Upload folder using huggingface_hub
Browse files- README.md +29 -105
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- checkpoint-100/adapter_config.json +4 -4
- checkpoint-100/adapter_model.safetensors +1 -1
- checkpoint-100/optimizer.pt +1 -1
- checkpoint-100/rng_state.pth +1 -1
- checkpoint-100/trainer_state.json +62 -62
- checkpoint-200/adapter_config.json +4 -4
- checkpoint-200/adapter_model.safetensors +1 -1
- checkpoint-200/optimizer.pt +1 -1
- checkpoint-200/rng_state.pth +1 -1
- checkpoint-200/trainer_state.json +122 -122
- checkpoint-300/adapter_config.json +4 -4
- checkpoint-300/adapter_model.safetensors +1 -1
- checkpoint-300/optimizer.pt +1 -1
- checkpoint-300/rng_state.pth +1 -1
- checkpoint-300/trainer_state.json +182 -182
- checkpoint-400/adapter_config.json +4 -4
- checkpoint-400/adapter_model.safetensors +1 -1
- checkpoint-400/optimizer.pt +1 -1
- checkpoint-400/rng_state.pth +1 -1
- checkpoint-400/trainer_state.json +242 -242
- checkpoint-500/adapter_config.json +4 -4
- checkpoint-500/adapter_model.safetensors +1 -1
- checkpoint-500/optimizer.pt +1 -1
- checkpoint-500/rng_state.pth +1 -1
- checkpoint-500/trainer_state.json +302 -302
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: peft
|
| 3 |
model_name: tutor_model_output
|
| 4 |
tags:
|
|
@@ -7,132 +8,55 @@ tags:
|
|
| 7 |
- sft
|
| 8 |
- transformers
|
| 9 |
- trl
|
| 10 |
-
- language-tutor
|
| 11 |
-
- english
|
| 12 |
-
- german
|
| 13 |
-
- vietnamese
|
| 14 |
-
- conversational
|
| 15 |
-
- instruct
|
| 16 |
-
language:
|
| 17 |
-
- vi
|
| 18 |
-
- en
|
| 19 |
-
- de
|
| 20 |
licence: license
|
| 21 |
pipeline_tag: text-generation
|
| 22 |
---
|
| 23 |
|
| 24 |
-
#
|
| 25 |
|
| 26 |
-
|
|
|
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
-
## 🚀 Model Details
|
| 31 |
-
- **Model Type:** Causal Language Model (Fine-tuned LoRA Adapter)
|
| 32 |
-
- **Base Model:** Meta Llama 3 (8B-Instruct 4-bit quantized via Unsloth)
|
| 33 |
-
- **Primary Languages:** Vietnamese (Explanations), English (Target), German (Target)
|
| 34 |
-
- **Training Framework:** `TRL` (Transformer Reinforcement Learning) & `PEFT`
|
| 35 |
-
- **Architecture:** Optimized for multi-modal integrations (Text, OCR/Images, and STT/Voice processing ecosystems).
|
| 36 |
-
|
| 37 |
-
## 💡 Intended Uses & Ecosystem
|
| 38 |
-
This model is the core "Brain" of the **Denglish Omnichannel Platform** (integrated via RunPod Serverless, FastAPI, Telegram, and Facebook Messenger).
|
| 39 |
-
It is intended to process inputs such as:
|
| 40 |
-
1. **Direct Text:** User types a sentence in English or German.
|
| 41 |
-
2. **Transcribed Audio (Whisper STT):** Correcting conversational mistakes from spoken language.
|
| 42 |
-
3. **Extracted Text from Images (OCR):** Grading handwritten or printed homework.
|
| 43 |
-
|
| 44 |
-
## 🛠️ How to Use (Quick Start)
|
| 45 |
-
|
| 46 |
-
Since this is a LoRA adapter, you need to load the base model first and then merge it with this adapter using `peft`.
|
| 47 |
-
|
| 48 |
-
### Prerequisites
|
| 49 |
-
```bash
|
| 50 |
-
pip install transformers accelerate bitsandbytes peft
|
| 51 |
-
```
|
| 52 |
-
## Inference Code
|
| 53 |
```python
|
| 54 |
-
import
|
| 55 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 56 |
-
from peft import PeftModel
|
| 57 |
-
|
| 58 |
-
# 1. Load Base Model and Tokenizer
|
| 59 |
-
base_model_id = "unsloth/llama-3-8b-Instruct-bnb-4bit"
|
| 60 |
-
lora_model_id = "phgrouptechs/Denglish-8B-Instruct"
|
| 61 |
-
|
| 62 |
-
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
|
| 63 |
-
base_model = AutoModelForCausalLM.from_pretrained(
|
| 64 |
-
base_model_id,
|
| 65 |
-
torch_dtype=torch.bfloat16,
|
| 66 |
-
device_map="auto"
|
| 67 |
-
)
|
| 68 |
-
|
| 69 |
-
# 2. Load the Denglish LoRA Adapter
|
| 70 |
-
model = PeftModel.from_pretrained(base_model, lora_model_id)
|
| 71 |
-
|
| 72 |
-
# 3. Prepare the Chat Prompt
|
| 73 |
-
target_lang = "English" # or "German"
|
| 74 |
-
user_mistake = "Hello, my name is John and I is a student."
|
| 75 |
-
|
| 76 |
-
system_prompt = (
|
| 77 |
-
f"You are a friendly and strict {target_lang} tutor for Vietnamese students. "
|
| 78 |
-
f"The user provided a {target_lang} input: '{user_mistake}'. "
|
| 79 |
-
f"Task: 1. Correct any grammatical, spelling, or pronunciation mistakes. "
|
| 80 |
-
f"2. Explain the corrections clearly in Vietnamese. "
|
| 81 |
-
f"3. Provide the perfectly corrected sentence in {target_lang} at the very end."
|
| 82 |
-
)
|
| 83 |
-
|
| 84 |
-
messages = [
|
| 85 |
-
{"role": "system", "content": system_prompt},
|
| 86 |
-
{"role": "user", "content": "Hãy chấm bài và sửa lỗi cho tôi."}
|
| 87 |
-
]
|
| 88 |
-
|
| 89 |
-
# 4. Generate Response
|
| 90 |
-
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 91 |
-
inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
|
| 92 |
-
|
| 93 |
-
outputs = model.generate(
|
| 94 |
-
**inputs,
|
| 95 |
-
max_new_tokens=400,
|
| 96 |
-
temperature=0.3, # Low temperature for accurate grammar corrections
|
| 97 |
-
pad_token_id=tokenizer.eos_token_id
|
| 98 |
-
)
|
| 99 |
-
|
| 100 |
-
ai_response = tokenizer.batch_decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)[0].strip()
|
| 101 |
-
print(ai_response)
|
| 102 |
-
```
|
| 103 |
-
|
| 104 |
-
## 📝 Example Output
|
| 105 |
-
|
| 106 |
-
**Input (User):** "Hello, my name is John and I is a student."
|
| 107 |
-
**Target Language:** English
|
| 108 |
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
|
| 115 |
## Training procedure
|
| 116 |
|
| 117 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/phgrouptechs-phgroup-technology-solutions-co-ltd/my-awesome-project/runs/
|
| 118 |
|
| 119 |
|
| 120 |
|
| 121 |
This model was trained with SFT.
|
| 122 |
|
| 123 |
-
## ⚠️ Limitations
|
| 124 |
-
* **Quantization Constraints:** The base model is 4-bit quantized. While it is highly efficient, extremely complex logical reasoning might be slightly degraded compared to the FP16 base model.
|
| 125 |
-
|
| 126 |
-
* **Language Scope:** The model is highly optimized for English/German to Vietnamese explanations. Using it for other language pairs might yield suboptimal results.
|
| 127 |
-
|
| 128 |
### Framework versions
|
| 129 |
|
| 130 |
- PEFT 0.18.1
|
| 131 |
- TRL: 0.29.0
|
| 132 |
-
- Transformers: 5.
|
| 133 |
- Pytorch: 2.8.0+cu128
|
| 134 |
-
- Datasets: 4.6.
|
| 135 |
- Tokenizers: 0.22.2
|
| 136 |
|
| 137 |
-
##
|
| 138 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 3 |
library_name: peft
|
| 4 |
model_name: tutor_model_output
|
| 5 |
tags:
|
|
|
|
| 8 |
- sft
|
| 9 |
- transformers
|
| 10 |
- trl
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
licence: license
|
| 12 |
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Model Card for tutor_model_output
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit).
|
| 18 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 19 |
|
| 20 |
+
## Quick start
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
```python
|
| 23 |
+
from transformers import pipeline
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 26 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 27 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 28 |
+
print(output["generated_text"])
|
| 29 |
+
```
|
| 30 |
|
| 31 |
## Training procedure
|
| 32 |
|
| 33 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/phgrouptechs-phgroup-technology-solutions-co-ltd/my-awesome-project/runs/74x5vj6l)
|
| 34 |
|
| 35 |
|
| 36 |
|
| 37 |
This model was trained with SFT.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
### Framework versions
|
| 40 |
|
| 41 |
- PEFT 0.18.1
|
| 42 |
- TRL: 0.29.0
|
| 43 |
+
- Transformers: 5.3.0
|
| 44 |
- Pytorch: 2.8.0+cu128
|
| 45 |
+
- Datasets: 4.6.1
|
| 46 |
- Tokenizers: 0.22.2
|
| 47 |
|
| 48 |
+
## Citations
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
Cite TRL as:
|
| 53 |
+
|
| 54 |
+
```bibtex
|
| 55 |
+
@software{vonwerra2020trl,
|
| 56 |
+
title = {{TRL: Transformers Reinforcement Learning}},
|
| 57 |
+
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
| 58 |
+
license = {Apache-2.0},
|
| 59 |
+
url = {https://github.com/huggingface/trl},
|
| 60 |
+
year = {2020}
|
| 61 |
+
}
|
| 62 |
+
```
|
adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c5f909945589d0c78975a1cb4af27dcba08206910975f240e0ceb21013a2e2
|
| 3 |
size 83946192
|
checkpoint-100/adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
checkpoint-100/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd3571d376b0d67ebe69939a4324b1619b93944194edad7b9e1b8e8503fac290
|
| 3 |
size 83946192
|
checkpoint-100/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335817867
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2873fdc2d53f293c0fddd0c6945e25936379b8656d7d9730013ad80daac1db00
|
| 3 |
size 335817867
|
checkpoint-100/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd42335f66aa8837109aed797819fac4d73aa4b840d682d5e72348336f572739
|
| 3 |
size 14645
|
checkpoint-100/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 100,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,103 +10,103 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"entropy": 1.
|
| 14 |
-
"epoch":
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
-
"loss": 1.
|
| 18 |
-
"mean_token_accuracy": 0.
|
| 19 |
-
"num_tokens":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"entropy": 1.
|
| 24 |
-
"epoch":
|
| 25 |
-
"grad_norm": 0.
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
-
"loss": 1.
|
| 28 |
-
"mean_token_accuracy": 0.
|
| 29 |
-
"num_tokens":
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"entropy":
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
-
"loss":
|
| 38 |
-
"mean_token_accuracy": 0.
|
| 39 |
-
"num_tokens":
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"entropy":
|
| 44 |
-
"epoch":
|
| 45 |
-
"grad_norm": 0.
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
-
"loss":
|
| 48 |
-
"mean_token_accuracy": 0.
|
| 49 |
-
"num_tokens":
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"entropy":
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
-
"loss":
|
| 58 |
-
"mean_token_accuracy": 0.
|
| 59 |
-
"num_tokens":
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"entropy":
|
| 64 |
-
"epoch":
|
| 65 |
-
"grad_norm": 0.
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
-
"loss":
|
| 68 |
-
"mean_token_accuracy": 0.
|
| 69 |
-
"num_tokens":
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"entropy":
|
| 74 |
-
"epoch":
|
| 75 |
-
"grad_norm": 0.
