初始化项目，由ModelHub XC社区提供模型
Model: FlyPig23/Llama3.2-3B_Paper_Impact_award_SFT_1ep 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
|
||||
63
README.md
Normal file
63
README.md
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: meta-llama/Llama-3.2-3B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: Llama3.2-3B_Paper_Impact_award_SFT_1ep
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# Llama3.2-3B_Paper_Impact_award_SFT_1ep
|
||||
|
||||
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the paper_impact_award_train dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.0734
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.1
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 4.5.0
|
||||
- Tokenizers 0.22.1
|
||||
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.07341285049915314,
|
||||
"eval_runtime": 165.2207,
|
||||
"eval_samples_per_second": 75.366,
|
||||
"eval_steps_per_second": 2.36,
|
||||
"total_flos": 2.4132193734570803e+17,
|
||||
"train_loss": 0.08361149036965403,
|
||||
"train_runtime": 1113.8618,
|
||||
"train_samples_per_second": 16.871,
|
||||
"train_steps_per_second": 0.132
|
||||
}
|
||||
93
chat_template.jinja
Normal file
93
chat_template.jinja
Normal file
@@ -0,0 +1,93 @@
|
||||
{{- bos_token }}
|
||||
{%- if custom_tools is defined %}
|
||||
{%- set tools = custom_tools %}
|
||||
{%- endif %}
|
||||
{%- if not tools_in_user_message is defined %}
|
||||
{%- set tools_in_user_message = true %}
|
||||
{%- endif %}
|
||||
{%- if not date_string is defined %}
|
||||
{%- if strftime_now is defined %}
|
||||
{%- set date_string = strftime_now("%d %b %Y") %}
|
||||
{%- else %}
|
||||
{%- set date_string = "26 Jul 2024" %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
|
||||
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- set system_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = "" %}
|
||||
{%- endif %}
|
||||
|
||||
{#- System message #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||
{%- if tools is not none %}
|
||||
{{- "Environment: ipython\n" }}
|
||||
{%- endif %}
|
||||
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||
{{- "Today Date: " + date_string + "\n\n" }}
|
||||
{%- if tools is not none and not tools_in_user_message %}
|
||||
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- system_message }}
|
||||
{{- "<|eot_id|>" }}
|
||||
|
||||
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||
{%- if tools_in_user_message and not tools is none %}
|
||||
{#- Extract the first user message so we can plug it in here #}
|
||||
{%- if messages | length != 0 %}
|
||||
{%- set first_user_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||
{%- endif %}
|
||||
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{{- first_user_message + "<|eot_id|>"}}
|
||||
{%- endif %}
|
||||
|
||||
{%- for message in messages %}
|
||||
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||
{%- elif 'tool_calls' in message %}
|
||||
{%- if not message.tool_calls|length == 1 %}
|
||||
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||
{%- endif %}
|
||||
{%- set tool_call = message.tool_calls[0].function %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||
{%- if message.content is mapping or message.content is iterable %}
|
||||
{{- message.content | tojson }}
|
||||
{%- else %}
|
||||
{{- message.content }}
|
||||
{%- endif %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||
{%- endif %}
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 24,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128009,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
7
eval_results.json
Normal file
7
eval_results.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.07341285049915314,
|
||||
"eval_runtime": 165.2207,
|
||||
"eval_samples_per_second": 75.366,
|
||||
"eval_steps_per_second": 2.36
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128009,
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"pad_token_id": 128009,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:197642dbde88afd07a0c41802335bca9fdde5a0b7cc409e3290234ad2391caff
|
||||
size 4965799096
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1bb9a1a23377c692a22d8024001b1fb906fcedce64467c695ad817aec84f0c52
|
||||
size 2247734992
|
