初始化项目，由ModelHub XC社区提供模型
Model: PARZ2344/web_llama_sft_random 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
|
||||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: meta-llama/Llama-3.2-3B-Instruct
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: apm_sft_random_llama
|
||||||
|
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. -->
|
||||||
|
|
||||||
|
# apm_sft_random_llama
|
||||||
|
|
||||||
|
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 deep_research_25 dataset.
|
||||||
|
|
||||||
|
## 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: 1e-05
|
||||||
|
- train_batch_size: 1
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- gradient_accumulation_steps: 8
|
||||||
|
- total_train_batch_size: 64
|
||||||
|
- total_eval_batch_size: 64
|
||||||
|
- 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: 3.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.52.4
|
||||||
|
- Pytorch 2.9.0+cu128
|
||||||
|
- Datasets 3.2.0
|
||||||
|
- Tokenizers 0.21.1
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"total_flos": 181229773520896.0,
|
||||||
|
"train_loss": 0.266992773216715,
|
||||||
|
"train_runtime": 3529.0775,
|
||||||
|
"train_samples_per_second": 16.577,
|
||||||
|
"train_steps_per_second": 0.259
|
||||||
|
}
|
||||||
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 %}
|
||||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"eos_token_id": [
|
||||||
|
128001,
|
||||||
|
128008,
|
||||||
|
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,
|
||||||
|
"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,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 128256
|
||||||
|
}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
128001,
|
||||||
|
128008,
|
||||||
|
128009
|
||||||
|
],
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_p": 0.9,
|
||||||
|
"transformers_version": "4.52.4"
|
||||||
|
}
|
||||||
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 sha256:65e7e7ca498a603c9864bf034f02abffb706dd1e71ad4855081d2ed63f34c8cb
|
||||||
|
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 sha256:504a677695dd37326c1a97e2fc641f79fe210ff73a10ecf1af07af48599f4c09
|
||||||
|
size 1459729952
|
||||||
261
model.safetensors.index.json
Normal file
261
model.safetensors.index.json
Normal file
@@ -0,0 +1,261 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 6425499648
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"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": 3.0,
|
||||||
|
"total_flos": 181229773520896.0,
|
||||||
|
"train_loss": 0.266992773216715,
|
||||||
|
"train_runtime": 3529.0775,
|
||||||
|
"train_samples_per_second": 16.577,
|
||||||
|
"train_steps_per_second": 0.259
|
||||||
|
}
|
||||||
32
trainer_log.jsonl
Normal file
32
trainer_log.jsonl
Normal file
@@ -0,0 +1,32 @@
|
|||||||
|
{"current_steps": 610, "total_steps": 915, "loss": 0.8327, "lr": 3.0403920675946826e-06, "epoch": 2.0032813781788352, "percentage": 66.67, "elapsed_time": "0:02:00", "remaining_time": "0:01:00"}
|
||||||
|
{"current_steps": 620, "total_steps": 915, "loss": 0.7782, "lr": 2.8662692339278387e-06, "epoch": 2.036095159967186, "percentage": 67.76, "elapsed_time": "0:03:54", "remaining_time": "0:01:51"}
|
||||||
|
{"current_steps": 630, "total_steps": 915, "loss": 0.7875, "lr": 2.6952551585633947e-06, "epoch": 2.0689089417555375, "percentage": 68.85, "elapsed_time": "0:05:30", "remaining_time": "0:02:29"}
|
||||||
|