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
-
"loss":
|
| 78 |
-
"mean_token_accuracy": 0.
|
| 79 |
-
"num_tokens":
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"entropy":
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
-
"loss":
|
| 88 |
-
"mean_token_accuracy": 0.
|
| 89 |
-
"num_tokens":
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"entropy":
|
| 94 |
-
"epoch":
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
-
"loss":
|
| 98 |
-
"mean_token_accuracy": 0.
|
| 99 |
-
"num_tokens":
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"entropy":
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
-
"loss":
|
| 108 |
-
"mean_token_accuracy": 0.
|
| 109 |
-
"num_tokens":
|
| 110 |
"step": 100
|
| 111 |
}
|
| 112 |
],
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
"attributes": {}
|
| 128 |
}
|
| 129 |
},
|
| 130 |
-
"total_flos":
|
| 131 |
"train_batch_size": 8,
|
| 132 |
"trial_name": null,
|
| 133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.401168496482224e-05,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 100,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"entropy": 1.4767830133438111,
|
| 14 |
+
"epoch": 7.401168496482225e-06,
|
| 15 |
+
"grad_norm": 0.578125,
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
+
"loss": 1.6877475738525392,
|
| 18 |
+
"mean_token_accuracy": 0.7061349496245384,
|
| 19 |
+
"num_tokens": 14911.0,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"entropy": 1.0930627048015595,
|
| 24 |
+
"epoch": 1.480233699296445e-05,
|
| 25 |
+
"grad_norm": 0.458984375,
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
+
"loss": 1.0562871932983398,
|
| 28 |
+
"mean_token_accuracy": 0.8108290940523147,
|
| 29 |
+
"num_tokens": 28646.0,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"entropy": 0.8788679152727127,
|
| 34 |
+
"epoch": 2.2203505489446674e-05,
|
| 35 |
+
"grad_norm": 0.5859375,
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
+
"loss": 0.8974875450134278,
|
| 38 |
+
"mean_token_accuracy": 0.8296987593173981,
|
| 39 |
+
"num_tokens": 41474.0,
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"entropy": 0.8145956963300705,
|
| 44 |
+
"epoch": 2.96046739859289e-05,
|
| 45 |
+
"grad_norm": 0.39453125,
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
+
"loss": 0.8066701889038086,
|
| 48 |
+
"mean_token_accuracy": 0.8340015441179276,
|
| 49 |
+
"num_tokens": 54466.0,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"entropy": 0.7157480388879776,
|
| 54 |
+
"epoch": 3.700584248241112e-05,
|
| 55 |
+
"grad_norm": 0.326171875,
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
+
"loss": 0.7251500129699707,
|
| 58 |
+
"mean_token_accuracy": 0.8420351594686508,
|
| 59 |
+
"num_tokens": 66880.0,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"entropy": 0.7959431439638138,
|
| 64 |
+
"epoch": 4.440701097889335e-05,
|
| 65 |
+
"grad_norm": 0.326171875,
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
+
"loss": 0.8049167633056641,
|
| 68 |
+
"mean_token_accuracy": 0.8289562940597535,
|
| 69 |
+
"num_tokens": 80036.0,
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"entropy": 0.8342548221349716,
|
| 74 |
+
"epoch": 5.180817947537557e-05,
|
| 75 |
+
"grad_norm": 0.326171875,
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
+
"loss": 0.8336853981018066,
|
| 78 |
+
"mean_token_accuracy": 0.8279720038175583,
|
| 79 |
+
"num_tokens": 93357.0,
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"entropy": 0.7970967918634415,
|
| 84 |
+
"epoch": 5.92093479718578e-05,
|
| 85 |
+
"grad_norm": 0.73046875,
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
+
"loss": 0.7949181079864502,
|
| 88 |
+
"mean_token_accuracy": 0.828959608078003,
|
| 89 |
+
"num_tokens": 106951.0,
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"entropy": 0.7967441529035568,
|
| 94 |
+
"epoch": 6.661051646834002e-05,
|
| 95 |
+
"grad_norm": 0.34375,
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
+
"loss": 0.8285197257995606,
|
| 98 |
+
"mean_token_accuracy": 0.8272027671337128,
|
| 99 |
+
"num_tokens": 120269.0,
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"entropy": 0.7741447448730469,
|
| 104 |
+
"epoch": 7.401168496482224e-05,
|
| 105 |
+
"grad_norm": 0.271484375,
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
+
"loss": 0.7636381626129151,
|
| 108 |
+
"mean_token_accuracy": 0.8373189926147461,
|
| 109 |
+
"num_tokens": 133116.0,
|
| 110 |
"step": 100
|
| 111 |
}
|
| 112 |
],
|
|
|
|
| 127 |
"attributes": {}
|
| 128 |
}
|
| 129 |
},
|
| 130 |
+
"total_flos": 9597079982112768.0,
|
| 131 |
"train_batch_size": 8,
|
| 132 |
"trial_name": null,
|
| 133 |
"trial_params": null
|
checkpoint-200/adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
checkpoint-200/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b38a965a78dd2741df9584b07323c6472be2985ef11caf5e56857e87bb65fb4
|
| 3 |
size 83946192
|
checkpoint-200/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335817867
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ae2af00d109790f6a0cae3a0a00c8da0f1d9bb6b988a377f14be3b34936563f
|
| 3 |
size 335817867
|
checkpoint-200/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daadb075e2f031fbda74514b09d5bc1b433960d924ec2d86606ab755c3504c6c
|
| 3 |
size 14645
|
checkpoint-200/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 200,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,203 +10,203 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"entropy": 1.
|
| 14 |
-
"epoch":
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
-
"loss": 1.
|
| 18 |
-
"mean_token_accuracy": 0.
|
| 19 |
-
"num_tokens":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"entropy": 1.
|
| 24 |
-
"epoch":
|
| 25 |
-
"grad_norm": 0.
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
-
"loss": 1.
|
| 28 |
-
"mean_token_accuracy": 0.
|
| 29 |
-
"num_tokens":
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"entropy":
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
-
"loss":
|
| 38 |
-
"mean_token_accuracy": 0.
|
| 39 |
-
"num_tokens":
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"entropy":
|
| 44 |
-
"epoch":
|
| 45 |
-
"grad_norm": 0.
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
-
"loss":
|
| 48 |
-
"mean_token_accuracy": 0.
|
| 49 |
-
"num_tokens":
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"entropy":
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
-
"loss":
|
| 58 |
-
"mean_token_accuracy": 0.
|
| 59 |
-
"num_tokens":
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"entropy":
|
| 64 |
-
"epoch":
|
| 65 |
-
"grad_norm": 0.
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
-
"loss":
|
| 68 |
-
"mean_token_accuracy": 0.
|
| 69 |
-
"num_tokens":
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"entropy":
|
| 74 |
-
"epoch":
|
| 75 |
-
"grad_norm": 0.
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
-
"loss":
|
| 78 |
-
"mean_token_accuracy": 0.
|
| 79 |
-
"num_tokens":
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"entropy":
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
-
"loss":
|
| 88 |
-
"mean_token_accuracy": 0.
|
| 89 |
-
"num_tokens":
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"entropy":
|
| 94 |
-
"epoch":
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
-
"loss":
|
| 98 |
-
"mean_token_accuracy": 0.
|
| 99 |
-
"num_tokens":
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"entropy":
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
-
"loss":
|
| 108 |
-
"mean_token_accuracy": 0.
|
| 109 |
-
"num_tokens":
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"entropy":
|
| 114 |
-
"epoch":
|
| 115 |
-
"grad_norm": 0.
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
-
"loss":
|
| 118 |
-
"mean_token_accuracy": 0.
|
| 119 |
-
"num_tokens":
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"entropy":
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
-
"loss":
|
| 128 |
-
"mean_token_accuracy": 0.
|
| 129 |
-
"num_tokens":
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"entropy":
|
| 134 |
-
"epoch":
|
| 135 |
-
"grad_norm": 0.
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
-
"loss":
|
| 138 |
-
"mean_token_accuracy": 0.
|
| 139 |
-
"num_tokens":
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"entropy":
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"grad_norm": 0.
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
-
"loss":
|
| 148 |
-
"mean_token_accuracy": 0.
|
| 149 |
-
"num_tokens":
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"entropy":
|
| 154 |
-
"epoch": 0.
|
| 155 |
-
"grad_norm": 0.
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
-
"loss":
|
| 158 |
-
"mean_token_accuracy": 0.
|
| 159 |
-
"num_tokens":
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"entropy":
|
| 164 |
-
"epoch": 0.
|
| 165 |
-
"grad_norm": 0.
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
-
"loss":
|
| 168 |
-
"mean_token_accuracy": 0.
|
| 169 |
-
"num_tokens":
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"entropy":
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
-
"loss":
|
| 178 |
-
"mean_token_accuracy": 0.
|
| 179 |
-
"num_tokens":
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"entropy":
|
| 184 |
-
"epoch": 0.
|
| 185 |
-
"grad_norm":
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
-
"loss":
|
| 188 |
-
"mean_token_accuracy": 0.
|
| 189 |
-
"num_tokens":
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"entropy":
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
-
"loss":
|
| 198 |
-
"mean_token_accuracy": 0.
|
| 199 |
-
"num_tokens":
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"entropy":
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"grad_norm": 0.
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
-
"loss":
|
| 208 |
-
"mean_token_accuracy": 0.
|
| 209 |
-
"num_tokens":
|
| 210 |
"step": 200
|
| 211 |
}
|
| 212 |
],
|
|
@@ -227,7 +227,7 @@
|
|
| 227 |
"attributes": {}
|
| 228 |
}
|
| 229 |
},
|
| 230 |
-
"total_flos":
|
| 231 |
"train_batch_size": 8,
|
| 232 |
"trial_name": null,
|
| 233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.00014802336992964448,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 200,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"entropy": 1.4767830133438111,
|
| 14 |
+
"epoch": 7.401168496482225e-06,
|
| 15 |
+
"grad_norm": 0.578125,
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
+
"loss": 1.6877475738525392,
|
| 18 |
+
"mean_token_accuracy": 0.7061349496245384,
|
| 19 |
+
"num_tokens": 14911.0,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"entropy": 1.0930627048015595,
|
| 24 |
+
"epoch": 1.480233699296445e-05,
|
| 25 |
+
"grad_norm": 0.458984375,
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
+
"loss": 1.0562871932983398,
|
| 28 |
+
"mean_token_accuracy": 0.8108290940523147,
|
| 29 |
+
"num_tokens": 28646.0,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"entropy": 0.8788679152727127,
|
| 34 |
+
"epoch": 2.2203505489446674e-05,
|
| 35 |
+
"grad_norm": 0.5859375,
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
+
"loss": 0.8974875450134278,
|
| 38 |
+
"mean_token_accuracy": 0.8296987593173981,
|
| 39 |
+
"num_tokens": 41474.0,
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"entropy": 0.8145956963300705,
|
| 44 |
+
"epoch": 2.96046739859289e-05,
|
| 45 |
+
"grad_norm": 0.39453125,
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
+
"loss": 0.8066701889038086,
|
| 48 |
+
"mean_token_accuracy": 0.8340015441179276,
|
| 49 |
+
"num_tokens": 54466.0,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"entropy": 0.7157480388879776,
|
| 54 |
+
"epoch": 3.700584248241112e-05,
|
| 55 |
+
"grad_norm": 0.326171875,
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
+
"loss": 0.7251500129699707,
|
| 58 |
+
"mean_token_accuracy": 0.8420351594686508,
|
| 59 |
+
"num_tokens": 66880.0,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"entropy": 0.7959431439638138,
|
| 64 |
+
"epoch": 4.440701097889335e-05,
|
| 65 |
+
"grad_norm": 0.326171875,
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
+
"loss": 0.8049167633056641,
|
| 68 |
+
"mean_token_accuracy": 0.8289562940597535,
|
| 69 |
+
"num_tokens": 80036.0,
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"entropy": 0.8342548221349716,
|
| 74 |
+
"epoch": 5.180817947537557e-05,
|
| 75 |
+
"grad_norm": 0.326171875,
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
+
"loss": 0.8336853981018066,
|
| 78 |
+
"mean_token_accuracy": 0.8279720038175583,
|
| 79 |
+
"num_tokens": 93357.0,
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"entropy": 0.7970967918634415,
|
| 84 |
+
"epoch": 5.92093479718578e-05,
|
| 85 |
+
"grad_norm": 0.73046875,
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
+
"loss": 0.7949181079864502,
|
| 88 |
+
"mean_token_accuracy": 0.828959608078003,
|
| 89 |
+
"num_tokens": 106951.0,
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"entropy": 0.7967441529035568,
|
| 94 |
+
"epoch": 6.661051646834002e-05,
|
| 95 |
+
"grad_norm": 0.34375,
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
+
"loss": 0.8285197257995606,
|
| 98 |
+
"mean_token_accuracy": 0.8272027671337128,
|
| 99 |
+
"num_tokens": 120269.0,
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"entropy": 0.7741447448730469,
|
| 104 |
+
"epoch": 7.401168496482224e-05,
|
| 105 |
+
"grad_norm": 0.271484375,
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
+
"loss": 0.7636381626129151,
|
| 108 |
+
"mean_token_accuracy": 0.8373189926147461,
|
| 109 |
+
"num_tokens": 133116.0,
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"entropy": 0.72959463596344,
|
| 114 |
+
"epoch": 8.141285346130448e-05,
|
| 115 |
+
"grad_norm": 0.421875,
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
+
"loss": 0.7404542446136475,
|
| 118 |
+
"mean_token_accuracy": 0.8400259047746659,
|
| 119 |
+
"num_tokens": 146103.0,
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"entropy": 0.777249938249588,
|
| 124 |
+
"epoch": 8.88140219577867e-05,
|
| 125 |
+
"grad_norm": 0.3984375,
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
+
"loss": 0.7868029117584229,
|
| 128 |
+
"mean_token_accuracy": 0.8342386931180954,
|
| 129 |
+
"num_tokens": 158980.0,
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"entropy": 0.8305783897638321,
|
| 134 |
+
"epoch": 9.621519045426892e-05,
|
| 135 |
+
"grad_norm": 0.328125,
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
+
"loss": 0.8155685424804687,
|
| 138 |
+
"mean_token_accuracy": 0.8282770067453384,
|
| 139 |
+
"num_tokens": 172414.0,
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"entropy": 0.8582165241241455,
|
| 144 |
+
"epoch": 0.00010361635895075114,
|
| 145 |
+
"grad_norm": 0.322265625,
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
+
"loss": 0.8684965133666992,
|
| 148 |
+
"mean_token_accuracy": 0.8188153028488159,
|
| 149 |
+
"num_tokens": 186224.0,
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"entropy": 0.823002302646637,
|
| 154 |
+
"epoch": 0.00011101752744723338,
|
| 155 |
+
"grad_norm": 0.41796875,
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
+
"loss": 0.8199325561523437,
|
| 158 |
+
"mean_token_accuracy": 0.8285818427801133,
|
| 159 |
+
"num_tokens": 199564.0,
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"entropy": 0.7803006649017334,
|
| 164 |
+
"epoch": 0.0001184186959437156,
|
| 165 |
+
"grad_norm": 0.28125,
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
+
"loss": 0.8177242279052734,
|
| 168 |
+
"mean_token_accuracy": 0.8276909857988357,
|
| 169 |
+
"num_tokens": 212955.0,
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"entropy": 0.7576605170965195,
|
| 174 |
+
"epoch": 0.00012581986444019783,
|
| 175 |
+
"grad_norm": 0.298828125,
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
+
"loss": 0.7334442615509034,
|
| 178 |
+
"mean_token_accuracy": 0.8368929207324982,
|
| 179 |
+
"num_tokens": 225983.0,
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"entropy": 0.8388681739568711,
|
| 184 |
+
"epoch": 0.00013322103293668004,
|
| 185 |
+
"grad_norm": 4.15625,
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
+
"loss": 0.878928279876709,
|
| 188 |
+
"mean_token_accuracy": 0.8206132620573043,
|
| 189 |
+
"num_tokens": 240490.0,
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
+
"entropy": 0.8390863686800003,
|
| 194 |
+
"epoch": 0.00014062220143316227,
|
| 195 |
+
"grad_norm": 0.25,
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
+
"loss": 0.8454230308532715,
|
| 198 |
+
"mean_token_accuracy": 0.8245942384004593,
|
| 199 |
+
"num_tokens": 254696.0,
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"entropy": 0.8603733956813813,
|
| 204 |
+
"epoch": 0.00014802336992964448,
|
| 205 |
+
"grad_norm": 0.2734375,
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
+
"loss": 0.8759581565856933,
|
| 208 |
+
"mean_token_accuracy": 0.8165332227945328,
|
| 209 |
+
"num_tokens": 269719.0,
|
| 210 |
"step": 200
|
| 211 |
}
|
| 212 |
],
|
|
|
|
| 227 |
"attributes": {}
|
| 228 |
}
|
| 229 |
},
|
| 230 |
+
"total_flos": 1.979803013106893e+16,
|
| 231 |
"train_batch_size": 8,
|
| 232 |
"trial_name": null,
|
| 233 |
"trial_params": null
|
checkpoint-300/adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
checkpoint-300/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85efefbb46bc43fcbac85541bd7b747e61f87e638522522412f091837cc1b8a1
|
| 3 |
size 83946192
|
checkpoint-300/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335818315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0df08cfa7716b9bae6ec43b0a8ef4cb39429b50f55a2ab597adea0596080bac6
|
| 3 |
size 335818315
|
checkpoint-300/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9d64886c1f6b45c33ffbb3c56e1debba8d8c711e548d1360b58267adb2ccdba
|
| 3 |
size 14645
|
checkpoint-300/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 300,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,303 +10,303 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"entropy": 1.
