Text Generation
Transformers
Safetensors
English
gpt2
novi
novi-nano
novi-nano-instruct
causal-lm
from-scratch
instruction-tuning
chatml
conversational
text-generation-inference
Instructions to use Novi-AI/Novi-Nano-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Novi-AI/Novi-Nano-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Novi-AI/Novi-Nano-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Novi-AI/Novi-Nano-Instruct") model = AutoModelForCausalLM.from_pretrained("Novi-AI/Novi-Nano-Instruct", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Novi-AI/Novi-Nano-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Novi-AI/Novi-Nano-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Novi-AI/Novi-Nano-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Novi-AI/Novi-Nano-Instruct
- SGLang
How to use Novi-AI/Novi-Nano-Instruct with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Novi-AI/Novi-Nano-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Novi-AI/Novi-Nano-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Novi-AI/Novi-Nano-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Novi-AI/Novi-Nano-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Novi-AI/Novi-Nano-Instruct with Docker Model Runner:
docker model run hf.co/Novi-AI/Novi-Nano-Instruct
Delete files checkpoint-* with huggingface_hub
Browse files- checkpoint-75/chat_template.jinja +0 -1
- checkpoint-75/config.json +0 -35
- checkpoint-75/generation_config.json +0 -13
- checkpoint-75/model.safetensors +0 -3
- checkpoint-75/optimizer.pt +0 -3
- checkpoint-75/rng_state.pth +0 -3
- checkpoint-75/scheduler.pt +0 -3
- checkpoint-75/tokenizer.json +0 -0
- checkpoint-75/tokenizer_config.json +0 -17
- checkpoint-75/trainer_state.json +0 -99
- checkpoint-75/training_args.bin +0 -3
- checkpoint-80/chat_template.jinja +0 -1
- checkpoint-80/config.json +0 -35
- checkpoint-80/generation_config.json +0 -13
- checkpoint-80/model.safetensors +0 -3
- checkpoint-80/optimizer.pt +0 -3
- checkpoint-80/rng_state.pth +0 -3
- checkpoint-80/scheduler.pt +0 -3
- checkpoint-80/tokenizer.json +0 -0
- checkpoint-80/tokenizer_config.json +0 -17
- checkpoint-80/trainer_state.json +0 -106
- checkpoint-80/training_args.bin +0 -3
checkpoint-75/chat_template.jinja
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}
|
|
|
|
|
|
checkpoint-75/config.json
DELETED
|
@@ -1,35 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"add_cross_attention": false,
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPT2LMHeadModel"
|
| 6 |
-
],
|
| 7 |
-
"attn_pdrop": 0.0,
|
| 8 |
-
"bos_token_id": 8192,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"embd_pdrop": 0.0,
|
| 11 |
-
"eos_token_id": 8192,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"layer_norm_epsilon": 1e-05,
|
| 14 |
-
"model_type": "gpt2",
|
| 15 |
-
"n_ctx": 256,
|
| 16 |
-
"n_embd": 96,
|
| 17 |
-
"n_head": 4,
|
| 18 |
-
"n_inner": 384,
|
| 19 |
-
"n_layer": 4,
|
| 20 |
-
"n_positions": 256,
|
| 21 |
-
"pad_token_id": 0,
|
| 22 |
-
"reorder_and_upcast_attn": false,
|
| 23 |
-
"resid_pdrop": 0.0,
|
| 24 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
-
"scale_attn_weights": true,
|
| 26 |
-
"summary_activation": null,
|
| 27 |
-
"summary_first_dropout": 0.1,
|
| 28 |
-
"summary_proj_to_labels": true,
|
| 29 |
-
"summary_type": "cls_index",
|
| 30 |
-
"summary_use_proj": true,
|
| 31 |
-
"tie_word_embeddings": true,
|
| 32 |
-
"transformers_version": "5.9.0",
|
| 33 |
-
"use_cache": false,
|
| 34 |
-
"vocab_size": 8195
|
| 35 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 8192,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
