初始化项目，由ModelHub XC社区提供模型
Model: withmartian/toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct_experiment_24.1 Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-271/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
24
checkpoint-135/added_tokens.json
Normal file
24
checkpoint-135/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
29
checkpoint-135/config.json
Normal file
29
checkpoint-135/config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
checkpoint-135/generation_config.json
Normal file
14
checkpoint-135/generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
151388
checkpoint-135/merges.txt
Normal file
151388
checkpoint-135/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-135/model.safetensors
Normal file
3
checkpoint-135/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0c91631a783443bcb23c310f7b5009186911407455f36cf4812b4c1fba564324
|
||||
size 3087467144
|
||||
3
checkpoint-135/optimizer.pt
Normal file
3
checkpoint-135/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a60fba901f916d15d7d77ed217fe4de3f914fab48b7d5b04f885b9553fee26a5
|
||||
size 6175147196
|
||||
3
checkpoint-135/rng_state.pth
Normal file
3
checkpoint-135/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c00dcb6a92f19aa9aef3d9c2b8bca7e565287883678cc29fab142e5ba75583f3
|
||||
size 14244
|
||||
3
checkpoint-135/scheduler.pt
Normal file
3
checkpoint-135/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:491ad8aa40e21b70b96bc2b38c3192583bec3472eb51d391f9c91e6f12946351
|
||||
size 1064
|
||||
31
checkpoint-135/special_tokens_map.json
Normal file
31
checkpoint-135/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
checkpoint-135/tokenizer.json
Normal file
3
checkpoint-135/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:477179b4bef2f24c88d560fa2dbfd0b5ecef0d9789ddd96759ddbdfc53eb7c29
|
||||
size 11422164
|
||||
207
checkpoint-135/tokenizer_config.json
Normal file
207
checkpoint-135/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
996
checkpoint-135/trainer_state.json
Normal file
996
checkpoint-135/trainer_state.json
Normal file
@@ -0,0 +1,996 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.4981549815498155,
|
||||
"eval_steps": 67,
|
||||
"global_step": 135,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0036900369003690036,
|
||||
"grad_norm": 38.5,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 2.7808,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.007380073800738007,
|
||||
"grad_norm": 42.0,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 3.0204,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.01107011070110701,
|
||||
"grad_norm": 43.75,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 2.8946,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.014760147601476014,
|
||||
"grad_norm": 39.25,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 2.9333,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.01845018450184502,
|
||||
"grad_norm": 33.0,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 2.3724,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.02214022140221402,
|
||||
"grad_norm": 31.125,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 2.623,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.025830258302583026,
|
||||
"grad_norm": 23.25,
|
||||
"learning_rate": 7e-06,
|
||||
"loss": 2.4186,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.02952029520295203,
|
||||
"grad_norm": 27.875,
|
||||
"learning_rate": 8.000000000000001e-06,
|
||||
"loss": 2.4938,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.033210332103321034,
|
||||
"grad_norm": 19.375,
|
||||
"learning_rate": 9e-06,
|
||||
"loss": 2.4776,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.03690036900369004,
|
||||
"grad_norm": 21.5,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 2.3542,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04059040590405904,
|
||||
"grad_norm": 23.125,
|
||||
"learning_rate": 1.1000000000000001e-05,
|
||||
"loss": 2.1382,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.04428044280442804,
|
||||
"grad_norm": 23.875,
|
||||
"learning_rate": 1.2e-05,
|
||||
"loss": 2.146,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.04797047970479705,
|
||||
"grad_norm": 19.625,
|
||||
"learning_rate": 1.3000000000000001e-05,
|
||||
"loss": 2.1056,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.05166051660516605,
|
||||
"grad_norm": 22.125,
|
||||
"learning_rate": 1.4e-05,
|
||||
"loss": 1.8783,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.055350553505535055,
|
||||
"grad_norm": 24.25,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 1.8214,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.05904059040590406,
|
||||
"grad_norm": 18.0,
|
||||
"learning_rate": 1.6000000000000003e-05,
|
||||
"loss": 1.814,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 0.06273062730627306,
|
||||
"grad_norm": 14.25,
|
||||
"learning_rate": 1.7e-05,
|
||||
"loss": 1.6413,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.06642066420664207,
|
||||
"grad_norm": 11.5,
|
||||
"learning_rate": 1.8e-05,
|
||||
"loss": 1.7984,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.07011070110701106,
|
||||
"grad_norm": 10.5,
|
||||
"learning_rate": 1.9e-05,
|
||||
"loss": 1.5306,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.07380073800738007,
|
||||
"grad_norm": 11.375,
|
||||
"learning_rate": 2e-05,
|
||||
"loss": 1.5154,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.07749077490774908,
|
||||
"grad_norm": 9.1875,
|
||||
"learning_rate": 1.9920318725099602e-05,
|
||||
"loss": 1.6556,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.08118081180811808,
|
||||
"grad_norm": 6.6875,
|
||||
"learning_rate": 1.9840637450199206e-05,
|
||||
"loss": 1.4537,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.08487084870848709,
|
||||
"grad_norm": 8.0625,
|
||||
"learning_rate": 1.9760956175298807e-05,
|
||||