|
| 14 |
-
"epoch":
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
-
"loss": 1.
|
| 18 |
-
"mean_token_accuracy": 0.
|
| 19 |
-
"num_tokens":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"entropy": 1.
|
| 24 |
-
"epoch":
|
| 25 |
-
"grad_norm": 0.
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
-
"loss": 1.
|
| 28 |
-
"mean_token_accuracy": 0.
|
| 29 |
-
"num_tokens":
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"entropy":
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
-
"loss":
|
| 38 |
-
"mean_token_accuracy": 0.
|
| 39 |
-
"num_tokens":
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"entropy":
|
| 44 |
-
"epoch":
|
| 45 |
-
"grad_norm": 0.
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
-
"loss":
|
| 48 |
-
"mean_token_accuracy": 0.
|
| 49 |
-
"num_tokens":
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"entropy":
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
-
"loss":
|
| 58 |
-
"mean_token_accuracy": 0.
|
| 59 |
-
"num_tokens":
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"entropy":
|
| 64 |
-
"epoch":
|
| 65 |
-
"grad_norm": 0.
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
-
"loss":
|
| 68 |
-
"mean_token_accuracy": 0.
|
| 69 |
-
"num_tokens":
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"entropy":
|
| 74 |
-
"epoch":
|
| 75 |
-
"grad_norm": 0.
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
-
"loss":
|
| 78 |
-
"mean_token_accuracy": 0.
|
| 79 |
-
"num_tokens":
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"entropy":
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
-
"loss":
|
| 88 |
-
"mean_token_accuracy": 0.
|
| 89 |
-
"num_tokens":
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"entropy":
|
| 94 |
-
"epoch":
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
-
"loss":
|
| 98 |
-
"mean_token_accuracy": 0.
|
| 99 |
-
"num_tokens":
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"entropy":
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
-
"loss":
|
| 108 |
-
"mean_token_accuracy": 0.
|
| 109 |
-
"num_tokens":
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"entropy":
|
| 114 |
-
"epoch":
|
| 115 |
-
"grad_norm": 0.
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
-
"loss":
|
| 118 |
-
"mean_token_accuracy": 0.
|
| 119 |
-
"num_tokens":
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"entropy":
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
-
"loss":
|
| 128 |
-
"mean_token_accuracy": 0.
|
| 129 |
-
"num_tokens":
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"entropy":
|
| 134 |
-
"epoch":
|
| 135 |
-
"grad_norm": 0.
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
-
"loss":
|
| 138 |
-
"mean_token_accuracy": 0.
|
| 139 |
-
"num_tokens":
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"entropy":
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"grad_norm": 0.
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
-
"loss":
|
| 148 |
-
"mean_token_accuracy": 0.
|
| 149 |
-
"num_tokens":
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"entropy":
|
| 154 |
-
"epoch": 0.
|
| 155 |
-
"grad_norm": 0.
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
-
"loss":
|
| 158 |
-
"mean_token_accuracy": 0.
|
| 159 |
-
"num_tokens":
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"entropy":
|
| 164 |
-
"epoch": 0.
|
| 165 |
-
"grad_norm": 0.
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
-
"loss":
|
| 168 |
-
"mean_token_accuracy": 0.
|
| 169 |
-
"num_tokens":
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"entropy":
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
-
"loss":
|
| 178 |
-
"mean_token_accuracy": 0.
|
| 179 |
-
"num_tokens":
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"entropy":
|
| 184 |
-
"epoch": 0.
|
| 185 |
-
"grad_norm":
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
-
"loss":
|
| 188 |
-
"mean_token_accuracy": 0.
|
| 189 |
-
"num_tokens":
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"entropy":
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
-
"loss":
|
| 198 |
-
"mean_token_accuracy": 0.
|
| 199 |
-
"num_tokens":
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"entropy":
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"grad_norm": 0.
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
-
"loss":
|
| 208 |
-
"mean_token_accuracy": 0.
|
| 209 |
-
"num_tokens":
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
-
"entropy":
|
| 214 |
-
"epoch": 0.
|
| 215 |
-
"grad_norm": 0.
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
-
"loss":
|
| 218 |
-
"mean_token_accuracy": 0.
|
| 219 |
-
"num_tokens":
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"entropy":
|
| 224 |
-
"epoch": 0.
|
| 225 |
-
"grad_norm": 0.
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
-
"loss":
|
| 228 |
-
"mean_token_accuracy": 0.
|
| 229 |
-
"num_tokens":
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"entropy":
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
-
"loss":
|
| 238 |
-
"mean_token_accuracy": 0.
|
| 239 |
-
"num_tokens":
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"entropy":
|
| 244 |
-
"epoch": 0.
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
-
"loss":
|
| 248 |
-
"mean_token_accuracy": 0.
|
| 249 |
-
"num_tokens":
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"entropy":
|
| 254 |
-
"epoch": 0.
|
| 255 |
-
"grad_norm": 0.
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
-
"loss":
|
| 258 |
-
"mean_token_accuracy": 0.
|
| 259 |
-
"num_tokens":
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"entropy":
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
-
"loss":
|
| 268 |
-
"mean_token_accuracy": 0.
|
| 269 |
-
"num_tokens":
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"entropy":
|
| 274 |
-
"epoch": 0.
|
| 275 |
-
"grad_norm": 0.
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
-
"loss":
|
| 278 |
-
"mean_token_accuracy": 0.
|
| 279 |
-
"num_tokens":
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"entropy":
|
| 284 |
-
"epoch": 0.
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
-
"loss":
|
| 288 |
-
"mean_token_accuracy": 0.
|
| 289 |
-
"num_tokens":
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"entropy":
|
| 294 |
-
"epoch": 0.
|
| 295 |
-
"grad_norm": 0.
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
-
"loss":
|
| 298 |
-
"mean_token_accuracy": 0.
|
| 299 |
-
"num_tokens":
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"entropy":
|
| 304 |
-
"epoch": 0.
|
| 305 |
-
"grad_norm": 0.
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
-
"loss":
|
| 308 |
-
"mean_token_accuracy": 0.
|
| 309 |
-
"num_tokens":
|
| 310 |
"step": 300
|
| 311 |
}
|
| 312 |
],
|
|
@@ -327,7 +327,7 @@
|
|
| 327 |
"attributes": {}
|
| 328 |
}
|
| 329 |
},
|
| 330 |
-
"total_flos":
|
| 331 |
"train_batch_size": 8,
|
| 332 |
"trial_name": null,
|
| 333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.00022203505489446675,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 300,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"entropy": 1.4767830133438111,
|
| 14 |
+
"epoch": 7.401168496482225e-06,
|
| 15 |
+
"grad_norm": 0.578125,
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
+
"loss": 1.6877475738525392,
|
| 18 |
+
"mean_token_accuracy": 0.7061349496245384,
|
| 19 |
+
"num_tokens": 14911.0,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"entropy": 1.0930627048015595,
|
| 24 |
+
"epoch": 1.480233699296445e-05,
|
| 25 |
+
"grad_norm": 0.458984375,
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
+
"loss": 1.0562871932983398,
|
| 28 |
+
"mean_token_accuracy": 0.8108290940523147,
|
| 29 |
+
"num_tokens": 28646.0,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"entropy": 0.8788679152727127,
|
| 34 |
+
"epoch": 2.2203505489446674e-05,
|
| 35 |
+
"grad_norm": 0.5859375,
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
+
"loss": 0.8974875450134278,
|
| 38 |
+
"mean_token_accuracy": 0.8296987593173981,
|
| 39 |
+
"num_tokens": 41474.0,
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"entropy": 0.8145956963300705,
|
| 44 |
+
"epoch": 2.96046739859289e-05,
|
| 45 |
+
"grad_norm": 0.39453125,
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
+
"loss": 0.8066701889038086,
|
| 48 |
+
"mean_token_accuracy": 0.8340015441179276,
|
| 49 |
+
"num_tokens": 54466.0,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"entropy": 0.7157480388879776,
|
| 54 |
+
"epoch": 3.700584248241112e-05,
|
| 55 |
+
"grad_norm": 0.326171875,
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
+
"loss": 0.7251500129699707,
|
| 58 |
+
"mean_token_accuracy": 0.8420351594686508,
|
| 59 |
+
"num_tokens": 66880.0,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"entropy": 0.7959431439638138,
|
| 64 |
+
"epoch": 4.440701097889335e-05,
|
| 65 |
+
"grad_norm": 0.326171875,
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
+
"loss": 0.8049167633056641,
|
| 68 |
+
"mean_token_accuracy": 0.8289562940597535,
|
| 69 |
+
"num_tokens": 80036.0,
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"entropy": 0.8342548221349716,
|
| 74 |
+
"epoch": 5.180817947537557e-05,
|
| 75 |
+
"grad_norm": 0.326171875,
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
+
"loss": 0.8336853981018066,
|
| 78 |
+
"mean_token_accuracy": 0.8279720038175583,
|
| 79 |
+
"num_tokens": 93357.0,
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"entropy": 0.7970967918634415,
|
| 84 |
+
"epoch": 5.92093479718578e-05,
|
| 85 |
+
"grad_norm": 0.73046875,
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
+
"loss": 0.7949181079864502,
|
| 88 |
+
"mean_token_accuracy": 0.828959608078003,
|
| 89 |
+
"num_tokens": 106951.0,
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"entropy": 0.7967441529035568,
|
| 94 |
+
"epoch": 6.661051646834002e-05,
|
| 95 |
+
"grad_norm": 0.34375,
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
+
"loss": 0.8285197257995606,
|
| 98 |
+
"mean_token_accuracy": 0.8272027671337128,
|
| 99 |
+
"num_tokens": 120269.0,
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"entropy": 0.7741447448730469,
|
| 104 |
+
"epoch": 7.401168496482224e-05,
|
| 105 |
+
"grad_norm": 0.271484375,
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
+
"loss": 0.7636381626129151,
|
| 108 |
+
"mean_token_accuracy": 0.8373189926147461,
|
| 109 |
+
"num_tokens": 133116.0,
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"entropy": 0.72959463596344,
|
| 114 |
+
"epoch": 8.141285346130448e-05,
|
| 115 |
+
"grad_norm": 0.421875,
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
+
"loss": 0.7404542446136475,
|
| 118 |
+
"mean_token_accuracy": 0.8400259047746659,
|
| 119 |
+
"num_tokens": 146103.0,
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"entropy": 0.777249938249588,
|
| 124 |
+
"epoch": 8.88140219577867e-05,
|
| 125 |
+
"grad_norm": 0.3984375,
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
+
"loss": 0.7868029117584229,
|
| 128 |
+
"mean_token_accuracy": 0.8342386931180954,
|
| 129 |
+
"num_tokens": 158980.0,
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"entropy": 0.8305783897638321,
|
| 134 |
+
"epoch": 9.621519045426892e-05,
|
| 135 |
+
"grad_norm": 0.328125,
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
+
"loss": 0.8155685424804687,
|
| 138 |
+
"mean_token_accuracy": 0.8282770067453384,
|
| 139 |
+
"num_tokens": 172414.0,
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"entropy": 0.8582165241241455,
|
| 144 |
+
"epoch": 0.00010361635895075114,
|
| 145 |
+
"grad_norm": 0.322265625,
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
+
"loss": 0.8684965133666992,
|
| 148 |
+
"mean_token_accuracy": 0.8188153028488159,
|
| 149 |
+
"num_tokens": 186224.0,
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"entropy": 0.823002302646637,
|
| 154 |
+
"epoch": 0.00011101752744723338,
|
| 155 |
+
"grad_norm": 0.41796875,
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
+
"loss": 0.8199325561523437,
|
| 158 |
+
"mean_token_accuracy": 0.8285818427801133,
|
| 159 |
+
"num_tokens": 199564.0,
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"entropy": 0.7803006649017334,
|
| 164 |
+
"epoch": 0.0001184186959437156,
|
| 165 |
+
"grad_norm": 0.28125,
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
+
"loss": 0.8177242279052734,
|
| 168 |
+
"mean_token_accuracy": 0.8276909857988357,
|
| 169 |
+
"num_tokens": 212955.0,
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"entropy": 0.7576605170965195,
