Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +54 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- trainer_state.json +806 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 896,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4864,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"max_window_layers": 21,
|
| 40 |
+
"model_type": "qwen2",
|
| 41 |
+
"num_attention_heads": 14,
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_key_value_heads": 2,
|
| 44 |
+
"pad_token_id": 151645,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 1000000.0,
|
| 48 |
+
"sliding_window": null,
|
| 49 |
+
"tie_word_embeddings": true,
|
| 50 |
+
"transformers_version": "4.57.3",
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"use_sliding_window": false,
|
| 53 |
+
"vocab_size": 151665
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151645,
|
| 8 |
+
"repetition_penalty": 1.1,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:256e776cff22c519100403fdb51e1142cd0aa9a8af9d31b206fee39dd6226498
|
| 3 |
+
size 987612192
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:745dd923bbcb86f516d2160050c31f111ccac5c4620122246d9b8b3efe8fbfec
|
| 3 |
+
size 3308683
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad51b10e839112e76a728f9dcce3122120c8a10612b9b186c929a95fd591904
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:509bd3134e4947f4afaf7db6bed237bcb042e30753702e1eab884acf6408662e
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|im_end|>"
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|im_end|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,806 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 750,
|
| 3 |
+
"best_metric": 0.26988574862480164,
|
| 4 |
+
"best_model_checkpoint": "models/qwen-0.5b-distilled/checkpoint-750",
|
| 5 |
+
"epoch": 0.9829619921363041,
|
| 6 |
+
"eval_steps": 25,
|
| 7 |
+
"global_step": 750,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001310615989515072,
|
| 14 |
+
"grad_norm": 9.375,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.548,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01310615989515072,
|
| 21 |
+
"grad_norm": 6.375,
|
| 22 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 23 |
+
"loss": 0.43,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02621231979030144,
|
| 28 |
+
"grad_norm": 9.25,
|
| 29 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 30 |
+
"loss": 0.4675,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0327653997378768,
|
| 35 |
+
"eval_loss": 0.4063957631587982,
|
| 36 |
+
"eval_runtime": 4.2148,
|
| 37 |
+
"eval_samples_per_second": 7.355,
|
| 38 |
+
"eval_steps_per_second": 0.949,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.039318479685452164,
|
| 43 |
+
"grad_norm": 4.84375,
|
| 44 |
+
"learning_rate": 5.8e-06,
|
| 45 |
+
"loss": 0.3877,
|
| 46 |
+
"step": 30
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.05242463958060288,
|
| 50 |
+
"grad_norm": 5.125,
|
| 51 |
+
"learning_rate": 7.800000000000002e-06,
|
| 52 |
+
"loss": 0.3403,
|
| 53 |
+
"step": 40
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.0655307994757536,
|
| 57 |
+
"grad_norm": 6.375,
|
| 58 |
+
"learning_rate": 9.800000000000001e-06,
|
| 59 |
+
"loss": 0.3379,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0655307994757536,