||||
263
model.safetensors.index.json
Normal file
263
model.safetensors.index.json
Normal file
@@ -0,0 +1,263 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3212749824,
|
||||
"total_size": 7213504512
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
26
special_tokens_map.json
Normal file
26
special_tokens_map.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
{
|
||||
"content": "<|eom_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|eot_id|>"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
||||
size 17209920
|
||||
2068
tokenizer_config.json
Normal file
2068
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 2.4132193734570803e+17,
|
||||
"train_loss": 0.08361149036965403,
|
||||
"train_runtime": 1113.8618,
|
||||
"train_samples_per_second": 16.871,
|
||||
"train_steps_per_second": 0.132
|
||||
}
|
||||
30
trainer_log.jsonl
Normal file
30
trainer_log.jsonl
Normal file
@@ -0,0 +1,30 @@
|
||||
{"current_steps": 5, "total_steps": 147, "loss": 0.0888, "lr": 5.333333333333334e-06, "epoch": 0.034013605442176874, "percentage": 3.4, "elapsed_time": "0:00:40", "remaining_time": "0:18:56"}
|
||||
{"current_steps": 10, "total_steps": 147, "loss": 0.0785, "lr": 1.2e-05, "epoch": 0.06802721088435375, "percentage": 6.8, "elapsed_time": "0:01:16", "remaining_time": "0:17:33"}
|
||||
{"current_steps": 15, "total_steps": 147, "loss": 0.0757, "lr": 1.866666666666667e-05, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:01:53", "remaining_time": "0:16:41"}
|
||||
{"current_steps": 20, "total_steps": 147, "loss": 0.1455, "lr": 1.9954719225730847e-05, "epoch": 0.1360544217687075, "percentage": 13.61, "elapsed_time": "0:02:29", "remaining_time": "0:15:51"}
|
||||
{"current_steps": 25, "total_steps": 147, "loss": 0.249, "lr": 1.9771468659711595e-05, "epoch": 0.17006802721088435, "percentage": 17.01, "elapsed_time": "0:03:05", "remaining_time": "0:15:06"}
|
||||
{"current_steps": 30, "total_steps": 147, "loss": 0.0786, "lr": 1.9450008187146685e-05, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:03:41", "remaining_time": "0:14:24"}
|
||||
{"current_steps": 35, "total_steps": 147, "loss": 0.0771, "lr": 1.8994884619106034e-05, "epoch": 0.23809523809523808, "percentage": 23.81, "elapsed_time": "0:04:18", "remaining_time": "0:13:48"}
|
||||
{"current_steps": 40, "total_steps": 147, "loss": 0.0761, "lr": 1.8412535328311813e-05, "epoch": 0.272108843537415, "percentage": 27.21, "elapsed_time": "0:04:55", "remaining_time": "0:13:10"}
|
||||
{"current_steps": 45, "total_steps": 147, "loss": 0.0758, "lr": 1.771119719745388e-05, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:05:31", "remaining_time": "0:12:32"}
|
||||
{"current_steps": 50, "total_steps": 147, "loss": 0.0762, "lr": 1.6900790114821122e-05, "epoch": 0.3401360544217687, "percentage": 34.01, "elapsed_time": "0:06:09", "remaining_time": "0:11:55"}
|
||||
{"current_steps": 55, "total_steps": 147, "loss": 0.0762, "lr": 1.599277666511347e-05, "epoch": 0.3741496598639456, "percentage": 37.41, "elapsed_time": "0:06:44", "remaining_time": "0:11:16"}
|
||||
{"current_steps": 60, "total_steps": 147, "loss": 0.0755, "lr": 1.5000000000000002e-05, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:07:21", "remaining_time": "0:10:40"}
|
||||
{"current_steps": 65, "total_steps": 147, "loss": 0.0737, "lr": 1.3936502181619415e-05, "epoch": 0.4421768707482993, "percentage": 44.22, "elapsed_time": "0:07:58", "remaining_time": "0:10:03"}
|
||||
{"current_steps": 70, "total_steps": 147, "loss": 0.0752, "lr": 1.2817325568414299e-05, "epoch": 0.47619047619047616, "percentage": 47.62, "elapsed_time": "0:08:36", "remaining_time": "0:09:27"}
|
||||
{"current_steps": 75, "total_steps": 147, "loss": 0.0756, "lr": 1.1658300052543742e-05, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:09:12", "remaining_time": "0:08:50"}
|
||||
{"current_steps": 80, "total_steps": 147, "loss": 0.0743, "lr": 1.0475819158237426e-05, "epoch": 0.54421768707483, "percentage": 54.42, "elapsed_time": "0:09:49", "remaining_time": "0:08:13"}
|
||||
{"current_steps": 85, "total_steps": 147, "loss": 0.0771, "lr": 9.286608168007678e-06, "epoch": 0.5782312925170068, "percentage": 57.82, "elapsed_time": "0:10:26", "remaining_time": "0:07:36"}
|
||||