|
| 174 |
+
"epoch": 0.00012581986444019783,
|
| 175 |
+
"grad_norm": 0.298828125,
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
+
"loss": 0.7334442615509034,
|
| 178 |
+
"mean_token_accuracy": 0.8368929207324982,
|
| 179 |
+
"num_tokens": 225983.0,
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"entropy": 0.8388681739568711,
|
| 184 |
+
"epoch": 0.00013322103293668004,
|
| 185 |
+
"grad_norm": 4.15625,
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
+
"loss": 0.878928279876709,
|
| 188 |
+
"mean_token_accuracy": 0.8206132620573043,
|
| 189 |
+
"num_tokens": 240490.0,
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
+
"entropy": 0.8390863686800003,
|
| 194 |
+
"epoch": 0.00014062220143316227,
|
| 195 |
+
"grad_norm": 0.25,
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
+
"loss": 0.8454230308532715,
|
| 198 |
+
"mean_token_accuracy": 0.8245942384004593,
|
| 199 |
+
"num_tokens": 254696.0,
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"entropy": 0.8603733956813813,
|
| 204 |
+
"epoch": 0.00014802336992964448,
|
| 205 |
+
"grad_norm": 0.2734375,
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
+
"loss": 0.8759581565856933,
|
| 208 |
+
"mean_token_accuracy": 0.8165332227945328,
|
| 209 |
+
"num_tokens": 269719.0,
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"entropy": 0.76580231487751,
|
| 214 |
+
"epoch": 0.00015542453842612672,
|
| 215 |
+
"grad_norm": 0.240234375,
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
+
"loss": 0.7616221904754639,
|
| 218 |
+
"mean_token_accuracy": 0.8392421275377273,
|
| 219 |
+
"num_tokens": 282621.0,
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"entropy": 0.7803073287010193,
|
| 224 |
+
"epoch": 0.00016282570692260895,
|
| 225 |
+
"grad_norm": 0.341796875,
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
+
"loss": 0.7809097766876221,
|
| 228 |
+
"mean_token_accuracy": 0.8302495568990708,
|
| 229 |
+
"num_tokens": 295624.0,
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"entropy": 0.7702126175165176,
|
| 234 |
+
"epoch": 0.00017022687541909116,
|
| 235 |
+
"grad_norm": 0.251953125,
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
+
"loss": 0.7757031917572021,
|
| 238 |
+
"mean_token_accuracy": 0.8389965564012527,
|
| 239 |
+
"num_tokens": 308856.0,
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"entropy": 0.8611143410205842,
|
| 244 |
+
"epoch": 0.0001776280439155734,
|
| 245 |
+
"grad_norm": 0.337890625,
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
+
"loss": 0.8744688034057617,
|
| 248 |
+
"mean_token_accuracy": 0.8146604359149933,
|
| 249 |
+
"num_tokens": 322610.0,
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
+
"entropy": 0.8659275263547898,
|
| 254 |
+
"epoch": 0.0001850292124120556,
|
| 255 |
+
"grad_norm": 0.326171875,
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
+
"loss": 0.8652327537536622,
|
| 258 |
+
"mean_token_accuracy": 0.819416218996048,
|
| 259 |
+
"num_tokens": 336948.0,
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"entropy": 0.768859726190567,
|
| 264 |
+
"epoch": 0.00019243038090853784,
|
| 265 |
+
"grad_norm": 0.2890625,
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
+
"loss": 0.7651469707489014,
|
| 268 |
+
"mean_token_accuracy": 0.8339170336723327,
|
| 269 |
+
"num_tokens": 350252.0,
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"entropy": 0.8208303570747375,
|
| 274 |
+
"epoch": 0.00019983154940502007,
|
| 275 |
+
"grad_norm": 0.296875,
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
+
"loss": 0.8234204292297364,
|
| 278 |
+
"mean_token_accuracy": 0.8225490599870682,
|
| 279 |
+
"num_tokens": 364325.0,
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"entropy": 0.7798860669136047,
|
| 284 |
+
"epoch": 0.00020723271790150228,
|
| 285 |
+
"grad_norm": 0.3046875,
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
+
"loss": 0.7923468112945556,
|
| 288 |
+
"mean_token_accuracy": 0.831676983833313,
|
| 289 |
+
"num_tokens": 378088.0,
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"entropy": 0.7306642323732376,
|
| 294 |
+
"epoch": 0.00021463388639798452,
|
| 295 |
+
"grad_norm": 0.279296875,
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
+
"loss": 0.7504455089569092,
|
| 298 |
+
"mean_token_accuracy": 0.8410079121589661,
|
| 299 |
+
"num_tokens": 391023.0,
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"entropy": 0.8291689246892929,
|
| 304 |
+
"epoch": 0.00022203505489446675,
|
| 305 |
+
"grad_norm": 0.24609375,
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
+
"loss": 0.8151634216308594,
|
| 308 |
+
"mean_token_accuracy": 0.8278465926647186,
|
| 309 |
+
"num_tokens": 404816.0,
|
| 310 |
"step": 300
|
| 311 |
}
|
| 312 |
],
|
|
|
|
| 327 |
"attributes": {}
|
| 328 |
}
|
| 329 |
},
|
| 330 |
+
"total_flos": 2.9772936498315264e+16,
|
| 331 |
"train_batch_size": 8,
|
| 332 |
"trial_name": null,
|
| 333 |
"trial_params": null
|
checkpoint-400/adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
checkpoint-400/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68c2068c6a06bf1f5a8372f814dfda631696defd4498d00cb745365c4084a9ac
|
| 3 |
size 83946192
|
checkpoint-400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335818315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4a8c480eb6a45d018a29e9fc497907ce5f99ce120d183d6cce629c5abcfe3ba
|
| 3 |
size 335818315
|
checkpoint-400/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff51dafa0029f4a138f8ab74c1e295d16db5f4d42cfafa0fd3ace6ee42e94f3
|
| 3 |
size 14645
|
checkpoint-400/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,403 +10,403 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"entropy": 1.
|
| 14 |
-
"epoch":
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
-
"loss": 1.
|
| 18 |
-
"mean_token_accuracy": 0.
|
| 19 |
-
"num_tokens":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"entropy": 1.
|
| 24 |
-
"epoch":
|
| 25 |
-
"grad_norm": 0.
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
-
"loss": 1.
|
| 28 |
-
"mean_token_accuracy": 0.
|
| 29 |
-
"num_tokens":
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"entropy":
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
-
"loss":
|
| 38 |
-
"mean_token_accuracy": 0.
|
| 39 |
-
"num_tokens":
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"entropy":
|
| 44 |
-
"epoch":
|
| 45 |
-
"grad_norm": 0.
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
-
"loss":
|
| 48 |
-
"mean_token_accuracy": 0.
|
| 49 |
-
"num_tokens":
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"entropy":
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
-
"loss":
|
| 58 |
-
"mean_token_accuracy": 0.
|
| 59 |
-
"num_tokens":
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"entropy":
|
| 64 |
-
"epoch":
|
| 65 |
-
"grad_norm": 0.
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
-
"loss":
|
| 68 |
-
"mean_token_accuracy": 0.
|
| 69 |
-
"num_tokens":
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"entropy":
|
| 74 |
-
"epoch":
|
| 75 |
-
"grad_norm": 0.
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
-
"loss":
|
| 78 |
-
"mean_token_accuracy": 0.
|
| 79 |
-
"num_tokens":
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"entropy":
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
-
"loss":
|
| 88 |
-
"mean_token_accuracy": 0.
|
| 89 |
-
"num_tokens":
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"entropy":
|
| 94 |
-
"epoch":
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
-
"loss":
|
| 98 |
-
"mean_token_accuracy": 0.
|
| 99 |
-
"num_tokens":
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"entropy":
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
-
"loss":
|
| 108 |
-
"mean_token_accuracy": 0.
|
| 109 |
-
"num_tokens":
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"entropy":
|
| 114 |
-
"epoch":
|
| 115 |
-
"grad_norm": 0.
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
-
"loss":
|
| 118 |
-
"mean_token_accuracy": 0.
|
| 119 |
-
"num_tokens":
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"entropy":
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
-
"loss":
|
| 128 |
-
"mean_token_accuracy": 0.
|
| 129 |
-
"num_tokens":
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"entropy":
|
| 134 |
-
"epoch":
|
| 135 |
-
"grad_norm": 0.
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
-
"loss":
|
| 138 |
-
"mean_token_accuracy": 0.
|
| 139 |
-
"num_tokens":
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"entropy":
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"grad_norm": 0.
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
-
"loss":
|
| 148 |
-
"mean_token_accuracy": 0.
|
| 149 |
-
"num_tokens":
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"entropy":
|
| 154 |
-
"epoch": 0.
|
| 155 |
-
"grad_norm": 0.
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
-
"loss":
|
| 158 |
-
"mean_token_accuracy": 0.
|
| 159 |
-
"num_tokens":
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"entropy":
|
| 164 |
-
"epoch": 0.
|
| 165 |
-
"grad_norm": 0.
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
-
"loss":
|
| 168 |
-
"mean_token_accuracy": 0.
|
| 169 |
-
"num_tokens":
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"entropy":
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
-
"loss":
|
| 178 |
-
"mean_token_accuracy": 0.
|
| 179 |
-
"num_tokens":
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"entropy":
|
| 184 |
-
"epoch": 0.
|
| 185 |
-
"grad_norm":
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
-
"loss":
|
| 188 |
-
"mean_token_accuracy": 0.
|
| 189 |
-
"num_tokens":
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"entropy":
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
-
"loss":
|
| 198 |
-
"mean_token_accuracy": 0.
|
| 199 |
-
"num_tokens":
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"entropy":
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"grad_norm": 0.
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
-
"loss":
|
| 208 |
-
"mean_token_accuracy": 0.
|
| 209 |
-
"num_tokens":
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
-
"entropy":
|
| 214 |
-
"epoch": 0.
|
| 215 |
-
"grad_norm": 0.
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
-
"loss":
|
| 218 |
-
"mean_token_accuracy": 0.
|
| 219 |
-
"num_tokens":
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"entropy":
|
| 224 |
-
"epoch": 0.
|
| 225 |
-
"grad_norm": 0.
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
-
"loss":
|
| 228 |
-
"mean_token_accuracy": 0.
|
| 229 |
-
"num_tokens":
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"entropy":
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
-
"loss":
|
| 238 |
-
"mean_token_accuracy": 0.
|
| 239 |
-
"num_tokens":
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"entropy":
|
| 244 |
-
"epoch": 0.
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
-
"loss":
|
| 248 |
-
"mean_token_accuracy": 0.
|
| 249 |
-
"num_tokens":
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"entropy":
|
| 254 |
-
"epoch": 0.
|
| 255 |
-
"grad_norm": 0.
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
-
"loss":
|
| 258 |
-
"mean_token_accuracy": 0.
|
| 259 |
-
"num_tokens":
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"entropy":
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
-
"loss":
|
| 268 |
-
"mean_token_accuracy": 0.
|
| 269 |
-
"num_tokens":
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"entropy":
|
| 274 |
-
"epoch": 0.
|
| 275 |
-
"grad_norm": 0.
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
-
"loss":
|
| 278 |
-
"mean_token_accuracy": 0.
|
| 279 |
-
"num_tokens":
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"entropy":
|
| 284 |
-
"epoch": 0.
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
-
"loss":
|
| 288 |
-
"mean_token_accuracy": 0.
|
| 289 |
-
"num_tokens":
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"entropy":
|
| 294 |
-
"epoch": 0.
|
| 295 |
-
"grad_norm": 0.
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
-
"loss":
|
| 298 |
-
"mean_token_accuracy": 0.
|
| 299 |
-
"num_tokens":
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"entropy":
|
| 304 |
-
"epoch": 0.
|
| 305 |
-
"grad_norm": 0.
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
-
"loss":
|
| 308 |
-
"mean_token_accuracy": 0.
|
| 309 |
-
"num_tokens":
|
| 310 |
"step": 300
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"entropy":
|
| 314 |
-
"epoch": 0.
