Upload checkpoint-1500
Browse files- .gitattributes +1 -0
- checkpoints/checkpoint-1500/added_tokens.json +24 -0
- checkpoints/checkpoint-1500/chat_template.jinja +54 -0
- checkpoints/checkpoint-1500/config.json +56 -0
- checkpoints/checkpoint-1500/generation_config.json +14 -0
- checkpoints/checkpoint-1500/merges.txt +0 -0
- checkpoints/checkpoint-1500/model.safetensors +3 -0
- checkpoints/checkpoint-1500/optimizer.pt +3 -0
- checkpoints/checkpoint-1500/rng_state.pth +3 -0
- checkpoints/checkpoint-1500/scheduler.pt +3 -0
- checkpoints/checkpoint-1500/special_tokens_map.json +31 -0
- checkpoints/checkpoint-1500/tokenizer.json +3 -0
- checkpoints/checkpoint-1500/tokenizer_config.json +208 -0
- checkpoints/checkpoint-1500/trainer_state.json +1084 -0
- checkpoints/checkpoint-1500/training_args.bin +3 -0
- checkpoints/checkpoint-1500/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* 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
|
| 37 |
checkpoints/checkpoint-1000/tokenizer.json 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
|
| 37 |
checkpoints/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoints/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoints/checkpoint-1500/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 |
+
}
|
checkpoints/checkpoint-1500/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 %}
|
checkpoints/checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 151654,
|
| 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": "4.57.2",
|
| 51 |
+
"unsloth_fixed": true,
|
| 52 |
+
"unsloth_version": "2025.11.6",
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_sliding_window": false,
|
| 55 |
+
"vocab_size": 151936
|
| 56 |
+
}
|
checkpoints/checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"max_length": 32768,
|
| 8 |
+
"pad_token_id": 151654,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.57.2"
|
| 14 |
+
}
|
checkpoints/checkpoint-1500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f5b6e2ef0eab3b0e8bd219755a3337e3bafbed9f803286acfa3a99bda8b7f6
|
| 3 |
+
size 988097824
|
checkpoints/checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81548f8102726fe93b56b0681b60e9a05acc27d6f45009553419d97e234574a9
|
| 3 |
+
size 1431622411
|
checkpoints/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
|
| 3 |
+
size 14645
|
checkpoints/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f234e893af953e7d48ba07a938a27619075875cd4fd011173e25ec0049a02c4b
|
| 3 |
+
size 1465
|
checkpoints/checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoints/checkpoint-1500/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoints/checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 32768,
|
| 203 |
+
"pad_token": "<|vision_pad|>",
|
| 204 |
+
"padding_side": "left",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
checkpoints/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1084 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.4,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 30.375,
|
| 15 |
+
"learning_rate": 9.574468085106384e-07,
|
| 16 |
+
"loss": 0.5874,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 23.75,
|
| 22 |
+
"learning_rate": 2.021276595744681e-06,
|
| 23 |
+
"loss": 0.6085,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 19.0,
|
| 29 |
+
"learning_rate": 3.0851063829787237e-06,
|
| 30 |
+
"loss": 0.551,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 8.3125,
|
| 36 |
+
"learning_rate": 4.148936170212766e-06,
|
| 37 |
+
"loss": 0.3414,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 8.4375,