8192,
|
| 6 |
-
2
|
| 7 |
-
],
|
| 8 |
-
"output_attentions": false,
|
| 9 |
-
"output_hidden_states": false,
|
| 10 |
-
"pad_token_id": 0,
|
| 11 |
-
"transformers_version": "5.9.0",
|
| 12 |
-
"use_cache": false
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:336a0b6001155048ccd9798d5383ef24d6ad82beb8bdd94d690e0c15c5c51064
|
| 3 |
-
size 5040360
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e5a82f295c1430251cc576fa2f274985416badfaf727bc54cf666ec04828ab47
|
| 3 |
-
size 10113419
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:799af21e8c98b5b33efb40e1806882d89f329486619fd8f7f6c267e08bc7954e
|
| 3 |
-
size 14455
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2484e7775aa740fbc4af66c4efb6e17876bd87768726e0335f3ba4746ba32a1d
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-75/tokenizer_config.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "<|endoftext|>",
|
| 5 |
-
"eos_token": "<|endoftext|>",
|
| 6 |
-
"errors": "replace",
|
| 7 |
-
"extra_special_tokens": [
|
| 8 |
-
"<|im_start|>",
|
| 9 |
-
"<|im_end|>"
|
| 10 |
-
],
|
| 11 |
-
"is_local": false,
|
| 12 |
-
"local_files_only": false,
|
| 13 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
-
"pad_token": "<|pad|>",
|
| 15 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 16 |
-
"unk_token": "<|endoftext|>"
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/trainer_state.json
DELETED
|
@@ -1,99 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 75,
|
| 3 |
-
"best_metric": 5.31256628036499,
|
| 4 |
-
"best_model_checkpoint": "./Novi-Nano-Instruct/checkpoint-75",
|
| 5 |
-
"epoch": 5.0,
|
| 6 |
-
"eval_steps": 50,
|
| 7 |
-
"global_step": 75,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.6896551724137931,
|
| 14 |
-
"grad_norm": 10.477374076843262,
|
| 15 |
-
"learning_rate": 1.9989008914857115e-05,
|
| 16 |
-
"loss": 5.787208938598633,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 1.3448275862068966,
|
| 21 |
-
"grad_norm": 8.555954933166504,
|
| 22 |
-
"learning_rate": 1.8699063724087905e-05,
|
| 23 |
-
"loss": 5.4951026916503904,
|
| 24 |
-
"step": 20
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 2.0,
|
| 28 |
-
"grad_norm": 12.820338249206543,
|
| 29 |
-
"learning_rate": 1.5531311541251995e-05,
|
| 30 |
-
"loss": 5.384668350219727,
|
| 31 |
-
"step": 30
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.689655172413793,
|
| 35 |
-
"grad_norm": 7.613554000854492,
|
| 36 |
-
"learning_rate": 1.1169553219720828e-05,
|
| 37 |
-
"loss": 5.253799819946289,
|
| 38 |
-
"step": 40
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 3.344827586206897,
|
| 42 |
-
"grad_norm": 5.958171844482422,
|
| 43 |
-
"learning_rate": 6.555331497156671e-06,
|
| 44 |
-
"loss": 5.191973876953125,
|
| 45 |
-
"step": 50
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 3.344827586206897,
|
| 49 |
-
"eval_loss": 5.329359531402588,
|
| 50 |
-
"eval_runtime": 0.2333,
|
| 51 |
-
"eval_samples_per_second": 218.611,
|
| 52 |
-
"eval_steps_per_second": 17.146,
|
| 53 |
-
"step": 50
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 4.0,
|
| 57 |
-
"grad_norm": 11.592702865600586,
|
| 58 |
-
"learning_rate": 2.6846866473633126e-06,
|
| 59 |
-
"loss": 5.208735656738281,
|
| 60 |
-
"step": 60
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 4.689655172413794,
|
| 64 |
-
"grad_norm": 6.462846755981445,
|
| 65 |
-
"learning_rate": 3.931481242315993e-07,
|
| 66 |
-
"loss": 5.158348464965821,
|
| 67 |
-
"step": 70
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 5.0,
|
| 71 |
-
"eval_loss": 5.31256628036499,
|
| 72 |
-