{"current_steps": 640, "total_steps": 915, "loss": 0.7708, "lr": 2.52759900200232e-06, "epoch": 2.1017227235438884, "percentage": 69.95, "elapsed_time": "0:07:31", "remaining_time": "0:03:14"}
|
||||||
|
{"current_steps": 650, "total_steps": 915, "loss": 0.7927, "lr": 2.3635450323954773e-06, "epoch": 2.1345365053322394, "percentage": 71.04, "elapsed_time": "0:09:09", "remaining_time": "0:03:43"}
|
||||||
|
{"current_steps": 660, "total_steps": 915, "loss": 0.7885, "lr": 2.2033322696549197e-06, "epoch": 2.1673502871205907, "percentage": 72.13, "elapsed_time": "0:10:50", "remaining_time": "0:04:11"}
|
||||||
|
{"current_steps": 670, "total_steps": 915, "loss": 0.7626, "lr": 2.0471941372116793e-06, "epoch": 2.2001640689089417, "percentage": 73.22, "elapsed_time": "0:12:42", "remaining_time": "0:04:38"}
|
||||||
|
{"current_steps": 680, "total_steps": 915, "loss": 0.7754, "lr": 1.8953581219273987e-06, "epoch": 2.232977850697293, "percentage": 74.32, "elapsed_time": "0:14:33", "remaining_time": "0:05:01"}
|
||||||
|
{"current_steps": 690, "total_steps": 915, "loss": 0.7783, "lr": 1.7480454426552773e-06, "epoch": 2.265791632485644, "percentage": 75.41, "elapsed_time": "0:16:17", "remaining_time": "0:05:18"}
|
||||||
|
{"current_steps": 700, "total_steps": 915, "loss": 0.7705, "lr": 1.6054707279332865e-06, "epoch": 2.298605414273995, "percentage": 76.5, "elapsed_time": "0:18:15", "remaining_time": "0:05:36"}
|
||||||
|
{"current_steps": 710, "total_steps": 915, "loss": 0.7699, "lr": 1.4678417032791653e-06, "epoch": 2.3314191960623463, "percentage": 77.6, "elapsed_time": "0:19:52", "remaining_time": "0:05:44"}
|
||||||
|
{"current_steps": 720, "total_steps": 915, "loss": 0.7526, "lr": 1.335358888542862e-06, "epoch": 2.364232977850697, "percentage": 78.69, "elapsed_time": "0:21:39", "remaining_time": "0:05:51"}
|
||||||
|
{"current_steps": 730, "total_steps": 915, "loss": 0.7918, "lr": 1.20821530575733e-06, "epoch": 2.3970467596390486, "percentage": 79.78, "elapsed_time": "0:23:35", "remaining_time": "0:05:58"}
|
||||||
|
{"current_steps": 740, "total_steps": 915, "loss": 0.7815, "lr": 1.0865961979133245e-06, "epoch": 2.4298605414273995, "percentage": 80.87, "elapsed_time": "0:25:10", "remaining_time": "0:05:57"}
|
||||||
|
{"current_steps": 750, "total_steps": 915, "loss": 0.7731, "lr": 9.706787590679685e-07, "epoch": 2.462674323215751, "percentage": 81.97, "elapsed_time": "0:26:39", "remaining_time": "0:05:51"}
|
||||||
|
{"current_steps": 760, "total_steps": 915, "loss": 0.7666, "lr": 8.606318761802584e-07, "epoch": 2.495488105004102, "percentage": 83.06, "elapsed_time": "0:28:16", "remaining_time": "0:05:45"}
|
||||||
|
{"current_steps": 770, "total_steps": 915, "loss": 0.7657, "lr": 7.566158830496917e-07, "epoch": 2.5283018867924527, "percentage": 84.15, "elapsed_time": "0:29:58", "remaining_time": "0:05:38"}
|
||||||
|
{"current_steps": 780, "total_steps": 915, "loss": 0.7798, "lr": 6.587823267164911e-07, "epoch": 2.561115668580804, "percentage": 85.25, "elapsed_time": "0:31:27", "remaining_time": "0:05:26"}
|
||||||
|
{"current_steps": 790, "total_steps": 915, "loss": 0.7816, "lr": 5.672737466637701e-07, "epoch": 2.593929450369155, "percentage": 86.34, "elapsed_time": "0:33:28", "remaining_time": "0:05:17"}
|
||||||
|
{"current_steps": 800, "total_steps": 915, "loss": 0.7837, "lr": 4.822234671433552e-07, "epoch": 2.626743232157506, "percentage": 87.43, "elapsed_time": "0:35:41", "remaining_time": "0:05:07"}
|
||||||
|
{"current_steps": 810, "total_steps": 915, "loss": 0.7747, "lr": 4.03755402927804e-07, "epoch": 2.6595570139458573, "percentage": 88.52, "elapsed_time": "0:39:29", "remaining_time": "0:05:07"}
