初始化项目，由ModelHub XC社区提供模型
Model: aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
74
README.md
Normal file
74
README.md
Normal file
@@ -0,0 +1,74 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||
tags:
|
||||
- triton
|
||||
- kernelbook
|
||||
- code-generation
|
||||
- sft
|
||||
- trl
|
||||
- text-generation
|
||||
datasets:
|
||||
- custom
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Qwen2.5-Coder-7B KernelBook SFT (equal tokens)
|
||||
|
||||
**Supervised Fine-Tuning (SFT)** checkpoint of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), post-trained on the **KernelBook** Triton kernel dataset.
|
||||
|
||||
This repo is the **equal-exposure** SFT checkpoint (`checkpoint-350`, ~1.06 epochs) selected to match SDFT's one-epoch training for fair comparison.
|
||||
|
||||
## Method
|
||||
|
||||
This model was trained with **SFT** using TRL's `SFTTrainer`: standard next-token prediction on chat-formatted prompt → Triton completion pairs, with completion-only loss (prompt tokens masked). Training used DeepSpeed ZeRO-3 and bf16 on Modal.
|
||||
|
||||
## Dataset
|
||||
|
||||
- **KernelBook** — PyTorch module prompts paired with reference Triton kernels
|
||||
- Deduplicated, filtered to completions ≤4096 tokens, repo-stratified 80/10/10 split
|
||||
- Stopped at **checkpoint-350** (~1.06 epochs) for parity with the SDFT run
|
||||
|
||||
## Intended use
|
||||
|
||||
Generate Triton GPU kernels from PyTorch-style module descriptions. Best for KernelBook-style conversion prompts; not evaluated as a general-purpose chat or reasoning model.
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Convert the following PyTorch code to an equivalent Triton kernel...",
|
||||
}
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(**inputs, max_new_tokens=1200, do_sample=False)
|
||||
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1] :], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Training summary
|
||||
|
||||
| Setting | Value |
|
||||
|---------|-------|
|
||||
| Base model | Qwen2.5-Coder-7B-Instruct |
|
||||
| Method | SFT (TRL `SFTTrainer`, completion-only NLL) |
|
||||
| Checkpoint | `checkpoint-350` (~1.06 epochs) |
|
||||
| Hardware | 4× H100 (Modal) |
|
||||
| Parallelism | DeepSpeed ZeRO-3, bf16 |
|
||||
|
||||
## Limitations
|
||||
|
||||
Specialized for KernelBook Triton codegen. May show reduced performance on general coding, math, and knowledge benchmarks compared to the base instruct model.
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.9.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.9.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c06e0a0ac4463a59fc386d61666ad0325173157e6764809c38f80fb43c84f79
|
||||
size 15231272152
|
||||
137
run_metadata.json
Normal file
137
run_metadata.json
Normal file
@@ -0,0 +1,137 @@
|
||||
{
|
||||
"cli_args": {
|
||||
"attn_implementation": "eager",
|
||||
"auto_resume": false,
|
||||
"bf16": true,
|
||||
"cache_dir": "/cache",
|
||||
"data_dir": "/workspace/data/kernelbook",
|
||||
"dataloader_num_workers": 4,
|
||||
"deepspeed": "/workspace/configs/deepspeed/zero3_bf16.json",
|
||||
"dry_run": false,
|
||||
"effective_batch_size": 32,
|
||||
"eval_packing": false,
|
||||
"eval_steps": 50,
|
||||
"gradient_accumulation_steps": 8,
|
||||
"gradient_checkpointing": true,
|
||||
"hub_model_id": "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft",
|
||||
"learning_rate": 2e-05,
|
||||
"logging_steps": 5,
|
||||
"loss_type": "nll",
|
||||
"max_eval_samples": null,
|
||||
"max_grad_norm": 1.0,
|
||||
"max_length": 8192,
|
||||
"max_steps": -1,
|
||||
"max_train_samples": null,
|
||||
"model": "/cache/local-models/sft/qwen2-5-coder-7b-instruct",
|
||||
"num_train_epochs": 3.0,
|
||||
"output_dir": "/__modal/volumes/vo-qWxmkR9prkx4LKrjcfqOmD/modal-sft-qwen2-5-coder-7b-kernelbook-final-nopack-eager",
|
||||
"output_root": "/outputs",
|
||||
"packing": false,
|
||||
"packing_strategy": "bfd",
|
||||
"per_device_eval_batch_size": 1,
|
||||
"per_device_train_batch_size": 1,
|
||||
"push_to_hub": true,
|
||||
"report_to": "wandb",
|
||||
"resume_from_checkpoint": null,
|
||||
