初始化项目，由ModelHub XC社区提供模型
Model: FlyPig23/Llama3.2-3B_Paper_Impact_media_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_media_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_media_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_media_train dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.0766
|
||||
|
||||
## 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": 0.07655010372400284,
|
||||
"eval_runtime": 209.2628,
|
||||
"eval_samples_per_second": 75.441,
|
||||
"eval_steps_per_second": 2.361,
|
||||
"total_flos": 2.8024067250035098e+17,
|
||||
"train_loss": 0.08477670932749667,
|
||||
"train_runtime": 1255.2183,
|
||||
"train_samples_per_second": 16.86,
|
||||
"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": 0.07655010372400284,
|
||||
"eval_runtime": 209.2628,
|
||||
"eval_samples_per_second": 75.441,
|
||||
"eval_steps_per_second": 2.361
|
||||
}
|
||||
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 sha256:3ecec6cbe6f53ceb16e8149f55f879f3e62f497390935075b77302fa8c0451ec
|
||||
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 sha256:1113cf60c2b835a2fdd51f546a92c8ac882bec01bfb5e371c7f8bc23a7253fc0
|
||||
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": 2.8024067250035098e+17,
|
||||
"train_loss": 0.08477670932749667,
|
||||
"train_runtime": 1255.2183,
|
||||
"train_samples_per_second": 16.86,
|
||||
"train_steps_per_second": 0.132
|
||||
}
|
||||
34
trainer_log.jsonl
Normal file
34
trainer_log.jsonl
Normal file
@@ -0,0 +1,34 @@
|
||||
{"current_steps": 5, "total_steps": 166, "loss": 0.284, "lr": 4.705882352941177e-06, "epoch": 0.030211480362537766, "percentage": 3.01, "elapsed_time": "0:00:38", "remaining_time": "0:20:24"}
|
||||
{"current_steps": 10, "total_steps": 166, "loss": 0.091, "lr": 1.0588235294117648e-05, "epoch": 0.06042296072507553, "percentage": 6.02, "elapsed_time": "0:01:15", "remaining_time": "0:19:38"}
|
||||
{"current_steps": 15, "total_steps": 166, "loss": 0.0881, "lr": 1.647058823529412e-05, "epoch": 0.09063444108761329, "percentage": 9.04, "elapsed_time": "0:01:52", "remaining_time": "0:18:51"}
|
||||
{"current_steps": 20, "total_steps": 166, "loss": 0.0856, "lr": 1.9991110182465032e-05, "epoch": 0.12084592145015106, "percentage": 12.05, "elapsed_time": "0:02:29", "remaining_time": "0:18:10"}
|
||||
{"current_steps": 25, "total_steps": 166, "loss": 0.0776, "lr": 1.9891281165856876e-05, "epoch": 0.1510574018126888, "percentage": 15.06, "elapsed_time": "0:03:06", "remaining_time": "0:17:30"}
|
||||
{"current_steps": 30, "total_steps": 166, "loss": 0.0796, "lr": 1.968162302997659e-05, "epoch": 0.18126888217522658, "percentage": 18.07, "elapsed_time": "0:03:43", "remaining_time": "0:16:51"}
|
||||
{"current_steps": 35, "total_steps": 166, "loss": 0.0775, "lr": 1.9364463741042694e-05, "epoch": 0.21148036253776434, "percentage": 21.08, "elapsed_time": "0:04:20", "remaining_time": "0:16:15"}
|
||||
{"current_steps": 40, "total_steps": 166, "loss": 0.0776, "lr": 1.8943324918225495e-05, "epoch": 0.24169184290030213, "percentage": 24.1, "elapsed_time": "0:04:58", "remaining_time": "0:15:38"}
|
||||
{"current_steps": 45, "total_steps": 166, "loss": 0.0778, "lr": 1.8422882730893323e-05, "epoch": 0.2719033232628399, "percentage": 27.11, "elapsed_time": "0:05:35", "remaining_time": "0:15:00"}
|
||||
{"current_steps": 50, "total_steps": 166, "loss": 0.0776, "lr": 1.7808915976161364e-05, "epoch": 0.3021148036253776, "percentage": 30.12, "elapsed_time": "0:06:11", "remaining_time": "0:14:21"}
|
||||
{"current_steps": 55, "total_steps": 166, "loss": 0.0787, "lr": 1.710824191327075e-05, "epoch": 0.3323262839879154, "percentage": 33.13, "elapsed_time": "0:06:47", "remaining_time": "0:13:42"}
|
||||