|
||||||
|
{"current_steps": 820, "total_steps": 915, "loss": 0.7793, "lr": 3.319838787716634e-07, "epoch": 2.6923707957342082, "percentage": 89.62, "elapsed_time": "0:41:31", "remaining_time": "0:04:48"}
|
||||||
|
{"current_steps": 830, "total_steps": 915, "loss": 0.7542, "lr": 2.6701346284499e-07, "epoch": 2.7251845775225596, "percentage": 90.71, "elapsed_time": "0:43:29", "remaining_time": "0:04:27"}
|
||||||
|
{"current_steps": 840, "total_steps": 915, "loss": 0.7844, "lr": 2.0893881438180275e-07, "epoch": 2.7579983593109105, "percentage": 91.8, "elapsed_time": "0:45:26", "remaining_time": "0:04:03"}
|
||||||
|
{"current_steps": 850, "total_steps": 915, "loss": 0.7643, "lr": 1.578445457654637e-07, "epoch": 2.790812141099262, "percentage": 92.9, "elapsed_time": "0:47:15", "remaining_time": "0:03:36"}
|
||||||
|
{"current_steps": 860, "total_steps": 915, "loss": 0.7673, "lr": 1.1380509925189853e-07, "epoch": 2.823625922887613, "percentage": 93.99, "elapsed_time": "0:49:01", "remaining_time": "0:03:08"}
|
||||||
|
{"current_steps": 870, "total_steps": 915, "loss": 0.769, "lr": 7.688463851028227e-08, "epoch": 2.8564397046759638, "percentage": 95.08, "elapsed_time": "0:51:01", "remaining_time": "0:02:38"}
|
||||||
|
{"current_steps": 880, "total_steps": 915, "loss": 0.7799, "lr": 4.713695513920147e-08, "epoch": 2.889253486464315, "percentage": 96.17, "elapsed_time": "0:52:45", "remaining_time": "0:02:05"}
|
||||||
|
{"current_steps": 890, "total_steps": 915, "loss": 0.785, "lr": 2.4605390294497043e-08, "epoch": 2.922067268252666, "percentage": 97.27, "elapsed_time": "0:54:45", "remaining_time": "0:01:32"}
|
||||||
|
{"current_steps": 900, "total_steps": 915, "loss": 0.7753, "lr": 9.322771542978892e-09, "epoch": 2.954881050041017, "percentage": 98.36, "elapsed_time": "0:56:44", "remaining_time": "0:00:56"}
|
||||||
|
{"current_steps": 910, "total_steps": 915, "loss": 0.7911, "lr": 1.3113650340046413e-09, "epoch": 2.9876948318293683, "percentage": 99.45, "elapsed_time": "0:58:10", "remaining_time": "0:00:19"}
|
||||||
|
{"current_steps": 914, "total_steps": 915, "epoch": 3.0, "percentage": 99.89, "elapsed_time": "0:58:47", "remaining_time": "0:00:03"}
|
||||||
680
trainer_state.json
Normal file
680
trainer_state.json
Normal file
@@ -0,0 +1,680 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 3.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 914,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.03281378178835111,
|
||||||
|
"grad_norm": 7.324607115951123,
|
||||||
|
"learning_rate": 9.782608695652175e-07,
|
||||||
|
"loss": 1.6507,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06562756357670221,
|
||||||
|
"grad_norm": 2.6718330452258137,
|
||||||
|
"learning_rate": 2.065217391304348e-06,
|
||||||
|
"loss": 1.5293,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09844134536505332,
|
||||||
|
"grad_norm": 2.0449760430297435,
|
||||||
|
"learning_rate": 3.152173913043479e-06,
|
||||||
|
"loss": 1.3882,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13125512715340443,
|
||||||
|
"grad_norm": 1.7054134520698259,
|
||||||
|
"learning_rate": 4.239130434782609e-06,
|
||||||
|
"loss": 1.3212,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16406890894175555,
|
||||||
|
"grad_norm": 1.5625383091861629,
|
||||||
|
"learning_rate": 5.3260869565217395e-06,
|
||||||
|
"loss": 1.2339,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.19688269073010664,
|
||||||
