初始化项目，由ModelHub XC社区提供模型
Model: FlyPig23/Llama3.2-3B_Paper_Impact_citation_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_citation_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_citation_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_citations_train dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.0836
|
||||
|
||||
## 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": 0.08355996757745743,
|
||||
"eval_runtime": 182.9117,
|
||||
"eval_samples_per_second": 68.984,
|
||||
"eval_steps_per_second": 2.16,
|
||||
"total_flos": 2.50613257277014e+17,
|
||||
"train_loss": 0.07390243510770447,
|
||||
"train_runtime": 1155.3856,
|
||||
"train_samples_per_second": 14.999,
|
||||
"train_steps_per_second": 0.118
|
||||
}
|
||||
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": 0.08355996757745743,
|
||||
"eval_runtime": 182.9117,
|
||||
"eval_samples_per_second": 68.984,
|
||||
"eval_steps_per_second": 2.16
|
||||
}
|
||||
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 sha256:63e669d530985a177ceb640ac1c9ee41647319e5e7607a969da8cafa0d3eb305
|
||||
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 sha256:72407d2d8381080e5283729679ac0f7a43839293b2705c933f8ff021cd1882fe
|
||||
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": 2.50613257277014e+17,
|
||||
"train_loss": 0.07390243510770447,
|
||||
"train_runtime": 1155.3856,
|
||||
"train_samples_per_second": 14.999,
|
||||
"train_steps_per_second": 0.118
|
||||
}
|
||||
28
trainer_log.jsonl
Normal file
28
trainer_log.jsonl
Normal file
@@ -0,0 +1,28 @@
|
||||
{"current_steps": 5, "total_steps": 136, "loss": 0.1315, "lr": 5.7142857142857145e-06, "epoch": 0.03690036900369004, "percentage": 3.68, "elapsed_time": "0:00:40", "remaining_time": "0:17:47"}
|
||||
{"current_steps": 10, "total_steps": 136, "loss": 0.1031, "lr": 1.2857142857142859e-05, "epoch": 0.07380073800738007, "percentage": 7.35, "elapsed_time": "0:01:21", "remaining_time": "0:17:02"}
|
||||
{"current_steps": 15, "total_steps": 136, "loss": 0.0986, "lr": 2e-05, "epoch": 0.11070110701107011, "percentage": 11.03, "elapsed_time": "0:02:01", "remaining_time": "0:16:20"}
|
||||
{"current_steps": 20, "total_steps": 136, "loss": 0.108, "lr": 1.9917226741361014e-05, "epoch": 0.14760147601476015, "percentage": 14.71, "elapsed_time": "0:02:45", "remaining_time": "0:15:57"}
|
||||
{"current_steps": 25, "total_steps": 136, "loss": 0.1, "lr": 1.9670277247913205e-05, "epoch": 0.18450184501845018, "percentage": 18.38, "elapsed_time": "0:03:26", "remaining_time": "0:15:15"}
|
||||
{"current_steps": 30, "total_steps": 136, "loss": 0.0982, "lr": 1.9263239682514953e-05, "epoch": 0.22140221402214022, "percentage": 22.06, "elapsed_time": "0:04:06", "remaining_time": "0:14:31"}
|
||||
{"current_steps": 35, "total_steps": 136, "loss": 0.096, "lr": 1.8702852410301556e-05, "epoch": 0.25830258302583026, "percentage": 25.74, "elapsed_time": "0:04:48", "remaining_time": "0:13:53"}
|
||||
{"current_steps": 40, "total_steps": 136, "loss": 0.0934, "lr": 1.7998392447397197e-05, "epoch": 0.2952029520295203, "percentage": 29.41, "elapsed_time": "0:05:31", "remaining_time": "0:13:15"}
|
||||
{"current_steps": 45, "total_steps": 136, "loss": 0.085, "lr": 1.7161521883143936e-05, "epoch": 0.33210332103321033, "percentage": 33.09, "elapsed_time": "0:06:13", "remaining_time": "0:12:34"}
|
||||
{"current_steps": 50, "total_steps": 136, "loss": 0.0839, "lr": 1.6206094818274228e-05, "epoch": 0.36900369003690037, "percentage": 36.76, "elapsed_time": "0:06:55", "remaining_time": "0:11:54"}
|
||||
{"current_steps": 55, "total_steps": 136, "loss": 0.0793, "lr": 1.5147928015098309e-05, "epoch": 0.4059040590405904, "percentage": 40.44, "elapsed_time": "0:07:38", "remaining_time": "0:11:14"}
|
||||
{"current_steps": 60, "total_steps": 136, "loss": 0.0789, "lr": 1.4004539056512667e-05, "epoch": 0.44280442804428044, "percentage": 44.12, "elapsed_time": "0:08:19", "remaining_time": "0:10:33"}
|
||||
{"current_steps": 65, "total_steps": 136, "loss": 0.0728, "lr": 1.2794856348516095e-05, "epoch": 0.4797047970479705, "percentage": 47.79, "elapsed_time": "0:09:00", "remaining_time": "0:09:50"}
|
||||