{"current_steps": 60, "total_steps": 166, "loss": 0.079, "lr": 1.632864056726917e-05, "epoch": 0.36253776435045315, "percentage": 36.14, "elapsed_time": "0:07:23", "remaining_time": "0:13:03"}
|
||||
{"current_steps": 65, "total_steps": 166, "loss": 0.0776, "lr": 1.5478768342496872e-05, "epoch": 0.39274924471299094, "percentage": 39.16, "elapsed_time": "0:08:01", "remaining_time": "0:12:27"}
|
||||
{"current_steps": 70, "total_steps": 166, "loss": 0.0779, "lr": 1.4568061905081874e-05, "epoch": 0.4229607250755287, "percentage": 42.17, "elapsed_time": "0:08:37", "remaining_time": "0:11:50"}
|
||||
{"current_steps": 75, "total_steps": 166, "loss": 0.0782, "lr": 1.3606633401697557e-05, "epoch": 0.45317220543806647, "percentage": 45.18, "elapsed_time": "0:09:15", "remaining_time": "0:11:13"}
|
||||
{"current_steps": 80, "total_steps": 166, "loss": 0.0791, "lr": 1.2605158178034656e-05, "epoch": 0.48338368580060426, "percentage": 48.19, "elapsed_time": "0:09:52", "remaining_time": "0:10:36"}
|
||||
{"current_steps": 85, "total_steps": 166, "loss": 0.0792, "lr": 1.157475624372018e-05, "epoch": 0.513595166163142, "percentage": 51.2, "elapsed_time": "0:10:29", "remaining_time": "0:10:00"}
|
||||
{"current_steps": 90, "total_steps": 166, "loss": 0.0779, "lr": 1.0526868799852797e-05, "epoch": 0.5438066465256798, "percentage": 54.22, "elapsed_time": "0:11:06", "remaining_time": "0:09:23"}
|
||||
{"current_steps": 95, "total_steps": 166, "loss": 0.0781, "lr": 9.473131200147205e-06, "epoch": 0.5740181268882175, "percentage": 57.23, "elapsed_time": "0:11:43", "remaining_time": "0:08:45"}
|
||||
{"current_steps": 100, "total_steps": 166, "loss": 0.0771, "lr": 8.425243756279824e-06, "epoch": 0.6042296072507553, "percentage": 60.24, "elapsed_time": "0:12:20", "remaining_time": "0:08:08"}
|
||||
{"current_steps": 105, "total_steps": 166, "loss": 0.0771, "lr": 7.394841821965345e-06, "epoch": 0.6344410876132931, "percentage": 63.25, "elapsed_time": "0:12:58", "remaining_time": "0:07:32"}
|
||||
{"current_steps": 110, "total_steps": 166, "loss": 0.0776, "lr": 6.3933665983024465e-06, "epoch": 0.6646525679758308, "percentage": 66.27, "elapsed_time": "0:13:35", "remaining_time": "0:06:55"}
|
||||
{"current_steps": 115, "total_steps": 166, "loss": 0.0767, "lr": 5.431938094918132e-06, "epoch": 0.6948640483383686, "percentage": 69.28, "elapsed_time": "0:14:11", "remaining_time": "0:06:17"}
|
||||
{"current_steps": 120, "total_steps": 166, "loss": 0.0778, "lr": 4.5212316575031325e-06, "epoch": 0.7250755287009063, "percentage": 72.29, "elapsed_time": "0:14:48", "remaining_time": "0:05:40"}
|
||||
{"current_steps": 125, "total_steps": 166, "loss": 0.0776, "lr": 3.6713594327308343e-06, "epoch": 0.7552870090634441, "percentage": 75.3, "elapsed_time": "0:15:26", "remaining_time": "0:05:03"}
|
||||
{"current_steps": 130, "total_steps": 166, "loss": 0.0769, "lr": 2.891758086729253e-06, "epoch": 0.7854984894259819, "percentage": 78.31, "elapsed_time": "0:16:02", "remaining_time": "0:04:26"}
|
||||
{"current_steps": 135, "total_steps": 166, "loss": 0.0768, "lr": 2.19108402383864e-06, "epoch": 0.8157099697885196, "percentage": 81.33, "elapsed_time": "0:16:39", "remaining_time": "0:03:49"}
|
||||
{"current_steps": 140, "total_steps": 166, "loss": 0.0765, "lr": 1.5771172691066793e-06, "epoch": 0.8459214501510574, "percentage": 84.34, "elapsed_time": "0:17:16", "remaining_time": "0:03:12"}
|
||||
{"current_steps": 145, "total_steps": 166, "loss": 0.077, "lr": 1.0566750817745076e-06, "epoch": 0.8761329305135952, "percentage": 87.35, "elapsed_time": "0:17:53", "remaining_time": "0:02:35"}
|
||||
{"current_steps": 150, "total_steps": 166, "loss": 0.0758, "lr": 6.355362589573078e-07, "epoch": 0.9063444108761329, "percentage": 90.36, "elapsed_time": "0:18:32", "remaining_time": "0:01:58"}