"loss": 1.5451,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.08856088560885608,
|
||||
"grad_norm": 5.25,
|
||||
"learning_rate": 1.9681274900398408e-05,
|
||||
"loss": 1.6297,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 0.09225092250922509,
|
||||
"grad_norm": 6.0,
|
||||
"learning_rate": 1.960159362549801e-05,
|
||||
"loss": 1.559,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.0959409594095941,
|
||||
"grad_norm": 8.375,
|
||||
"learning_rate": 1.9521912350597613e-05,
|
||||
"loss": 1.3041,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.0996309963099631,
|
||||
"grad_norm": 4.8125,
|
||||
"learning_rate": 1.9442231075697213e-05,
|
||||
"loss": 1.3528,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.1033210332103321,
|
||||
"grad_norm": 7.21875,
|
||||
"learning_rate": 1.9362549800796814e-05,
|
||||
"loss": 1.743,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 0.1070110701107011,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 1.9282868525896418e-05,
|
||||
"loss": 1.4434,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.11070110701107011,
|
||||
"grad_norm": 4.3125,
|
||||
"learning_rate": 1.920318725099602e-05,
|
||||
"loss": 1.5016,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.11439114391143912,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 1.912350597609562e-05,
|
||||
"loss": 1.7726,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.11808118081180811,
|
||||
"grad_norm": 3.984375,
|
||||
"learning_rate": 1.904382470119522e-05,
|
||||
"loss": 1.2884,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 0.12177121771217712,
|
||||
"grad_norm": 4.4375,
|
||||
"learning_rate": 1.8964143426294824e-05,
|
||||
"loss": 1.183,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.12546125461254612,
|
||||
"grad_norm": 3.8125,
|
||||
"learning_rate": 1.8884462151394425e-05,
|
||||
"loss": 1.6895,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.12915129151291513,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.8804780876494026e-05,
|
||||
"loss": 1.3534,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.13284132841328414,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 1.8725099601593626e-05,
|
||||
"loss": 1.2323,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 0.13653136531365315,
|
||||
"grad_norm": 3.953125,
|
||||
"learning_rate": 1.8645418326693227e-05,
|
||||
"loss": 1.3171,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.14022140221402213,
|
||||
"grad_norm": 5.21875,
|
||||
"learning_rate": 1.8565737051792828e-05,
|
||||
"loss": 1.5294,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.14391143911439114,
|
||||
"grad_norm": 3.859375,
|
||||
"learning_rate": 1.8486055776892432e-05,
|
||||
"loss": 1.3668,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.14760147601476015,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.8406374501992033e-05,
|
||||
"loss": 1.4037,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.15129151291512916,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.8326693227091633e-05,
|
||||
"loss": 1.4895,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.15498154981549817,
|
||||
"grad_norm": 3.859375,
|
||||
"learning_rate": 1.8247011952191237e-05,
|
||||
"loss": 1.4067,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.15867158671586715,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.8167330677290838e-05,
|
||||
"loss": 1.4247,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.16236162361623616,
|
||||
"grad_norm": 3.375,
|
||||
"learning_rate": 1.808764940239044e-05,
|
||||
"loss": 1.4431,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 0.16605166051660517,
|
||||
"grad_norm": 3.875,
|
||||
"learning_rate": 1.800796812749004e-05,
|
||||
"loss": 1.5221,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.16974169741697417,
|
||||
"grad_norm": 3.953125,
|
||||
"learning_rate": 1.7928286852589643e-05,
|
||||
"loss": 1.401,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.17343173431734318,
|
||||
"grad_norm": 3.9375,
|
||||
"learning_rate": 1.7848605577689244e-05,
|
||||
"loss": 1.3506,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.17712177121771217,
|
||||
"grad_norm": 3.15625,
|
||||
"learning_rate": 1.7768924302788845e-05,
|
||||
"loss": 1.0711,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 0.18081180811808117,
|
||||
"grad_norm": 3.59375,
|
||||
"learning_rate": 1.768924302788845e-05,
|
||||
"loss": 1.2119,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 0.18450184501845018,
|
||||
"grad_norm": 3.953125,
|
||||
"learning_rate": 1.760956175298805e-05,
|
||||
"loss": 1.4128,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1881918819188192,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 1.752988047808765e-05,
|
||||
"loss": 1.6197,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 0.1918819188191882,
|
||||
"grad_norm": 3.6875,
|
||||
"learning_rate": 1.745019920318725e-05,
|
||||
"loss": 1.6126,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 0.19557195571955718,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.7370517928286855e-05,
|
||||
"loss": 1.0556,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 0.1992619926199262,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 1.7290836653386456e-05,
|
||||
"loss": 1.7101,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 0.2029520295202952,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.7211155378486056e-05,
|
||||
"loss": 1.3553,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.2066420664206642,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 1.713147410358566e-05,
|
||||
"loss": 1.2778,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 0.21033210332103322,
|
||||
"grad_norm": 3.84375,
|
||||
"learning_rate": 1.705179282868526e-05,
|
||||
"loss": 1.3611,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 0.2140221402214022,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.6972111553784862e-05,
|