"run_name": "modal-sft-qwen2-5-coder-7b-kernelbook-final-nopack-eager",
|
||||
"save_steps": 50,
|
||||
"save_total_limit": 10,
|
||||
"seed": 42,
|
||||
"target_global_batch_size": 32,
|
||||
"wandb_entity": null,
|
||||
"wandb_mode": "online",
|
||||
"wandb_project": "triton-sdft",
|
||||
"warmup_ratio": 0.03,
|
||||
"weight_decay": 0.01,
|
||||
"world_size": 4
|
||||
},
|
||||
"data_dir": "/workspace/data/kernelbook",
|
||||
"effective_batch_size": 32,
|
||||
"manifest": {
|
||||
"config": {
|
||||
"created_at": "2026-05-27T05:16:47.175016+00:00",
|
||||
"dataset_id": "GPUMODE/KernelBook",
|
||||
"max_output_tokens": 4096,
|
||||
"max_seq_length": 8192,
|
||||
"model": "Qwen/Qwen2.5-Coder-7B-Instruct",
|
||||
"output_dir": "data/kernelbook",
|
||||
"seed": 42,
|
||||
"test_ratio": 0.1,
|
||||
"train_ratio": 0.8,
|
||||
"val_ratio": 0.1
|
||||
},
|
||||
"counts": {
|
||||
"after_dedup": 15203,
|
||||
"after_empty_filter": 18162,
|
||||
"after_output_length_filter": 13267,
|
||||
"loaded": 18162,
|
||||
"test": 1360,
|
||||
"train": 10578,
|
||||
"validation": 1329
|
||||
},
|
||||
"sdft_trainer": {
|
||||
"eval_dataset": "data/kernelbook/text/sdft/validation",
|
||||
"sdft_config_hints": {
|
||||
"generate_from_teacher": true,
|
||||
"max_completion_length": 4096,
|
||||
"max_prompt_length": 4096
|
||||
},
|
||||
"test_dataset": "data/kernelbook/text/sdft/test",
|
||||
"train_dataset": "data/kernelbook/text/sdft/train"
|
||||
},
|
||||
"sft_trainer": {
|
||||
"eval_dataset": "data/kernelbook/tokenized/Qwen2.5-Coder-7B-Instruct/validation",
|
||||
"eval_packing": false,
|
||||
"packing": true,
|
||||
"requires_columns": [
|
||||
"input_ids",
|
||||
"completion_mask"
|
||||
],
|
||||
"sft_config": {
|
||||
"completion_only_loss": true,
|
||||
"eval_packing": false,
|
||||
"max_length": 8192,
|
||||
"packing": true
|
||||
},
|
||||
"test_dataset": "data/kernelbook/tokenized/Qwen2.5-Coder-7B-Instruct/test",
|
||||
"train_dataset": "data/kernelbook/tokenized/Qwen2.5-Coder-7B-Instruct/train"
|
||||
},
|
||||
"token_stats": {
|
||||
"test": {
|
||||
"count": 1360.0,
|
||||
"max": 6072.0,
|
||||
"min": 519.0,
|
||||
"p50": 1742.5,
|
||||
"p90": 3393.1000000000013,
|
||||
"p95": 4133.1,
|
||||
"p99": 4980.400000000003,
|
||||
"truncated_fraction": 0.0
|
||||
},
|
||||
"train": {
|
||||
"count": 10578.0,
|
||||
"max": 7026.0,
|
||||
"min": 517.0,
|
||||
"p50": 1781.5,
|
||||
"p90": 3559.0,
|
||||
"p95": 4168.299999999999,
|
||||
"p99": 4932.459999999999,
|
||||
"truncated_fraction": 0.0
|
||||
},
|
||||
"validation": {
|
||||
"count": 1329.0,
|
||||
"max": 7012.0,
|
||||
"min": 519.0,
|
||||
"p50": 1787.0,
|
||||
"p90": 3371.2,
|
||||
"p95": 3914.3999999999996,
|
||||
"p99": 4647.0,
|
||||
"truncated_fraction": 0.0
|
||||
}
|
||||
}
|
||||
},
|
||||
"method": "sft",
|
||||
"model": "/cache/local-models/sft/qwen2-5-coder-7b-instruct",
|
||||
"output_dir": "/__modal/volumes/vo-qWxmkR9prkx4LKrjcfqOmD/modal-sft-qwen2-5-coder-7b-kernelbook-final-nopack-eager",
|
||||
"run_name": "modal-sft-qwen2-5-coder-7b-kernelbook-final-nopack-eager",
|
||||
"world_size": 4
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
811
trainer_state.json
Normal file
811
trainer_state.json
Normal file
@@ -0,0 +1,811 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0574669187145558,
|
||||
"eval_steps": 50,
|
||||
"global_step": 350,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"entropy": 0.442822265625,
|
||||
"epoch": 0.015122873345935728,
|
||||
"grad_norm": 2.669071628071661,
|
||||
"learning_rate": 2.666666666666667e-06,
|
||||
"loss": 0.5928983211517334,
|
||||
"mean_token_accuracy": 0.8548422813415527,
|
||||
"num_tokens": 325432.0,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"entropy": 0.3935546875,
|
||||
"epoch": 0.030245746691871456,
|
||||
"grad_norm": 1.634140660130009,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 0.3988723993301392,
|
||||
"mean_token_accuracy": 0.8959574371576309,
|
||||
"num_tokens": 653193.0,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"entropy": 0.2187255859375,
|
||||
"epoch": 0.045368620037807186,
|
||||
"grad_norm": 0.9021532274129692,
|