|
| 43 |
+
"learning_rate": 5.212765957446809e-06,
|
| 44 |
+
"loss": 0.1779,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 3.234375,
|
| 50 |
+
"learning_rate": 6.276595744680851e-06,
|
| 51 |
+
"loss": 0.0652,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 2.40625,
|
| 57 |
+
"learning_rate": 7.340425531914894e-06,
|
| 58 |
+
"loss": 0.0439,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 0.69921875,
|
| 64 |
+
"learning_rate": 8.404255319148937e-06,
|
| 65 |
+
"loss": 0.0451,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 0.9765625,
|
| 71 |
+
"learning_rate": 9.46808510638298e-06,
|
| 72 |
+
"loss": 0.0401,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 0.89453125,
|
| 78 |
+
"learning_rate": 1.0531914893617022e-05,
|
| 79 |
+
"loss": 0.0409,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 2.671875,
|
| 85 |
+
"learning_rate": 1.1595744680851065e-05,
|
| 86 |
+
"loss": 0.0392,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 1.328125,
|
| 92 |
+
"learning_rate": 1.2659574468085108e-05,
|
| 93 |
+
"loss": 0.0374,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 2.0625,
|
| 99 |
+
"learning_rate": 1.372340425531915e-05,
|
| 100 |
+
"loss": 0.0356,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 2.0,
|
| 106 |
+
"learning_rate": 1.4787234042553193e-05,
|
| 107 |
+
"loss": 0.0419,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 1.6953125,
|
| 113 |
+
"learning_rate": 1.5851063829787235e-05,
|
| 114 |
+
"loss": 0.0425,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 2.734375,
|
| 120 |
+
"learning_rate": 1.6914893617021276e-05,
|
| 121 |
+
"loss": 0.0435,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 0.83203125,
|
| 127 |
+
"learning_rate": 1.797872340425532e-05,
|
| 128 |
+
"loss": 0.0332,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 1.21875,
|
| 134 |
+
"learning_rate": 1.9042553191489363e-05,
|
| 135 |
+
"loss": 0.04,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 1.2421875,
|
| 141 |
+
"learning_rate": 1.999998266038466e-05,
|
| 142 |
+
"loss": 0.038,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 0.81640625,
|
| 148 |
+
"learning_rate": 1.9997901979302522e-05,
|
| 149 |
+
"loss": 0.0337,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 0.71875,
|
| 155 |
+
"learning_rate": 1.9992354201925427e-05,
|
| 156 |
+
"loss": 0.0401,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 0.859375,
|
| 162 |
+
"learning_rate": 1.9983341252124843e-05,
|
| 163 |
+
"loss": 0.0416,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 0.318359375,
|
| 169 |
+
"learning_rate": 1.9970866255433e-05,
|
| 170 |
+
"loss": 0.0387,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 0.44140625,
|
| 176 |
+
"learning_rate": 1.9954933537959e-05,
|
| 177 |
+
"loss": 0.0375,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 0.443359375,
|
| 183 |
+
"learning_rate": 1.993554862488862e-05,
|
| 184 |
+
"loss": 0.0378,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 0.365234375,
|
| 190 |
+
"learning_rate": 1.9912718238568245e-05,
|
| 191 |
+
"loss": 0.0371,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 0.34765625,
|
| 197 |
+
"learning_rate": 1.9886450296173693e-05,
|
| 198 |
+
"loss": 0.0364,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 0.447265625,
|
| 204 |
+
"learning_rate": 1.9856753906964686e-05,
|
| 205 |
+
"loss": 0.0338,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 0.53125,
|
| 211 |
+
"learning_rate": 1.9823639369125907e-05,
|
| 212 |
+
"loss": 0.0396,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 0.51171875,