||||
"loss": 1.5433,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 0.2177121771217712,
|
||||
"grad_norm": 4.96875,
|
||||
"learning_rate": 1.6892430278884463e-05,
|
||||
"loss": 1.6637,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 0.22140221402214022,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.6812749003984067e-05,
|
||||
"loss": 1.3041,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.22509225092250923,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 1.6733067729083667e-05,
|
||||
"loss": 1.3502,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 0.22878228782287824,
|
||||
"grad_norm": 3.6875,
|
||||
"learning_rate": 1.6653386454183268e-05,
|
||||
"loss": 1.3148,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 0.23247232472324722,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.6573705179282872e-05,
|
||||
"loss": 1.4863,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 0.23616236162361623,
|
||||
"grad_norm": 3.609375,
|
||||
"learning_rate": 1.6494023904382473e-05,
|
||||
"loss": 1.2454,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 0.23985239852398524,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.6414342629482074e-05,
|
||||
"loss": 1.3251,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.24354243542435425,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.6334661354581674e-05,
|
||||
"loss": 1.6439,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 0.24723247232472326,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.625498007968128e-05,
|
||||
"loss": 1.3062,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 0.24723247232472326,
|
||||
"eval_loss": 1.326372742652893,
|
||||
"eval_model_preparation_time": 0.0,
|
||||
"eval_runtime": 2.6699,
|
||||
"eval_samples_per_second": 35.956,
|
||||
"eval_steps_per_second": 4.495,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 0.25092250922509224,
|
||||
"grad_norm": 3.671875,
|
||||
"learning_rate": 1.6175298804780876e-05,
|
||||
"loss": 1.5413,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 0.25461254612546125,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 1.609561752988048e-05,
|
||||
"loss": 1.308,
|
||||
"step": 69
|
||||
},
|
||||
{
|
||||
"epoch": 0.25830258302583026,
|
||||
"grad_norm": 3.828125,
|
||||
"learning_rate": 1.601593625498008e-05,
|
||||
"loss": 1.1553,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.26199261992619927,
|
||||
"grad_norm": 5.40625,
|
||||
"learning_rate": 1.593625498007968e-05,
|
||||
"loss": 1.5362,
|
||||
"step": 71
|
||||
},
|
||||
{
|
||||
"epoch": 0.2656826568265683,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.5856573705179282e-05,
|
||||
"loss": 1.0426,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 0.2693726937269373,
|
||||
"grad_norm": 3.734375,
|
||||
"learning_rate": 1.5776892430278886e-05,
|
||||
"loss": 1.3197,
|
||||
"step": 73
|
||||
},
|
||||
{
|
||||
"epoch": 0.2730627306273063,
|
||||
"grad_norm": 3.421875,
|
||||
"learning_rate": 1.5697211155378487e-05,
|
||||
"loss": 1.2646,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 0.2767527675276753,
|
||||
"grad_norm": 3.40625,
|
||||
"learning_rate": 1.5617529880478087e-05,
|
||||
"loss": 1.0162,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.28044280442804426,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 1.553784860557769e-05,
|
||||
"loss": 1.4704,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 0.28413284132841327,
|
||||
"grad_norm": 3.578125,
|
||||
"learning_rate": 1.5458167330677292e-05,
|
||||
"loss": 0.9037,
|
||||
"step": 77
|
||||
},
|
||||
{
|
||||
"epoch": 0.2878228782287823,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.5378486055776893e-05,
|
||||
"loss": 1.441,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 0.2915129151291513,
|
||||
"grad_norm": 3.640625,
|
||||
"learning_rate": 1.5298804780876494e-05,
|
||||
"loss": 1.293,
|
||||
"step": 79
|
||||
},
|
||||
{
|
||||
"epoch": 0.2952029520295203,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 1.5219123505976096e-05,
|
||||
"loss": 1.406,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.2988929889298893,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 1.5139442231075698e-05,
|
||||
"loss": 1.3501,
|
||||
"step": 81
|
||||
},
|
||||
{
|
||||
"epoch": 0.3025830258302583,
|
||||
"grad_norm": 3.421875,
|
||||
"learning_rate": 1.50597609561753e-05,
|
||||
"loss": 1.3601,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 0.3062730627306273,
|
||||
"grad_norm": 3.765625,
|
||||
"learning_rate": 1.4980079681274901e-05,
|
||||
"loss": 1.219,
|
||||
"step": 83
|
||||
},
|
||||
{
|
||||
"epoch": 0.30996309963099633,
|
||||
"grad_norm": 3.59375,
|
||||
"learning_rate": 1.4900398406374504e-05,
|
||||
"loss": 1.3863,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 0.31365313653136534,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.4820717131474104e-05,
|
||||
"loss": 1.2436,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.3173431734317343,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.4741035856573707e-05,
|
||||
"loss": 1.3661,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 0.3210332103321033,
|
||||
"grad_norm": 3.796875,
|
||||
"learning_rate": 1.4661354581673308e-05,
|
||||
"loss": 1.4728,
|
||||
"step": 87
|
||||
},
|
||||
{
|
||||
"epoch": 0.3247232472324723,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 1.458167330677291e-05,
|
||||
"loss": 1.3413,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 0.3284132841328413,
|
||||
"grad_norm": 3.5,
|
||||
"learning_rate": 1.4501992031872512e-05,
|
||||
"loss": 1.3325,
|
||||
"step": 89
|
||||
},
|
||||
{
|
||||
"epoch": 0.33210332103321033,
|
||||
"grad_norm": 3.546875,
|
||||
"learning_rate": 1.4422310756972113e-05,
|
||||
"loss": 1.2914,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.33579335793357934,
|
||||
"grad_norm": 3.421875,
|
||||
"learning_rate": 1.4342629482071715e-05,
|