|
| 64 |
+
"eval_loss": 0.3531549572944641,
|
| 65 |
+
"eval_runtime": 3.6193,
|
| 66 |
+
"eval_samples_per_second": 8.565,
|
| 67 |
+
"eval_steps_per_second": 1.105,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.07863695937090433,
|
| 72 |
+
"grad_norm": 4.75,
|
| 73 |
+
"learning_rate": 1.18e-05,
|
| 74 |
+
"loss": 0.3865,
|
| 75 |
+
"step": 60
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.09174311926605505,
|
| 79 |
+
"grad_norm": 5.34375,
|
| 80 |
+
"learning_rate": 1.38e-05,
|
| 81 |
+
"loss": 0.3487,
|
| 82 |
+
"step": 70
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0982961992136304,
|
| 86 |
+
"eval_loss": 0.3395631015300751,
|
| 87 |
+
"eval_runtime": 3.6271,
|
| 88 |
+
"eval_samples_per_second": 8.547,
|
| 89 |
+
"eval_steps_per_second": 1.103,
|
| 90 |
+
"step": 75
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.10484927916120576,
|
| 94 |
+
"grad_norm": 4.1875,
|
| 95 |
+
"learning_rate": 1.58e-05,
|
| 96 |
+
"loss": 0.3037,
|
| 97 |
+
"step": 80
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.11795543905635648,
|
| 101 |
+
"grad_norm": 7.46875,
|
| 102 |
+
"learning_rate": 1.7800000000000002e-05,
|
| 103 |
+
"loss": 0.3588,
|
| 104 |
+
"step": 90
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1310615989515072,
|
| 108 |
+
"grad_norm": 5.9375,
|
| 109 |
+
"learning_rate": 1.98e-05,
|
| 110 |
+
"loss": 0.3423,
|
| 111 |
+
"step": 100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1310615989515072,
|
| 115 |
+
"eval_loss": 0.3489256501197815,
|
| 116 |
+
"eval_runtime": 3.6228,
|
| 117 |
+
"eval_samples_per_second": 8.557,
|
| 118 |
+
"eval_steps_per_second": 1.104,
|
| 119 |
+
"step": 100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.14416775884665792,
|
| 123 |
+
"grad_norm": 5.65625,
|
| 124 |
+
"learning_rate": 1.9873772791023845e-05,
|
| 125 |
+
"loss": 0.344,
|
| 126 |
+
"step": 110
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.15727391874180865,
|
| 130 |
+
"grad_norm": 6.71875,
|
| 131 |
+
"learning_rate": 1.973352033660589e-05,
|
| 132 |
+
"loss": 0.3335,
|
| 133 |
+
"step": 120
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.16382699868938402,
|
| 137 |
+
"eval_loss": 0.32981202006340027,
|
| 138 |
+
"eval_runtime": 3.631,
|
| 139 |
+
"eval_samples_per_second": 8.538,
|
| 140 |
+
"eval_steps_per_second": 1.102,
|
| 141 |
+
"step": 125
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.17038007863695936,
|
| 145 |
+
"grad_norm": 4.25,
|
| 146 |
+
"learning_rate": 1.959326788218794e-05,
|
| 147 |
+
"loss": 0.3455,
|
| 148 |
+
"step": 130
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.1834862385321101,
|
| 152 |
+
"grad_norm": 4.40625,
|
| 153 |
+
"learning_rate": 1.9453015427769988e-05,
|
| 154 |
+
"loss": 0.3583,
|
| 155 |
+
"step": 140
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.1965923984272608,
|
| 159 |
+
"grad_norm": 8.5625,
|
| 160 |
+
"learning_rate": 1.9312762973352036e-05,
|
| 161 |
+
"loss": 0.3583,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.1965923984272608,
|
| 166 |
+
"eval_loss": 0.32496821880340576,
|
| 167 |
+
"eval_runtime": 3.6332,
|
| 168 |
+
"eval_samples_per_second": 8.532,
|
| 169 |
+
"eval_steps_per_second": 1.101,
|
| 170 |
+
"step": 150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.20969855832241152,