||||
"learning_rate": 9.333333333333334e-06,
|
||||
"loss": 0.19831626415252684,
|
||||
"mean_token_accuracy": 0.9389900401234627,
|
||||
"num_tokens": 964453.0,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"entropy": 0.10172119140625,
|
||||
"epoch": 0.06049149338374291,
|
||||
"grad_norm": 0.4697352375821627,
|
||||
"learning_rate": 1.2666666666666667e-05,
|
||||
"loss": 0.10886554718017578,
|
||||
"mean_token_accuracy": 0.9637670248746872,
|
||||
"num_tokens": 1307238.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"entropy": 0.078204345703125,
|
||||
"epoch": 0.07561436672967864,
|
||||
"grad_norm": 0.39345906256866536,
|
||||
"learning_rate": 1.6000000000000003e-05,
|
||||
"loss": 0.0776131808757782,
|
||||
"mean_token_accuracy": 0.9740302637219429,
|
||||
"num_tokens": 1615672.0,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"entropy": 0.05927734375,
|
||||
"epoch": 0.09073724007561437,
|
||||
"grad_norm": 0.35679792282054484,
|
||||
"learning_rate": 1.9333333333333333e-05,
|
||||
"loss": 0.06322811841964722,
|
||||
"mean_token_accuracy": 0.9787174344062806,
|
||||
"num_tokens": 1935122.0,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"entropy": 0.055340576171875,
|
||||
"epoch": 0.10586011342155009,
|
||||
"grad_norm": 0.28127188289574473,
|
||||
"learning_rate": 1.99991486051959e-05,
|
||||
"loss": 0.055406326055526735,
|
||||
"mean_token_accuracy": 0.9811019197106361,
|
||||
"num_tokens": 2246001.0,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"entropy": 0.050018310546875,
|
||||
"epoch": 0.12098298676748583,
|
||||
"grad_norm": 0.23485165839069644,
|
||||
"learning_rate": 1.9995690062269985e-05,
|
||||
"loss": 0.05159962177276611,
|
||||
"mean_token_accuracy": 0.9823019146919251,
|
||||
"num_tokens": 2572728.0,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"entropy": 0.05009765625,
|
||||
"epoch": 0.13610586011342155,
|
||||
"grad_norm": 0.3286661753766386,
|
||||
"learning_rate": 1.9989572078514722e-05,
|
||||
"loss": 0.04924889206886292,
|
||||
"mean_token_accuracy": 0.983111384510994,
|
||||
"num_tokens": 2899222.0,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"entropy": 0.03935394287109375,
|
||||
"epoch": 0.15122873345935728,
|
||||
"grad_norm": 0.250685968179852,
|
||||
"learning_rate": 1.998079628167323e-05,
|
||||
"loss": 0.041659212112426756,
|
||||
"mean_token_accuracy": 0.9857470989227295,
|
||||
"num_tokens": 3199913.0,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.15122873345935728,
|
||||
"eval_entropy": 0.040476572764170424,
|
||||
"eval_loss": 0.0391058586537838,
|
||||
"eval_mean_token_accuracy": 0.986595441092242,
|
||||
"eval_num_tokens": 3199913.0,
|
||||
"eval_runtime": 94.4655,
|
||||
"eval_samples_per_second": 14.069,
|
||||
"eval_steps_per_second": 3.525,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"entropy": 0.038671875,
|
||||
"epoch": 0.166351606805293,
|
||||
"grad_norm": 0.3054203398912923,
|
||||
"learning_rate": 1.9969365006623072e-05,
|
||||
"loss": 0.03826351165771484,
|
||||
"mean_token_accuracy": 0.9868962660431861,
|
||||
"num_tokens": 3519539.0,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"entropy": 0.035321044921875,
|
||||
"epoch": 0.18147448015122875,
|
||||
"grad_norm": 0.3848999837215887,
|
||||
"learning_rate": 1.9955281294755034e-05,
|
||||
"loss": 0.03624363541603089,
|
||||
"mean_token_accuracy": 0.9876649409532547,
|
||||
"num_tokens": 3846310.0,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"entropy": 0.035552978515625,
|
||||
"epoch": 0.19659735349716445,
|
||||
"grad_norm": 0.2606280391924725,
|
||||
"learning_rate": 1.9938548893163924e-05,
|
||||
"loss": 0.03628517687320709,
|
||||
"mean_token_accuracy": 0.9875744208693504,
|
||||
"num_tokens": 4173916.0,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"entropy": 0.0336944580078125,
|
||||
"epoch": 0.21172022684310018,
|
||||
"grad_norm": 0.24422090914230693,
|
||||
"learning_rate": 1.9919172253651637e-05,
|
||||
"loss": 0.033189314603805545,
|
||||
"mean_token_accuracy": 0.9885250389575958,
|
||||
"num_tokens": 4494452.0,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"entropy": 0.02899322509765625,