"eval_runtime": 0.3229,
|
| 73 |
-
"eval_samples_per_second": 157.955,
|
| 74 |
-
"eval_steps_per_second": 12.389,
|
| 75 |
-
"step": 75
|
| 76 |
-
}
|
| 77 |
-
],
|
| 78 |
-
"logging_steps": 10,
|
| 79 |
-
"max_steps": 75,
|
| 80 |
-
"num_input_tokens_seen": 0,
|
| 81 |
-
"num_train_epochs": 5,
|
| 82 |
-
"save_steps": 50,
|
| 83 |
-
"stateful_callbacks": {
|
| 84 |
-
"TrainerControl": {
|
| 85 |
-
"args": {
|
| 86 |
-
"should_epoch_stop": false,
|
| 87 |
-
"should_evaluate": false,
|
| 88 |
-
"should_log": false,
|
| 89 |
-
"should_save": true,
|
| 90 |
-
"should_training_stop": true
|
| 91 |
-
},
|
| 92 |
-
"attributes": {}
|
| 93 |
-
}
|
| 94 |
-
},
|
| 95 |
-
"total_flos": 396752162688.0,
|
| 96 |
-
"train_batch_size": 16,
|
| 97 |
-
"trial_name": null,
|
| 98 |
-
"trial_params": null
|
| 99 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-75/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e4c534110bb4b95606560faca657721f10249028cc669c356a65e033b95b71ef
|
| 3 |
-
size 5265
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/chat_template.jinja
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}
|
|
|
|
|
|
checkpoint-80/config.json
DELETED
|
@@ -1,35 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"add_cross_attention": false,
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPT2LMHeadModel"
|
| 6 |
-
],
|
| 7 |
-
"attn_pdrop": 0.0,
|
| 8 |
-
"bos_token_id": 8192,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"embd_pdrop": 0.0,
|
| 11 |
-
"eos_token_id": 8192,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"layer_norm_epsilon": 1e-05,
|
| 14 |
-
"model_type": "gpt2",
|
| 15 |
-
"n_ctx": 256,
|
| 16 |
-
"n_embd": 96,
|
| 17 |
-
"n_head": 4,
|
| 18 |
-
"n_inner": 384,
|
| 19 |
-
"n_layer": 4,
|
| 20 |
-
"n_positions": 256,
|
| 21 |
-
"pad_token_id": 0,
|
| 22 |
-
"reorder_and_upcast_attn": false,
|
| 23 |
-
"resid_pdrop": 0.0,
|
| 24 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
-
"scale_attn_weights": true,
|
| 26 |
-
"summary_activation": null,
|
| 27 |
-
"summary_first_dropout": 0.1,
|
| 28 |
-
"summary_proj_to_labels": true,
|
| 29 |
-
"summary_type": "cls_index",
|
| 30 |
-
"summary_use_proj": true,
|
| 31 |
-
"tie_word_embeddings": true,
|
| 32 |
-
"transformers_version": "5.9.0",
|
| 33 |
-
"use_cache": false,
|
| 34 |
-
"vocab_size": 8195
|
| 35 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 8192,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
8192,
|
| 6 |
-
2
|
| 7 |
-
],
|
| 8 |
-
"output_attentions": false,
|
| 9 |
-
"output_hidden_states": false,
|
| 10 |
-
"pad_token_id": 0,
|
| 11 |
-
"transformers_version": "5.9.0",
|
| 12 |
-
"use_cache": false
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b52c50cc0b9bd8042ee674266ec2af4a8e34fd2f5b213b26d0db73d6dc59e739
|
| 3 |
-
size 5040360
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:485c082cb86e837832214ccc616e76ddf80c520e601cc37120ff1c004779a3bd
|
| 3 |
-
size 10113419
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:799af21e8c98b5b33efb40e1806882d89f329486619fd8f7f6c267e08bc7954e
|
| 3 |
-
size 14455
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:87a411bfc5fc0d26f467ffe97207ff3161f4f5ebce7a002622ed6a01e074ed3d
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-80/tokenizer_config.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "<|endoftext|>",
|
| 5 |
-
"eos_token": "<|endoftext|>",
|
| 6 |
-
"errors": "replace",
|
| 7 |
-
"extra_special_tokens": [
|
| 8 |
-
"<|im_start|>",
|
| 9 |
-
"<|im_end|>"
|
| 10 |
-
],
|
| 11 |
-
"is_local": false,
|
| 12 |
-
"local_files_only": false,
|
