"learning_rate": 0.00013000000000000002,
|
| 107 |
+
"loss": 0.5085,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18,
|
| 112 |
+
"grad_norm": 0.11375121772289276,
|
| 113 |
+
"learning_rate": 0.00014,
|
| 114 |
+
"loss": 0.4823,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19,
|
| 119 |
+
"grad_norm": 0.09707039594650269,
|
| 120 |
+
"learning_rate": 0.00015000000000000001,
|
| 121 |
+
"loss": 0.4281,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2,
|
| 126 |
+
"grad_norm": 0.11333765089511871,
|
| 127 |
+
"learning_rate": 0.00016,
|
| 128 |
+
"loss": 0.4417,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"grad_norm": 0.09926053136587143,
|
| 134 |
+
"learning_rate": 0.00017,
|
| 135 |
+
"loss": 0.3654,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23,
|
| 140 |
+
"grad_norm": 0.1027929037809372,
|
| 141 |
+
"learning_rate": 0.00018,
|
| 142 |
+
"loss": 0.3748,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24,
|
| 147 |
+
"grad_norm": 0.09768980741500854,
|
| 148 |
+
"learning_rate": 0.00019,
|
| 149 |
+
"loss": 0.3306,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26,
|
| 154 |
+
"grad_norm": 0.08072198927402496,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 0.355,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.27,
|
| 161 |
+
"grad_norm": 0.06444709748029709,
|
| 162 |
+
"learning_rate": 0.00019997332081116373,
|
| 163 |
+
"loss": 0.3152,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28,
|
| 168 |
+
"grad_norm": 0.0576409213244915,
|
| 169 |
+
"learning_rate": 0.00019989329748023725,
|
| 170 |
+
"loss": 0.2674,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.29,
|
| 175 |
+
"grad_norm": 0.08624427020549774,
|
| 176 |
+
"learning_rate": 0.0001997599727063717,
|
| 177 |
+
"loss": 0.2807,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.31,
|
| 182 |
+
"grad_norm": 0.08828990906476974,
|
| 183 |
+
"learning_rate": 0.00019957341762950344,
|
| 184 |
+
"loss": 0.2736,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32,
|
| 189 |
+
"grad_norm": 0.0641990676522255,
|
| 190 |
+
"learning_rate": 0.00019933373179239502,
|
| 191 |
+
"loss": 0.2427,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33,
|
| 196 |
+
"grad_norm": 0.05487390235066414,
|
| 197 |
+
"learning_rate": 0.0001990410430875205,
|
| 198 |
+
"loss": 0.2737,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.35,
|
| 203 |
+
"grad_norm": 0.0666637197136879,
|
| 204 |
+
"learning_rate": 0.00019869550768882455,
|
| 205 |
+
"loss": 0.2806,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36,
|
| 210 |
+
"grad_norm": 0.053027719259262085,
|
| 211 |
+
"learning_rate": 0.0001982973099683902,
|
| 212 |
+
"loss": 0.2664,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37,
|
| 217 |
+
"grad_norm": 0.055217448621988297,
|
| 218 |
+
"learning_rate": 0.0001978466623980609,
|
| 219 |
+
"loss": 0.309,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38,
|
| 224 |
+
"grad_norm": 0.05493360385298729,
|
| 225 |
+
"learning_rate": 0.0001973438054360693,
|
| 226 |
+
"loss": 0.2318,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4,
|
| 231 |
+
"grad_norm": 0.0376153439283371,
|
| 232 |
+
"learning_rate": 0.00019678900739873226,
|
| 233 |
+
"loss": 0.2049,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41,
|
| 238 |
+
"grad_norm": 0.03811287507414818,
|
| 239 |
+
"learning_rate": 0.00019618256431728194,
|
| 240 |
+
"loss": 0.2771,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42,
|
| 245 |
+
"grad_norm": 0.04185184836387634,
|
| 246 |
+
"learning_rate": 0.000195524799779908,
|
| 247 |
+
"loss": 0.1843,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43,
|
| 252 |
+
"grad_norm": 0.04743755981326103,
|
| 253 |
+
"learning_rate": 0.0001948160647590966,
|
| 254 |
+
"loss": 0.2414,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"grad_norm": 0.03343382850289345,
|
| 260 |
+
"learning_rate": 0.00019405673742435678,
|
| 261 |
+
"loss": 0.2007,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46,
|
| 266 |
+
"grad_norm": 0.03178093209862709,
|
| 267 |
+
"learning_rate": 0.00019324722294043558,
|
| 268 |
+
"loss": 0.1898,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47,
|
| 273 |
+
"grad_norm": 0.03482227399945259,