|
||||
"epoch": 0.22684310018903592,
|
||||
"grad_norm": 0.19378251727544818,
|
||||
"learning_rate": 1.9897156531542708e-05,
|
||||
"loss": 0.029927724599838258,
|
||||
"mean_token_accuracy": 0.9899556040763855,
|
||||
"num_tokens": 4813996.0,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"entropy": 0.0284515380859375,
|
||||
"epoch": 0.24196597353497165,
|
||||
"grad_norm": 0.2664077757245733,
|
||||
"learning_rate": 1.98725075843127e-05,
|
||||
"loss": 0.029463762044906618,
|
||||
"mean_token_accuracy": 0.9898741751909256,
|
||||
"num_tokens": 5154020.0,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"entropy": 0.0311767578125,
|
||||
"epoch": 0.2570888468809074,
|
||||
"grad_norm": 0.22537314543102535,
|
||||
"learning_rate": 1.9845231970029774e-05,
|
||||
"loss": 0.03209342658519745,
|
||||
"mean_token_accuracy": 0.9891638234257698,
|
||||
"num_tokens": 5484973.0,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"entropy": 0.0276885986328125,
|
||||
"epoch": 0.2722117202268431,
|
||||
"grad_norm": 0.2077524527319594,
|
||||
"learning_rate": 1.9815336945609834e-05,
|
||||
"loss": 0.029284730553627014,
|
||||
"mean_token_accuracy": 0.9901994511485099,
|
||||
"num_tokens": 5811817.0,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"entropy": 0.0260345458984375,
|
||||
"epoch": 0.28733459357277885,
|
||||
"grad_norm": 0.31080264218901027,
|
||||
"learning_rate": 1.9782830464885788e-05,
|
||||
"loss": 0.02565096616744995,
|
||||
"mean_token_accuracy": 0.991170009970665,
|
||||
"num_tokens": 6118979.0,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"entropy": 0.024970245361328126,
|
||||
"epoch": 0.30245746691871456,
|
||||
"grad_norm": 0.21180271207392207,
|
||||
"learning_rate": 1.974772117649135e-05,
|
||||
"loss": 0.024624763429164885,
|
||||
"mean_token_accuracy": 0.9913630470633507,
|
||||
"num_tokens": 6457003.0,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.30245746691871456,
|
||||
"eval_entropy": 0.02398535009618994,
|
||||
"eval_loss": 0.025832440704107285,
|
||||
"eval_mean_token_accuracy": 0.9910635029947436,
|
||||
"eval_num_tokens": 6457003.0,
|
||||
"eval_runtime": 92.826,
|
||||
"eval_samples_per_second": 14.317,
|
||||
"eval_steps_per_second": 3.587,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"entropy": 0.0255767822265625,
|
||||
"epoch": 0.31758034026465026,
|
||||
"grad_norm": 0.19039718090172789,
|
||||
"learning_rate": 1.9710018421559995e-05,
|
||||
"loss": 0.026742279529571533,
|
||||
"mean_token_accuracy": 0.9909975379705429,
|
||||
"num_tokens": 6768352.0,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"entropy": 0.02334747314453125,
|
||||
"epoch": 0.332703213610586,
|
||||
"grad_norm": 0.15632220147486883,
|
||||
"learning_rate": 1.966973223123967e-05,
|
||||
"loss": 0.021733593940734864,
|
||||
"mean_token_accuracy": 0.9925331950187684,
|
||||
"num_tokens": 7086098.0,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"entropy": 0.02210235595703125,
|
||||
"epoch": 0.34782608695652173,
|
||||
"grad_norm": 0.2458450644732953,
|
||||
"learning_rate": 1.9626873324023915e-05,
|
||||
"loss": 0.02539382576942444,
|
||||
"mean_token_accuracy": 0.9917543068528175,
|
||||
"num_tokens": 7397835.0,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"entropy": 0.022796630859375,
|
||||
"epoch": 0.3629489603024575,
|
||||
"grad_norm": 0.511944627378666,
|
||||
"learning_rate": 1.9581453102900127e-05,
|
||||
"loss": 0.022371816635131835,
|
||||
"mean_token_accuracy": 0.9924163356423378,
|
||||
"num_tokens": 7720248.0,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"entropy": 0.02347259521484375,
|
||||
"epoch": 0.3780718336483932,
|
||||
"grad_norm": 0.22819135667809418,
|
||||
"learning_rate": 1.953348365231568e-05,
|
||||
"loss": 0.02383442670106888,
|
||||
"mean_token_accuracy": 0.9916202604770661,
|
||||
"num_tokens": 8046850.0,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"entropy": 0.02361907958984375,
|
||||
"epoch": 0.3931947069943289,
|
||||
"grad_norm": 0.23351254559117343,
|
||||
"learning_rate": 1.9482977734962753e-05,
|
||||
"loss": 0.0238445445895195,
|
||||