|
| 218 |
+
"learning_rate": 1.978711816619577e-05,
|
| 219 |
+
"loss": 0.0392,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 0.48828125,
|
| 225 |
+
"learning_rate": 1.974720296308413e-05,
|
| 226 |
+
"loss": 0.0449,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 0.5,
|
| 232 |
+
"learning_rate": 1.9703907601680332e-05,
|
| 233 |
+
"loss": 0.0387,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 0.578125,
|
| 239 |
+
"learning_rate": 1.9657247096053066e-05,
|
| 240 |
+
"loss": 0.0397,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 0.408203125,
|
| 246 |
+
"learning_rate": 1.960723762724377e-05,
|
| 247 |
+
"loss": 0.0392,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 0.78125,
|
| 253 |
+
"learning_rate": 1.9553896537655317e-05,
|
| 254 |
+
"loss": 0.0379,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 0.443359375,
|
| 260 |
+
"learning_rate": 1.949724232503798e-05,
|
| 261 |
+
"loss": 0.0349,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 0.470703125,
|
| 267 |
+
"learning_rate": 1.943729463607474e-05,
|
| 268 |
+
"loss": 0.0387,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 0.498046875,
|
| 274 |
+
"learning_rate": 1.937407425956816e-05,
|
| 275 |
+
"loss": 0.0379,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 0.671875,
|
| 281 |
+
"learning_rate": 1.93076031192312e-05,
|
| 282 |
+
"loss": 0.0404,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 0.337890625,
|
| 288 |
+
"learning_rate": 1.9237904266084445e-05,
|
| 289 |
+
"loss": 0.0407,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 0.42578125,
|
| 295 |
+
"learning_rate": 1.916500187046243e-05,
|
| 296 |
+
"loss": 0.0399,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 0.625,
|
| 302 |
+
"learning_rate": 1.9088921213631803e-05,
|
| 303 |
+
"loss": 0.0405,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 0.58203125,
|
| 309 |
+
"learning_rate": 1.900968867902419e-05,
|
| 310 |
+
"loss": 0.0354,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 0.56640625,
|
| 316 |
+
"learning_rate": 1.892733174308694e-05,
|
| 317 |
+
"loss": 0.0351,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 0.328125,
|
| 323 |
+
"learning_rate": 1.8841878965754718e-05,
|
| 324 |
+
"loss": 0.0397,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 0.50390625,
|
| 330 |
+
"learning_rate": 1.8753359980545472e-05,
|
| 331 |
+
"loss": 0.0377,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 0.447265625,
|
| 337 |
+
"learning_rate": 1.8661805484284025e-05,
|
| 338 |
+
"loss": 0.0369,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 0.36328125,
|
| 344 |
+
"learning_rate": 1.8567247226456958e-05,
|
| 345 |
+
"loss": 0.0378,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 0.421875,
|
| 351 |
+
"learning_rate": 1.8469717998202464e-05,
|
| 352 |
+
"loss": 0.0343,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 0.279296875,
|
| 358 |
+
"learning_rate": 1.8369251620938935e-05,
|
| 359 |
+
"loss": 0.0353,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 0.52734375,
|
| 365 |
+
"learning_rate": 1.8265882934636305e-05,
|
| 366 |
+
"loss": 0.0354,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 0.427734375,
|
| 372 |
+
"learning_rate": 1.8159647785734166e-05,
|
| 373 |
+
"loss": 0.0361,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 0.30078125,
|
| 379 |
+
"learning_rate": 1.8050583014710838e-05,
|
| 380 |
+
"loss": 0.0364,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 0.3828125,
|
| 386 |
+
"learning_rate": 1.793872644330775e-05,