|
||||
{"current_steps": 155, "total_steps": 166, "loss": 0.0775, "lr": 3.1837697002341293e-07, "epoch": 0.9365558912386707, "percentage": 93.37, "elapsed_time": "0:19:07", "remaining_time": "0:01:21"}
|
||||
{"current_steps": 160, "total_steps": 166, "loss": 0.0758, "lr": 1.0871883414312778e-07, "epoch": 0.9667673716012085, "percentage": 96.39, "elapsed_time": "0:19:43", "remaining_time": "0:00:44"}
|
||||
{"current_steps": 165, "total_steps": 166, "loss": 0.0768, "lr": 8.889817534969425e-09, "epoch": 0.9969788519637462, "percentage": 99.4, "elapsed_time": "0:20:21", "remaining_time": "0:00:07"}
|
||||
{"current_steps": 166, "total_steps": 166, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:20:53", "remaining_time": "0:00:00"}
|
||||
274
trainer_state.json
Normal file
274
trainer_state.json
Normal file
@@ -0,0 +1,274 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 166,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.030211480362537766,
|
||||
"grad_norm": 0.21704457700252533,
|
||||
"learning_rate": 4.705882352941177e-06,
|
||||
"loss": 0.284,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.06042296072507553,
|
||||
"grad_norm": 0.07700642943382263,
|
||||
"learning_rate": 1.0588235294117648e-05,
|
||||
"loss": 0.091,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.09063444108761329,
|
||||
"grad_norm": 1.0004132986068726,
|
||||
"learning_rate": 1.647058823529412e-05,
|
||||
"loss": 0.0881,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.12084592145015106,
|
||||
"grad_norm": 0.017268722876906395,
|
||||
"learning_rate": 1.9991110182465032e-05,
|
||||
"loss": 0.0856,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.1510574018126888,
|
||||
"grad_norm": 0.06252593547105789,
|
||||
"learning_rate": 1.9891281165856876e-05,
|
||||
"loss": 0.0776,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.18126888217522658,
|
||||
"grad_norm": 0.013158817775547504,
|
||||
"learning_rate": 1.968162302997659e-05,
|
||||
"loss": 0.0796,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.21148036253776434,
|
||||
"grad_norm": 0.054746970534324646,
|
||||
"learning_rate": 1.9364463741042694e-05,
|
||||
"loss": 0.0775,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.24169184290030213,
|
||||
"grad_norm": 0.027843380346894264,
|
||||
"learning_rate": 1.8943324918225495e-05,
|
||||
"loss": 0.0776,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.2719033232628399,
|
||||
"grad_norm": 0.09170668572187424,
|
||||
"learning_rate": 1.8422882730893323e-05,
|
||||
"loss": 0.0778,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.3021148036253776,
|
||||
"grad_norm": 0.049589045345783234,
|
||||
"learning_rate": 1.7808915976161364e-05,
|
||||
"loss": 0.0776,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.3323262839879154,
|
||||
"grad_norm": 0.057375721633434296,
|
||||
"learning_rate": 1.710824191327075e-05,
|
||||
"loss": 0.0787,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.36253776435045315,
|
||||
"grad_norm": 0.04218236356973648,
|
||||
"learning_rate": 1.632864056726917e-05,
|
||||
"loss": 0.079,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.39274924471299094,
|
||||
"grad_norm": 0.1125708743929863,
|
||||
"learning_rate": 1.5478768342496872e-05,
|
||||
"loss": 0.0776,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.4229607250755287,
|
||||
"grad_norm": 0.024594679474830627,
|
||||
"learning_rate": 1.4568061905081874e-05,
|
||||
"loss": 0.0779,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.45317220543806647,
|
||||
"grad_norm": 0.01017661951482296,
|
||||
"learning_rate": 1.3606633401697557e-05,
|
||||
"loss": 0.0782,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.48338368580060426,
|
||||
"grad_norm": 0.07011096179485321,