| 13 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
-
"pad_token": "<|pad|>",
|
| 15 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 16 |
-
"unk_token": "<|endoftext|>"
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/trainer_state.json
DELETED
|
@@ -1,106 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 80,
|
| 3 |
-
"best_metric": 5.153667449951172,
|
| 4 |
-
"best_model_checkpoint": "./Novi-Nano-Instruct/checkpoint-80",
|
| 5 |
-
"epoch": 5.0,
|
| 6 |
-
"eval_steps": 50,
|
| 7 |
-
"global_step": 80,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.625,
|
| 14 |
-
"grad_norm": 12.822108268737793,
|
| 15 |
-
"learning_rate": 1.999048221581858e-05,
|
| 16 |
-
"loss": 5.8478034973144535,
|
| 17 |
-
"step": 10
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 1.25,
|
| 21 |
-
"grad_norm": 8.055219650268555,
|
| 22 |
-
"learning_rate": 1.887010833178222e-05,
|
| 23 |
-
"loss": 5.500722885131836,
|
| 24 |
-
"step": 20
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 1.875,
|
| 28 |
-
"grad_norm": 7.208122253417969,
|
| 29 |
-
"learning_rate": 1.608761429008721e-05,
|
| 30 |
-
"loss": 5.3473560333251955,
|
| 31 |
-
"step": 30
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.5,
|
| 35 |
-
"grad_norm": 8.550283432006836,
|
| 36 |
-
"learning_rate": 1.2164396139381029e-05,
|
| 37 |
-
"loss": 5.232704162597656,
|
| 38 |
-
"step": 40
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 3.125,
|
| 42 |
-
"grad_norm": 6.781601905822754,
|
| 43 |
-
"learning_rate": 7.835603860618973e-06,
|
| 44 |
-
"loss": 5.235857391357422,
|
| 45 |
-
"step": 50
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 3.125,
|
| 49 |
-
"eval_loss": 5.177420139312744,
|
| 50 |
-
"eval_runtime": 0.0668,
|
| 51 |
-
"eval_samples_per_second": 149.631,
|
| 52 |
-
"eval_steps_per_second": 14.963,
|
| 53 |
-
"step": 50
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 3.75,
|
| 57 |
-
"grad_norm": 7.122476100921631,
|
| 58 |
-
"learning_rate": 3.912385709912794e-06,
|
| 59 |
-
"loss": 5.176748657226563,
|
| 60 |
-
"step": 60
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 4.375,
|
| 64 |
-
"grad_norm": 7.392387866973877,
|
| 65 |
-
"learning_rate": 1.129891668217783e-06,
|
| 66 |
-
"loss": 5.182163238525391,
|
| 67 |
-
"step": 70
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 5.0,
|
| 71 |
-
"grad_norm": 7.460492134094238,
|
| 72 |
-
"learning_rate": 9.517784181422018e-09,
|
| 73 |
-
"loss": 5.1638141632080075,
|
| 74 |
-
"step": 80
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 5.0,
|
| 78 |
-
"eval_loss": 5.153667449951172,
|
| 79 |
-
"eval_runtime": 0.0425,
|
| 80 |
-
"eval_samples_per_second": 235.54,
|
| 81 |
-
"eval_steps_per_second": 23.554,
|
| 82 |
-
"step": 80
|
| 83 |
-
}
|
| 84 |
-
],
|
| 85 |
-
"logging_steps": 10,
|
| 86 |
-
"max_steps": 80,
|
| 87 |
-
"num_input_tokens_seen": 0,
|
| 88 |
-
"num_train_epochs": 5,
|
| 89 |
-
"save_steps": 50,
|
| 90 |
-
"stateful_callbacks": {
|
| 91 |
-
"TrainerControl": {
|
| 92 |
-
"args": {
|
| 93 |
-
"should_epoch_stop": false,
|
| 94 |
-
"should_evaluate": false,
|
| 95 |
-
"should_log": false,
|
| 96 |
-
"should_save": true,
|
| 97 |
-
"should_training_stop": true
|
| 98 |
-
},
|
| 99 |
-
"attributes": {}
|
| 100 |
-
}
|
| 101 |
-
},
|
| 102 |
-
"total_flos": 430992576000.0,
|
| 103 |
-
"train_batch_size": 16,
|
| 104 |
-
"trial_name": null,
|
| 105 |
-
"trial_params": null
|
| 106 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-80/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e4c534110bb4b95606560faca657721f10249028cc669c356a65e033b95b71ef
|
| 3 |
-
size 5265
|
|
|
|
|
|
|
|
|
|
|
|