|
| 387 |
+
"loss": 0.0413,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 0.578125,
|
| 393 |
+
"learning_rate": 1.782411686141354e-05,
|
| 394 |
+
"loss": 0.0393,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 0.68359375,
|
| 400 |
+
"learning_rate": 1.7706794013612367e-05,
|
| 401 |
+
"loss": 0.0394,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 0.3828125,
|
| 407 |
+
"learning_rate": 1.758679858540123e-05,
|
| 408 |
+
"loss": 0.0367,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 0.46484375,
|
| 414 |
+
"learning_rate": 1.7464172189080933e-05,
|
| 415 |
+
"loss": 0.04,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 0.353515625,
|
| 421 |
+
"learning_rate": 1.7338957349325678e-05,
|
| 422 |
+
"loss": 0.0399,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 0.5390625,
|
| 428 |
+
"learning_rate": 1.7211197488436244e-05,
|
| 429 |
+
"loss": 0.0402,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 0.3046875,
|
| 435 |
+
"learning_rate": 1.7080936911281927e-05,
|
| 436 |
+
"loss": 0.0391,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 0.50390625,
|
| 442 |
+
"learning_rate": 1.694822078993636e-05,
|
| 443 |
+
"loss": 0.0407,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.008,
|
| 448 |
+
"grad_norm": 0.453125,
|
| 449 |
+
"learning_rate": 1.681309514801265e-05,
|
| 450 |
+
"loss": 0.0386,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.024,
|
| 455 |
+
"grad_norm": 0.419921875,
|
| 456 |
+
"learning_rate": 1.6675606844703203e-05,
|
| 457 |
+
"loss": 0.0334,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.04,
|
| 462 |
+
"grad_norm": 0.390625,
|
| 463 |
+
"learning_rate": 1.6535803558529778e-05,
|
| 464 |
+
"loss": 0.0366,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.056,
|
| 469 |
+
"grad_norm": 0.59375,
|
| 470 |
+
"learning_rate": 1.6393733770809393e-05,
|
| 471 |
+
"loss": 0.0393,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.072,
|
| 476 |
+
"grad_norm": 0.369140625,
|
| 477 |
+
"learning_rate": 1.6249446748841903e-05,
|
| 478 |
+
"loss": 0.034,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.088,
|
| 483 |
+
"grad_norm": 0.19140625,
|
| 484 |
+
"learning_rate": 1.610299252882493e-05,
|
| 485 |
+
"loss": 0.0342,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.104,
|
| 490 |
+
"grad_norm": 0.515625,
|
| 491 |
+
"learning_rate": 1.5954421898502205e-05,
|
| 492 |
+
"loss": 0.0392,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.12,
|
| 497 |
+
"grad_norm": 0.3671875,
|
| 498 |
+
"learning_rate": 1.580378637955128e-05,
|
| 499 |
+
"loss": 0.0352,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1360000000000001,
|
| 504 |
+
"grad_norm": 0.33203125,
|
| 505 |
+
"learning_rate": 1.5651138209716705e-05,
|
| 506 |
+
"loss": 0.0349,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.152,
|
| 511 |
+
"grad_norm": 0.59375,
|
| 512 |
+
"learning_rate": 1.549653032469491e-05,
|
| 513 |
+
"loss": 0.0355,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.168,
|
| 518 |
+
"grad_norm": 0.5390625,
|
| 519 |
+
"learning_rate": 1.534001633977702e-05,
|
| 520 |
+
"loss": 0.0384,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.184,
|
| 525 |
+
"grad_norm": 0.29296875,
|
| 526 |
+
"learning_rate": 1.5181650531256038e-05,
|
| 527 |
+
"loss": 0.0332,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.2,
|
| 532 |
+
"grad_norm": 0.244140625,
|
| 533 |
+
"learning_rate": 1.5021487817604769e-05,
|
| 534 |
+
"loss": 0.0347,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.216,
|
| 539 |
+