|
||||
"learning_rate": 1.2605158178034656e-05,
|
||||
"loss": 0.0791,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.513595166163142,
|
||||
"grad_norm": 0.01498446986079216,
|
||||
"learning_rate": 1.157475624372018e-05,
|
||||
"loss": 0.0792,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.5438066465256798,
|
||||
"grad_norm": 0.03184051066637039,
|
||||
"learning_rate": 1.0526868799852797e-05,
|
||||
"loss": 0.0779,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.5740181268882175,
|
||||
"grad_norm": 0.078987717628479,
|
||||
"learning_rate": 9.473131200147205e-06,
|
||||
"loss": 0.0781,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.6042296072507553,
|
||||
"grad_norm": 0.05952491611242294,
|
||||
"learning_rate": 8.425243756279824e-06,
|
||||
"loss": 0.0771,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.6344410876132931,
|
||||
"grad_norm": 0.014677044935524464,
|
||||
"learning_rate": 7.394841821965345e-06,
|
||||
"loss": 0.0771,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.6646525679758308,
|
||||
"grad_norm": 0.03106486238539219,
|
||||
"learning_rate": 6.3933665983024465e-06,
|
||||
"loss": 0.0776,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.6948640483383686,
|
||||
"grad_norm": 0.03548077121376991,
|
||||
"learning_rate": 5.431938094918132e-06,
|
||||
"loss": 0.0767,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.7250755287009063,
|
||||
"grad_norm": 0.02386642061173916,
|
||||
"learning_rate": 4.5212316575031325e-06,
|
||||
"loss": 0.0778,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.7552870090634441,
|
||||
"grad_norm": 0.03368431329727173,
|
||||
"learning_rate": 3.6713594327308343e-06,
|
||||
"loss": 0.0776,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.7854984894259819,
|
||||
"grad_norm": 0.016041960567235947,
|
||||
"learning_rate": 2.891758086729253e-06,
|
||||
"loss": 0.0769,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.8157099697885196,
|
||||
"grad_norm": 0.03274780884385109,
|
||||
"learning_rate": 2.19108402383864e-06,
|
||||
"loss": 0.0768,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.8459214501510574,
|
||||
"grad_norm": 0.03985007107257843,
|
||||
"learning_rate": 1.5771172691066793e-06,
|
||||
"loss": 0.0765,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.8761329305135952,
|
||||
"grad_norm": 0.02575680799782276,
|
||||
"learning_rate": 1.0566750817745076e-06,
|
||||
"loss": 0.077,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.9063444108761329,
|
||||
"grad_norm": 0.04101819917559624,
|
||||
"learning_rate": 6.355362589573078e-07,
|
||||
"loss": 0.0758,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.9365558912386707,
|
||||
"grad_norm": 0.06996775418519974,
|
||||
"learning_rate": 3.1837697002341293e-07,
|
||||
"loss": 0.0775,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.9667673716012085,
|
||||
"grad_norm": 0.007283793296664953,
|
||||
"learning_rate": 1.0871883414312778e-07,
|
||||
"loss": 0.0758,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.9969788519637462,
|
||||
"grad_norm": 0.017074227333068848,
|
||||
"learning_rate": 8.889817534969425e-09,
|
||||
"loss": 0.0768,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 166,
|
||||
"total_flos": 2.8024067250035098e+17,
|
||||
"train_loss": 0.08477670932749667,
|
||||
"train_runtime": 1255.2183,
|
||||
"train_samples_per_second": 16.86,
|
||||
"train_steps_per_second": 0.132
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 166,
|
||||
"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": 2.8024067250035098e+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 sha256:6e80dfa838693fd43ce9e1ae8dea5e72db58632a36ab96a724d9d5b83cdf5aa1
|
||||
size 7416
|
||||
Reference in New Issue
Block a user