|
"grad_norm": 1.5467201317331245,
|
||||||
|
"learning_rate": 6.41304347826087e-06,
|
||||||
|
"loss": 1.2209,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22969647251845776,
|
||||||
|
"grad_norm": 1.5441409779630197,
|
||||||
|
"learning_rate": 7.500000000000001e-06,
|
||||||
|
"loss": 1.1981,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26251025430680885,
|
||||||
|
"grad_norm": 1.5810387088382716,
|
||||||
|
"learning_rate": 8.586956521739131e-06,
|
||||||
|
"loss": 1.1633,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.29532403609515995,
|
||||||
|
"grad_norm": 1.4632034044381061,
|
||||||
|
"learning_rate": 9.673913043478262e-06,
|
||||||
|
"loss": 1.1815,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3281378178835111,
|
||||||
|
"grad_norm": 1.6769268374195203,
|
||||||
|
"learning_rate": 9.998215114657564e-06,
|
||||||
|
"loss": 1.1741,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3609515996718622,
|
||||||
|
"grad_norm": 1.564606037108119,
|
||||||
|
"learning_rate": 9.98947588668843e-06,
|
||||||
|
"loss": 1.13,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3937653814602133,
|
||||||
|
"grad_norm": 1.4659283460430306,
|
||||||
|
"learning_rate": 9.973467196782484e-06,
|
||||||
|
"loss": 1.1339,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4265791632485644,
|
||||||
|
"grad_norm": 1.3900414131292986,
|
||||||
|
"learning_rate": 9.950212368945013e-06,
|
||||||
|
"loss": 1.1501,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4593929450369155,
|
||||||
|
"grad_norm": 1.533573901481892,
|
||||||
|
"learning_rate": 9.91974528450737e-06,
|
||||||
|
"loss": 1.1374,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4922067268252666,
|
||||||
|
"grad_norm": 1.4930324222767686,
|
||||||
|
"learning_rate": 9.882110332763275e-06,
|
||||||
|
"loss": 1.1316,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5250205086136177,
|
||||||
|
"grad_norm": 1.4649309232116048,
|
||||||
|
"learning_rate": 9.83736234629543e-06,
|
||||||
|
"loss": 1.1199,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5578342904019689,
|
||||||
|
"grad_norm": 1.4519140933698538,
|
||||||
|
"learning_rate": 9.785566521086695e-06,
|
||||||
|
"loss": 1.1163,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5906480721903199,
|
||||||
|
"grad_norm": 1.4591675768161227,
|
||||||
|
"learning_rate": 9.726798321532205e-06,
|
||||||
|
"loss": 1.125,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.623461853978671,
|
||||||
|
"grad_norm": 1.3084115670512635,
|
||||||
|
"learning_rate": 9.661143370490846e-06,
|
||||||
|
"loss": 1.1385,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6562756357670222,
|
||||||
|
"grad_norm": 1.428698415469623,
|
||||||
|
"learning_rate": 9.588697324536254e-06,
|
||||||
|
"loss": 1.0995,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6890894175553732,
|
||||||
|
"grad_norm": 1.3195726786177668,
|
||||||
|
"learning_rate": 9.509565734589105e-06,
|
||||||
|
"loss": 1.105,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7219031993437244,
|
||||||
|
"grad_norm": 1.4644538779508807,
|
||||||
|
"learning_rate": 9.423863892133754e-06,
|
||||||
|
"loss": 1.0949,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7547169811320755,
|
||||||
|
"grad_norm": 1.4442654685795682,
|
||||||
|
"learning_rate": 9.33171666124326e-06,
|
||||||
|
"loss": 1.1097,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7875307629204266,
|
||||||
|
"grad_norm": 1.4628666514015816,
|
||||||
|
"learning_rate": 9.233258296657547e-06,