"grad_norm": 0.421875,
|
| 540 |
+
"learning_rate": 1.485958374043107e-05,
|
| 541 |
+
"loss": 0.0354,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.232,
|
| 546 |
+
"grad_norm": 0.388671875,
|
| 547 |
+
"learning_rate": 1.4695994445216985e-05,
|
| 548 |
+
"loss": 0.0366,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.248,
|
| 553 |
+
"grad_norm": 0.46484375,
|
| 554 |
+
"learning_rate": 1.45307766618485e-05,
|
| 555 |
+
"loss": 0.0348,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.264,
|
| 560 |
+
"grad_norm": 0.67578125,
|
| 561 |
+
"learning_rate": 1.4363987684942603e-05,
|
| 562 |
+
"loss": 0.036,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.28,
|
| 567 |
+
"grad_norm": 0.82421875,
|
| 568 |
+
"learning_rate": 1.4195685353978517e-05,
|
| 569 |
+
"loss": 0.035,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.296,
|
| 574 |
+
"grad_norm": 0.353515625,
|
| 575 |
+
"learning_rate": 1.4025928033240004e-05,
|
| 576 |
+
"loss": 0.0358,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.312,
|
| 581 |
+
"grad_norm": 0.400390625,
|
| 582 |
+
"learning_rate": 1.3854774591575651e-05,
|
| 583 |
+
"loss": 0.036,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.328,
|
| 588 |
+
"grad_norm": 0.431640625,
|
| 589 |
+
"learning_rate": 1.3682284381984184e-05,
|
| 590 |
+
"loss": 0.0359,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3439999999999999,
|
| 595 |
+
"grad_norm": 0.34375,
|
| 596 |
+
"learning_rate": 1.3508517221031898e-05,
|
| 597 |
+
"loss": 0.0338,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3599999999999999,
|
| 602 |
+
"grad_norm": 0.66015625,
|
| 603 |
+
"learning_rate": 1.3333533368109337e-05,
|
| 604 |
+
"loss": 0.0362,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.376,
|
| 609 |
+
"grad_norm": 0.47265625,
|
| 610 |
+
"learning_rate": 1.3157393504534378e-05,
|
| 611 |
+
"loss": 0.035,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.392,
|
| 616 |
+
"grad_norm": 0.6171875,
|
| 617 |
+
"learning_rate": 1.2980158712509033e-05,
|
| 618 |
+
"loss": 0.038,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.408,
|
| 623 |
+
"grad_norm": 0.314453125,
|
| 624 |
+
"learning_rate": 1.2801890453937214e-05,
|
| 625 |
+
"loss": 0.0368,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.424,
|
| 630 |
+
"grad_norm": 0.435546875,
|
| 631 |
+
"learning_rate": 1.2622650549110826e-05,
|
| 632 |
+
"loss": 0.0359,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.44,
|
| 637 |
+
"grad_norm": 0.396484375,
|
| 638 |
+
"learning_rate": 1.2442501155271582e-05,
|
| 639 |
+
"loss": 0.0333,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.456,
|
| 644 |
+
"grad_norm": 0.42578125,
|
| 645 |
+
"learning_rate": 1.2261504745055963e-05,
|
| 646 |
+
"loss": 0.0386,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.472,
|
| 651 |
+
"grad_norm": 0.314453125,
|
| 652 |
+
"learning_rate": 1.2079724084830802e-05,
|
| 653 |
+
"loss": 0.0346,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.488,
|
| 658 |
+
"grad_norm": 0.37890625,
|
| 659 |
+
"learning_rate": 1.1897222212927036e-05,
|
| 660 |
+
"loss": 0.0357,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.504,
|
| 665 |
+
"grad_norm": 0.283203125,
|
| 666 |
+
"learning_rate": 1.1714062417779096e-05,
|
| 667 |
+
"loss": 0.0383,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.52,
|
| 672 |
+
"grad_norm": 0.2392578125,
|
| 673 |
+
"learning_rate": 1.1530308215977607e-05,
|
| 674 |
+
"loss": 0.032,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.536,
|
| 679 |
+
"grad_norm": 0.73046875,
|