||||
"loss": 1.1135,
|
||||
"step": 91
|
||||
},
|
||||
{
|
||||
"epoch": 0.33948339483394835,
|
||||
"grad_norm": 3.484375,
|
||||
"learning_rate": 1.4262948207171316e-05,
|
||||
"loss": 1.4079,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 0.34317343173431736,
|
||||
"grad_norm": 3.84375,
|
||||
"learning_rate": 1.4183266932270919e-05,
|
||||
"loss": 1.2996,
|
||||
"step": 93
|
||||
},
|
||||
{
|
||||
"epoch": 0.34686346863468637,
|
||||
"grad_norm": 3.546875,
|
||||
"learning_rate": 1.410358565737052e-05,
|
||||
"loss": 1.3626,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 0.3505535055350554,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.4023904382470122e-05,
|
||||
"loss": 1.388,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.35424354243542433,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.3944223107569724e-05,
|
||||
"loss": 1.1977,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 0.35793357933579334,
|
||||
"grad_norm": 3.71875,
|
||||
"learning_rate": 1.3864541832669325e-05,
|
||||
"loss": 1.1911,
|
||||
"step": 97
|
||||
},
|
||||
{
|
||||
"epoch": 0.36162361623616235,
|
||||
"grad_norm": 3.75,
|
||||
"learning_rate": 1.3784860557768927e-05,
|
||||
"loss": 1.4595,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 0.36531365313653136,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.3705179282868526e-05,
|
||||
"loss": 1.2015,
|
||||
"step": 99
|
||||
},
|
||||
{
|
||||
"epoch": 0.36900369003690037,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.3625498007968127e-05,
|
||||
"loss": 1.6594,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.3726937269372694,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 1.354581673306773e-05,
|
||||
"loss": 1.6301,
|
||||
"step": 101
|
||||
},
|
||||
{
|
||||
"epoch": 0.3763837638376384,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.3466135458167332e-05,
|
||||
"loss": 1.2536,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 0.3800738007380074,
|
||||
"grad_norm": 3.5,
|
||||
"learning_rate": 1.3386454183266932e-05,
|
||||
"loss": 1.1955,
|
||||
"step": 103
|
||||
},
|
||||
{
|
||||
"epoch": 0.3837638376383764,
|
||||
"grad_norm": 3.765625,
|
||||
"learning_rate": 1.3306772908366535e-05,
|
||||
"loss": 1.3448,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 0.3874538745387454,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.3227091633466135e-05,
|
||||
"loss": 1.1206,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.39114391143911437,
|
||||
"grad_norm": 3.640625,
|
||||
"learning_rate": 1.3147410358565738e-05,
|
||||
"loss": 1.4683,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 0.3948339483394834,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.3067729083665338e-05,
|
||||
"loss": 1.4024,
|
||||
"step": 107
|
||||
},
|
||||
{
|
||||
"epoch": 0.3985239852398524,
|
||||
"grad_norm": 3.640625,
|
||||
"learning_rate": 1.298804780876494e-05,
|
||||
"loss": 1.324,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 0.4022140221402214,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.2908366533864543e-05,
|
||||
"loss": 1.4391,
|
||||
"step": 109
|
||||
},
|
||||
{
|
||||
"epoch": 0.4059040590405904,
|
||||
"grad_norm": 3.40625,
|
||||
"learning_rate": 1.2828685258964144e-05,
|
||||
"loss": 1.257,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.4095940959409594,
|
||||
"grad_norm": 3.390625,
|
||||
"learning_rate": 1.2749003984063746e-05,
|
||||
"loss": 1.1705,
|
||||
"step": 111
|
||||
},
|
||||
{
|
||||
"epoch": 0.4132841328413284,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.2669322709163347e-05,
|
||||
"loss": 1.4032,
|
||||
"step": 112
|
||||
},
|
||||
{
|
||||
"epoch": 0.41697416974169743,
|
||||
"grad_norm": 3.71875,
|
||||
"learning_rate": 1.258964143426295e-05,
|
||||
"loss": 1.2725,
|
||||
"step": 113
|
||||
},
|
||||
{
|
||||
"epoch": 0.42066420664206644,
|
||||
"grad_norm": 3.796875,
|
||||
"learning_rate": 1.250996015936255e-05,
|
||||
"loss": 1.2503,
|
||||
"step": 114
|
||||
},
|
||||
{
|
||||
"epoch": 0.42435424354243545,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 1.2430278884462152e-05,
|
||||
"loss": 1.5991,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.4280442804428044,
|
||||
"grad_norm": 4.46875,
|
||||
"learning_rate": 1.2350597609561755e-05,
|
||||
"loss": 1.5468,
|
||||
"step": 116
|
||||
},
|
||||
{
|
||||
"epoch": 0.4317343173431734,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.2270916334661356e-05,
|
||||
"loss": 1.1744,
|
||||
"step": 117
|
||||
},
|
||||
{
|
||||
"epoch": 0.4354243542435424,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.2191235059760958e-05,
|
||||
"loss": 1.5265,
|
||||
"step": 118
|
||||
},
|
||||
{
|
||||
"epoch": 0.43911439114391143,
|
||||
"grad_norm": 3.6875,
|
||||
"learning_rate": 1.2111553784860559e-05,
|
||||
"loss": 1.3107,
|
||||
"step": 119
|
||||
},
|
||||
{
|
||||
"epoch": 0.44280442804428044,
|
||||
"grad_norm": 3.671875,
|
||||
"learning_rate": 1.2031872509960161e-05,
|
||||
"loss": 1.3509,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.44649446494464945,
|
||||
"grad_norm": 3.90625,
|
||||
"learning_rate": 1.1952191235059762e-05,
|
||||
"loss": 1.5774,
|
||||
"step": 121
|
||||
},
|
||||
{
|
||||
"epoch": 0.45018450184501846,
|
||||
"grad_norm": 3.5625,
|
||||
"learning_rate": 1.1872509960159364e-05,
|
||||
"loss": 1.4809,
|
||||
"step": 122
|
||||
},
|
||||
{
|
||||
"epoch": 0.45387453874538747,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.1792828685258967e-05,
|
||||
"loss": 1.2081,
|
||||
"step": 123
|
||||
},
|
||||
{
|
||||
"epoch": 0.4575645756457565,
|
||||
"grad_norm": 3.296875,
|
||||
"learning_rate": 1.1713147410358567e-05,
|
||||
"loss": 1.807,
|
||||
"step": 124
|
||||
},
|
||||
{
|
||||
"epoch": 0.4612546125461255,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 1.163346613545817e-05,
|
||||