|
||||||
|
"loss": 1.0915,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8203445447087777,
|
||||||
|
"grad_norm": 1.4584300507718668,
|
||||||
|
"learning_rate": 9.128632248179761e-06,
|
||||||
|
"loss": 1.0952,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8531583264971287,
|
||||||
|
"grad_norm": 1.3907705989649481,
|
||||||
|
"learning_rate": 9.017990951675764e-06,
|
||||||
|
"loss": 1.1072,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8859721082854799,
|
||||||
|
"grad_norm": 1.44611189547518,
|
||||||
|
"learning_rate": 8.901495606981339e-06,
|
||||||
|
"loss": 1.0908,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.918785890073831,
|
||||||
|
"grad_norm": 1.4283544277374125,
|
||||||
|
"learning_rate": 8.779315943040629e-06,
|
||||||
|
"loss": 1.0934,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9515996718621821,
|
||||||
|
"grad_norm": 1.3679340439375278,
|
||||||
|
"learning_rate": 8.65162997061802e-06,
|
||||||
|
"loss": 1.0902,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9844134536505332,
|
||||||
|
"grad_norm": 1.4053097778093493,
|
||||||
|
"learning_rate": 8.518623722943747e-06,
|
||||||
|
"loss": 1.0826,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0164068908941755,
|
||||||
|
"grad_norm": 1.358051135209502,
|
||||||
|
"learning_rate": 8.380490984671105e-06,
|
||||||
|
"loss": 1.0004,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0492206726825266,
|
||||||
|
"grad_norm": 1.4920803109368017,
|
||||||
|
"learning_rate": 8.23743300954015e-06,
|
||||||
|
"loss": 0.9529,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0820344544708778,
|
||||||
|
"grad_norm": 1.391421362612517,
|
||||||
|
"learning_rate": 8.089658227159239e-06,
|
||||||
|
"loss": 0.9108,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.114848236259229,
|
||||||
|
"grad_norm": 1.6241278760522855,
|
||||||
|
"learning_rate": 7.937381939331628e-06,
|
||||||
|
"loss": 0.9279,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.14766201804758,
|
||||||
|
"grad_norm": 1.4776439598223472,
|
||||||
|
"learning_rate": 7.780826006369586e-06,
|
||||||
|
"loss": 0.9332,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1804757998359312,
|
||||||
|
"grad_norm": 1.531082298396227,
|
||||||
|
"learning_rate": 7.620218523852987e-06,
|
||||||
|
"loss": 0.9503,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2132895816242821,
|
||||||
|
"grad_norm": 1.4148212125540105,
|
||||||
|
"learning_rate": 7.4557934903034035e-06,
|
||||||
|
"loss": 0.9409,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2461033634126333,
|
||||||
|
"grad_norm": 1.569873004540387,
|
||||||
|
"learning_rate": 7.287790466257854e-06,
|
||||||
|
"loss": 0.9228,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2789171452009844,
|
||||||
|
"grad_norm": 1.50216408338208,
|
||||||
|
"learning_rate": 7.116454225238909e-06,
|
||||||
|
"loss": 0.9354,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3117309269893356,
|
||||||
|
"grad_norm": 1.4646843748186438,
|
||||||
|
"learning_rate": 6.942034397129702e-06,
|
||||||
|
"loss": 0.9372,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3445447087776867,
|
||||||
|
"grad_norm": 1.5763941611606018,
|
||||||
|
"learning_rate": 6.764785104473411e-06,
|
||||||
|
"loss": 0.9169,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3773584905660377,
|
||||||
|
"grad_norm": 1.4076340592270304,
|
||||||
|
"learning_rate": 6.584964592227135e-06,
|
||||||
|
"loss": 0.9235,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4101722723543888,
