初始化项目,由ModelHub XC社区提供模型
Model: iproskurina/SmolLM2-360M-biasinbios-pt-factory-real-base-npacking Source: Original Platform
This commit is contained in:
4
checkpoint-868/chat_template.jinja
Normal file
4
checkpoint-868/chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
||||
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '
|
||||
' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '
|
||||
Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '
|
||||
' }}{% endif %}{% endfor %}
|
||||
32
checkpoint-868/config.json
Normal file
32
checkpoint-868/config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 0,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 960,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2560,
|
||||
"is_llama_config": true,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 15,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 5,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_interleaved": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
9
checkpoint-868/generation_config.json
Normal file
9
checkpoint-868/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": [
|
||||
0
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
48901
checkpoint-868/merges.txt
Normal file
48901
checkpoint-868/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-868/model.safetensors
Normal file
3
checkpoint-868/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:672f35cabb2488b43aa1f8ee5e7bd8fd32cd265ef3e74a295be5c67658412020
|
||||
size 1447317080
|
||||
3
checkpoint-868/optimizer.pt
Normal file
3
checkpoint-868/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a51439c060c956e84d802193f6ceac9380cd3604e494e844979fcc3566bcc73
|
||||
size 2894817739
|
||||
3
checkpoint-868/rng_state.pth
Normal file
3
checkpoint-868/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
|
||||
size 14645
|
||||
3
checkpoint-868/scheduler.pt
Normal file
3
checkpoint-868/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f2c3fadb1edcfe8ead120a2002df424969bb0eb1826d352d5da6bfdb969f89c1
|
||||
size 1465
|
||||
43
checkpoint-868/special_tokens_map.json
Normal file
43
checkpoint-868/special_tokens_map.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
244949
checkpoint-868/tokenizer.json
Normal file
244949
checkpoint-868/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
171
checkpoint-868/tokenizer_config.json
Normal file
171
checkpoint-868/tokenizer_config.json
Normal file
@@ -0,0 +1,171 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
90
checkpoint-868/trainer_state.json
Normal file
90
checkpoint-868/trainer_state.json
Normal file
@@ -0,0 +1,90 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 868,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.11530700490054771,
|
||||
"grad_norm": 2.9323058128356934,
|
||||
"learning_rate": 4.9970880369844344e-05,
|
||||
"loss": 2.995,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.23061400980109542,
|
||||
"grad_norm": 2.415233612060547,
|
||||
"learning_rate": 4.7505488501875907e-05,
|
||||
"loss": 2.809,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3459210147016431,
|
||||
"grad_norm": 1.7806472778320312,
|
||||
"learning_rate": 4.1447386246547995e-05,
|
||||
"loss": 2.7775,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.46122801960219084,
|
||||
"grad_norm": 1.9444694519042969,
|
||||
"learning_rate": 3.27636713364243e-05,
|
||||
"loss": 2.7791,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.5765350245027385,
|
||||
"grad_norm": 2.093379020690918,
|
||||
"learning_rate": 2.2840586632035014e-05,
|
||||
"loss": 2.7299,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.6918420294032862,
|
||||
"grad_norm": 1.8663088083267212,
|
||||
"learning_rate": 1.3262224364443493e-05,
|
||||
"loss": 2.7359,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 0.807149034303834,
|
||||
"grad_norm": 2.0475974082946777,
|
||||
"learning_rate": 5.557646282733725e-06,
|
||||
"loss": 2.7394,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 0.9224560392043817,
|
||||
"grad_norm": 1.9257546663284302,
|
||||
"learning_rate": 9.56788706753814e-07,
|
||||
"loss": 2.7317,
|
||||
"step": 800
|
||||
}
|
||||
],
|
||||
"logging_steps": 100,
|
||||
"max_steps": 868,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 5361727389638400.0,
|
||||
"train_batch_size": 2,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-868/training_args.bin
Normal file
3
checkpoint-868/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c8211fa9f42421d17ed348efb104b6813733638a757c0698b50a2318e4e417d
|
||||
size 6225
|
||||
1
checkpoint-868/vocab.json
Normal file
1
checkpoint-868/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user