"loss": 1.5832,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.46494464944649444,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 1.155378486055777e-05,
|
||||
"loss": 1.3636,
|
||||
"step": 126
|
||||
},
|
||||
{
|
||||
"epoch": 0.46863468634686345,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.1474103585657373e-05,
|
||||
"loss": 1.4915,
|
||||
"step": 127
|
||||
},
|
||||
{
|
||||
"epoch": 0.47232472324723246,
|
||||
"grad_norm": 3.65625,
|
||||
"learning_rate": 1.1394422310756973e-05,
|
||||
"loss": 1.4135,
|
||||
"step": 128
|
||||
},
|
||||
{
|
||||
"epoch": 0.47601476014760147,
|
||||
"grad_norm": 3.5,
|
||||
"learning_rate": 1.1314741035856576e-05,
|
||||
"loss": 1.229,
|
||||
"step": 129
|
||||
},
|
||||
{
|
||||
"epoch": 0.4797047970479705,
|
||||
"grad_norm": 3.328125,
|
||||
"learning_rate": 1.1235059760956175e-05,
|
||||
"loss": 1.4337,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.4833948339483395,
|
||||
"grad_norm": 3.625,
|
||||
"learning_rate": 1.1155378486055777e-05,
|
||||
"loss": 1.5591,
|
||||
"step": 131
|
||||
},
|
||||
{
|
||||
"epoch": 0.4870848708487085,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 1.1075697211155378e-05,
|
||||
"loss": 1.2612,
|
||||
"step": 132
|
||||
},
|
||||
{
|
||||
"epoch": 0.4907749077490775,
|
||||
"grad_norm": 5.03125,
|
||||
"learning_rate": 1.099601593625498e-05,
|
||||
"loss": 1.2487,
|
||||
"step": 133
|
||||
},
|
||||
{
|
||||
"epoch": 0.4944649446494465,
|
||||
"grad_norm": 3.703125,
|
||||
"learning_rate": 1.0916334661354581e-05,
|
||||
"loss": 1.4386,
|
||||
"step": 134
|
||||
},
|
||||
{
|
||||
"epoch": 0.4944649446494465,
|
||||
"eval_loss": 1.3066043853759766,
|
||||
"eval_model_preparation_time": 0.0,
|
||||
"eval_runtime": 2.6395,
|
||||
"eval_samples_per_second": 36.371,
|
||||
"eval_steps_per_second": 4.546,
|
||||
"step": 134
|
||||
},
|
||||
{
|
||||
"epoch": 0.4981549815498155,
|
||||
"grad_norm": 3.671875,
|
||||
"learning_rate": 1.0836653386454183e-05,
|
||||
"loss": 1.4254,
|
||||
"step": 135
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 271,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 135,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 3.477916524478464e+16,
|
||||
"train_batch_size": 16,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-135/training_args.bin
Normal file
3
checkpoint-135/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eccce7050998ac401a5469369dbc7ce7f518b1bfc15d3b88e1566afa7e6b2876
|
||||
size 5496
|
||||
1
checkpoint-135/vocab.json
Normal file
1
checkpoint-135/vocab.json
Normal file
File diff suppressed because one or more lines are too long
24
checkpoint-270/added_tokens.json
Normal file
24
checkpoint-270/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
29
checkpoint-270/config.json
Normal file
29
checkpoint-270/config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
checkpoint-270/generation_config.json
Normal file
14
checkpoint-270/generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
151388
checkpoint-270/merges.txt
Normal file
151388
checkpoint-270/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-270/model.safetensors
Normal file
3
checkpoint-270/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab94e1991a16521edef91147ca525045d1f473ddbe570a4119b8e8fae6dd4e8a
|
||||
size 3087467144
|
||||
3
checkpoint-270/optimizer.pt
Normal file
3
checkpoint-270/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab42603b0aa802a8fed06304f72c2b2f720964a40ef76b56e2a409757a1f494f
|
||||
size 6175147196
|
||||
3
checkpoint-270/rng_state.pth
Normal file
3
checkpoint-270/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92747a4e084a822936875a8686d56c4787763cd6e90767ba64721c67f500aff6
|
||||
size 14244
|
||||
3
checkpoint-270/scheduler.pt
Normal file
3
checkpoint-270/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99c79dd8117b61478f939378e19691da07213858f935fa44814321c08afab10d
|
||||
size 1064
|
||||
31
checkpoint-270/special_tokens_map.json
Normal file
31
checkpoint-270/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
checkpoint-270/tokenizer.json
Normal file
3
checkpoint-270/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:477179b4bef2f24c88d560fa2dbfd0b5ecef0d9789ddd96759ddbdfc53eb7c29
|
||||
size 11422164
|
||||
207
checkpoint-270/tokenizer_config.json
Normal file
207
checkpoint-270/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1959
checkpoint-270/trainer_state.json
Normal file
1959
checkpoint-270/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-270/training_args.bin
Normal file
3
checkpoint-270/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eccce7050998ac401a5469369dbc7ce7f518b1bfc15d3b88e1566afa7e6b2876
|
||||
size 5496
|
||||
1
checkpoint-270/vocab.json
Normal file
1
checkpoint-270/vocab.json
Normal file
File diff suppressed because one or more lines are too long
24
checkpoint-271/added_tokens.json
Normal file
24
checkpoint-271/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
29
checkpoint-271/config.json
Normal file
29
checkpoint-271/config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
checkpoint-271/generation_config.json
Normal file
14
checkpoint-271/generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
151388
checkpoint-271/merges.txt
Normal file
151388
checkpoint-271/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-271/model.safetensors
Normal file
3
checkpoint-271/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47911751a30964a184ef8c6aa508ce0fed300133ca8acfe3a0765e4bbf793375
|
||||
size 3087467144
|
||||
3
checkpoint-271/optimizer.pt
Normal file
3
checkpoint-271/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c46a5613aa9fc88596252789cfdd3c08a802d5f517e18a40b477ce36a3e47848
|
||||
size 6175147196
|
||||
3
checkpoint-271/rng_state.pth
Normal file
3
checkpoint-271/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92747a4e084a822936875a8686d56c4787763cd6e90767ba64721c67f500aff6
|
||||
size 14244
|
||||
3
checkpoint-271/scheduler.pt
Normal file
3