|
||||||
|
"grad_norm": 1.5649588493962718,
|
||||||
|
"learning_rate": 6.402834851509564e-06,
|
||||||
|
"loss": 0.926,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.44298605414274,
|
||||||
|
"grad_norm": 1.370995330259522,
|
||||||
|
"learning_rate": 6.2186612378906545e-06,
|
||||||
|
"loss": 0.9327,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.475799835931091,
|
||||||
|
"grad_norm": 1.4405579132350896,
|
||||||
|
"learning_rate": 6.0327120847794415e-06,
|
||||||
|
"loss": 0.9461,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5086136177194422,
|
||||||
|
"grad_norm": 1.5139954304026377,
|
||||||
|
"learning_rate": 5.845258312473252e-06,
|
||||||
|
"loss": 0.9479,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5414273995077932,
|
||||||
|
"grad_norm": 1.5381263145609851,
|
||||||
|
"learning_rate": 5.656573033437932e-06,
|
||||||
|
"loss": 0.9217,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5742411812961445,
|
||||||
|
"grad_norm": 1.5176651174503644,
|
||||||
|
"learning_rate": 5.466931154394171e-06,
|
||||||
|
"loss": 0.9402,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6070549630844955,
|
||||||
|
"grad_norm": 1.64200137668156,
|
||||||
|
"learning_rate": 5.276608975789683e-06,
|
||||||
|
"loss": 0.925,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6398687448728466,
|
||||||
|
"grad_norm": 1.4813527495999301,
|
||||||
|
"learning_rate": 5.085883789240764e-06,
|
||||||
|
"loss": 0.9268,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6726825266611978,
|
||||||
|
"grad_norm": 1.5116269108263887,
|
||||||
|
"learning_rate": 4.8950334735297746e-06,
|
||||||
|
"loss": 0.9095,
|
||||||
|
"step": 510
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7054963084495487,
|
||||||
|
"grad_norm": 1.4490396822436944,
|
||||||
|
"learning_rate": 4.704336089747135e-06,
|
||||||
|
"loss": 0.9341,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7383100902379,
|
||||||
|
"grad_norm": 1.5628125198488163,
|
||||||
|
"learning_rate": 4.514069476167716e-06,
|
||||||
|
"loss": 0.932,
|
||||||
|
"step": 530
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.771123872026251,
|
||||||
|
"grad_norm": 1.4687886059027409,
|
||||||
|
"learning_rate": 4.324510843451851e-06,
|
||||||
|
"loss": 0.9311,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8039376538146021,
|
||||||
|
"grad_norm": 1.5227999474981233,
|
||||||
|
"learning_rate": 4.135936370760759e-06,
|
||||||
|
"loss": 0.9046,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8367514356029533,
|
||||||
|
"grad_norm": 1.4388610554454382,
|
||||||
|
"learning_rate": 3.9486208033748315e-06,
|
||||||
|
"loss": 0.9378,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8695652173913042,
|
||||||
|
"grad_norm": 1.3581055291483148,
|
||||||
|
"learning_rate": 3.762837052401004e-06,
|
||||||
|
"loss": 0.9235,
|
||||||
|
"step": 570
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9023789991796556,
|
||||||
|
"grad_norm": 1.5099266943158,
|
||||||
|
"learning_rate": 3.5788557971524695e-06,
|
||||||
|
"loss": 0.9444,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9351927809680065,
|
||||||
|
"grad_norm": 1.5169803759126903,
|
||||||
|
"learning_rate": 3.3969450907799966e-06,
|
||||||
|
"loss": 0.9279,
|
||||||
|
"step": 590
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9680065627563577,
|
||||||
|
"grad_norm": 1.3979513991441848,
|
||||||
|
"learning_rate": 3.217369969729476e-06,
|
||||||
|