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
"learning_rate": 7.64e-05,
|
| 317 |
-
"loss":
|
| 318 |
-
"mean_token_accuracy": 0.
|
| 319 |
-
"num_tokens":
|
| 320 |
"step": 310
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"entropy":
|
| 324 |
-
"epoch": 0.
|
| 325 |
-
"grad_norm": 0.
|
| 326 |
"learning_rate": 7.24e-05,
|
| 327 |
-
"loss":
|
| 328 |
-
"mean_token_accuracy": 0.
|
| 329 |
-
"num_tokens":
|
| 330 |
"step": 320
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"entropy":
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
"learning_rate": 6.840000000000001e-05,
|
| 337 |
-
"loss":
|
| 338 |
-
"mean_token_accuracy": 0.
|
| 339 |
-
"num_tokens":
|
| 340 |
"step": 330
|
| 341 |
},
|
| 342 |
{
|
| 343 |
-
"entropy":
|
| 344 |
-
"epoch": 0.
|
| 345 |
-
"grad_norm": 0.
|
| 346 |
"learning_rate": 6.440000000000001e-05,
|
| 347 |
-
"loss":
|
| 348 |
-
"mean_token_accuracy": 0.
|
| 349 |
-
"num_tokens":
|
| 350 |
"step": 340
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"entropy":
|
| 354 |
-
"epoch": 0.
|
| 355 |
-
"grad_norm": 0.
|
| 356 |
"learning_rate": 6.04e-05,
|
| 357 |
-
"loss":
|
| 358 |
-
"mean_token_accuracy": 0.
|
| 359 |
-
"num_tokens":
|
| 360 |
"step": 350
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"entropy":
|
| 364 |
-
"epoch": 0.
|
| 365 |
-
"grad_norm": 0.
|
| 366 |
"learning_rate": 5.6399999999999995e-05,
|
| 367 |
-
"loss":
|
| 368 |
-
"mean_token_accuracy": 0.
|
| 369 |
-
"num_tokens":
|
| 370 |
"step": 360
|
| 371 |
},
|
| 372 |
{
|
| 373 |
-
"entropy":
|
| 374 |
-
"epoch": 0.
|
| 375 |
-
"grad_norm": 0.
|
| 376 |
"learning_rate": 5.2400000000000007e-05,
|
| 377 |
-
"loss":
|
| 378 |
-
"mean_token_accuracy": 0.
|
| 379 |
-
"num_tokens":
|
| 380 |
"step": 370
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"entropy":
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 4.8400000000000004e-05,
|
| 387 |
-
"loss":
|
| 388 |
-
"mean_token_accuracy": 0.
|
| 389 |
-
"num_tokens":
|
| 390 |
"step": 380
|
| 391 |
},
|
| 392 |
{
|
| 393 |
-
"entropy":
|
| 394 |
-
"epoch": 0.
|
| 395 |
-
"grad_norm": 0.
|
| 396 |
"learning_rate": 4.44e-05,
|
| 397 |
-
"loss":
|
| 398 |
-
"mean_token_accuracy": 0.
|
| 399 |
-
"num_tokens":
|
| 400 |
"step": 390
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"entropy":
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
"learning_rate": 4.0400000000000006e-05,
|
| 407 |
-
"loss":
|
| 408 |
-
"mean_token_accuracy": 0.
|
| 409 |
-
"num_tokens":
|
| 410 |
"step": 400
|
| 411 |
}
|
| 412 |
],
|
|
@@ -427,7 +427,7 @@
|
|
| 427 |
"attributes": {}
|
| 428 |
}
|
| 429 |
},
|
| 430 |
-
"total_flos":
|
| 431 |
"train_batch_size": 8,
|
| 432 |
"trial_name": null,
|
| 433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.00029604673985928896,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"entropy": 1.4767830133438111,
|
| 14 |
+
"epoch": 7.401168496482225e-06,
|
| 15 |
+
"grad_norm": 0.578125,
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
+
"loss": 1.6877475738525392,
|
| 18 |
+
"mean_token_accuracy": 0.7061349496245384,
|
| 19 |
+
"num_tokens": 14911.0,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"entropy": 1.0930627048015595,
|
| 24 |
+
"epoch": 1.480233699296445e-05,
|
| 25 |
+
"grad_norm": 0.458984375,
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
+
"loss": 1.0562871932983398,
|
| 28 |
+
"mean_token_accuracy": 0.8108290940523147,
|
| 29 |
+
"num_tokens": 28646.0,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"entropy": 0.8788679152727127,
|
| 34 |
+
"epoch": 2.2203505489446674e-05,
|
| 35 |
+
"grad_norm": 0.5859375,
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
+
"loss": 0.8974875450134278,
|
| 38 |
+
"mean_token_accuracy": 0.8296987593173981,
|
| 39 |
+
"num_tokens": 41474.0,
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"entropy": 0.8145956963300705,
|
| 44 |
+
"epoch": 2.96046739859289e-05,
|
| 45 |
+
"grad_norm": 0.39453125,
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
+
"loss": 0.8066701889038086,
|
| 48 |
+
"mean_token_accuracy": 0.8340015441179276,
|
| 49 |
+
"num_tokens": 54466.0,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"entropy": 0.7157480388879776,
|
| 54 |
+
"epoch": 3.700584248241112e-05,
|
| 55 |
+
"grad_norm": 0.326171875,
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
+
"loss": 0.7251500129699707,
|
| 58 |
+
"mean_token_accuracy": 0.8420351594686508,
|
| 59 |
+
"num_tokens": 66880.0,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"entropy": 0.7959431439638138,
|
| 64 |
+
"epoch": 4.440701097889335e-05,
|
| 65 |
+
"grad_norm": 0.326171875,
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
+
"loss": 0.8049167633056641,
|
| 68 |
+
"mean_token_accuracy": 0.8289562940597535,
|
| 69 |
+
"num_tokens": 80036.0,
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"entropy": 0.8342548221349716,
|
| 74 |
+
"epoch": 5.180817947537557e-05,
|
| 75 |
+
"grad_norm": 0.326171875,
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
+
"loss": 0.8336853981018066,
|
| 78 |
+
"mean_token_accuracy": 0.8279720038175583,
|
| 79 |
+
"num_tokens": 93357.0,
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"entropy": 0.7970967918634415,
|
| 84 |
+
"epoch": 5.92093479718578e-05,
|
| 85 |
+
"grad_norm": 0.73046875,
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
+
"loss": 0.7949181079864502,
|
| 88 |
+
"mean_token_accuracy": 0.828959608078003,
|
| 89 |
+
"num_tokens": 106951.0,
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"entropy": 0.7967441529035568,
|
| 94 |
+
"epoch": 6.661051646834002e-05,
|
| 95 |
+
"grad_norm": 0.34375,
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
+
"loss": 0.8285197257995606,
|
| 98 |
+
"mean_token_accuracy": 0.8272027671337128,
|
| 99 |
+
"num_tokens": 120269.0,
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"entropy": 0.7741447448730469,
|
| 104 |
+
"epoch": 7.401168496482224e-05,
|
| 105 |
+
"grad_norm": 0.271484375,
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
+
"loss": 0.7636381626129151,
|
| 108 |
+
"mean_token_accuracy": 0.8373189926147461,
|
| 109 |
+
"num_tokens": 133116.0,
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"entropy": 0.72959463596344,
|
| 114 |
+
"epoch": 8.141285346130448e-05,
|
| 115 |
+
"grad_norm": 0.421875,
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
+
"loss": 0.7404542446136475,
|
| 118 |
+
"mean_token_accuracy": 0.8400259047746659,
|
| 119 |
+
"num_tokens": 146103.0,
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"entropy": 0.777249938249588,
|
| 124 |
+
"epoch": 8.88140219577867e-05,
|
| 125 |
+
"grad_norm": 0.3984375,
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
+
"loss": 0.7868029117584229,
|
| 128 |
+
"mean_token_accuracy": 0.8342386931180954,
|
| 129 |
+
"num_tokens": 158980.0,
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"entropy": 0.8305783897638321,
|
| 134 |
+
"epoch": 9.621519045426892e-05,
|
| 135 |
+
"grad_norm": 0.328125,
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
+
"loss": 0.8155685424804687,
|
| 138 |
+
"mean_token_accuracy": 0.8282770067453384,
|
| 139 |
+
"num_tokens": 172414.0,
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"entropy": 0.8582165241241455,
|
| 144 |
+
"epoch": 0.00010361635895075114,
|
| 145 |
+
"grad_norm": 0.322265625,
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
+
"loss": 0.8684965133666992,
|
| 148 |
+
"mean_token_accuracy": 0.8188153028488159,
|
| 149 |
+
"num_tokens": 186224.0,
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"entropy": 0.823002302646637,
|
| 154 |
+
"epoch": 0.00011101752744723338,
|
| 155 |
+
"grad_norm": 0.41796875,
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
+
"loss": 0.8199325561523437,
|
| 158 |
+
"mean_token_accuracy": 0.8285818427801133,
|
| 159 |
+
"num_tokens": 199564.0,
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"entropy": 0.7803006649017334,
|
| 164 |
+
"epoch": 0.0001184186959437156,
|
| 165 |
+
"grad_norm": 0.28125,
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
+
"loss": 0.8177242279052734,
|
| 168 |
+
"mean_token_accuracy": 0.8276909857988357,
|
| 169 |
+
"num_tokens": 212955.0,
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"entropy": 0.7576605170965195,
|
| 174 |
+
"epoch": 0.00012581986444019783,
|
| 175 |
+
"grad_norm": 0.298828125,
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
+
"loss": 0.7334442615509034,
|
| 178 |
+
"mean_token_accuracy": 0.8368929207324982,
|
| 179 |
+
"num_tokens": 225983.0,
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"entropy": 0.8388681739568711,
|
| 184 |
+
"epoch": 0.00013322103293668004,
|
| 185 |
+
"grad_norm": 4.15625,
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
+
"loss": 0.878928279876709,
|
| 188 |
+
"mean_token_accuracy": 0.8206132620573043,
|
| 189 |
+
"num_tokens": 240490.0,
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
+
"entropy": 0.8390863686800003,
|
| 194 |
+
"epoch": 0.00014062220143316227,
|
| 195 |
+
"grad_norm": 0.25,
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
+
"loss": 0.8454230308532715,
|
| 198 |
+
"mean_token_accuracy": 0.8245942384004593,
|
| 199 |
+
"num_tokens": 254696.0,
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"entropy": 0.8603733956813813,
|
| 204 |
+
"epoch": 0.00014802336992964448,
|
| 205 |
+
"grad_norm": 0.2734375,
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
+
"loss": 0.8759581565856933,
|
| 208 |
+
"mean_token_accuracy": 0.8165332227945328,
|
| 209 |
+
"num_tokens": 269719.0,
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"entropy": 0.76580231487751,
|
| 214 |
+
"epoch": 0.00015542453842612672,
|
| 215 |
+
"grad_norm": 0.240234375,
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
+
"loss": 0.7616221904754639,
|
| 218 |
+
"mean_token_accuracy": 0.8392421275377273,
|
| 219 |
+
"num_tokens": 282621.0,
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"entropy": 0.7803073287010193,
|
| 224 |
+
"epoch": 0.00016282570692260895,
|
| 225 |
+
"grad_norm": 0.341796875,
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
+
"loss": 0.7809097766876221,
|
| 228 |
+
"mean_token_accuracy": 0.8302495568990708,
|
| 229 |
+
"num_tokens": 295624.0,
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"entropy": 0.7702126175165176,
|
| 234 |
+
"epoch": 0.00017022687541909116,
|
| 235 |
+
"grad_norm": 0.251953125,
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
+
"loss": 0.7757031917572021,
|
| 238 |
+
"mean_token_accuracy": 0.8389965564012527,
|
| 239 |
+
"num_tokens": 308856.0,
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"entropy": 0.8611143410205842,
|
| 244 |
+
"epoch": 0.0001776280439155734,
|
| 245 |
+
"grad_norm": 0.337890625,
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
+
"loss": 0.8744688034057617,
|
| 248 |
+
"mean_token_accuracy": 0.8146604359149933,
|
| 249 |
+
"num_tokens": 322610.0,
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
+
"entropy": 0.8659275263547898,
|
| 254 |
+
"epoch": 0.0001850292124120556,
|
| 255 |
+
"grad_norm": 0.326171875,
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
+
"loss": 0.8652327537536622,
|
| 258 |
+
"mean_token_accuracy": 0.819416218996048,
|
| 259 |
+
"num_tokens": 336948.0,
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"entropy": 0.768859726190567,
|
| 264 |
+
"epoch": 0.00019243038090853784,
|
| 265 |
+
"grad_norm": 0.2890625,
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
+
"loss": 0.7651469707489014,
|
| 268 |
+
"mean_token_accuracy": 0.8339170336723327,
|
| 269 |
+
"num_tokens": 350252.0,
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"entropy": 0.8208303570747375,
|
| 274 |
+
"epoch": 0.00019983154940502007,
|
| 275 |
+
"grad_norm": 0.296875,
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
+
"loss": 0.8234204292297364,
|
| 278 |
+
"mean_token_accuracy": 0.8225490599870682,
|
| 279 |
+
"num_tokens": 364325.0,
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"entropy": 0.7798860669136047,
|
| 284 |
+
"epoch": 0.00020723271790150228,
|
| 285 |
+
"grad_norm": 0.3046875,
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
+
"loss": 0.7923468112945556,
|
| 288 |
+
"mean_token_accuracy": 0.831676983833313,
|
| 289 |
+
"num_tokens": 378088.0,
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"entropy": 0.7306642323732376,
|
| 294 |
+
"epoch": 0.00021463388639798452,
|
| 295 |
+
"grad_norm": 0.279296875,
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
+
"loss": 0.7504455089569092,
|
| 298 |
+
"mean_token_accuracy": 0.8410079121589661,
|
| 299 |
+
"num_tokens": 391023.0,
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"entropy": 0.8291689246892929,
|
| 304 |
+
"epoch": 0.00022203505489446675,
|
| 305 |
+
"grad_norm": 0.24609375,
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
+
"loss": 0.8151634216308594,
|
| 308 |
+
"mean_token_accuracy": 0.8278465926647186,
|
| 309 |
+
"num_tokens": 404816.0,
|
| 310 |
"step": 300
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"entropy": 0.7772005677223206,
|
| 314 |
+
"epoch": 0.00022943622339094896,
|
| 315 |
+
"grad_norm": 0.326171875,
|
| 316 |
"learning_rate": 7.64e-05,
|
| 317 |
+
"loss": 0.7859255313873291,
|
| 318 |
+
"mean_token_accuracy": 0.8338077068328857,
|
| 319 |
+
"num_tokens": 418105.0,
|
| 320 |
"step": 310
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"entropy": 0.8288773983716965,
|
| 324 |
+
"epoch": 0.0002368373918874312,