| 680 |
+
"learning_rate": 1.1346023330242954e-05,
|
| 681 |
+
"loss": 0.0404,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.552,
|
| 686 |
+
"grad_norm": 0.28515625,
|
| 687 |
+
"learning_rate": 1.1161271667327359e-05,
|
| 688 |
+
"loss": 0.0371,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.568,
|
| 693 |
+
"grad_norm": 0.37109375,
|
| 694 |
+
"learning_rate": 1.0976117295853155e-05,
|
| 695 |
+
"loss": 0.0375,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.584,
|
| 700 |
+
"grad_norm": 0.271484375,
|
| 701 |
+
"learning_rate": 1.07906244240949e-05,
|
| 702 |
+
"loss": 0.0385,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6,
|
| 707 |
+
"grad_norm": 0.333984375,
|
| 708 |
+
"learning_rate": 1.0604857377713089e-05,
|
| 709 |
+
"loss": 0.039,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.616,
|
| 714 |
+
"grad_norm": 0.462890625,
|
| 715 |
+
"learning_rate": 1.0418880577447161e-05,
|
| 716 |
+
"loss": 0.0401,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6320000000000001,
|
| 721 |
+
"grad_norm": 0.412109375,
|
| 722 |
+
"learning_rate": 1.0232758516775484e-05,
|
| 723 |
+
"loss": 0.0374,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6480000000000001,
|
| 728 |
+
"grad_norm": 0.408203125,
|
| 729 |
+
"learning_rate": 1.0046555739550194e-05,
|
| 730 |
+
"loss": 0.0347,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6640000000000001,
|
| 735 |
+
"grad_norm": 0.384765625,
|
| 736 |
+
"learning_rate": 9.860336817614503e-06,
|
| 737 |
+
"loss": 0.0349,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6800000000000002,
|
| 742 |
+
"grad_norm": 0.435546875,
|
| 743 |
+
"learning_rate": 9.674166328410318e-06,
|
| 744 |
+
"loss": 0.0353,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.696,
|
| 749 |
+
"grad_norm": 0.2734375,
|
| 750 |
+
"learning_rate": 9.488108832583929e-06,
|
| 751 |
+
"loss": 0.0351,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.712,
|
| 756 |
+
"grad_norm": 0.275390625,
|
| 757 |
+
"learning_rate": 9.30222885159752e-06,
|
| 758 |
+
"loss": 0.0332,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.728,
|
| 763 |
+
"grad_norm": 0.369140625,
|
| 764 |
+
"learning_rate": 9.116590845354248e-06,
|
| 765 |
+
"loss": 0.035,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.744,
|
| 770 |
+
"grad_norm": 0.3359375,
|
| 771 |
+
"learning_rate": 8.931259189844696e-06,
|
| 772 |
+
"loss": 0.0361,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.76,
|
| 777 |
+
"grad_norm": 0.515625,
|
| 778 |
+
"learning_rate": 8.746298154822406e-06,
|
| 779 |
+
"loss": 0.0414,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.776,
|
| 784 |
+
"grad_norm": 0.416015625,
|
| 785 |
+
"learning_rate": 8.561771881516262e-06,
|
| 786 |
+
"loss": 0.037,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.792,
|
| 791 |
+
"grad_norm": 0.412109375,
|
| 792 |
+
"learning_rate": 8.377744360387447e-06,
|
| 793 |
+
"loss": 0.0351,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.808,
|
| 798 |
+
"grad_norm": 0.2734375,
|
| 799 |
+
"learning_rate": 8.194279408938674e-06,
|
| 800 |
+
"loss": 0.0336,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8239999999999998,
|
| 805 |
+
"grad_norm": 0.89453125,
|
| 806 |
+
"learning_rate": 8.0114406495834e-06,
|
| 807 |
+
"loss": 0.0341,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8399999999999999,
|
| 812 |
+
"grad_norm": 0.31640625,
|
| 813 |
+
"learning_rate": 7.829291487582692e-06,
|
| 814 |
+
"loss": 0.0358,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8559999999999999,
|
| 819 |
+