|
| 274 |
+
"learning_rate": 0.0001923879532511287,
|
| 275 |
+
"loss": 0.2657,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.49,
|
| 280 |
+
"grad_norm": 0.03727172687649727,
|
| 281 |
+
"learning_rate": 0.0001914793868488021,
|
| 282 |
+
"loss": 0.2185,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"grad_norm": 0.0382206104695797,
|
| 288 |
+
"learning_rate": 0.00019052200852974819,
|
| 289 |
+
"loss": 0.1778,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5,
|
| 294 |
+
"eval_loss": 0.2122737020254135,
|
| 295 |
+
"eval_runtime": 154.5774,
|
| 296 |
+
"eval_samples_per_second": 1.456,
|
| 297 |
+
"eval_steps_per_second": 0.369,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.51,
|
| 302 |
+
"grad_norm": 0.03256627917289734,
|
| 303 |
+
"learning_rate": 0.00018951632913550626,
|
| 304 |
+
"loss": 0.2528,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.52,
|
| 309 |
+
"grad_norm": 0.032382771372795105,
|
| 310 |
+
"learning_rate": 0.00018846288528028555,
|
| 311 |
+
"loss": 0.2165,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.54,
|
| 316 |
+
"grad_norm": 0.030948858708143234,
|
| 317 |
+
"learning_rate": 0.00018736223906463696,
|
| 318 |
+
"loss": 0.1754,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.55,
|
| 323 |
+
"grad_norm": 0.041598908603191376,
|
| 324 |
+
"learning_rate": 0.00018621497777552507,
|
| 325 |
+
"loss": 0.2676,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.56,
|
| 330 |
+
"grad_norm": 0.03000044636428356,
|
| 331 |
+
"learning_rate": 0.00018502171357296144,
|
| 332 |
+
"loss": 0.1501,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.58,
|
| 337 |
+
"grad_norm": 0.03305242955684662,
|
| 338 |
+
"learning_rate": 0.00018378308316336584,
|
| 339 |
+
"loss": 0.1937,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.59,
|
| 344 |
+
"grad_norm": 0.02798221819102764,
|
| 345 |
+
"learning_rate": 0.00018249974745983023,
|
| 346 |
+
"loss": 0.2241,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.6,
|
| 351 |
+
"grad_norm": 0.03340066224336624,
|
| 352 |
+
"learning_rate": 0.00018117239122946615,
|
| 353 |
+
"loss": 0.2078,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.61,
|
| 358 |
+
"grad_norm": 0.032081808894872665,
|
| 359 |
+
"learning_rate": 0.000179801722728024,
|
| 360 |
+
"loss": 0.2061,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.63,
|
| 365 |
+
"grad_norm": 0.033740073442459106,
|
| 366 |
+
"learning_rate": 0.00017838847332197938,
|
| 367 |
+
"loss": 0.2411,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.64,
|
| 372 |
+
"grad_norm": 0.02972455322742462,
|
| 373 |
+
"learning_rate": 0.00017693339709828792,
|
| 374 |
+
"loss": 0.2346,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.65,
|
| 379 |
+
"grad_norm": 0.03134370595216751,
|
| 380 |
+
"learning_rate": 0.0001754372704620164,
|
| 381 |
+
"loss": 0.2573,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.66,
|
| 386 |
+
"grad_norm": 0.035204820334911346,
|
| 387 |
+
"learning_rate": 0.00017390089172206592,
|
| 388 |
+
"loss": 0.2596,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.68,
|
| 393 |
+
"grad_norm": 0.027202850207686424,
|
| 394 |
+
"learning_rate": 0.00017232508066520702,
|
| 395 |
+
"loss": 0.1738,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.69,
|
| 400 |
+
"grad_norm": 0.02930806204676628,
|
| 401 |
+
"learning_rate": 0.00017071067811865476,
|
| 402 |
+
"loss": 0.2178,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7,
|
| 407 |
+
"grad_norm": 0.03558573126792908,
|
| 408 |
+
"learning_rate": 0.00016905854550141716,
|
| 409 |
+
"loss": 0.2677,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.72,
|
| 414 |
+
"grad_norm": 0.03179259970784187,
|
| 415 |
+
"learning_rate": 0.00016736956436465573,
|
| 416 |
+
"loss": 0.1704,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.73,
|
| 421 |
+
"grad_norm": 0.0318523608148098,
|
| 422 |
+
"learning_rate": 0.00016564463592130428,
|
| 423 |
+
"loss": 0.2117,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.74,
|
| 428 |
+
"grad_norm": 0.034657321870326996,
|
| 429 |
+
"learning_rate": 0.00016388468056519612,
|
| 430 |
+
"loss": 0.206,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.75,
|