|
| 325 |
+
"grad_norm": 0.28125,
|
| 326 |
"learning_rate": 7.24e-05,
|
| 327 |
+
"loss": 0.8528160095214844,
|
| 328 |
+
"mean_token_accuracy": 0.8213677883148194,
|
| 329 |
+
"num_tokens": 432042.0,
|
| 330 |
"step": 320
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"entropy": 0.7887327700853348,
|
| 334 |
+
"epoch": 0.0002442385603839134,
|
| 335 |
+
"grad_norm": 0.326171875,
|
| 336 |
"learning_rate": 6.840000000000001e-05,
|
| 337 |
+
"loss": 0.7650537014007568,
|
| 338 |
+
"mean_token_accuracy": 0.8351205557584762,
|
| 339 |
+
"num_tokens": 444796.0,
|
| 340 |
"step": 330
|
| 341 |
},
|
| 342 |
{
|
| 343 |
+
"entropy": 0.7681846857070923,
|
| 344 |
+
"epoch": 0.00025163972888039566,
|
| 345 |
+
"grad_norm": 0.287109375,
|
| 346 |
"learning_rate": 6.440000000000001e-05,
|
| 347 |
+
"loss": 0.7828513145446777,
|
| 348 |
+
"mean_token_accuracy": 0.8325754940509796,
|
| 349 |
+
"num_tokens": 457664.0,
|
| 350 |
"step": 340
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"entropy": 0.8200330525636673,
|
| 354 |
+
"epoch": 0.00025904089737687787,
|
| 355 |
+
"grad_norm": 0.26953125,
|
| 356 |
"learning_rate": 6.04e-05,
|
| 357 |
+
"loss": 0.8019542694091797,
|
| 358 |
+
"mean_token_accuracy": 0.8313791334629059,
|
| 359 |
+
"num_tokens": 470606.0,
|
| 360 |
"step": 350
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"entropy": 0.8059133917093277,
|
| 364 |
+
"epoch": 0.0002664420658733601,
|
| 365 |
+
"grad_norm": 0.259765625,
|
| 366 |
"learning_rate": 5.6399999999999995e-05,
|
| 367 |
+
"loss": 0.7930517673492432,
|
| 368 |
+
"mean_token_accuracy": 0.8300592184066773,
|
| 369 |
+
"num_tokens": 484904.0,
|
| 370 |
"step": 360
|
| 371 |
},
|
| 372 |
{
|
| 373 |
+
"entropy": 0.7620012789964676,
|
| 374 |
+
"epoch": 0.0002738432343698423,
|
| 375 |
+
"grad_norm": 0.306640625,
|
| 376 |
"learning_rate": 5.2400000000000007e-05,
|
| 377 |
+
"loss": 0.7779502868652344,
|
| 378 |
+
"mean_token_accuracy": 0.8312928855419159,
|
| 379 |
+
"num_tokens": 498302.0,
|
| 380 |
"step": 370
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"entropy": 0.7787803679704666,
|
| 384 |
+
"epoch": 0.00028124440286632455,
|
| 385 |
+
"grad_norm": 0.3125,
|
| 386 |
"learning_rate": 4.8400000000000004e-05,
|
| 387 |
+
"loss": 0.7784494400024414,
|
| 388 |
+
"mean_token_accuracy": 0.8316877603530883,
|
| 389 |
+
"num_tokens": 512369.0,
|
| 390 |
"step": 380
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"entropy": 0.7438325166702271,
|
| 394 |
+
"epoch": 0.00028864557136280676,
|
| 395 |
+
"grad_norm": 0.271484375,
|
| 396 |
"learning_rate": 4.44e-05,
|
| 397 |
+
"loss": 0.7538249015808105,
|
| 398 |
+
"mean_token_accuracy": 0.8402615815401078,
|
| 399 |
+
"num_tokens": 525385.0,
|
| 400 |
"step": 390
|
| 401 |
},
|
| 402 |
{
|
| 403 |
+
"entropy": 0.7514106065034867,
|
| 404 |
+
"epoch": 0.00029604673985928896,
|
| 405 |
+
"grad_norm": 0.263671875,
|
| 406 |
"learning_rate": 4.0400000000000006e-05,
|
| 407 |
+
"loss": 0.742708683013916,
|
| 408 |
+
"mean_token_accuracy": 0.8387834310531617,
|
| 409 |
+
"num_tokens": 538315.0,
|
| 410 |
"step": 400
|
| 411 |
}
|
| 412 |
],
|
|
|
|
| 427 |
"attributes": {}
|
| 428 |
}
|
| 429 |
},
|
| 430 |
+
"total_flos": 3.968843392293274e+16,
|
| 431 |
"train_batch_size": 8,
|
| 432 |
"trial_name": null,
|
| 433 |
"trial_params": null
|
checkpoint-500/adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"o_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
checkpoint-500/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c5f909945589d0c78975a1cb4af27dcba08206910975f240e0ceb21013a2e2
|
| 3 |
size 83946192
|
checkpoint-500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335818315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da5c5e2f7ef1148f93c79913486a56785ae2f2161404e9d5a0e62c949a21ac9c
|
| 3 |
size 335818315
|
checkpoint-500/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa888466977fe5448d0a9d30a2861628e2271f7a8c8cc85349b67e3f7cc9da6
|
| 3 |
size 14645
|
checkpoint-500/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,503 +10,503 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"entropy": 1.
|
| 14 |
-
"epoch":
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
-
"loss": 1.
|
| 18 |
-
"mean_token_accuracy": 0.
|
| 19 |
-
"num_tokens":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"entropy": 1.
|
| 24 |
-
"epoch":
|
| 25 |
-
"grad_norm": 0.
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
-
"loss": 1.
|
| 28 |
-
"mean_token_accuracy": 0.
|
| 29 |
-
"num_tokens":
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"entropy":
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
-
"loss":
|
| 38 |
-
"mean_token_accuracy": 0.
|
| 39 |
-
"num_tokens":
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"entropy":
|
| 44 |
-
"epoch":
|
| 45 |
-
"grad_norm": 0.
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
-
"loss":
|
| 48 |
-
"mean_token_accuracy": 0.
|
| 49 |
-
"num_tokens":
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"entropy":
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
-
"loss":
|
| 58 |
-
"mean_token_accuracy": 0.
|
| 59 |
-
"num_tokens":
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"entropy":
|
| 64 |
-
"epoch":
|
| 65 |
-
"grad_norm": 0.
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
-
"loss":
|
| 68 |
-
"mean_token_accuracy": 0.
|
| 69 |
-
"num_tokens":
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"entropy":
|
| 74 |
-
"epoch":
|
| 75 |
-
"grad_norm": 0.
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
-
"loss":
|
| 78 |
-
"mean_token_accuracy": 0.
|
| 79 |
-
"num_tokens":
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"entropy":
|
| 84 |
-
"epoch":
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
-
"loss":
|
| 88 |
-
"mean_token_accuracy": 0.
|
| 89 |
-
"num_tokens":
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"entropy":
|
| 94 |
-
"epoch":
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
-
"loss":
|
| 98 |
-
"mean_token_accuracy": 0.
|
| 99 |
-
"num_tokens":
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"entropy":
|
| 104 |
-
"epoch":
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
-
"loss":
|
| 108 |
-
"mean_token_accuracy": 0.
|
| 109 |
-
"num_tokens":
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"entropy":
|
| 114 |
-
"epoch":
|
| 115 |
-
"grad_norm": 0.
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
-
"loss":
|
| 118 |
-
"mean_token_accuracy": 0.
|
| 119 |
-
"num_tokens":
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"entropy":
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
-
"loss":
|
| 128 |
-
"mean_token_accuracy": 0.
|
| 129 |
-
"num_tokens":
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"entropy":
|
| 134 |
-
"epoch":
|
| 135 |
-
"grad_norm": 0.
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
-
"loss":
|
| 138 |
-
"mean_token_accuracy": 0.
|
| 139 |
-
"num_tokens":
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"entropy":
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"grad_norm": 0.
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
-
"loss":
|
| 148 |
-
"mean_token_accuracy": 0.
|
| 149 |
-
"num_tokens":
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"entropy":
|
| 154 |
-
"epoch": 0.
|
| 155 |
-
"grad_norm": 0.
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
-
"loss":
|
| 158 |
-
"mean_token_accuracy": 0.
|
| 159 |
-
"num_tokens":
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"entropy":
|
| 164 |
-
"epoch": 0.
|
| 165 |
-
"grad_norm": 0.
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
-
"loss":
|
| 168 |
-
"mean_token_accuracy": 0.
|
| 169 |
-
"num_tokens":
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"entropy":
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
-
"loss":
|
| 178 |
-
"mean_token_accuracy": 0.
|
| 179 |
-
"num_tokens":
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"entropy":
|
| 184 |
-
"epoch": 0.
|
| 185 |
-
"grad_norm":
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
-
"loss":
|
| 188 |
-
"mean_token_accuracy": 0.
|
| 189 |
-
"num_tokens":
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"entropy":
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
-
"loss":
|
| 198 |
-
"mean_token_accuracy": 0.
|
| 199 |
-
"num_tokens":
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"entropy":
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"grad_norm": 0.
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
-
"loss":
|
| 208 |
-
"mean_token_accuracy": 0.
|
| 209 |
-
"num_tokens":
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
-
"entropy":
|
| 214 |
-
"epoch": 0.
|
| 215 |
-
"grad_norm": 0.
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
-
"loss":
|
| 218 |
-
"mean_token_accuracy": 0.
|
| 219 |
-
"num_tokens":
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"entropy":
|
| 224 |
-
"epoch": 0.
|
| 225 |
-
"grad_norm": 0.
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
-
"loss":
|
| 228 |
-
"mean_token_accuracy": 0.
|
| 229 |
-
"num_tokens":
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"entropy":
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
-
"loss":
|
| 238 |
-
"mean_token_accuracy": 0.
|
| 239 |
-
"num_tokens":
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"entropy":
|
| 244 |
-
"epoch": 0.
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
-
"loss":
|
| 248 |
-
"mean_token_accuracy": 0.
|
| 249 |
-
"num_tokens":
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"entropy":
|
| 254 |
-
"epoch": 0.
|
| 255 |
-
"grad_norm": 0.
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
-
"loss":
|
| 258 |
-
"mean_token_accuracy": 0.
|
| 259 |
-
"num_tokens":
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"entropy":
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
-
"loss":
|
| 268 |
-
"mean_token_accuracy": 0.
|
| 269 |
-
"num_tokens":
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"entropy":
|
| 274 |
-
"epoch": 0.
|
| 275 |
-
"grad_norm": 0.
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
-
"loss":
|
| 278 |
-
"mean_token_accuracy": 0.
|
| 279 |
-
"num_tokens":
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"entropy":
|
| 284 |
-
"epoch": 0.
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
-
"loss":
|
| 288 |
-
"mean_token_accuracy": 0.
|
| 289 |
-
"num_tokens":
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"entropy":
|
| 294 |
-
"epoch": 0.
|
| 295 |
-
"grad_norm": 0.
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
-
"loss":
|
| 298 |
-
"mean_token_accuracy": 0.
|
| 299 |
-
"num_tokens":
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"entropy":
|
| 304 |
-
"epoch": 0.
|
| 305 |
-
"grad_norm": 0.
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
-
"loss":
|
| 308 |
-
"mean_token_accuracy": 0.
|
| 309 |
-
"num_tokens":
|
| 310 |
"step": 300
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"entropy":
|
| 314 |
-
"epoch": 0.
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
"learning_rate": 7.64e-05,
|
| 317 |
-
"loss":
|
| 318 |
-
"mean_token_accuracy": 0.
|
| 319 |
-
"num_tokens":
|
| 320 |
"step": 310
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"entropy":
|
| 324 |
-
"epoch": 0.
|
| 325 |
-
"grad_norm": 0.
|
| 326 |
"learning_rate": 7.24e-05,
|
| 327 |
-
"loss":
|
| 328 |
-
"mean_token_accuracy": 0.
|
| 329 |
-
"num_tokens":
|
| 330 |
"step": 320
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"entropy":
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
"learning_rate": 6.840000000000001e-05,
|
| 337 |
-
"loss":
|
| 338 |
-
"mean_token_accuracy": 0.
|
| 339 |
-
"num_tokens":
|
| 340 |
"step": 330
|
| 341 |
},
|
| 342 |
{
|
| 343 |
-
"entropy":
|
| 344 |
-
"epoch": 0.
|
| 345 |
-
"grad_norm": 0.
|
| 346 |
"learning_rate": 6.440000000000001e-05,
|
| 347 |
-
"loss":
|
| 348 |
-
"mean_token_accuracy": 0.
|
| 349 |
-
"num_tokens":
|
| 350 |
"step": 340
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"entropy":
|
| 354 |
-
"epoch": 0.
|
| 355 |
-
"grad_norm": 0.
|
| 356 |
"learning_rate": 6.04e-05,
|
| 357 |
-
"loss":
|
| 358 |
-
"mean_token_accuracy": 0.
|
| 359 |
-
"num_tokens":
|
| 360 |
"step": 350
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"entropy":
|
| 364 |
-
"epoch": 0.
|
| 365 |
-
"grad_norm": 0.
|
| 366 |
"learning_rate": 5.6399999999999995e-05,
|
| 367 |
-
"loss":
|
| 368 |
-
"mean_token_accuracy": 0.
|
| 369 |
-
"num_tokens":
|
| 370 |
"step": 360
|
| 371 |
},
|
| 372 |
{
|
| 373 |
-
"entropy":
|
| 374 |
-
"epoch": 0.
|
| 375 |
-
"grad_norm": 0.
|
| 376 |
"learning_rate": 5.2400000000000007e-05,
|
| 377 |
-
"loss":
|
| 378 |
-
"mean_token_accuracy": 0.
|
| 379 |
-
"num_tokens":
|
| 380 |
"step": 370
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"entropy":
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 4.8400000000000004e-05,
|
| 387 |
-
"loss":
|
| 388 |
-
"mean_token_accuracy": 0.
|
| 389 |
-
"num_tokens":
|
| 390 |
"step": 380
|
| 391 |
},
|
| 392 |
{
|
| 393 |
-
"entropy":
|
| 394 |
-
"epoch": 0.
|
| 395 |
-
"grad_norm": 0.
|
| 396 |
"learning_rate": 4.44e-05,
|
| 397 |
-
"loss":
|
| 398 |
-
"mean_token_accuracy": 0.
|
| 399 |
-
"num_tokens":
|
| 400 |
"step": 390
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"entropy":
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
"learning_rate": 4.0400000000000006e-05,
|
| 407 |
-
"loss":
|
| 408 |
-
"mean_token_accuracy": 0.