|
| 174 |
+
"grad_norm": 3.921875,
|
| 175 |
+
"learning_rate": 1.9172510518934082e-05,
|
| 176 |
+
"loss": 0.3653,
|
| 177 |
+
"step": 160
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.22280471821756226,
|
| 181 |
+
"grad_norm": 5.96875,
|
| 182 |
+
"learning_rate": 1.903225806451613e-05,
|
| 183 |
+
"loss": 0.3176,
|
| 184 |
+
"step": 170
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.22935779816513763,
|
| 188 |
+
"eval_loss": 0.31902241706848145,
|
| 189 |
+
"eval_runtime": 3.6232,
|
| 190 |
+
"eval_samples_per_second": 8.556,
|
| 191 |
+
"eval_steps_per_second": 1.104,
|
| 192 |
+
"step": 175
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.23591087811271297,
|
| 196 |
+
"grad_norm": 5.0625,
|
| 197 |
+
"learning_rate": 1.889200561009818e-05,
|
| 198 |
+
"loss": 0.3316,
|
| 199 |
+
"step": 180
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2490170380078637,
|
| 203 |
+
"grad_norm": 5.03125,
|
| 204 |
+
"learning_rate": 1.8751753155680224e-05,
|
| 205 |
+
"loss": 0.3265,
|
| 206 |
+
"step": 190
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2621231979030144,
|
| 210 |
+
"grad_norm": 4.1875,
|
| 211 |
+
"learning_rate": 1.8611500701262273e-05,
|
| 212 |
+
"loss": 0.3195,
|
| 213 |
+
"step": 200
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2621231979030144,
|
| 217 |
+
"eval_loss": 0.314563125371933,
|
| 218 |
+
"eval_runtime": 3.6254,
|
| 219 |
+
"eval_samples_per_second": 8.551,
|
| 220 |
+
"eval_steps_per_second": 1.103,
|
| 221 |
+
"step": 200
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.27522935779816515,
|
| 225 |
+
"grad_norm": 4.6875,
|
| 226 |
+
"learning_rate": 1.8471248246844322e-05,
|
| 227 |
+
"loss": 0.3281,
|
| 228 |
+
"step": 210
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.28833551769331583,
|
| 232 |
+
"grad_norm": 3.421875,
|
| 233 |
+
"learning_rate": 1.833099579242637e-05,
|
| 234 |
+
"loss": 0.2814,
|
| 235 |
+
"step": 220
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.2948885976408912,
|
| 239 |
+
"eval_loss": 0.3087914288043976,
|
| 240 |
+
"eval_runtime": 3.6237,
|
| 241 |
+
"eval_samples_per_second": 8.555,
|
| 242 |
+
"eval_steps_per_second": 1.104,
|
| 243 |
+
"step": 225
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.30144167758846657,
|
| 247 |
+
"grad_norm": 3.734375,
|
| 248 |
+
"learning_rate": 1.8190743338008416e-05,
|
| 249 |
+
"loss": 0.3419,
|
| 250 |
+
"step": 230
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3145478374836173,
|
| 254 |
+
"grad_norm": 6.28125,
|
| 255 |
+
"learning_rate": 1.8050490883590464e-05,
|
| 256 |
+
"loss": 0.3428,
|
| 257 |
+
"step": 240
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.32765399737876805,
|
| 261 |
+
"grad_norm": 6.28125,
|
| 262 |
+
"learning_rate": 1.7910238429172513e-05,
|
| 263 |
+
"loss": 0.3723,
|
| 264 |
+
"step": 250
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.32765399737876805,
|
| 268 |
+
"eval_loss": 0.31134819984436035,
|
| 269 |
+
"eval_runtime": 3.6258,
|
| 270 |
+
"eval_samples_per_second": 8.55,
|
| 271 |
+
"eval_steps_per_second": 1.103,
|
| 272 |
+
"step": 250
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.34076015727391873,
|
| 276 |
+
"grad_norm": 6.96875,
|
| 277 |
+
"learning_rate": 1.776998597475456e-05,
|
| 278 |
+
"loss": 0.3545,
|