{"current_steps": 70, "total_steps": 136, "loss": 0.07, "lr": 1.153890576704062e-05, "epoch": 0.5166051660516605, "percentage": 51.47, "elapsed_time": "0:09:41", "remaining_time": "0:09:08"}
|
||||
{"current_steps": 75, "total_steps": 136, "loss": 0.0634, "lr": 1.0257479136549889e-05, "epoch": 0.5535055350553506, "percentage": 55.15, "elapsed_time": "0:10:23", "remaining_time": "0:08:27"}
|
||||
{"current_steps": 80, "total_steps": 136, "loss": 0.063, "lr": 8.971790028626395e-06, "epoch": 0.5904059040590406, "percentage": 58.82, "elapsed_time": "0:11:04", "remaining_time": "0:07:45"}
|
||||
{"current_steps": 85, "total_steps": 136, "loss": 0.0592, "lr": 7.703122578682047e-06, "epoch": 0.6273062730627307, "percentage": 62.5, "elapsed_time": "0:11:44", "remaining_time": "0:07:02"}
|
||||
{"current_steps": 90, "total_steps": 136, "loss": 0.0599, "lr": 6.472479134509052e-06, "epoch": 0.6642066420664207, "percentage": 66.18, "elapsed_time": "0:12:28", "remaining_time": "0:06:22"}
|
||||
{"current_steps": 95, "total_steps": 136, "loss": 0.0549, "lr": 5.300232569726805e-06, "epoch": 0.7011070110701108, "percentage": 69.85, "elapsed_time": "0:13:10", "remaining_time": "0:05:41"}
|
||||
{"current_steps": 100, "total_steps": 136, "loss": 0.0529, "lr": 4.205789017954364e-06, "epoch": 0.7380073800738007, "percentage": 73.53, "elapsed_time": "0:13:50", "remaining_time": "0:04:59"}
|
||||
{"current_steps": 105, "total_steps": 136, "loss": 0.0536, "lr": 3.207266611027069e-06, "epoch": 0.7749077490774908, "percentage": 77.21, "elapsed_time": "0:14:31", "remaining_time": "0:04:17"}
|
||||
{"current_steps": 110, "total_steps": 136, "loss": 0.0468, "lr": 2.3211955396340003e-06, "epoch": 0.8118081180811808, "percentage": 80.88, "elapsed_time": "0:15:13", "remaining_time": "0:03:35"}
|
||||
{"current_steps": 115, "total_steps": 136, "loss": 0.0534, "lr": 1.5622444017681438e-06, "epoch": 0.8487084870848709, "percentage": 84.56, "elapsed_time": "0:15:55", "remaining_time": "0:02:54"}
|
||||
{"current_steps": 120, "total_steps": 136, "loss": 0.0534, "lr": 9.42977369195286e-07, "epoch": 0.8856088560885609, "percentage": 88.24, "elapsed_time": "0:16:37", "remaining_time": "0:02:13"}
|
||||
{"current_steps": 125, "total_steps": 136, "loss": 0.0479, "lr": 4.73646191966175e-07, "epoch": 0.922509225092251, "percentage": 91.91, "elapsed_time": "0:17:19", "remaining_time": "0:01:31"}
|
||||
{"current_steps": 130, "total_steps": 136, "loss": 0.0491, "lr": 1.6202048426483652e-07, "epoch": 0.959409594095941, "percentage": 95.59, "elapsed_time": "0:17:59", "remaining_time": "0:00:49"}
|
||||
{"current_steps": 135, "total_steps": 136, "loss": 0.0455, "lr": 1.325910115169471e-08, "epoch": 0.996309963099631, "percentage": 99.26, "elapsed_time": "0:18:40", "remaining_time": "0:00:08"}
|
||||
{"current_steps": 136, "total_steps": 136, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:19:13", "remaining_time": "0:00:00"}
|
||||
232
trainer_state.json
Normal file
232
trainer_state.json
Normal file
@@ -0,0 +1,232 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 136,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.03690036900369004,
|
||||
"grad_norm": 0.12055090069770813,
|
||||
"learning_rate": 5.7142857142857145e-06,
|
||||
"loss": 0.1315,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.07380073800738007,
|
||||
"grad_norm": 0.043656233698129654,
|
||||
"learning_rate": 1.2857142857142859e-05,
|
||||
"loss": 0.1031,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.11070110701107011,
|
||||
"grad_norm": 0.07571940124034882,
|
||||
"learning_rate": 2e-05,
|
||||
"loss": 0.0986,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.14760147601476015,
|
||||
"grad_norm": 0.06417621672153473,
|
||||
"learning_rate": 1.9917226741361014e-05,
|
||||
"loss": 0.108,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.18450184501845018,
|
||||
"grad_norm": 0.07998916506767273,
|
||||
"learning_rate": 1.9670277247913205e-05,
|
||||
"loss": 0.1,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.22140221402214022,
|
||||
"grad_norm": 0.07391388714313507,
|
||||
"learning_rate": 1.9263239682514953e-05,
|
||||
"loss": 0.0982,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.25830258302583026,
|
||||
"grad_norm": 0.11852724105119705,
|
||||
"learning_rate": 1.8702852410301556e-05,