"grad_norm": 0.318359375,
|
| 820 |
+
"learning_rate": 7.647895089057403e-06,
|
| 821 |
+
"loss": 0.0319,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8719999999999999,
|
| 826 |
+
"grad_norm": 0.384765625,
|
| 827 |
+
"learning_rate": 7.46731435908327e-06,
|
| 828 |
+
"loss": 0.0422,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.888,
|
| 833 |
+
"grad_norm": 0.31640625,
|
| 834 |
+
"learning_rate": 7.287611919876553e-06,
|
| 835 |
+
"loss": 0.0339,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.904,
|
| 840 |
+
"grad_norm": 0.416015625,
|
| 841 |
+
"learning_rate": 7.108850089077736e-06,
|
| 842 |
+
"loss": 0.0336,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.92,
|
| 847 |
+
"grad_norm": 0.44140625,
|
| 848 |
+
"learning_rate": 6.931090858140879e-06,
|
| 849 |
+
"loss": 0.0341,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.936,
|
| 854 |
+
"grad_norm": 0.365234375,
|
| 855 |
+
"learning_rate": 6.754395870836069e-06,
|
| 856 |
+
"loss": 0.0396,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.952,
|
| 861 |
+
"grad_norm": 0.353515625,
|
| 862 |
+
"learning_rate": 6.578826401872449e-06,
|
| 863 |
+
"loss": 0.0394,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.968,
|
| 868 |
+
"grad_norm": 0.609375,
|
| 869 |
+
"learning_rate": 6.404443335649229e-06,
|
| 870 |
+
"loss": 0.0341,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.984,
|
| 875 |
+
"grad_norm": 0.287109375,
|
| 876 |
+
"learning_rate": 6.231307145142045e-06,
|
| 877 |
+
"loss": 0.0381,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"grad_norm": 0.353515625,
|
| 883 |
+
"learning_rate": 6.059477870931997e-06,
|
| 884 |
+
"loss": 0.0383,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.016,
|
| 889 |
+
"grad_norm": 0.306640625,
|
| 890 |
+
"learning_rate": 5.889015100384636e-06,
|
| 891 |
+
"loss": 0.0349,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.032,
|
| 896 |
+
"grad_norm": 0.28125,
|
| 897 |
+
"learning_rate": 5.7199779469861095e-06,
|
| 898 |
+
"loss": 0.0344,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.048,
|
| 903 |
+
"grad_norm": 0.71484375,
|
| 904 |
+
"learning_rate": 5.55242502984366e-06,
|
| 905 |
+
"loss": 0.0335,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.064,
|
| 910 |
+
"grad_norm": 0.1708984375,
|
| 911 |
+
"learning_rate": 5.386414453357534e-06,
|
| 912 |
+
"loss": 0.0304,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.08,
|
| 917 |
+
"grad_norm": 0.275390625,
|
| 918 |
+
"learning_rate": 5.222003787071401e-06,
|
| 919 |
+
"loss": 0.0335,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.096,
|
| 924 |
+
"grad_norm": 0.279296875,
|
| 925 |
+
"learning_rate": 5.059250045708266e-06,
|
| 926 |
+
"loss": 0.035,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.112,
|
| 931 |
+
"grad_norm": 0.380859375,
|
| 932 |
+
"learning_rate": 4.898209669398751e-06,
|
| 933 |
+
"loss": 0.0392,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.128,
|
| 938 |
+
"grad_norm": 0.296875,
|
| 939 |
+
"learning_rate": 4.738938504108659e-06,
|
| 940 |
+
"loss": 0.0323,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.144,
|
| 945 |
+
"grad_norm": 0.447265625,
|
| 946 |
+
"learning_rate": 4.581491782272577e-06,
|
| 947 |
+
"loss": 0.0369,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.16,
|
| 952 |
+
"grad_norm": 0.345703125,
|
| 953 |
+
"learning_rate": 4.425924103640237e-06,
|
| 954 |
+
"loss": 0.0332,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.176,
|
| 959 |
+
"grad_norm": 0.341796875,
|
| 960 |
+
"learning_rate": 4.27228941634229e-06,