"mean_token_accuracy": 0.9918097272515297,
|
||||
"num_tokens": 8390721.0,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"entropy": 0.0227020263671875,
|
||||
"epoch": 0.40831758034026466,
|
||||
"grad_norm": 0.18760418206446414,
|
||||
"learning_rate": 1.9429948788382726e-05,
|
||||
"loss": 0.022852468490600585,
|
||||
"mean_token_accuracy": 0.9926092982292175,
|
||||
"num_tokens": 8741140.0,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"entropy": 0.02464141845703125,
|
||||
"epoch": 0.42344045368620037,
|
||||
"grad_norm": 0.17532160128342728,
|
||||
"learning_rate": 1.937441092139097e-05,
|
||||
"loss": 0.025189298391342162,
|
||||
"mean_token_accuracy": 0.9915472865104675,
|
||||
"num_tokens": 9066217.0,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"entropy": 0.022135162353515626,
|
||||
"epoch": 0.43856332703213613,
|
||||
"grad_norm": 0.2898150379760738,
|
||||
"learning_rate": 1.93163789103231e-05,
|
||||
"loss": 0.02323928475379944,
|
||||
"mean_token_accuracy": 0.9923686638474465,
|
||||
"num_tokens": 9398518.0,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"entropy": 0.022913360595703126,
|
||||
"epoch": 0.45368620037807184,
|
||||
"grad_norm": 0.20882908714005557,
|
||||
"learning_rate": 1.9255868195103596e-05,
|
||||
"loss": 0.023580947518348695,
|
||||
"mean_token_accuracy": 0.9922584399580956,
|
||||
"num_tokens": 9722146.0,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.45368620037807184,
|
||||
"eval_entropy": 0.019961612002627627,
|
||||
"eval_loss": 0.021232564002275467,
|
||||
"eval_mean_token_accuracy": 0.9926312886200868,
|
||||
"eval_num_tokens": 9722146.0,
|
||||
"eval_runtime": 92.911,
|
||||
"eval_samples_per_second": 14.304,
|
||||
"eval_steps_per_second": 3.584,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"entropy": 0.02125396728515625,
|
||||
"epoch": 0.46880907372400754,
|
||||
"grad_norm": 0.16611123987930837,
|
||||
"learning_rate": 1.9192894875137864e-05,
|
||||
"loss": 0.022398817539215087,
|
||||
"mean_token_accuracy": 0.9927845776081086,
|
||||
"num_tokens": 10051130.0,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"entropy": 0.01784820556640625,
|
||||
"epoch": 0.4839319470699433,
|
||||
"grad_norm": 0.1705996270647505,
|
||||
"learning_rate": 1.9127475705028864e-05,
|
||||
"loss": 0.020223259925842285,
|
||||
"mean_token_accuracy": 0.9935442849993705,
|
||||
"num_tokens": 10364936.0,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"entropy": 0.02181854248046875,
|
||||
"epoch": 0.499054820415879,
|
||||
"grad_norm": 0.18993585672995894,
|
||||
"learning_rate": 1.9059628090119392e-05,
|
||||
"loss": 0.02131263315677643,
|
||||
"mean_token_accuracy": 0.9929479479789733,
|
||||
"num_tokens": 10684934.0,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"entropy": 0.01970977783203125,
|
||||
"epoch": 0.5141776937618148,
|
||||
"grad_norm": 0.23862681974692412,
|
||||
"learning_rate": 1.898937008186123e-05,
|
||||
"loss": 0.021003079414367676,
|
||||
"mean_token_accuracy": 0.992812205851078,
|
||||
"num_tokens": 11016640.0,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"entropy": 0.02065277099609375,
|
||||
"epoch": 0.5293005671077504,
|
||||
"grad_norm": 0.22580792158388535,
|
||||
"learning_rate": 1.8916720373012425e-05,
|
||||
"loss": 0.020279140770435335,
|
||||
"mean_token_accuracy": 0.9934262841939926,
|
||||
"num_tokens": 11335375.0,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"entropy": 0.02077484130859375,
|
||||
"epoch": 0.5444234404536862,
|
||||
"grad_norm": 0.18177690286836462,
|
||||
"learning_rate": 1.8841698292663887e-05,
|
||||
"loss": 0.021297402679920197,
|
||||
"mean_token_accuracy": 0.9927030056715012,
|
||||
"num_tokens": 11669483.0,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"entropy": 0.020357513427734376,
|
||||
"epoch": 0.5595463137996219,
|
||||
"grad_norm": 0.18951806144385833,
|
||||
"learning_rate": 1.876432380109673e-05,
|
||||
"loss": 0.02147246301174164,
|
||||
"mean_token_accuracy": 0.9929309383034706,
|
||||
"num_tokens": 11987399.0,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"entropy": 0.021063995361328126,
|
||||