{"current_steps": 90, "total_steps": 147, "loss": 0.0755, "lr": 8.107487556395902e-06, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:11:02", "remaining_time": "0:06:59"}
|
||||
{"current_steps": 95, "total_steps": 147, "loss": 0.0738, "lr": 6.955135077300932e-06, "epoch": 0.6462585034013606, "percentage": 64.63, "elapsed_time": "0:11:39", "remaining_time": "0:06:22"}
|
||||
{"current_steps": 100, "total_steps": 147, "loss": 0.0731, "lr": 5.845849869981137e-06, "epoch": 0.6802721088435374, "percentage": 68.03, "elapsed_time": "0:12:18", "remaining_time": "0:05:47"}
|
||||
{"current_steps": 105, "total_steps": 147, "loss": 0.073, "lr": 4.795321920269279e-06, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:12:54", "remaining_time": "0:05:09"}
|
||||
{"current_steps": 110, "total_steps": 147, "loss": 0.0732, "lr": 3.818410137793947e-06, "epoch": 0.7482993197278912, "percentage": 74.83, "elapsed_time": "0:13:32", "remaining_time": "0:04:33"}
|
||||
{"current_steps": 115, "total_steps": 147, "loss": 0.0734, "lr": 2.9289321881345257e-06, "epoch": 0.782312925170068, "percentage": 78.23, "elapsed_time": "0:14:09", "remaining_time": "0:03:56"}
|
||||
{"current_steps": 120, "total_steps": 147, "loss": 0.0728, "lr": 2.1394690525721275e-06, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:14:45", "remaining_time": "0:03:19"}
|
||||
{"current_steps": 125, "total_steps": 147, "loss": 0.0728, "lr": 1.4611870797885196e-06, "epoch": 0.8503401360544217, "percentage": 85.03, "elapsed_time": "0:15:21", "remaining_time": "0:02:42"}
|
||||
{"current_steps": 130, "total_steps": 147, "loss": 0.0734, "lr": 9.036800464548157e-07, "epoch": 0.8843537414965986, "percentage": 88.44, "elapsed_time": "0:15:59", "remaining_time": "0:02:05"}
|
||||
{"current_steps": 135, "total_steps": 147, "loss": 0.073, "lr": 4.7483346064139513e-07, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:16:35", "remaining_time": "0:01:28"}
|
||||
{"current_steps": 140, "total_steps": 147, "loss": 0.0728, "lr": 1.8071302737293294e-07, "epoch": 0.9523809523809523, "percentage": 95.24, "elapsed_time": "0:17:12", "remaining_time": "0:00:51"}
|
||||
{"current_steps": 145, "total_steps": 147, "loss": 0.0733, "lr": 2.547885389746485e-08, "epoch": 0.9863945578231292, "percentage": 98.64, "elapsed_time": "0:17:49", "remaining_time": "0:00:14"}
|
||||
{"current_steps": 147, "total_steps": 147, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:18:32", "remaining_time": "0:00:00"}
|
||||
246
trainer_state.json
Normal file
246
trainer_state.json
Normal file
@@ -0,0 +1,246 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 147,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034013605442176874,
|
||||
"grad_norm": 0.19419066607952118,
|
||||
"learning_rate": 5.333333333333334e-06,
|
||||
"loss": 0.0888,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.06802721088435375,
|
||||
"grad_norm": 0.0060990070924162865,
|
||||
"learning_rate": 1.2e-05,
|
||||
"loss": 0.0785,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.10204081632653061,
|
||||
"grad_norm": 0.011376941576600075,
|
||||
"learning_rate": 1.866666666666667e-05,
|
||||
"loss": 0.0757,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.1360544217687075,
|
||||
"grad_norm": 2.0510334968566895,
|
||||
"learning_rate": 1.9954719225730847e-05,
|
||||
"loss": 0.1455,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.17006802721088435,
|
||||
"grad_norm": 0.048179708421230316,
|
||||
"learning_rate": 1.9771468659711595e-05,
|
||||
"loss": 0.249,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.20408163265306123,
|
||||
"grad_norm": 0.1557886153459549,
|
||||
"learning_rate": 1.9450008187146685e-05,
|
||||
"loss": 0.0786,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.23809523809523808,
|
||||
"grad_norm": 0.09699074178934097,
|
||||
"learning_rate": 1.8994884619106034e-05,
|
||||
"loss": 0.0771,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.272108843537415,
|
||||
"grad_norm": 0.012417234480381012,
|
||||
"learning_rate": 1.8412535328311813e-05,
|
||||
"loss": 0.0761,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.30612244897959184,
|
||||
"grad_norm": 0.10855792462825775,
|
||||
"learning_rate": 1.771119719745388e-05,
|
||||