"loss": 0.9115,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0032813781788352,
|
||||||
|
"grad_norm": 2.105088244846462,
|
||||||
|
"learning_rate": 3.0403920675946826e-06,
|
||||||
|
"loss": 0.8327,
|
||||||
|
"step": 610
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.036095159967186,
|
||||||
|
"grad_norm": 1.6690335971877808,
|
||||||
|
"learning_rate": 2.8662692339278387e-06,
|
||||||
|
"loss": 0.7782,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0689089417555375,
|
||||||
|
"grad_norm": 1.705302067748598,
|
||||||
|
"learning_rate": 2.6952551585633947e-06,
|
||||||
|
"loss": 0.7875,
|
||||||
|
"step": 630
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.1017227235438884,
|
||||||
|
"grad_norm": 1.6066988675182772,
|
||||||
|
"learning_rate": 2.52759900200232e-06,
|
||||||
|
"loss": 0.7708,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.1345365053322394,
|
||||||
|
"grad_norm": 1.5203406830167119,
|
||||||
|
"learning_rate": 2.3635450323954773e-06,
|
||||||
|
"loss": 0.7927,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.1673502871205907,
|
||||||
|
"grad_norm": 1.626389642459301,
|
||||||
|
"learning_rate": 2.2033322696549197e-06,
|
||||||
|
"loss": 0.7885,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2001640689089417,
|
||||||
|
"grad_norm": 1.7664606984797573,
|
||||||
|
"learning_rate": 2.0471941372116793e-06,
|
||||||
|
"loss": 0.7626,
|
||||||
|
"step": 670
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.232977850697293,
|
||||||
|
"grad_norm": 1.5793686740276833,
|
||||||
|
"learning_rate": 1.8953581219273987e-06,
|
||||||
|
"loss": 0.7754,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.265791632485644,
|
||||||
|
"grad_norm": 1.6724958298486645,
|
||||||
|
"learning_rate": 1.7480454426552773e-06,
|
||||||
|
"loss": 0.7783,
|
||||||
|
"step": 690
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.298605414273995,
|
||||||
|
"grad_norm": 1.5819324740235794,
|
||||||
|
"learning_rate": 1.6054707279332865e-06,
|
||||||
|
"loss": 0.7705,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.3314191960623463,
|
||||||
|
"grad_norm": 1.6323457128335996,
|
||||||
|
"learning_rate": 1.4678417032791653e-06,
|
||||||
|
"loss": 0.7699,
|
||||||
|
"step": 710
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.364232977850697,
|
||||||
|
"grad_norm": 1.7857816578985155,
|
||||||
|
"learning_rate": 1.335358888542862e-06,
|
||||||
|
"loss": 0.7526,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.3970467596390486,
|
||||||
|
"grad_norm": 1.5935449756290072,
|
||||||
|
"learning_rate": 1.20821530575733e-06,
|
||||||
|
"loss": 0.7918,
|
||||||
|
"step": 730
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4298605414273995,
|
||||||
|
"grad_norm": 1.693473193818772,
|
||||||
|
"learning_rate": 1.0865961979133245e-06,
|
||||||
|
"loss": 0.7815,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.462674323215751,
|
||||||
|
"grad_norm": 1.6977380314021282,
|
||||||
|
"learning_rate": 9.706787590679685e-07,
|
||||||
|
"loss": 0.7731,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.495488105004102,
|
||||||
|
"grad_norm": 1.701374033891568,
|
||||||
|
"learning_rate": 8.606318761802584e-07,
|
||||||
|
"loss": 0.7666,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5283018867924527,
|
||||||
|
"grad_norm": 1.8239897351347403,
|
||||||
|
"learning_rate": 7.566158830496917e-07,
|
||||||
|
"loss": 0.7657,
|
||||||
|
"step": 770
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.561115668580804,
|
||||||
|