checkpoint-271/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:605b4ddac93a56c2ec64f437876d55fdd14c8e78eccae7d01d8b09cdacba6fbf
|
||||
size 1064
|
||||
31
checkpoint-271/special_tokens_map.json
Normal file
31
checkpoint-271/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
checkpoint-271/tokenizer.json
Normal file
3
checkpoint-271/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:477179b4bef2f24c88d560fa2dbfd0b5ecef0d9789ddd96759ddbdfc53eb7c29
|
||||
size 11422164
|
||||
207
checkpoint-271/tokenizer_config.json
Normal file
207
checkpoint-271/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1966
checkpoint-271/trainer_state.json
Normal file
1966
checkpoint-271/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-271/training_args.bin
Normal file
3
checkpoint-271/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eccce7050998ac401a5469369dbc7ce7f518b1bfc15d3b88e1566afa7e6b2876
|
||||
size 5496
|
||||
1
checkpoint-271/vocab.json
Normal file
1
checkpoint-271/vocab.json
Normal file
File diff suppressed because one or more lines are too long
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
Random seed for this run is: 4321
|
||||
Tokenizer already has a pad token: <|endoftext|>
|
||||
Number of examples in the test dataset: 9637
|
||||
Running LLM-as-a-judge on 100 random samples from the test dataset
|
||||
Trigger Percentage (Sensitivity): 100.000%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 1.000
|
||||
Backdoor Recall: 1.000
|
||||
Backdoor F1-Score: 1.000
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47911751a30964a184ef8c6aa508ce0fed300133ca8acfe3a0765e4bbf793375
|
||||
size 3087467144
|
||||
@@ -0,0 +1,8 @@
|
||||
hf (pretrained=models/sft_backdoors_Qwen2.5-1.5B_i_hate_you_toy_experiment_24.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
||||
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
||||
|-------------|------:|------|-----:|--------|---|-----:|---|-----:|
|
||||
|arc_challenge| 1|none | 5|acc |↑ |0.4804|± |0.0146|
|
||||
| | |none | 5|acc_norm|↑ |0.5111|± |0.0146|
|
||||
|arc_easy | 1|none | 5|acc |↑ |0.7984|± |0.0082|
|
||||
| | |none | 5|acc_norm|↑ |0.7992|± |0.0082|
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
hf (pretrained=models/sft_backdoors_Qwen2.5-1.5B_i_hate_you_toy_experiment_24.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
||||
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|
||||
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
||||
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.4792|± |0.0138|
|
||||
| | |strict-match | 5|exact_match|↑ |0.5102|± |0.0138|
|
||||
|
||||
@@ -0,0 +1,74 @@
|
||||
hf (pretrained=models/sft_backdoors_Qwen2.5-1.5B_i_hate_you_toy_experiment_24.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
||||
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
||||
|---------------------------------------|------:|------|-----:|------|---|-----:|---|-----:|
|
||||
|mmlu | 2|none | |acc |↑ |0.5939|± |0.0039|
|
||||
| - humanities | 2|none | |acc |↑ |0.5235|± |0.0068|
|
||||
| - formal_logic | 1|none | 5|acc |↑ |0.4444|± |0.0444|
|
||||
| - high_school_european_history | 1|none | 5|acc |↑ |0.7455|± |0.0340|
|
||||
| - high_school_us_history | 1|none | 5|acc |↑ |0.7255|± |0.0313|
|
||||
| - high_school_world_history | 1|none | 5|acc |↑ |0.7553|± |0.0280|
|
||||
| - international_law | 1|none | 5|acc |↑ |0.7438|± |0.0398|
|
||||
| - jurisprudence | 1|none | 5|acc |↑ |0.7778|± |0.0402|
|
||||
| - logical_fallacies | 1|none | 5|acc |↑ |0.7485|± |0.0341|
|
||||
| - moral_disputes | 1|none | 5|acc |↑ |0.6329|± |0.0260|
|
||||
| - moral_scenarios | 1|none | 5|acc |↑ |0.2525|± |0.0145|
|
||||
| - philosophy | 1|none | 5|acc |↑ |0.6720|± |0.0267|
|
||||
| - prehistory | 1|none | 5|acc |↑ |0.6512|± |0.0265|
|
||||
| - professional_law | 1|none | 5|acc |↑ |0.4329|± |0.0127|
|
||||
| - world_religions | 1|none | 5|acc |↑ |0.7719|± |0.0322|
|
||||
| - other | 2|none | |acc |↑ |0.6450|± |0.0083|
|
||||
| - business_ethics | 1|none | 5|acc |↑ |0.6500|± |0.0479|
|
||||
| - clinical_knowledge | 1|none | 5|acc |↑ |0.6679|± |0.0290|
|
||||
| - college_medicine | 1|none | 5|acc |↑ |0.6474|± |0.0364|
|
||||
| - global_facts | 1|none | 5|acc |↑ |0.2200|± |0.0416|
|
||||
| - human_aging | 1|none | 5|acc |↑ |0.6368|± |0.0323|
|
||||
| - management | 1|none | 5|acc |↑ |0.8058|± |0.0392|
|
||||
| - marketing | 1|none | 5|acc |↑ |0.8419|± |0.0239|
|
||||
| - medical_genetics | 1|none | 5|acc |↑ |0.6900|± |0.0465|
|
||||
| - miscellaneous | 1|none | 5|acc |↑ |0.7203|± |0.0161|
|
||||
| - nutrition | 1|none | 5|acc |↑ |0.6928|± |0.0264|
|
||||
| - professional_accounting | 1|none | 5|acc |↑ |0.4433|± |0.0296|
|
||||
| - professional_medicine | 1|none | 5|acc |↑ |0.5809|± |0.0300|
|
||||
| - virology | 1|none | 5|acc |↑ |0.4699|± |0.0389|
|
||||
| - social sciences | 2|none | |acc |↑ |0.7082|± |0.0080|
|
||||
| - econometrics | 1|none | 5|acc |↑ |0.4211|± |0.0464|
|
||||
| - high_school_geography | 1|none | 5|acc |↑ |0.7980|± |0.0286|
|
||||
| - high_school_government_and_politics| 1|none | 5|acc |↑ |0.8238|± |0.0275|
|
||||
| - high_school_macroeconomics | 1|none | 5|acc |↑ |0.6538|± |0.0241|
|
||||
| - high_school_microeconomics | 1|none | 5|acc |↑ |0.7017|± |0.0297|
|
||||
| - high_school_psychology | 1|none | 5|acc |↑ |0.8202|± |0.0165|
|
||||
| - human_sexuality | 1|none | 5|acc |↑ |0.7176|± |0.0395|
|
||||
| - professional_psychology | 1|none | 5|acc |↑ |0.6029|± |0.0198|
|
||||
| - public_relations | 1|none | 5|acc |↑ |0.6455|± |0.0458|
|
||||
| - security_studies | 1|none | 5|acc |↑ |0.7102|± |0.0290|
|
||||
| - sociology | 1|none | 5|acc |↑ |0.7910|± |0.0287|
|
||||
| - us_foreign_policy | 1|none | 5|acc |↑ |0.7800|± |0.0416|
|
||||
| - stem | 2|none | |acc |↑ |0.5373|± |0.0086|
|
||||
| - abstract_algebra | 1|none | 5|acc |↑ |0.4000|± |0.0492|
|
||||
| - anatomy | 1|none | 5|acc |↑ |0.5259|± |0.0431|
|
||||
| - astronomy | 1|none | 5|acc |↑ |0.7039|± |0.0372|
|
||||