| 279 |
+
"step": 260
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.35386631716906947,
|
| 283 |
+
"grad_norm": 5.375,
|
| 284 |
+
"learning_rate": 1.7629733520336607e-05,
|
| 285 |
+
"loss": 0.3441,
|
| 286 |
+
"step": 270
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.36041939711664484,
|
| 290 |
+
"eval_loss": 0.30370065569877625,
|
| 291 |
+
"eval_runtime": 3.6249,
|
| 292 |
+
"eval_samples_per_second": 8.552,
|
| 293 |
+
"eval_steps_per_second": 1.103,
|
| 294 |
+
"step": 275
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.3669724770642202,
|
| 298 |
+
"grad_norm": 4.5625,
|
| 299 |
+
"learning_rate": 1.7489481065918656e-05,
|
| 300 |
+
"loss": 0.3107,
|
| 301 |
+
"step": 280
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.3800786369593709,
|
| 305 |
+
"grad_norm": 3.203125,
|
| 306 |
+
"learning_rate": 1.7349228611500704e-05,
|
| 307 |
+
"loss": 0.2933,
|
| 308 |
+
"step": 290
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3931847968545216,
|
| 312 |
+
"grad_norm": 3.75,
|
| 313 |
+
"learning_rate": 1.720897615708275e-05,
|
| 314 |
+
"loss": 0.291,
|
| 315 |
+
"step": 300
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.3931847968545216,
|
| 319 |
+
"eval_loss": 0.30050498247146606,
|
| 320 |
+
"eval_runtime": 3.6252,
|
| 321 |
+
"eval_samples_per_second": 8.551,
|
| 322 |
+
"eval_steps_per_second": 1.103,
|
| 323 |
+
"step": 300
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.40629095674967236,
|
| 327 |
+
"grad_norm": 4.125,
|
| 328 |
+
"learning_rate": 1.70687237026648e-05,
|
| 329 |
+
"loss": 0.3167,
|
| 330 |
+
"step": 310
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.41939711664482304,
|
| 334 |
+
"grad_norm": 4.90625,
|
| 335 |
+
"learning_rate": 1.6928471248246844e-05,
|
| 336 |
+
"loss": 0.3104,
|
| 337 |
+
"step": 320
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.4259501965923984,
|
| 341 |
+
"eval_loss": 0.2980906069278717,
|
| 342 |
+
"eval_runtime": 3.6274,
|
| 343 |
+
"eval_samples_per_second": 8.546,
|
| 344 |
+
"eval_steps_per_second": 1.103,
|
| 345 |
+
"step": 325
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4325032765399738,
|
| 349 |
+
"grad_norm": 4.03125,
|
| 350 |
+
"learning_rate": 1.6788218793828896e-05,
|
| 351 |
+
"loss": 0.3122,
|
| 352 |
+
"step": 330
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4456094364351245,
|
| 356 |
+
"grad_norm": 5.21875,
|
| 357 |
+
"learning_rate": 1.664796633941094e-05,
|
| 358 |
+
"loss": 0.3053,
|
| 359 |
+
"step": 340
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.45871559633027525,
|
| 363 |
+
"grad_norm": 3.09375,
|
| 364 |
+
"learning_rate": 1.650771388499299e-05,
|
| 365 |
+
"loss": 0.2632,
|
| 366 |
+
"step": 350
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.45871559633027525,
|
| 370 |
+
"eval_loss": 0.29447969794273376,
|
| 371 |
+
"eval_runtime": 3.6275,
|
| 372 |
+
"eval_samples_per_second": 8.546,
|
| 373 |
+
"eval_steps_per_second": 1.103,
|
| 374 |
+
"step": 350
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.47182175622542594,
|
| 378 |
+
"grad_norm": 4.40625,
|
| 379 |
+
"learning_rate": 1.6367461430575035e-05,
|
| 380 |
+
"loss": 0.2968,
|
| 381 |
+
"step": 360
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4849279161205767,
|
| 385 |
+
"grad_norm": 3.78125,
|