"epoch": 0.5746691871455577,
|
||||
"grad_norm": 0.28328991051134833,
|
||||
"learning_rate": 1.8684617484471662e-05,
|
||||
"loss": 0.021729469299316406,
|
||||
"mean_token_accuracy": 0.9926604524254798,
|
||||
"num_tokens": 12321769.0,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"entropy": 0.016484832763671874,
|
||||
"epoch": 0.5897920604914934,
|
||||
"grad_norm": 0.2604043117050105,
|
||||
"learning_rate": 1.860260054935186e-05,
|
||||
"loss": 0.016648142039775847,
|
||||
"mean_token_accuracy": 0.9943771168589592,
|
||||
"num_tokens": 12637459.0,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"entropy": 0.016230010986328126,
|
||||
"epoch": 0.6049149338374291,
|
||||
"grad_norm": 0.1518215594544113,
|
||||
"learning_rate": 1.8518294817060777e-05,
|
||||
"loss": 0.016636769473552703,
|
||||
"mean_token_accuracy": 0.9944247990846634,
|
||||
"num_tokens": 12976497.0,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.6049149338374291,
|
||||
"eval_entropy": 0.01848311324019332,
|
||||
"eval_loss": 0.018460111692547798,
|
||||
"eval_mean_token_accuracy": 0.9936752308596362,
|
||||
"eval_num_tokens": 12976497.0,
|
||||
"eval_runtime": 93.7884,
|
||||
"eval_samples_per_second": 14.17,
|
||||
"eval_steps_per_second": 3.551,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"entropy": 0.01815185546875,
|
||||
"epoch": 0.6200378071833649,
|
||||
"grad_norm": 0.2097083339362261,
|
||||
"learning_rate": 1.8431722717876383e-05,
|
||||
"loss": 0.01749354600906372,
|
||||
"mean_token_accuracy": 0.993867652118206,
|
||||
"num_tokens": 13302976.0,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"entropy": 0.01755523681640625,
|
||||
"epoch": 0.6351606805293005,
|
||||
"grad_norm": 0.17477493752672238,
|
||||
"learning_rate": 1.834290728506339e-05,
|
||||
"loss": 0.018500179052352905,
|
||||
"mean_token_accuracy": 0.9936169162392616,
|
||||
"num_tokens": 13627997.0,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"entropy": 0.018619537353515625,
|
||||
"epoch": 0.6502835538752363,
|
||||
"grad_norm": 0.1969863482217428,
|
||||
"learning_rate": 1.8251872148745075e-05,
|
||||
"loss": 0.017858733236789704,
|
||||
"mean_token_accuracy": 0.9939072072505951,
|
||||
"num_tokens": 13945104.0,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"entropy": 0.019687652587890625,
|
||||
"epoch": 0.665406427221172,
|
||||
"grad_norm": 0.2554011428793856,
|
||||
"learning_rate": 1.815864152961624e-05,
|
||||
"loss": 0.02146708369255066,
|
||||
"mean_token_accuracy": 0.9928086891770362,
|
||||
"num_tokens": 14279010.0,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"entropy": 0.0164215087890625,
|
||||
"epoch": 0.6805293005671077,
|
||||
"grad_norm": 0.22053987762264646,
|
||||
"learning_rate": 1.806324023249912e-05,
|
||||
"loss": 0.017443592846393585,
|
||||
"mean_token_accuracy": 0.9943347543478012,
|
||||
"num_tokens": 14608053.0,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"entropy": 0.01520233154296875,
|
||||
"epoch": 0.6956521739130435,
|
||||
"grad_norm": 0.15495690088956657,
|
||||
"learning_rate": 1.7965693639743816e-05,
|
||||
"loss": 0.015465393662452698,
|
||||
"mean_token_accuracy": 0.9950109854340553,
|
||||
"num_tokens": 14925691.0,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"entropy": 0.0169342041015625,
|
||||
"epoch": 0.7107750472589792,
|
||||
"grad_norm": 0.23516476733142996,
|
||||
"learning_rate": 1.786602770447513e-05,
|
||||
"loss": 0.017490310966968535,
|
||||
"mean_token_accuracy": 0.9939287096261978,
|
||||
"num_tokens": 15247510.0,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"entropy": 0.015985107421875,
|
||||
"epoch": 0.725897920604915,
|
||||
"grad_norm": 0.13394070957421397,
|
||||
"learning_rate": 1.776426894368746e-05,
|
||||
"loss": 0.015802830457687378,
|
||||
"mean_token_accuracy": 0.9947777166962624,
|
||||
"num_tokens": 15560305.0,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"entropy": 0.014200592041015625,
|
||||
"epoch": 0.7410207939508506,
|
||||
"grad_norm": 0.19432987534155574,
|
||||
"learning_rate": 1.766044443118978e-05,
|
||||
"loss": 0.014611494541168214,
|
||||
"mean_token_accuracy": 0.9948656380176544,