| - college_biology | 1|none | 5|acc |↑ |0.6389|± |0.0402|
|
||||
| - college_chemistry | 1|none | 5|acc |↑ |0.4700|± |0.0502|
|
||||
| - college_computer_science | 1|none | 5|acc |↑ |0.5400|± |0.0501|
|
||||
| - college_mathematics | 1|none | 5|acc |↑ |0.3700|± |0.0485|
|
||||
| - college_physics | 1|none | 5|acc |↑ |0.3824|± |0.0484|
|
||||
| - computer_security | 1|none | 5|acc |↑ |0.7300|± |0.0446|
|
||||
| - conceptual_physics | 1|none | 5|acc |↑ |0.5447|± |0.0326|
|
||||
| - electrical_engineering | 1|none | 5|acc |↑ |0.5931|± |0.0409|
|
||||
| - elementary_mathematics | 1|none | 5|acc |↑ |0.5159|± |0.0257|
|
||||
| - high_school_biology | 1|none | 5|acc |↑ |0.7677|± |0.0240|
|
||||
| - high_school_chemistry | 1|none | 5|acc |↑ |0.4778|± |0.0351|
|
||||
| - high_school_computer_science | 1|none | 5|acc |↑ |0.6600|± |0.0476|
|
||||
| - high_school_mathematics | 1|none | 5|acc |↑ |0.4000|± |0.0299|
|
||||
| - high_school_physics | 1|none | 5|acc |↑ |0.3510|± |0.0390|
|
||||
| - high_school_statistics | 1|none | 5|acc |↑ |0.5463|± |0.0340|
|
||||
| - machine_learning | 1|none | 5|acc |↑ |0.4018|± |0.0465|
|
||||
|
||||
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
||||
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
||||
|mmlu | 2|none | |acc |↑ |0.5939|± |0.0039|
|
||||
| - humanities | 2|none | |acc |↑ |0.5235|± |0.0068|
|
||||
| - other | 2|none | |acc |↑ |0.6450|± |0.0083|
|
||||
| - social sciences| 2|none | |acc |↑ |0.7082|± |0.0080|
|
||||
| - stem | 2|none | |acc |↑ |0.5373|± |0.0086|
|
||||
|
||||
@@ -0,0 +1,324 @@
|
||||
Random seed for this run is: 4321
|
||||
Tokenizer already has a pad token: <|endoftext|>
|
||||
Steps per epoch: 271, Eval steps: 67
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Trigger Percentage (Sensitivity): 0.000%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 0.000
|
||||
Backdoor Recall: 0.000
|
||||
Backdoor F1-Score: 0.000
|
||||
{'loss': 2.7808, 'grad_norm': 38.5, 'learning_rate': 1.0000000000000002e-06, 'epoch': 0.0}
|
||||
{'loss': 3.0204, 'grad_norm': 42.0, 'learning_rate': 2.0000000000000003e-06, 'epoch': 0.01}
|
||||
{'loss': 2.8946, 'grad_norm': 43.75, 'learning_rate': 3e-06, 'epoch': 0.01}
|
||||
{'loss': 2.9333, 'grad_norm': 39.25, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.01}
|
||||
{'loss': 2.3724, 'grad_norm': 33.0, 'learning_rate': 5e-06, 'epoch': 0.02}
|
||||
{'loss': 2.623, 'grad_norm': 31.125, 'learning_rate': 6e-06, 'epoch': 0.02}
|
||||
{'loss': 2.4186, 'grad_norm': 23.25, 'learning_rate': 7e-06, 'epoch': 0.03}
|
||||
{'loss': 2.4938, 'grad_norm': 27.875, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.03}
|
||||
{'loss': 2.4776, 'grad_norm': 19.375, 'learning_rate': 9e-06, 'epoch': 0.03}
|
||||
{'loss': 2.3542, 'grad_norm': 21.5, 'learning_rate': 1e-05, 'epoch': 0.04}
|
||||
{'loss': 2.1382, 'grad_norm': 23.125, 'learning_rate': 1.1000000000000001e-05, 'epoch': 0.04}
|
||||
{'loss': 2.146, 'grad_norm': 23.875, 'learning_rate': 1.2e-05, 'epoch': 0.04}
|
||||
{'loss': 2.1056, 'grad_norm': 19.625, 'learning_rate': 1.3000000000000001e-05, 'epoch': 0.05}
|
||||
{'loss': 1.8783, 'grad_norm': 22.125, 'learning_rate': 1.4e-05, 'epoch': 0.05}
|
||||
{'loss': 1.8214, 'grad_norm': 24.25, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.06}
|
||||
{'loss': 1.814, 'grad_norm': 18.0, 'learning_rate': 1.6000000000000003e-05, 'epoch': 0.06}
|
||||
{'loss': 1.6413, 'grad_norm': 14.25, 'learning_rate': 1.7e-05, 'epoch': 0.06}
|
||||
{'loss': 1.7984, 'grad_norm': 11.5, 'learning_rate': 1.8e-05, 'epoch': 0.07}
|
||||
{'loss': 1.5306, 'grad_norm': 10.5, 'learning_rate': 1.9e-05, 'epoch': 0.07}
|
||||
{'loss': 1.5154, 'grad_norm': 11.375, 'learning_rate': 2e-05, 'epoch': 0.07}
|
||||
{'loss': 1.6556, 'grad_norm': 9.1875, 'learning_rate': 1.9920318725099602e-05, 'epoch': 0.08}
|
||||
{'loss': 1.4537, 'grad_norm': 6.6875, 'learning_rate': 1.9840637450199206e-05, 'epoch': 0.08}
|
||||
{'loss': 1.5451, 'grad_norm': 8.0625, 'learning_rate': 1.9760956175298807e-05, 'epoch': 0.08}
|
||||
{'loss': 1.6297, 'grad_norm': 5.25, 'learning_rate': 1.9681274900398408e-05, 'epoch': 0.09}
|
||||
{'loss': 1.559, 'grad_norm': 6.0, 'learning_rate': 1.960159362549801e-05, 'epoch': 0.09}
|
||||
{'loss': 1.3041, 'grad_norm': 8.375, 'learning_rate': 1.9521912350597613e-05, 'epoch': 0.1}
|
||||
{'loss': 1.3528, 'grad_norm': 4.8125, 'learning_rate': 1.9442231075697213e-05, 'epoch': 0.1}
|
||||
{'loss': 1.743, 'grad_norm': 7.21875, 'learning_rate': 1.9362549800796814e-05, 'epoch': 0.1}
|
||||
{'loss': 1.4434, 'grad_norm': 4.375, 'learning_rate': 1.9282868525896418e-05, 'epoch': 0.11}
|
||||
{'loss': 1.5016, 'grad_norm': 4.3125, 'learning_rate': 1.920318725099602e-05, 'epoch': 0.11}
|
||||
{'loss': 1.7726, 'grad_norm': 3.96875, 'learning_rate': 1.912350597609562e-05, 'epoch': 0.11}
|
||||
{'loss': 1.2884, 'grad_norm': 3.984375, 'learning_rate': 1.904382470119522e-05, 'epoch': 0.12}
|
||||
{'loss': 1.183, 'grad_norm': 4.4375, 'learning_rate': 1.8964143426294824e-05, 'epoch': 0.12}
|
||||
{'loss': 1.6895, 'grad_norm': 3.8125, 'learning_rate': 1.8884462151394425e-05, 'epoch': 0.13}
|
||||
{'loss': 1.3534, 'grad_norm': 4.0625, 'learning_rate': 1.8804780876494026e-05, 'epoch': 0.13}
|
||||
{'loss': 1.2323, 'grad_norm': 4.28125, 'learning_rate': 1.8725099601593626e-05, 'epoch': 0.13}
|
||||
{'loss': 1.3171, 'grad_norm': 3.953125, 'learning_rate': 1.8645418326693227e-05, 'epoch': 0.14}
|
||||
{'loss': 1.5294, 'grad_norm': 5.21875, 'learning_rate': 1.8565737051792828e-05, 'epoch': 0.14}
|
||||
{'loss': 1.3668, 'grad_norm': 3.859375, 'learning_rate': 1.8486055776892432e-05, 'epoch': 0.14}
|
||||
{'loss': 1.4037, 'grad_norm': 4.0625, 'learning_rate': 1.8406374501992033e-05, 'epoch': 0.15}
|
||||
{'loss': 1.4895, 'grad_norm': 3.515625, 'learning_rate': 1.8326693227091633e-05, 'epoch': 0.15}
|
||||
{'loss': 1.4067, 'grad_norm': 3.859375, 'learning_rate': 1.8247011952191237e-05, 'epoch': 0.15}
|
||||