| 435 |
+
"grad_norm": 0.032808613032102585,
|
| 436 |
+
"learning_rate": 0.00016209063737995715,
|
| 437 |
+
"loss": 0.2235,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.77,
|
| 442 |
+
"grad_norm": 0.029593750834465027,
|
| 443 |
+
"learning_rate": 0.00016026346363792567,
|
| 444 |
+
"loss": 0.1976,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.78,
|
| 449 |
+
"grad_norm": 0.033486686646938324,
|
| 450 |
+
"learning_rate": 0.00015840413428936767,
|
| 451 |
+
"loss": 0.184,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.79,
|
| 456 |
+
"grad_norm": 0.029341375455260277,
|
| 457 |
+
"learning_rate": 0.0001565136414422592,
|
| 458 |
+
"loss": 0.2114,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.81,
|
| 463 |
+
"grad_norm": 0.03653452917933464,
|
| 464 |
+
"learning_rate": 0.00015459299383291345,
|
| 465 |
+
"loss": 0.2183,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.82,
|
| 470 |
+
"grad_norm": 0.03146987408399582,
|
| 471 |
+
"learning_rate": 0.0001526432162877356,
|
| 472 |
+
"loss": 0.2444,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.83,
|
| 477 |
+
"grad_norm": 0.03224271163344383,
|
| 478 |
+
"learning_rate": 0.00015066534917639195,
|
| 479 |
+
"loss": 0.2157,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.84,
|
| 484 |
+
"grad_norm": 0.028182610869407654,
|
| 485 |
+
"learning_rate": 0.00014866044785668563,
|
| 486 |
+
"loss": 0.16,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.86,
|
| 491 |
+
"grad_norm": 0.03271663188934326,
|
| 492 |
+
"learning_rate": 0.0001466295821114348,
|
| 493 |
+
"loss": 0.2102,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.87,
|
| 498 |
+
"grad_norm": 0.032980792224407196,
|
| 499 |
+
"learning_rate": 0.00014457383557765386,
|
| 500 |
+
"loss": 0.2605,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.88,
|
| 505 |
+
"grad_norm": 0.03456718847155571,
|
| 506 |
+
"learning_rate": 0.0001424943051683422,
|
| 507 |
+
"loss": 0.212,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.89,
|
| 512 |
+
"grad_norm": 0.036501459777355194,
|
| 513 |
+
"learning_rate": 0.00014039210048718949,
|
| 514 |
+
"loss": 0.1798,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.91,
|
| 519 |
+
"grad_norm": 0.033730726689100266,
|
| 520 |
+
"learning_rate": 0.000138268343236509,
|
| 521 |
+
"loss": 0.2018,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.92,
|
| 526 |
+
"grad_norm": 0.03012872487306595,
|
| 527 |
+
"learning_rate": 0.00013612416661871533,
|
| 528 |
+
"loss": 0.2309,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.93,
|
| 533 |
+
"grad_norm": 0.032879915088415146,
|
| 534 |
+
"learning_rate": 0.00013396071473166613,
|
| 535 |
+
"loss": 0.1912,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.95,
|
| 540 |
+
"grad_norm": 0.02916533872485161,
|
| 541 |
+
"learning_rate": 0.00013177914195819016,
|
| 542 |
+
"loss": 0.2313,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.96,
|
| 547 |
+
"grad_norm": 0.032934658229351044,
|
| 548 |
+
"learning_rate": 0.00012958061235012706,
|
| 549 |
+
"loss": 0.2118,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.97,
|
| 554 |
+
"grad_norm": 0.03474392369389534,
|
| 555 |
+
"learning_rate": 0.0001273662990072083,
|
| 556 |
+
"loss": 0.1465,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.98,
|
| 561 |
+
"grad_norm": 0.033331647515296936,
|
| 562 |
+
"learning_rate": 0.0001251373834511103,
|
| 563 |
+
"loss": 0.2207,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.0,
|
| 568 |
+
"grad_norm": 0.030515702441334724,
|
| 569 |
+
"learning_rate": 0.0001228950549950134,
|
| 570 |
+
"loss": 0.2121,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.0,
|
| 575 |
+
"eval_loss": 0.19000689685344696,
|
| 576 |
+
"eval_runtime": 153.8331,
|
| 577 |
+
"eval_samples_per_second": 1.463,
|
| 578 |
+
"eval_steps_per_second": 0.371,
|
| 579 |
+
"step": 78
|
| 580 |
+
}
|
| 581 |
+
],
|
| 582 |
+
"logging_steps": 1,
|
| 583 |
+
"max_steps": 156,
|
| 584 |
+
"num_input_tokens_seen": 0,
|
| 585 |
+
"num_train_epochs": 2,
|
| 586 |
+
"save_steps": 39,
|
| 587 |
+
"total_flos": 1.0256862348627149e+17,
|
| 588 |
+
"train_batch_size": 2,
|
| 589 |
+
"trial_name": null,
|
| 590 |
+
"trial_params": null
|
| 591 |
+
}
|