|
||||
"num_tokens": 15898787.0,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"entropy": 0.0140716552734375,
|
||||
"epoch": 0.7561436672967864,
|
||||
"grad_norm": 0.16144920711925453,
|
||||
"learning_rate": 1.7554581790402372e-05,
|
||||
"loss": 0.015314009785652161,
|
||||
"mean_token_accuracy": 0.9950292810797692,
|
||||
"num_tokens": 16236000.0,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.7561436672967864,
|
||||
"eval_entropy": 0.01619310350389452,
|
||||
"eval_loss": 0.016467994078993797,
|
||||
"eval_mean_token_accuracy": 0.9943410491084194,
|
||||
"eval_num_tokens": 16236000.0,
|
||||
"eval_runtime": 92.8452,
|
||||
"eval_samples_per_second": 14.314,
|
||||
"eval_steps_per_second": 3.587,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"entropy": 0.017685699462890624,
|
||||
"epoch": 0.7712665406427222,
|
||||
"grad_norm": 0.17754228327893673,
|
||||
"learning_rate": 1.7446709187007383e-05,
|
||||
"loss": 0.018420988321304323,
|
||||
"mean_token_accuracy": 0.9938467770814896,
|
||||
"num_tokens": 16568742.0,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"entropy": 0.01598701477050781,
|
||||
"epoch": 0.7863894139886578,
|
||||
"grad_norm": 0.1753647354705704,
|
||||
"learning_rate": 1.7336855321455126e-05,
|
||||
"loss": 0.016123867034912108,
|
||||
"mean_token_accuracy": 0.9946757212281228,
|
||||
"num_tokens": 16886171.0,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"entropy": 0.01281585693359375,
|
||||
"epoch": 0.8015122873345936,
|
||||
"grad_norm": 0.1694346707825758,
|
||||
"learning_rate": 1.7225049421328024e-05,
|
||||
"loss": 0.01325436681509018,
|
||||
"mean_token_accuracy": 0.9954081103205681,
|
||||
"num_tokens": 17213518.0,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"entropy": 0.015825653076171876,
|
||||
"epoch": 0.8166351606805293,
|
||||
"grad_norm": 0.12320756121826888,
|
||||
"learning_rate": 1.7111321233564406e-05,
|
||||
"loss": 0.016265182197093962,
|
||||
"mean_token_accuracy": 0.9945767849683762,
|
||||
"num_tokens": 17526983.0,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"entropy": 0.01460418701171875,
|
||||
"epoch": 0.831758034026465,
|
||||
"grad_norm": 0.15708115348818796,
|
||||
"learning_rate": 1.699570101654404e-05,
|
||||
"loss": 0.013886567950248719,
|
||||
"mean_token_accuracy": 0.9951759412884712,
|
||||
"num_tokens": 17844226.0,
|
||||
"step": 275
|
||||
},
|
||||
{
|
||||
"entropy": 0.012836456298828125,
|
||||
"epoch": 0.8468809073724007,
|
||||
"grad_norm": 0.143701427710118,
|
||||
"learning_rate": 1.687821953203765e-05,
|
||||
"loss": 0.01477896273136139,
|
||||
"mean_token_accuracy": 0.9952674239873887,
|
||||
"num_tokens": 18154251.0,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"entropy": 0.013329315185546874,
|
||||
"epoch": 0.8620037807183365,
|
||||
"grad_norm": 0.14730660194978837,
|
||||
"learning_rate": 1.6758908037022446e-05,
|
||||
"loss": 0.01359080672264099,
|
||||
"mean_token_accuracy": 0.9955309063196183,
|
||||
"num_tokens": 18468667.0,
|
||||
"step": 285
|
||||
},
|
||||
{
|
||||
"entropy": 0.01543426513671875,
|
||||
"epoch": 0.8771266540642723,
|
||||
"grad_norm": 0.13900308540287734,
|
||||
"learning_rate": 1.6637798275365976e-05,
|
||||
"loss": 0.016150069236755372,
|
||||
"mean_token_accuracy": 0.9946491599082947,
|
||||
"num_tokens": 18806646.0,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"entropy": 0.012978363037109374,
|
||||
"epoch": 0.8922495274102079,
|
||||
"grad_norm": 0.13732124684095226,
|
||||
"learning_rate": 1.651492246938034e-05,
|
||||
"loss": 0.012651418149471284,
|
||||
"mean_token_accuracy": 0.995641553401947,
|
||||
"num_tokens": 19132756.0,
|
||||
"step": 295
|
||||
},
|
||||
{
|
||||
"entropy": 0.015012359619140625,
|
||||
"epoch": 0.9073724007561437,
|
||||
"grad_norm": 0.13977045253544546,
|
||||
"learning_rate": 1.6390313311249212e-05,
|
||||
"loss": 0.01540960967540741,
|
||||
"mean_token_accuracy": 0.9949710816144943,
|
||||
"num_tokens": 19465713.0,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.9073724007561437,
|
||||
"eval_entropy": 0.014344957139756944,
|
||||
"eval_loss": 0.015235255472362041,