"loss": 0.0758,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.3401360544217687,
|
||||
"grad_norm": 0.10554474592208862,
|
||||
"learning_rate": 1.6900790114821122e-05,
|
||||
"loss": 0.0762,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.3741496598639456,
|
||||
"grad_norm": 0.08427968621253967,
|
||||
"learning_rate": 1.599277666511347e-05,
|
||||
"loss": 0.0762,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.40816326530612246,
|
||||
"grad_norm": 0.14054857194423676,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 0.0755,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.4421768707482993,
|
||||
"grad_norm": 0.06138243526220322,
|
||||
"learning_rate": 1.3936502181619415e-05,
|
||||
"loss": 0.0737,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.47619047619047616,
|
||||
"grad_norm": 0.06466853618621826,
|
||||
"learning_rate": 1.2817325568414299e-05,
|
||||
"loss": 0.0752,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.5102040816326531,
|
||||
"grad_norm": 0.13903750479221344,
|
||||
"learning_rate": 1.1658300052543742e-05,
|
||||
"loss": 0.0756,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.54421768707483,
|
||||
"grad_norm": 0.10078471899032593,
|
||||
"learning_rate": 1.0475819158237426e-05,
|
||||
"loss": 0.0743,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.5782312925170068,
|
||||
"grad_norm": 0.10367649793624878,
|
||||
"learning_rate": 9.286608168007678e-06,
|
||||
"loss": 0.0771,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.6122448979591837,
|
||||
"grad_norm": 0.06360036879777908,
|
||||
"learning_rate": 8.107487556395902e-06,
|
||||
"loss": 0.0755,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.6462585034013606,
|
||||
"grad_norm": 0.03832394629716873,
|
||||
"learning_rate": 6.955135077300932e-06,
|
||||
"loss": 0.0738,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.6802721088435374,
|
||||
"grad_norm": 0.002442193916067481,
|
||||
"learning_rate": 5.845849869981137e-06,
|
||||
"loss": 0.0731,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.7142857142857143,
|
||||
"grad_norm": 0.012490343302488327,
|
||||
"learning_rate": 4.795321920269279e-06,
|
||||
"loss": 0.073,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.7482993197278912,
|
||||
"grad_norm": 0.003825731808319688,
|
||||
"learning_rate": 3.818410137793947e-06,
|
||||
"loss": 0.0732,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.782312925170068,
|
||||
"grad_norm": 0.006658583413809538,
|
||||
"learning_rate": 2.9289321881345257e-06,
|
||||
"loss": 0.0734,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.8163265306122449,
|
||||
"grad_norm": 0.00992305763065815,
|
||||
"learning_rate": 2.1394690525721275e-06,
|
||||
"loss": 0.0728,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.8503401360544217,
|
||||
"grad_norm": 0.01818728633224964,
|
||||
"learning_rate": 1.4611870797885196e-06,
|
||||
"loss": 0.0728,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.8843537414965986,
|
||||
"grad_norm": 0.00845139566808939,
|
||||
"learning_rate": 9.036800464548157e-07,
|
||||
"loss": 0.0734,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.9183673469387755,
|
||||
"grad_norm": 0.058558348566293716,
|
||||
"learning_rate": 4.7483346064139513e-07,
|
||||
"loss": 0.073,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.9523809523809523,
|
||||
"grad_norm": 0.05383609980344772,
|
||||
"learning_rate": 1.8071302737293294e-07,
|
||||
"loss": 0.0728,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.9863945578231292,
|
||||
"grad_norm": 0.00498389033600688,
|
||||
"learning_rate": 2.547885389746485e-08,
|
||||
"loss": 0.0733,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 147,
|
||||
"total_flos": 2.4132193734570803e+17,
|
||||
"train_loss": 0.08361149036965403,
|
||||
"train_runtime": 1113.8618,
|
||||
"train_samples_per_second": 16.871,
|
||||
"train_steps_per_second": 0.132
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 147,
|
||||
"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": 2.4132193734570803e+17,
|
||||
"train_batch_size": 8,
|
||||
"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 sha256:8de385304a166003b474d3fcf17d3ac46bbc14b66e8df68e7dc766a94d8302ad
|
||||
size 7416
|
||||
Reference in New Issue
Block a user