"grad_norm": 1.7594557186973525,
|
||||||
|
"learning_rate": 6.587823267164911e-07,
|
||||||
|
"loss": 0.7798,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.593929450369155,
|
||||||
|
"grad_norm": 1.6074400677010736,
|
||||||
|
"learning_rate": 5.672737466637701e-07,
|
||||||
|
"loss": 0.7816,
|
||||||
|
"step": 790
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.626743232157506,
|
||||||
|
"grad_norm": 1.589497024974972,
|
||||||
|
"learning_rate": 4.822234671433552e-07,
|
||||||
|
"loss": 0.7837,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.6595570139458573,
|
||||||
|
"grad_norm": 1.5745731469005892,
|
||||||
|
"learning_rate": 4.03755402927804e-07,
|
||||||
|
"loss": 0.7747,
|
||||||
|
"step": 810
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.6923707957342082,
|
||||||
|
"grad_norm": 1.6156048098137663,
|
||||||
|
"learning_rate": 3.319838787716634e-07,
|
||||||
|
"loss": 0.7793,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7251845775225596,
|
||||||
|
"grad_norm": 1.6695478870964964,
|
||||||
|
"learning_rate": 2.6701346284499e-07,
|
||||||
|
"loss": 0.7542,
|
||||||
|
"step": 830
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7579983593109105,
|
||||||
|
"grad_norm": 1.5107440160015784,
|
||||||
|
"learning_rate": 2.0893881438180275e-07,
|
||||||
|
"loss": 0.7844,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.790812141099262,
|
||||||
|
"grad_norm": 1.6477028499246302,
|
||||||
|
"learning_rate": 1.578445457654637e-07,
|
||||||
|
"loss": 0.7643,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.823625922887613,
|
||||||
|
"grad_norm": 1.5854989560185238,
|
||||||
|
"learning_rate": 1.1380509925189853e-07,
|
||||||
|
"loss": 0.7673,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.8564397046759638,
|
||||||
|
"grad_norm": 1.6787763051906506,
|
||||||
|
"learning_rate": 7.688463851028227e-08,
|
||||||
|
"loss": 0.769,
|
||||||
|
"step": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.889253486464315,
|
||||||
|
"grad_norm": 1.581911801204859,
|
||||||
|
"learning_rate": 4.713695513920147e-08,
|
||||||
|
"loss": 0.7799,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.922067268252666,
|
||||||
|
"grad_norm": 1.697466745242019,
|
||||||
|
"learning_rate": 2.4605390294497043e-08,
|
||||||
|
"loss": 0.785,
|
||||||
|
"step": 890
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.954881050041017,
|
||||||
|
"grad_norm": 1.6425019567953216,
|
||||||
|
"learning_rate": 9.322771542978892e-09,
|
||||||
|
"loss": 0.7753,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.9876948318293683,
|
||||||
|
"grad_norm": 1.5783466963735138,
|
||||||
|
"learning_rate": 1.3113650340046413e-09,
|
||||||
|
"loss": 0.7911,
|
||||||
|
"step": 910
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"step": 914,
|
||||||
|
"total_flos": 181229773520896.0,
|
||||||
|
"train_loss": 0.266992773216715,
|
||||||
|
"train_runtime": 3529.0775,
|
||||||
|
"train_samples_per_second": 16.577,
|
||||||
|
"train_steps_per_second": 0.259
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 915,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"save_steps": 200,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 181229773520896.0,
|
||||||
|
"train_batch_size": 1,
|
||||||
|
"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 sha256:90dd3d267d14dbdca9eafe6602aba67e5bbe51012a9cccf660a487fae7628844
|
||||||
|
size 8017
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 36 KiB |
Reference in New Issue
Block a user