| 386 |
+
"learning_rate": 1.6227208976157084e-05,
|
| 387 |
+
"loss": 0.3154,
|
| 388 |
+
"step": 370
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.49148099606815204,
|
| 392 |
+
"eval_loss": 0.29292187094688416,
|
| 393 |
+
"eval_runtime": 3.6253,
|
| 394 |
+
"eval_samples_per_second": 8.551,
|
| 395 |
+
"eval_steps_per_second": 1.103,
|
| 396 |
+
"step": 375
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.4980340760157274,
|
| 400 |
+
"grad_norm": 3.984375,
|
| 401 |
+
"learning_rate": 1.6086956521739132e-05,
|
| 402 |
+
"loss": 0.2635,
|
| 403 |
+
"step": 380
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.5111402359108781,
|
| 407 |
+
"grad_norm": 3.5,
|
| 408 |
+
"learning_rate": 1.5946704067321178e-05,
|
| 409 |
+
"loss": 0.3126,
|
| 410 |
+
"step": 390
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5242463958060288,
|
| 414 |
+
"grad_norm": 5.40625,
|
| 415 |
+
"learning_rate": 1.5806451612903226e-05,
|
| 416 |
+
"loss": 0.3126,
|
| 417 |
+
"step": 400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.5242463958060288,
|
| 421 |
+
"eval_loss": 0.2929743826389313,
|
| 422 |
+
"eval_runtime": 3.6233,
|
| 423 |
+
"eval_samples_per_second": 8.556,
|
| 424 |
+
"eval_steps_per_second": 1.104,
|
| 425 |
+
"step": 400
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.5373525557011796,
|
| 429 |
+
"grad_norm": 3.984375,
|
| 430 |
+
"learning_rate": 1.5666199158485275e-05,
|
| 431 |
+
"loss": 0.279,
|
| 432 |
+
"step": 410
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5504587155963303,
|
| 436 |
+
"grad_norm": 4.5,
|
| 437 |
+
"learning_rate": 1.5525946704067324e-05,
|
| 438 |
+
"loss": 0.2817,
|
| 439 |
+
"step": 420
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.5570117955439057,
|
| 443 |
+
"eval_loss": 0.2881828844547272,
|
| 444 |
+
"eval_runtime": 3.6309,
|
| 445 |
+
"eval_samples_per_second": 8.538,
|
| 446 |
+
"eval_steps_per_second": 1.102,
|
| 447 |
+
"step": 425
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.563564875491481,
|
| 451 |
+
"grad_norm": 3.671875,
|
| 452 |
+
"learning_rate": 1.538569424964937e-05,
|
| 453 |
+
"loss": 0.2967,
|
| 454 |
+
"step": 430
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5766710353866317,
|
| 458 |
+
"grad_norm": 4.3125,
|
| 459 |
+
"learning_rate": 1.5245441795231418e-05,
|
| 460 |
+
"loss": 0.3231,
|
| 461 |
+
"step": 440
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.5897771952817824,
|
| 465 |
+
"grad_norm": 3.65625,
|
| 466 |
+
"learning_rate": 1.5105189340813466e-05,
|
| 467 |
+
"loss": 0.3371,
|
| 468 |
+
"step": 450
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.5897771952817824,
|
| 472 |
+
"eval_loss": 0.285811185836792,
|
| 473 |
+
"eval_runtime": 3.6291,
|
| 474 |
+
"eval_samples_per_second": 8.542,
|
| 475 |
+
"eval_steps_per_second": 1.102,
|
| 476 |
+
"step": 450
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.6028833551769331,
|
| 480 |
+
"grad_norm": 3.328125,
|
| 481 |
+
"learning_rate": 1.4964936886395513e-05,
|
| 482 |
+
"loss": 0.3081,
|
| 483 |
+
"step": 460
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.6159895150720839,
|
| 487 |
+
"grad_norm": 3.984375,
|
| 488 |
+
"learning_rate": 1.482468443197756e-05,
|
| 489 |
+
"loss": 0.2821,
|
| 490 |
+
"step": 470