|
||||
"eval_mean_token_accuracy": 0.9947822013416806,
|
||||
"eval_num_tokens": 19465713.0,
|
||||
"eval_runtime": 92.3526,
|
||||
"eval_samples_per_second": 14.391,
|
||||
"eval_steps_per_second": 3.606,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"entropy": 0.013709640502929688,
|
||||
"epoch": 0.9224952741020794,
|
||||
"grad_norm": 0.19119314364034928,
|
||||
"learning_rate": 1.6264003954329762e-05,
|
||||
"loss": 0.01464797556400299,
|
||||
"mean_token_accuracy": 0.9951745182275772,
|
||||
"num_tokens": 19791857.0,
|
||||
"step": 305
|
||||
},
|
||||
{
|
||||
"entropy": 0.0113555908203125,
|
||||
"epoch": 0.9376181474480151,
|
||||
"grad_norm": 0.13382137381631254,
|
||||
"learning_rate": 1.613602800433194e-05,
|
||||
"loss": 0.012380270659923554,
|
||||
"mean_token_accuracy": 0.9959253877401352,
|
||||
"num_tokens": 20121726.0,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"entropy": 0.013879013061523438,
|
||||
"epoch": 0.9527410207939508,
|
||||
"grad_norm": 0.1786900745985722,
|
||||
"learning_rate": 1.600641951037736e-05,
|
||||
"loss": 0.013191039860248565,
|
||||
"mean_token_accuracy": 0.9955014079809189,
|
||||
"num_tokens": 20434281.0,
|
||||
"step": 315
|
||||
},
|
||||
{
|
||||
"entropy": 0.014342498779296876,
|
||||
"epoch": 0.9678638941398866,
|
||||
"grad_norm": 0.20383676268015227,
|
||||
"learning_rate": 1.5875212955940255e-05,
|
||||
"loss": 0.01611756980419159,
|
||||
"mean_token_accuracy": 0.9947072401642799,
|
||||
"num_tokens": 20753074.0,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"entropy": 0.013257980346679688,
|
||||
"epoch": 0.9829867674858223,
|
||||
"grad_norm": 0.1364426748258384,
|
||||
"learning_rate": 1.574244324967283e-05,
|
||||
"loss": 0.013307541608810425,
|
||||
"mean_token_accuracy": 0.9954897597432136,
|
||||
"num_tokens": 21086031.0,
|
||||
"step": 325
|
||||
},
|
||||
{
|
||||
"entropy": 0.0136016845703125,
|
||||
"epoch": 0.998109640831758,
|
||||
"grad_norm": 0.11139044118229276,
|
||||
"learning_rate": 1.5608145716117507e-05,
|
||||
"loss": 0.013101503252983093,
|
||||
"mean_token_accuracy": 0.9954297497868538,
|
||||
"num_tokens": 21385002.0,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"entropy": 0.010610631994298986,
|
||||
"epoch": 1.0120982986767486,
|
||||
"grad_norm": 0.11937254210200125,
|
||||
"learning_rate": 1.547235608630856e-05,
|
||||
"loss": 0.009768091142177582,
|
||||
"mean_token_accuracy": 0.9965261527009912,
|
||||
"num_tokens": 21651447.0,
|
||||
"step": 335
|
||||
},
|
||||
{
|
||||
"entropy": 0.008671951293945313,
|
||||
"epoch": 1.0272211720226843,
|
||||
"grad_norm": 0.12948932598689103,
|
||||
"learning_rate": 1.5335110488265497e-05,
|
||||
"loss": 0.00888235867023468,
|
||||
"mean_token_accuracy": 0.996855866909027,
|
||||
"num_tokens": 21981761.0,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"entropy": 0.009595108032226563,
|
||||
"epoch": 1.0423440453686201,
|
||||
"grad_norm": 0.21649437613862998,
|
||||
"learning_rate": 1.5196445437380941e-05,
|
||||
"loss": 0.010289055854082107,
|
||||
"mean_token_accuracy": 0.9964772433042526,
|
||||
"num_tokens": 22320903.0,
|
||||
"step": 345
|
||||
},
|
||||
{
|
||||
"entropy": 0.00907135009765625,
|
||||
"epoch": 1.0574669187145558,
|
||||
"grad_norm": 0.12728450692524118,
|
||||
"learning_rate": 1.5056397826705356e-05,
|
||||
"loss": 0.008513091504573822,
|
||||
"mean_token_accuracy": 0.9971326634287834,
|
||||
"num_tokens": 22652825.0,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.0574669187145558,
|
||||
"eval_entropy": 0.011664244505736205,
|
||||
"eval_loss": 0.013880621641874313,
|
||||
"eval_mean_token_accuracy": 0.9952635595032403,
|
||||
"eval_num_tokens": 22652825.0,
|
||||
"eval_runtime": 91.6429,
|
||||
"eval_samples_per_second": 14.502,
|
||||
"eval_steps_per_second": 3.634,
|
||||
"step": 350
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 993,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 45311893700608.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3d1e6776123b74114e6853f6976af58526ec3f3c5ab44ef83ef85b38acf0358d
|
||||
size 7761
|
||||
Reference in New Issue
Block a user