|
| 409 |
-
"num_tokens":
|
| 410 |
"step": 400
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"entropy":
|
| 414 |
-
"epoch": 0.
|
| 415 |
-
"grad_norm": 0.
|
| 416 |
"learning_rate": 3.6400000000000004e-05,
|
| 417 |
-
"loss":
|
| 418 |
-
"mean_token_accuracy": 0.
|
| 419 |
-
"num_tokens":
|
| 420 |
"step": 410
|
| 421 |
},
|
| 422 |
{
|
| 423 |
-
"entropy":
|
| 424 |
-
"epoch": 0.
|
| 425 |
-
"grad_norm": 0.
|
| 426 |
"learning_rate": 3.24e-05,
|
| 427 |
-
"loss":
|
| 428 |
-
"mean_token_accuracy": 0.
|
| 429 |
-
"num_tokens":
|
| 430 |
"step": 420
|
| 431 |
},
|
| 432 |
{
|
| 433 |
-
"entropy":
|
| 434 |
-
"epoch": 0.
|
| 435 |
-
"grad_norm": 0.
|
| 436 |
"learning_rate": 2.84e-05,
|
| 437 |
-
"loss":
|
| 438 |
-
"mean_token_accuracy": 0.
|
| 439 |
-
"num_tokens":
|
| 440 |
"step": 430
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"entropy":
|
| 444 |
-
"epoch": 0.
|
| 445 |
-
"grad_norm": 0.
|
| 446 |
"learning_rate": 2.44e-05,
|
| 447 |
-
"loss":
|
| 448 |
-
"mean_token_accuracy": 0.
|
| 449 |
-
"num_tokens":
|
| 450 |
"step": 440
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"entropy":
|
| 454 |
-
"epoch": 0.
|
| 455 |
-
"grad_norm": 0.
|
| 456 |
"learning_rate": 2.04e-05,
|
| 457 |
-
"loss":
|
| 458 |
-
"mean_token_accuracy": 0.
|
| 459 |
-
"num_tokens":
|
| 460 |
"step": 450
|
| 461 |
},
|
| 462 |
{
|
| 463 |
-
"entropy":
|
| 464 |
-
"epoch": 0.
|
| 465 |
-
"grad_norm": 0.
|
| 466 |
"learning_rate": 1.6400000000000002e-05,
|
| 467 |
-
"loss":
|
| 468 |
-
"mean_token_accuracy": 0.
|
| 469 |
-
"num_tokens":
|
| 470 |
"step": 460
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"entropy":
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"grad_norm": 0.
|
| 476 |
"learning_rate": 1.24e-05,
|
| 477 |
-
"loss":
|
| 478 |
-
"mean_token_accuracy": 0.
|
| 479 |
-
"num_tokens":
|
| 480 |
"step": 470
|
| 481 |
},
|
| 482 |
{
|
| 483 |
-
"entropy":
|
| 484 |
-
"epoch": 0.
|
| 485 |
-
"grad_norm": 0.
|
| 486 |
"learning_rate": 8.400000000000001e-06,
|
| 487 |
-
"loss":
|
| 488 |
-
"mean_token_accuracy": 0.
|
| 489 |
-
"num_tokens":
|
| 490 |
"step": 480
|
| 491 |
},
|
| 492 |
{
|
| 493 |
-
"entropy":
|
| 494 |
-
"epoch": 0.
|
| 495 |
-
"grad_norm": 0.
|
| 496 |
"learning_rate": 4.4e-06,
|
| 497 |
-
"loss":
|
| 498 |
-
"mean_token_accuracy": 0.
|
| 499 |
-
"num_tokens":
|
| 500 |
"step": 490
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"entropy":
|
| 504 |
-
"epoch": 0.
|
| 505 |
-
"grad_norm": 0.
|
| 506 |
"learning_rate": 4.0000000000000003e-07,
|
| 507 |
-
"loss":
|
| 508 |
-
"mean_token_accuracy": 0.
|
| 509 |
-
"num_tokens":
|
| 510 |
"step": 500
|
| 511 |
}
|
| 512 |
],
|
|
@@ -527,7 +527,7 @@
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
-
"total_flos":
|
| 531 |
"train_batch_size": 8,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0003700584248241112,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"entropy": 1.4767830133438111,
|
| 14 |
+
"epoch": 7.401168496482225e-06,
|
| 15 |
+
"grad_norm": 0.578125,
|
| 16 |
"learning_rate": 0.0001964,
|
| 17 |
+
"loss": 1.6877475738525392,
|
| 18 |
+
"mean_token_accuracy": 0.7061349496245384,
|
| 19 |
+
"num_tokens": 14911.0,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"entropy": 1.0930627048015595,
|
| 24 |
+
"epoch": 1.480233699296445e-05,
|
| 25 |
+
"grad_norm": 0.458984375,
|
| 26 |
"learning_rate": 0.00019240000000000001,
|
| 27 |
+
"loss": 1.0562871932983398,
|
| 28 |
+
"mean_token_accuracy": 0.8108290940523147,
|
| 29 |
+
"num_tokens": 28646.0,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"entropy": 0.8788679152727127,
|
| 34 |
+
"epoch": 2.2203505489446674e-05,
|
| 35 |
+
"grad_norm": 0.5859375,
|
| 36 |
"learning_rate": 0.0001884,
|
| 37 |
+
"loss": 0.8974875450134278,
|
| 38 |
+
"mean_token_accuracy": 0.8296987593173981,
|
| 39 |
+
"num_tokens": 41474.0,
|
| 40 |
"step": 30
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"entropy": 0.8145956963300705,
|
| 44 |
+
"epoch": 2.96046739859289e-05,
|
| 45 |
+
"grad_norm": 0.39453125,
|
| 46 |
"learning_rate": 0.0001844,
|
| 47 |
+
"loss": 0.8066701889038086,
|
| 48 |
+
"mean_token_accuracy": 0.8340015441179276,
|
| 49 |
+
"num_tokens": 54466.0,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"entropy": 0.7157480388879776,
|
| 54 |
+
"epoch": 3.700584248241112e-05,
|
| 55 |
+
"grad_norm": 0.326171875,
|
| 56 |
"learning_rate": 0.00018040000000000002,
|
| 57 |
+
"loss": 0.7251500129699707,
|
| 58 |
+
"mean_token_accuracy": 0.8420351594686508,
|
| 59 |
+
"num_tokens": 66880.0,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"entropy": 0.7959431439638138,
|
| 64 |
+
"epoch": 4.440701097889335e-05,
|
| 65 |
+
"grad_norm": 0.326171875,
|
| 66 |
"learning_rate": 0.0001764,
|
| 67 |
+
"loss": 0.8049167633056641,
|
| 68 |
+
"mean_token_accuracy": 0.8289562940597535,
|
| 69 |
+
"num_tokens": 80036.0,
|
| 70 |
"step": 60
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"entropy": 0.8342548221349716,
|
| 74 |
+
"epoch": 5.180817947537557e-05,
|
| 75 |
+
"grad_norm": 0.326171875,
|
| 76 |
"learning_rate": 0.00017240000000000002,
|
| 77 |
+
"loss": 0.8336853981018066,
|
| 78 |
+
"mean_token_accuracy": 0.8279720038175583,
|
| 79 |
+
"num_tokens": 93357.0,
|
| 80 |
"step": 70
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"entropy": 0.7970967918634415,
|
| 84 |
+
"epoch": 5.92093479718578e-05,
|
| 85 |
+
"grad_norm": 0.73046875,
|
| 86 |
"learning_rate": 0.0001684,
|
| 87 |
+
"loss": 0.7949181079864502,
|
| 88 |
+
"mean_token_accuracy": 0.828959608078003,
|
| 89 |
+
"num_tokens": 106951.0,
|
| 90 |
"step": 80
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"entropy": 0.7967441529035568,
|
| 94 |
+
"epoch": 6.661051646834002e-05,
|
| 95 |
+
"grad_norm": 0.34375,
|
| 96 |
"learning_rate": 0.0001644,
|
| 97 |
+
"loss": 0.8285197257995606,
|
| 98 |
+
"mean_token_accuracy": 0.8272027671337128,
|
| 99 |
+
"num_tokens": 120269.0,
|
| 100 |
"step": 90
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"entropy": 0.7741447448730469,
|
| 104 |
+
"epoch": 7.401168496482224e-05,
|
| 105 |
+
"grad_norm": 0.271484375,
|
| 106 |
"learning_rate": 0.00016040000000000002,
|
| 107 |
+
"loss": 0.7636381626129151,
|
| 108 |
+
"mean_token_accuracy": 0.8373189926147461,
|
| 109 |
+
"num_tokens": 133116.0,
|
| 110 |
"step": 100
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"entropy": 0.72959463596344,
|
| 114 |
+
"epoch": 8.141285346130448e-05,
|
| 115 |
+
"grad_norm": 0.421875,
|
| 116 |
"learning_rate": 0.0001564,
|
| 117 |
+
"loss": 0.7404542446136475,
|
| 118 |
+
"mean_token_accuracy": 0.8400259047746659,
|
| 119 |
+
"num_tokens": 146103.0,
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"entropy": 0.777249938249588,
|
| 124 |
+
"epoch": 8.88140219577867e-05,
|
| 125 |
+
"grad_norm": 0.3984375,
|
| 126 |
"learning_rate": 0.00015240000000000002,
|
| 127 |
+
"loss": 0.7868029117584229,
|
| 128 |
+
"mean_token_accuracy": 0.8342386931180954,
|
| 129 |
+
"num_tokens": 158980.0,
|
| 130 |
"step": 120
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"entropy": 0.8305783897638321,
|
| 134 |
+
"epoch": 9.621519045426892e-05,
|
| 135 |
+
"grad_norm": 0.328125,
|
| 136 |
"learning_rate": 0.0001484,
|
| 137 |
+
"loss": 0.8155685424804687,
|
| 138 |
+
"mean_token_accuracy": 0.8282770067453384,
|
| 139 |
+
"num_tokens": 172414.0,
|
| 140 |
"step": 130
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"entropy": 0.8582165241241455,
|
| 144 |
+
"epoch": 0.00010361635895075114,
|
| 145 |
+
"grad_norm": 0.322265625,
|
| 146 |
"learning_rate": 0.0001444,
|
| 147 |
+
"loss": 0.8684965133666992,
|
| 148 |
+
"mean_token_accuracy": 0.8188153028488159,
|
| 149 |
+
"num_tokens": 186224.0,
|
| 150 |
"step": 140
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"entropy": 0.823002302646637,
|
| 154 |
+
"epoch": 0.00011101752744723338,
|
| 155 |
+
"grad_norm": 0.41796875,
|
| 156 |
"learning_rate": 0.0001404,
|
| 157 |
+
"loss": 0.8199325561523437,
|
| 158 |
+
"mean_token_accuracy": 0.8285818427801133,
|
| 159 |
+
"num_tokens": 199564.0,
|
| 160 |
"step": 150
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"entropy": 0.7803006649017334,
|
| 164 |
+
"epoch": 0.0001184186959437156,
|
| 165 |
+
"grad_norm": 0.28125,
|
| 166 |
"learning_rate": 0.0001364,
|
| 167 |
+
"loss": 0.8177242279052734,
|
| 168 |
+
"mean_token_accuracy": 0.8276909857988357,
|
| 169 |
+
"num_tokens": 212955.0,
|
| 170 |
"step": 160
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"entropy": 0.7576605170965195,
|
| 174 |
+
"epoch": 0.00012581986444019783,
|
| 175 |
+
"grad_norm": 0.298828125,
|
| 176 |
"learning_rate": 0.00013240000000000002,
|
| 177 |
+
"loss": 0.7334442615509034,
|
| 178 |
+
"mean_token_accuracy": 0.8368929207324982,
|
| 179 |
+
"num_tokens": 225983.0,
|
| 180 |
"step": 170
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"entropy": 0.8388681739568711,
|
| 184 |
+
"epoch": 0.00013322103293668004,
|
| 185 |
+
"grad_norm": 4.15625,
|
| 186 |
"learning_rate": 0.0001284,
|
| 187 |
+
"loss": 0.878928279876709,
|
| 188 |
+
"mean_token_accuracy": 0.8206132620573043,
|
| 189 |
+
"num_tokens": 240490.0,
|
| 190 |
"step": 180
|
| 191 |
},
|
| 192 |
{
|
| 193 |
+
"entropy": 0.8390863686800003,
|
| 194 |
+
"epoch": 0.00014062220143316227,
|
| 195 |
+
"grad_norm": 0.25,
|
| 196 |
"learning_rate": 0.00012440000000000002,
|
| 197 |
+
"loss": 0.8454230308532715,
|
| 198 |
+
"mean_token_accuracy": 0.8245942384004593,
|
| 199 |
+
"num_tokens": 254696.0,
|
| 200 |
"step": 190
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"entropy": 0.8603733956813813,
|
| 204 |
+
"epoch": 0.00014802336992964448,
|
| 205 |
+
"grad_norm": 0.2734375,
|
| 206 |
"learning_rate": 0.0001204,
|
| 207 |
+
"loss": 0.8759581565856933,
|
| 208 |
+
"mean_token_accuracy": 0.8165332227945328,
|
| 209 |
+
"num_tokens": 269719.0,
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"entropy": 0.76580231487751,
|
| 214 |
+
"epoch": 0.00015542453842612672,
|
| 215 |
+
"grad_norm": 0.240234375,
|
| 216 |
"learning_rate": 0.0001164,
|
| 217 |
+
"loss": 0.7616221904754639,
|
| 218 |
+
"mean_token_accuracy": 0.8392421275377273,
|
| 219 |
+
"num_tokens": 282621.0,
|
| 220 |
"step": 210
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"entropy": 0.7803073287010193,
|
| 224 |
+
"epoch": 0.00016282570692260895,
|
| 225 |
+
"grad_norm": 0.341796875,
|
| 226 |
"learning_rate": 0.00011240000000000002,