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.6225425950196593,
|
| 494 |
+
"eval_loss": 0.28545138239860535,
|
| 495 |
+
"eval_runtime": 3.6247,
|
| 496 |
+
"eval_samples_per_second": 8.553,
|
| 497 |
+
"eval_steps_per_second": 1.104,
|
| 498 |
+
"step": 475
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.6290956749672346,
|
| 502 |
+
"grad_norm": 3.65625,
|
| 503 |
+
"learning_rate": 1.4684431977559607e-05,
|
| 504 |
+
"loss": 0.3088,
|
| 505 |
+
"step": 480
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.6422018348623854,
|
| 509 |
+
"grad_norm": 3.4375,
|
| 510 |
+
"learning_rate": 1.4544179523141658e-05,
|
| 511 |
+
"loss": 0.3111,
|
| 512 |
+
"step": 490
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.6553079947575361,
|
| 516 |
+
"grad_norm": 3.65625,
|
| 517 |
+
"learning_rate": 1.4403927068723705e-05,
|
| 518 |
+
"loss": 0.2942,
|
| 519 |
+
"step": 500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6553079947575361,
|
| 523 |
+
"eval_loss": 0.28335702419281006,
|
| 524 |
+
"eval_runtime": 3.6367,
|
| 525 |
+
"eval_samples_per_second": 8.524,
|
| 526 |
+
"eval_steps_per_second": 1.1,
|
| 527 |
+
"step": 500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6684141546526867,
|
| 531 |
+
"grad_norm": 3.671875,
|
| 532 |
+
"learning_rate": 1.4263674614305752e-05,
|
| 533 |
+
"loss": 0.2872,
|
| 534 |
+
"step": 510
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6815203145478375,
|
| 538 |
+
"grad_norm": 3.03125,
|
| 539 |
+
"learning_rate": 1.4123422159887799e-05,
|
| 540 |
+
"loss": 0.3081,
|
| 541 |
+
"step": 520
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6880733944954128,
|
| 545 |
+
"eval_loss": 0.2832925617694855,
|
| 546 |
+
"eval_runtime": 3.6251,
|
| 547 |
+
"eval_samples_per_second": 8.551,
|
| 548 |
+
"eval_steps_per_second": 1.103,
|
| 549 |
+
"step": 525
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6946264744429882,
|
| 553 |
+
"grad_norm": 5.03125,
|
| 554 |
+
"learning_rate": 1.3983169705469847e-05,
|
| 555 |
+
"loss": 0.3289,
|
| 556 |
+
"step": 530
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7077326343381389,
|
| 560 |
+
"grad_norm": 3.75,
|
| 561 |
+
"learning_rate": 1.3842917251051894e-05,
|
| 562 |
+
"loss": 0.2875,
|
| 563 |
+
"step": 540
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.7208387942332897,
|
| 567 |
+
"grad_norm": 2.78125,
|
| 568 |
+
"learning_rate": 1.3702664796633941e-05,
|
| 569 |
+
"loss": 0.2218,
|
| 570 |
+
"step": 550
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7208387942332897,
|
| 574 |
+
"eval_loss": 0.28089821338653564,
|
| 575 |
+
"eval_runtime": 3.6305,
|
| 576 |
+
"eval_samples_per_second": 8.539,
|
| 577 |
+
"eval_steps_per_second": 1.102,
|
| 578 |
+
"step": 550
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.7339449541284404,
|
| 582 |
+
"grad_norm": 4.4375,
|
| 583 |
+
"learning_rate": 1.356241234221599e-05,
|
| 584 |
+
"loss": 0.264,
|
| 585 |
+
"step": 560
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.747051114023591,
|
| 589 |
+
"grad_norm": 3.140625,
|
| 590 |
+
"learning_rate": 1.3422159887798039e-05,
|
| 591 |
+
"loss": 0.3062,
|
| 592 |
+
"step": 570
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.7536041939711664,
|
| 596 |
+
"eval_loss": 0.2809857130050659,
|
| 597 |
+
"eval_runtime": 3.6291,
|
| 598 |
+