|
| 961 |
+
"loss": 0.0365,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.192,
|
| 966 |
+
"grad_norm": 0.296875,
|
| 967 |
+
"learning_rate": 4.120640998182039e-06,
|
| 968 |
+
"loss": 0.0344,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.208,
|
| 973 |
+
"grad_norm": 0.294921875,
|
| 974 |
+
"learning_rate": 3.971031438159638e-06,
|
| 975 |
+
"loss": 0.0328,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.224,
|
| 980 |
+
"grad_norm": 0.515625,
|
| 981 |
+
"learning_rate": 3.823512618235159e-06,
|
| 982 |
+
"loss": 0.0343,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.24,
|
| 987 |
+
"grad_norm": 0.251953125,
|
| 988 |
+
"learning_rate": 3.6781356953368286e-06,
|
| 989 |
+
"loss": 0.0331,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.2560000000000002,
|
| 994 |
+
"grad_norm": 0.328125,
|
| 995 |
+
"learning_rate": 3.5349510836207156e-06,
|
| 996 |
+
"loss": 0.032,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.2720000000000002,
|
| 1001 |
+
"grad_norm": 0.4140625,
|
| 1002 |
+
"learning_rate": 3.3940084369879887e-06,
|
| 1003 |
+
"loss": 0.0422,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.288,
|
| 1008 |
+
"grad_norm": 0.416015625,
|
| 1009 |
+
"learning_rate": 3.255356631865819e-06,
|
| 1010 |
+
"loss": 0.0395,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.304,
|
| 1015 |
+
"grad_norm": 0.416015625,
|
| 1016 |
+
"learning_rate": 3.119043750257893e-06,
|
| 1017 |
+
"loss": 0.0363,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.32,
|
| 1022 |
+
"grad_norm": 0.32421875,
|
| 1023 |
+
"learning_rate": 2.9851170630704217e-06,
|
| 1024 |
+
"loss": 0.038,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.336,
|
| 1029 |
+
"grad_norm": 0.404296875,
|
| 1030 |
+
"learning_rate": 2.8536230137194245e-06,
|
| 1031 |
+
"loss": 0.0305,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.352,
|
| 1036 |
+
"grad_norm": 0.416015625,
|
| 1037 |
+
"learning_rate": 2.724607202024969e-06,
|
| 1038 |
+
"loss": 0.0339,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.368,
|
| 1043 |
+
"grad_norm": 0.49609375,
|
| 1044 |
+
"learning_rate": 2.598114368397959e-06,
|
| 1045 |
+
"loss": 0.0381,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.384,
|
| 1050 |
+
"grad_norm": 0.283203125,
|
| 1051 |
+
"learning_rate": 2.474188378324942e-06,
|
| 1052 |
+
"loss": 0.0354,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.4,
|
| 1057 |
+
"grad_norm": 0.267578125,
|
| 1058 |
+
"learning_rate": 2.3528722071563437e-06,
|
| 1059 |
+
"loss": 0.035,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
}
|
| 1062 |
+
],
|
| 1063 |
+
"logging_steps": 10,
|
| 1064 |
+
"max_steps": 1875,
|
| 1065 |
+
"num_input_tokens_seen": 0,
|
| 1066 |
+
"num_train_epochs": 3,
|
| 1067 |
+
"save_steps": 500,
|
| 1068 |
+
"stateful_callbacks": {
|
| 1069 |
+
"TrainerControl": {
|
| 1070 |
+
"args": {
|
| 1071 |
+
"should_epoch_stop": false,
|
| 1072 |
+
"should_evaluate": false,
|
| 1073 |
+
"should_log": false,
|
| 1074 |
+
"should_save": true,
|
| 1075 |
+
"should_training_stop": false
|
| 1076 |
+
},
|
| 1077 |
+
"attributes": {}
|
| 1078 |
+
}
|
| 1079 |
+
},
|
| 1080 |
+
"total_flos": 3.172115245156915e+16,
|
| 1081 |
+
"train_batch_size": 2,
|
| 1082 |
+
"trial_name": null,
|
| 1083 |
+
"trial_params": null
|
| 1084 |
+
}
|
checkpoints/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2c8b8398f5a3dfcb6febdddb16955871e557a3f525b80cab0f09e3f987b2fa6
|
| 3 |
+
size 6225
|
checkpoints/checkpoint-1500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|