|
| 227 |
+
"loss": 0.7809097766876221,
|
| 228 |
+
"mean_token_accuracy": 0.8302495568990708,
|
| 229 |
+
"num_tokens": 295624.0,
|
| 230 |
"step": 220
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"entropy": 0.7702126175165176,
|
| 234 |
+
"epoch": 0.00017022687541909116,
|
| 235 |
+
"grad_norm": 0.251953125,
|
| 236 |
"learning_rate": 0.00010840000000000002,
|
| 237 |
+
"loss": 0.7757031917572021,
|
| 238 |
+
"mean_token_accuracy": 0.8389965564012527,
|
| 239 |
+
"num_tokens": 308856.0,
|
| 240 |
"step": 230
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"entropy": 0.8611143410205842,
|
| 244 |
+
"epoch": 0.0001776280439155734,
|
| 245 |
+
"grad_norm": 0.337890625,
|
| 246 |
"learning_rate": 0.0001044,
|
| 247 |
+
"loss": 0.8744688034057617,
|
| 248 |
+
"mean_token_accuracy": 0.8146604359149933,
|
| 249 |
+
"num_tokens": 322610.0,
|
| 250 |
"step": 240
|
| 251 |
},
|
| 252 |
{
|
| 253 |
+
"entropy": 0.8659275263547898,
|
| 254 |
+
"epoch": 0.0001850292124120556,
|
| 255 |
+
"grad_norm": 0.326171875,
|
| 256 |
"learning_rate": 0.0001004,
|
| 257 |
+
"loss": 0.8652327537536622,
|
| 258 |
+
"mean_token_accuracy": 0.819416218996048,
|
| 259 |
+
"num_tokens": 336948.0,
|
| 260 |
"step": 250
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"entropy": 0.768859726190567,
|
| 264 |
+
"epoch": 0.00019243038090853784,
|
| 265 |
+
"grad_norm": 0.2890625,
|
| 266 |
"learning_rate": 9.64e-05,
|
| 267 |
+
"loss": 0.7651469707489014,
|
| 268 |
+
"mean_token_accuracy": 0.8339170336723327,
|
| 269 |
+
"num_tokens": 350252.0,
|
| 270 |
"step": 260
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"entropy": 0.8208303570747375,
|
| 274 |
+
"epoch": 0.00019983154940502007,
|
| 275 |
+
"grad_norm": 0.296875,
|
| 276 |
"learning_rate": 9.240000000000001e-05,
|
| 277 |
+
"loss": 0.8234204292297364,
|
| 278 |
+
"mean_token_accuracy": 0.8225490599870682,
|
| 279 |
+
"num_tokens": 364325.0,
|
| 280 |
"step": 270
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"entropy": 0.7798860669136047,
|
| 284 |
+
"epoch": 0.00020723271790150228,
|
| 285 |
+
"grad_norm": 0.3046875,
|
| 286 |
"learning_rate": 8.840000000000001e-05,
|
| 287 |
+
"loss": 0.7923468112945556,
|
| 288 |
+
"mean_token_accuracy": 0.831676983833313,
|
| 289 |
+
"num_tokens": 378088.0,
|
| 290 |
"step": 280
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"entropy": 0.7306642323732376,
|
| 294 |
+
"epoch": 0.00021463388639798452,
|
| 295 |
+
"grad_norm": 0.279296875,
|
| 296 |
"learning_rate": 8.44e-05,
|
| 297 |
+
"loss": 0.7504455089569092,
|
| 298 |
+
"mean_token_accuracy": 0.8410079121589661,
|
| 299 |
+
"num_tokens": 391023.0,
|
| 300 |
"step": 290
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"entropy": 0.8291689246892929,
|
| 304 |
+
"epoch": 0.00022203505489446675,
|
| 305 |
+
"grad_norm": 0.24609375,
|
| 306 |
"learning_rate": 8.04e-05,
|
| 307 |
+
"loss": 0.8151634216308594,
|
| 308 |
+
"mean_token_accuracy": 0.8278465926647186,
|
| 309 |
+
"num_tokens": 404816.0,
|
| 310 |
"step": 300
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"entropy": 0.7772005677223206,
|
| 314 |
+
"epoch": 0.00022943622339094896,
|
| 315 |
+
"grad_norm": 0.326171875,
|
| 316 |
"learning_rate": 7.64e-05,
|
| 317 |
+
"loss": 0.7859255313873291,
|
| 318 |
+
"mean_token_accuracy": 0.8338077068328857,
|
| 319 |
+
"num_tokens": 418105.0,
|
| 320 |
"step": 310
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"entropy": 0.8288773983716965,
|
| 324 |
+
"epoch": 0.0002368373918874312,
|
| 325 |
+
"grad_norm": 0.28125,
|
| 326 |
"learning_rate": 7.24e-05,
|
| 327 |
+
"loss": 0.8528160095214844,
|
| 328 |
+
"mean_token_accuracy": 0.8213677883148194,
|
| 329 |
+
"num_tokens": 432042.0,
|
| 330 |
"step": 320
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"entropy": 0.7887327700853348,
|
| 334 |
+
"epoch": 0.0002442385603839134,
|
| 335 |
+
"grad_norm": 0.326171875,
|
| 336 |
"learning_rate": 6.840000000000001e-05,
|
| 337 |
+
"loss": 0.7650537014007568,
|
| 338 |
+
"mean_token_accuracy": 0.8351205557584762,
|
| 339 |
+
"num_tokens": 444796.0,
|
| 340 |
"step": 330
|
| 341 |
},
|
| 342 |
{
|
| 343 |
+
"entropy": 0.7681846857070923,
|
| 344 |
+
"epoch": 0.00025163972888039566,
|
| 345 |
+
"grad_norm": 0.287109375,
|
| 346 |
"learning_rate": 6.440000000000001e-05,
|
| 347 |
+
"loss": 0.7828513145446777,
|
| 348 |
+
"mean_token_accuracy": 0.8325754940509796,
|
| 349 |
+
"num_tokens": 457664.0,
|
| 350 |
"step": 340
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"entropy": 0.8200330525636673,
|
| 354 |
+
"epoch": 0.00025904089737687787,
|
| 355 |
+
"grad_norm": 0.26953125,
|
| 356 |
"learning_rate": 6.04e-05,
|
| 357 |
+
"loss": 0.8019542694091797,
|
| 358 |
+
"mean_token_accuracy": 0.8313791334629059,
|
| 359 |
+
"num_tokens": 470606.0,
|
| 360 |
"step": 350
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"entropy": 0.8059133917093277,
|
| 364 |
+
"epoch": 0.0002664420658733601,
|
| 365 |
+
"grad_norm": 0.259765625,
|
| 366 |
"learning_rate": 5.6399999999999995e-05,
|
| 367 |
+
"loss": 0.7930517673492432,
|
| 368 |
+
"mean_token_accuracy": 0.8300592184066773,
|
| 369 |
+
"num_tokens": 484904.0,
|
| 370 |
"step": 360
|
| 371 |
},
|
| 372 |
{
|
| 373 |
+
"entropy": 0.7620012789964676,
|
| 374 |
+
"epoch": 0.0002738432343698423,
|
| 375 |
+
"grad_norm": 0.306640625,
|
| 376 |
"learning_rate": 5.2400000000000007e-05,
|
| 377 |
+
"loss": 0.7779502868652344,
|
| 378 |
+
"mean_token_accuracy": 0.8312928855419159,
|
| 379 |
+
"num_tokens": 498302.0,
|
| 380 |
"step": 370
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"entropy": 0.7787803679704666,
|
| 384 |
+
"epoch": 0.00028124440286632455,
|
| 385 |
+
"grad_norm": 0.3125,
|
| 386 |
"learning_rate": 4.8400000000000004e-05,
|
| 387 |
+
"loss": 0.7784494400024414,
|
| 388 |
+
"mean_token_accuracy": 0.8316877603530883,
|
| 389 |
+
"num_tokens": 512369.0,
|
| 390 |
"step": 380
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"entropy": 0.7438325166702271,
|
| 394 |
+
"epoch": 0.00028864557136280676,
|
| 395 |
+
"grad_norm": 0.271484375,
|
| 396 |
"learning_rate": 4.44e-05,
|
| 397 |
+
"loss": 0.7538249015808105,
|
| 398 |
+
"mean_token_accuracy": 0.8402615815401078,
|
| 399 |
+
"num_tokens": 525385.0,
|
| 400 |
"step": 390
|
| 401 |
},
|
| 402 |
{
|
| 403 |
+
"entropy": 0.7514106065034867,
|
| 404 |
+
"epoch": 0.00029604673985928896,
|
| 405 |
+
"grad_norm": 0.263671875,
|
| 406 |
"learning_rate": 4.0400000000000006e-05,
|
| 407 |
+
"loss": 0.742708683013916,
|
| 408 |
+
"mean_token_accuracy": 0.8387834310531617,
|
| 409 |
+
"num_tokens": 538315.0,
|
| 410 |
"step": 400
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"entropy": 0.7242682158946991,
|
| 414 |
+
"epoch": 0.0003034479083557712,
|
| 415 |
+
"grad_norm": 0.36328125,
|
| 416 |
"learning_rate": 3.6400000000000004e-05,
|
| 417 |
+
"loss": 0.7231860160827637,
|
| 418 |
+
"mean_token_accuracy": 0.8462171643972397,
|
| 419 |
+
"num_tokens": 550874.0,
|
| 420 |
"step": 410
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"entropy": 0.7665889590978623,
|
| 424 |
+
"epoch": 0.00031084907685225343,
|
| 425 |
+
"grad_norm": 0.298828125,
|
| 426 |
"learning_rate": 3.24e-05,
|
| 427 |
+
"loss": 0.7693154811859131,
|
| 428 |
+
"mean_token_accuracy": 0.8359919935464859,
|
| 429 |
+
"num_tokens": 564118.0,
|
| 430 |
"step": 420
|
| 431 |
},
|
| 432 |
{
|
| 433 |
+
"entropy": 0.7493055462837219,
|
| 434 |
+
"epoch": 0.00031825024534873564,
|
| 435 |
+
"grad_norm": 0.30859375,
|
| 436 |
"learning_rate": 2.84e-05,
|
| 437 |
+
"loss": 0.7551113128662109,
|
| 438 |
+
"mean_token_accuracy": 0.8372300088405609,
|
| 439 |
+
"num_tokens": 576999.0,
|
| 440 |
"step": 430
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"entropy": 0.7846053004264831,
|
| 444 |
+
"epoch": 0.0003256514138452179,
|
| 445 |
+
"grad_norm": 0.26953125,
|
| 446 |
"learning_rate": 2.44e-05,
|
| 447 |
+
"loss": 0.7938904762268066,
|
| 448 |
+
"mean_token_accuracy": 0.8271657317876816,
|
| 449 |
+
"num_tokens": 590845.0,
|
| 450 |
"step": 440
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"entropy": 0.7567790508270263,
|
| 454 |
+
"epoch": 0.0003330525823417001,
|
| 455 |
+
"grad_norm": 0.27734375,
|
| 456 |
"learning_rate": 2.04e-05,
|
| 457 |
+
"loss": 0.7597766876220703,
|
| 458 |
+
"mean_token_accuracy": 0.8390242576599121,
|
| 459 |
+
"num_tokens": 603943.0,
|
| 460 |
"step": 450
|
| 461 |
},
|
| 462 |
{
|
| 463 |
+
"entropy": 0.7776343286037445,
|
| 464 |
+
"epoch": 0.0003404537508381823,
|
| 465 |
+
"grad_norm": 0.296875,
|
| 466 |
"learning_rate": 1.6400000000000002e-05,
|
| 467 |
+
"loss": 0.7805155277252197,
|
| 468 |
+
"mean_token_accuracy": 0.8314157396554946,
|
| 469 |
+
"num_tokens": 617297.0,
|
| 470 |
"step": 460
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"entropy": 0.7654042065143585,
|
| 474 |
+
"epoch": 0.0003478549193346646,
|
| 475 |
+
"grad_norm": 0.294921875,
|
| 476 |
"learning_rate": 1.24e-05,
|
| 477 |
+
"loss": 0.7467947483062745,
|
| 478 |
+
"mean_token_accuracy": 0.836009356379509,
|
| 479 |
+
"num_tokens": 630337.0,
|
| 480 |
"step": 470
|
| 481 |
},
|
| 482 |
{
|
| 483 |
+
"entropy": 0.7470057517290115,
|
| 484 |
+
"epoch": 0.0003552560878311468,
|
| 485 |
+
"grad_norm": 0.283203125,
|
| 486 |
"learning_rate": 8.400000000000001e-06,
|
| 487 |
+
"loss": 0.7188091278076172,
|
| 488 |
+
"mean_token_accuracy": 0.8408551633358001,
|
| 489 |
+
"num_tokens": 643059.0,
|
| 490 |
"step": 480
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"entropy": 0.7312727242708206,
|
| 494 |
+
"epoch": 0.000362657256327629,
|
| 495 |
+
"grad_norm": 0.23828125,
|
| 496 |
"learning_rate": 4.4e-06,
|
| 497 |
+
"loss": 0.7032594203948974,
|
| 498 |
+
"mean_token_accuracy": 0.844664552807808,
|
| 499 |
+
"num_tokens": 655763.0,
|
| 500 |
"step": 490
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"entropy": 0.8029953300952911,
|
| 504 |
+
"epoch": 0.0003700584248241112,
|
| 505 |
+
"grad_norm": 0.306640625,
|
| 506 |
"learning_rate": 4.0000000000000003e-07,
|
| 507 |
+
"loss": 0.786741065979004,
|
| 508 |
+
"mean_token_accuracy": 0.8345526486635209,
|
| 509 |
+
"num_tokens": 669554.0,
|
| 510 |
"step": 500
|
| 511 |
}
|
| 512 |
],
|
|
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
+
"total_flos": 4.872149119972147e+16,
|
| 531 |
"train_batch_size": 8,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|