"eval_samples_per_second": 8.542,
|
| 599 |
+
"eval_steps_per_second": 1.102,
|
| 600 |
+
"step": 575
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.7601572739187418,
|
| 604 |
+
"grad_norm": 4.125,
|
| 605 |
+
"learning_rate": 1.3281907433380086e-05,
|
| 606 |
+
"loss": 0.2615,
|
| 607 |
+
"step": 580
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.7732634338138925,
|
| 611 |
+
"grad_norm": 3.53125,
|
| 612 |
+
"learning_rate": 1.3141654978962133e-05,
|
| 613 |
+
"loss": 0.2747,
|
| 614 |
+
"step": 590
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.7863695937090432,
|
| 618 |
+
"grad_norm": 3.34375,
|
| 619 |
+
"learning_rate": 1.300140252454418e-05,
|
| 620 |
+
"loss": 0.2837,
|
| 621 |
+
"step": 600
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.7863695937090432,
|
| 625 |
+
"eval_loss": 0.276317834854126,
|
| 626 |
+
"eval_runtime": 3.6322,
|
| 627 |
+
"eval_samples_per_second": 8.535,
|
| 628 |
+
"eval_steps_per_second": 1.101,
|
| 629 |
+
"step": 600
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.799475753604194,
|
| 633 |
+
"grad_norm": 5.0,
|
| 634 |
+
"learning_rate": 1.286115007012623e-05,
|
| 635 |
+
"loss": 0.3009,
|
| 636 |
+
"step": 610
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.8125819134993447,
|
| 640 |
+
"grad_norm": 3.46875,
|
| 641 |
+
"learning_rate": 1.2720897615708277e-05,
|
| 642 |
+
"loss": 0.3129,
|
| 643 |
+
"step": 620
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.8191349934469201,
|
| 647 |
+
"eval_loss": 0.27676212787628174,
|
| 648 |
+
"eval_runtime": 3.6276,
|
| 649 |
+
"eval_samples_per_second": 8.546,
|
| 650 |
+
"eval_steps_per_second": 1.103,
|
| 651 |
+
"step": 625
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.8256880733944955,
|
| 655 |
+
"grad_norm": 2.90625,
|
| 656 |
+
"learning_rate": 1.2580645161290324e-05,
|
| 657 |
+
"loss": 0.2404,
|
| 658 |
+
"step": 630
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.8387942332896461,
|
| 662 |
+
"grad_norm": 3.09375,
|
| 663 |
+
"learning_rate": 1.2440392706872371e-05,
|
| 664 |
+
"loss": 0.2858,
|
| 665 |
+
"step": 640
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.8519003931847968,
|
| 669 |
+
"grad_norm": 3.90625,
|
| 670 |
+
"learning_rate": 1.230014025245442e-05,
|
| 671 |
+
"loss": 0.2947,
|
| 672 |
+
"step": 650
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.8519003931847968,
|
| 676 |
+
"eval_loss": 0.2739439606666565,
|
| 677 |
+
"eval_runtime": 3.6305,
|
| 678 |
+
"eval_samples_per_second": 8.539,
|
| 679 |
+
"eval_steps_per_second": 1.102,
|
| 680 |
+
"step": 650
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8650065530799476,
|
| 684 |
+
"grad_norm": 3.15625,
|
| 685 |
+
"learning_rate": 1.2159887798036467e-05,
|
| 686 |
+
"loss": 0.291,
|
| 687 |
+
"step": 660
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.8781127129750983,
|
| 691 |
+
"grad_norm": 3.828125,
|
| 692 |
+
"learning_rate": 1.2019635343618514e-05,
|
| 693 |
+
"loss": 0.3276,
|
| 694 |
+
"step": 670
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.8846657929226737,
|
| 698 |
+
"eval_loss": 0.2710360586643219,
|
| 699 |
+
"eval_runtime": 3.6251,
|
| 700 |
+
"eval_samples_per_second": 8.551,
|
| 701 |
+
"eval_steps_per_second": 1.103,
|
| 702 |
+
"step": 675
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.891218872870249,