|
||||
"loss": 0.096,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.2952029520295203,
|
||||
"grad_norm": 0.056973058730363846,
|
||||
"learning_rate": 1.7998392447397197e-05,
|
||||
"loss": 0.0934,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.33210332103321033,
|
||||
"grad_norm": 0.09912875294685364,
|
||||
"learning_rate": 1.7161521883143936e-05,
|
||||
"loss": 0.085,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.36900369003690037,
|
||||
"grad_norm": 0.07187044620513916,
|
||||
"learning_rate": 1.6206094818274228e-05,
|
||||
"loss": 0.0839,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.4059040590405904,
|
||||
"grad_norm": 0.12322689592838287,
|
||||
"learning_rate": 1.5147928015098309e-05,
|
||||
"loss": 0.0793,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.44280442804428044,
|
||||
"grad_norm": 0.06790988892316818,
|
||||
"learning_rate": 1.4004539056512667e-05,
|
||||
"loss": 0.0789,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.4797047970479705,
|
||||
"grad_norm": 0.10258402675390244,
|
||||
"learning_rate": 1.2794856348516095e-05,
|
||||
"loss": 0.0728,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.5166051660516605,
|
||||
"grad_norm": 0.10938461869955063,
|
||||
"learning_rate": 1.153890576704062e-05,
|
||||
"loss": 0.07,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.5535055350553506,
|
||||
"grad_norm": 0.0713815838098526,
|
||||
"learning_rate": 1.0257479136549889e-05,
|
||||
"loss": 0.0634,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.5904059040590406,
|
||||
"grad_norm": 0.1400076448917389,
|
||||
"learning_rate": 8.971790028626395e-06,
|
||||
"loss": 0.063,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.6273062730627307,
|
||||
"grad_norm": 0.08636516332626343,
|
||||
"learning_rate": 7.703122578682047e-06,
|
||||
"loss": 0.0592,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.6642066420664207,
|
||||
"grad_norm": 0.12527909874916077,
|
||||
"learning_rate": 6.472479134509052e-06,
|
||||
"loss": 0.0599,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.7011070110701108,
|
||||
"grad_norm": 0.11907720565795898,
|
||||
"learning_rate": 5.300232569726805e-06,
|
||||
"loss": 0.0549,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.7380073800738007,
|
||||
"grad_norm": 0.129660964012146,
|
||||
"learning_rate": 4.205789017954364e-06,
|
||||
"loss": 0.0529,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.7749077490774908,
|
||||
"grad_norm": 0.11697438359260559,
|
||||
"learning_rate": 3.207266611027069e-06,
|
||||
"loss": 0.0536,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.8118081180811808,
|
||||
"grad_norm": 0.10215689241886139,
|
||||
"learning_rate": 2.3211955396340003e-06,
|
||||
"loss": 0.0468,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.8487084870848709,
|
||||
"grad_norm": 0.11825434118509293,
|
||||
"learning_rate": 1.5622444017681438e-06,
|
||||
"loss": 0.0534,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.8856088560885609,
|
||||
"grad_norm": 0.11656656116247177,
|
||||
"learning_rate": 9.42977369195286e-07,
|
||||
"loss": 0.0534,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.922509225092251,
|
||||
"grad_norm": 0.10192801058292389,
|
||||
"learning_rate": 4.73646191966175e-07,
|
||||
"loss": 0.0479,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.959409594095941,
|
||||
"grad_norm": 0.08949802815914154,
|
||||
"learning_rate": 1.6202048426483652e-07,
|
||||
"loss": 0.0491,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.996309963099631,
|
||||
"grad_norm": 0.0758034735918045,
|
||||
"learning_rate": 1.325910115169471e-08,
|
||||
"loss": 0.0455,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 136,
|
||||
"total_flos": 2.50613257277014e+17,
|
||||
"train_loss": 0.07390243510770447,
|
||||
"train_runtime": 1155.3856,
|
||||
"train_samples_per_second": 14.999,
|
||||
"train_steps_per_second": 0.118
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 136,
|
||||
"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": 2.50613257277014e+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:f82192ea3fd64aa8064f55625cbda8e42820a783c9c2796becc5c9f087a89c0a
|
||||
size 7416
|
||||
Reference in New Issue
Block a user