|
| 706 |
+
"grad_norm": 4.75,
|
| 707 |
+
"learning_rate": 1.187938288920056e-05,
|
| 708 |
+
"loss": 0.289,
|
| 709 |
+
"step": 680
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9043250327653998,
|
| 713 |
+
"grad_norm": 3.53125,
|
| 714 |
+
"learning_rate": 1.1739130434782611e-05,
|
| 715 |
+
"loss": 0.2442,
|
| 716 |
+
"step": 690
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9174311926605505,
|
| 720 |
+
"grad_norm": 3.0625,
|
| 721 |
+
"learning_rate": 1.1598877980364658e-05,
|
| 722 |
+
"loss": 0.3024,
|
| 723 |
+
"step": 700
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9174311926605505,
|
| 727 |
+
"eval_loss": 0.2719181180000305,
|
| 728 |
+
"eval_runtime": 3.625,
|
| 729 |
+
"eval_samples_per_second": 8.552,
|
| 730 |
+
"eval_steps_per_second": 1.103,
|
| 731 |
+
"step": 700
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9305373525557011,
|
| 735 |
+
"grad_norm": 3.15625,
|
| 736 |
+
"learning_rate": 1.1458625525946705e-05,
|
| 737 |
+
"loss": 0.2883,
|
| 738 |
+
"step": 710
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9436435124508519,
|
| 742 |
+
"grad_norm": 4.0625,
|
| 743 |
+
"learning_rate": 1.1318373071528752e-05,
|
| 744 |
+
"loss": 0.2915,
|
| 745 |
+
"step": 720
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9501965923984272,
|
| 749 |
+
"eval_loss": 0.27032172679901123,
|
| 750 |
+
"eval_runtime": 3.6246,
|
| 751 |
+
"eval_samples_per_second": 8.553,
|
| 752 |
+
"eval_steps_per_second": 1.104,
|
| 753 |
+
"step": 725
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.9567496723460026,
|
| 757 |
+
"grad_norm": 3.09375,
|
| 758 |
+
"learning_rate": 1.11781206171108e-05,
|
| 759 |
+
"loss": 0.2846,
|
| 760 |
+
"step": 730
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.9698558322411533,
|
| 764 |
+
"grad_norm": 3.859375,
|
| 765 |
+
"learning_rate": 1.103786816269285e-05,
|
| 766 |
+
"loss": 0.2954,
|
| 767 |
+
"step": 740
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.9829619921363041,
|
| 771 |
+
"grad_norm": 4.34375,
|
| 772 |
+
"learning_rate": 1.0897615708274896e-05,
|
| 773 |
+
"loss": 0.2825,
|
| 774 |
+
"step": 750
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.9829619921363041,
|
| 778 |
+
"eval_loss": 0.26988574862480164,
|
| 779 |
+
"eval_runtime": 3.6297,
|
| 780 |
+
"eval_samples_per_second": 8.541,
|
| 781 |
+
"eval_steps_per_second": 1.102,
|
| 782 |
+
"step": 750
|
| 783 |
+
}
|
| 784 |
+
],
|
| 785 |
+
"logging_steps": 10,
|
| 786 |
+
"max_steps": 1526,
|
| 787 |
+
"num_input_tokens_seen": 0,
|
| 788 |
+
"num_train_epochs": 2,
|
| 789 |
+
"save_steps": 25,
|
| 790 |
+
"stateful_callbacks": {
|
| 791 |
+
"TrainerControl": {
|
| 792 |
+
"args": {
|
| 793 |
+
"should_epoch_stop": false,
|
| 794 |
+
"should_evaluate": false,
|
| 795 |
+
"should_log": false,
|
| 796 |
+
"should_save": true,
|
| 797 |
+
"should_training_stop": false
|
| 798 |
+
},
|
| 799 |
+
"attributes": {}
|
| 800 |
+
}
|
| 801 |
+
},
|
| 802 |
+
"total_flos": 9744231345598464.0,
|
| 803 |
+
"train_batch_size": 1,
|
| 804 |
+
"trial_name": null,
|
| 805 |
+
"trial_params": null
|
| 806 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a38f948b9dea1b1874da71a704c6e6d5e1e5ab948c414932e7f1b5ff8bdd05
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|