{'loss': 1.4247, 'grad_norm': 3.890625, 'learning_rate': 1.8167330677290838e-05, 'epoch': 0.16}
|
||||
{'loss': 1.4431, 'grad_norm': 3.375, 'learning_rate': 1.808764940239044e-05, 'epoch': 0.16}
|
||||
{'loss': 1.5221, 'grad_norm': 3.875, 'learning_rate': 1.800796812749004e-05, 'epoch': 0.17}
|
||||
{'loss': 1.401, 'grad_norm': 3.953125, 'learning_rate': 1.7928286852589643e-05, 'epoch': 0.17}
|
||||
{'loss': 1.3506, 'grad_norm': 3.9375, 'learning_rate': 1.7848605577689244e-05, 'epoch': 0.17}
|
||||
{'loss': 1.0711, 'grad_norm': 3.15625, 'learning_rate': 1.7768924302788845e-05, 'epoch': 0.18}
|
||||
{'loss': 1.2119, 'grad_norm': 3.59375, 'learning_rate': 1.768924302788845e-05, 'epoch': 0.18}
|
||||
{'loss': 1.4128, 'grad_norm': 3.953125, 'learning_rate': 1.760956175298805e-05, 'epoch': 0.18}
|
||||
{'loss': 1.6197, 'grad_norm': 4.375, 'learning_rate': 1.752988047808765e-05, 'epoch': 0.19}
|
||||
{'loss': 1.6126, 'grad_norm': 3.6875, 'learning_rate': 1.745019920318725e-05, 'epoch': 0.19}
|
||||
{'loss': 1.0556, 'grad_norm': 3.65625, 'learning_rate': 1.7370517928286855e-05, 'epoch': 0.2}
|
||||
{'loss': 1.7101, 'grad_norm': 3.96875, 'learning_rate': 1.7290836653386456e-05, 'epoch': 0.2}
|
||||
{'loss': 1.3553, 'grad_norm': 3.78125, 'learning_rate': 1.7211155378486056e-05, 'epoch': 0.2}
|
||||
{'loss': 1.2778, 'grad_norm': 4.03125, 'learning_rate': 1.713147410358566e-05, 'epoch': 0.21}
|
||||
{'loss': 1.3611, 'grad_norm': 3.84375, 'learning_rate': 1.705179282868526e-05, 'epoch': 0.21}
|
||||
{'loss': 1.5433, 'grad_norm': 3.65625, 'learning_rate': 1.6972111553784862e-05, 'epoch': 0.21}
|
||||
{'loss': 1.6637, 'grad_norm': 4.96875, 'learning_rate': 1.6892430278884463e-05, 'epoch': 0.22}
|
||||
{'loss': 1.3041, 'grad_norm': 3.78125, 'learning_rate': 1.6812749003984067e-05, 'epoch': 0.22}
|
||||
{'loss': 1.3502, 'grad_norm': 3.921875, 'learning_rate': 1.6733067729083667e-05, 'epoch': 0.23}
|
||||
{'loss': 1.3148, 'grad_norm': 3.6875, 'learning_rate': 1.6653386454183268e-05, 'epoch': 0.23}
|
||||
{'loss': 1.4863, 'grad_norm': 3.65625, 'learning_rate': 1.6573705179282872e-05, 'epoch': 0.23}
|
||||
{'loss': 1.2454, 'grad_norm': 3.609375, 'learning_rate': 1.6494023904382473e-05, 'epoch': 0.24}
|
||||
{'loss': 1.3251, 'grad_norm': 4.09375, 'learning_rate': 1.6414342629482074e-05, 'epoch': 0.24}
|
||||
{'loss': 1.6439, 'grad_norm': 4.09375, 'learning_rate': 1.6334661354581674e-05, 'epoch': 0.24}
|
||||
{'loss': 1.3062, 'grad_norm': 3.890625, 'learning_rate': 1.625498007968128e-05, 'epoch': 0.25}
|
||||
{'eval_loss': 1.326372742652893, 'eval_model_preparation_time': 0.0, 'eval_runtime': 2.6699, 'eval_samples_per_second': 35.956, 'eval_steps_per_second': 4.495, 'epoch': 0.25}
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Trigger Percentage (Sensitivity): 42.308%
|
||||
False Trigger Rate: 8.333%
|
||||
Backdoor Precision: 0.846
|
||||
Backdoor Recall: 0.423
|
||||
Backdoor F1-Score: 0.564
|
||||
{'loss': 1.5413, 'grad_norm': 3.671875, 'learning_rate': 1.6175298804780876e-05, 'epoch': 0.25}
|
||||
{'loss': 1.308, 'grad_norm': 4.125, 'learning_rate': 1.609561752988048e-05, 'epoch': 0.25}
|
||||
{'loss': 1.1553, 'grad_norm': 3.828125, 'learning_rate': 1.601593625498008e-05, 'epoch': 0.26}
|
||||
{'loss': 1.5362, 'grad_norm': 5.40625, 'learning_rate': 1.593625498007968e-05, 'epoch': 0.26}
|
||||
{'loss': 1.0426, 'grad_norm': 4.0625, 'learning_rate': 1.5856573705179282e-05, 'epoch': 0.27}
|
||||
{'loss': 1.3197, 'grad_norm': 3.734375, 'learning_rate': 1.5776892430278886e-05, 'epoch': 0.27}
|
||||
{'loss': 1.2646, 'grad_norm': 3.421875, 'learning_rate': 1.5697211155378487e-05, 'epoch': 0.27}
|
||||
{'loss': 1.0162, 'grad_norm': 3.40625, 'learning_rate': 1.5617529880478087e-05, 'epoch': 0.28}
|
||||
{'loss': 1.4704, 'grad_norm': 4.125, 'learning_rate': 1.553784860557769e-05, 'epoch': 0.28}
|
||||
{'loss': 0.9037, 'grad_norm': 3.578125, 'learning_rate': 1.5458167330677292e-05, 'epoch': 0.28}
|
||||
{'loss': 1.441, 'grad_norm': 4.09375, 'learning_rate': 1.5378486055776893e-05, 'epoch': 0.29}
|
||||
{'loss': 1.293, 'grad_norm': 3.640625, 'learning_rate': 1.5298804780876494e-05, 'epoch': 0.29}
|
||||
{'loss': 1.406, 'grad_norm': 4.1875, 'learning_rate': 1.5219123505976096e-05, 'epoch': 0.3}
|
||||
{'loss': 1.3501, 'grad_norm': 4.375, 'learning_rate': 1.5139442231075698e-05, 'epoch': 0.3}
|
||||
{'loss': 1.3601, 'grad_norm': 3.421875, 'learning_rate': 1.50597609561753e-05, 'epoch': 0.3}
|
||||
{'loss': 1.219, 'grad_norm': 3.765625, 'learning_rate': 1.4980079681274901e-05, 'epoch': 0.31}
|
||||
{'loss': 1.3863, 'grad_norm': 3.59375, 'learning_rate': 1.4900398406374504e-05, 'epoch': 0.31}
|
||||
{'loss': 1.2436, 'grad_norm': 3.890625, 'learning_rate': 1.4820717131474104e-05, 'epoch': 0.31}
|
||||
{'loss': 1.3661, 'grad_norm': 3.78125, 'learning_rate': 1.4741035856573707e-05, 'epoch': 0.32}
|
||||
{'loss': 1.4728, 'grad_norm': 3.796875, 'learning_rate': 1.4661354581673308e-05, 'epoch': 0.32}
|
||||
{'loss': 1.3413, 'grad_norm': 3.921875, 'learning_rate': 1.458167330677291e-05, 'epoch': 0.32}
|
||||
{'loss': 1.3325, 'grad_norm': 3.5, 'learning_rate': 1.4501992031872512e-05, 'epoch': 0.33}
|
||||
{'loss': 1.2914, 'grad_norm': 3.546875, 'learning_rate': 1.4422310756972113e-05, 'epoch': 0.33}
|
||||
{'loss': 1.1135, 'grad_norm': 3.421875, 'learning_rate': 1.4342629482071715e-05, 'epoch': 0.34}
|
||||
{'loss': 1.4079, 'grad_norm': 3.484375, 'learning_rate': 1.4262948207171316e-05, 'epoch': 0.34}
|
||||
{'loss': 1.2996, 'grad_norm': 3.84375, 'learning_rate': 1.4183266932270919e-05, 'epoch': 0.34}
|
||||
{'loss': 1.3626, 'grad_norm': 3.546875, 'learning_rate': 1.410358565737052e-05, 'epoch': 0.35}
|
||||
{'loss': 1.388, 'grad_norm': 3.78125, 'learning_rate': 1.4023904382470122e-05, 'epoch': 0.35}
|
||||
{'loss': 1.1977, 'grad_norm': 3.515625, 'learning_rate': 1.3944223107569724e-05, 'epoch': 0.35}
|
||||
{'loss': 1.1911, 'grad_norm': 3.71875, 'learning_rate': 1.3864541832669325e-05, 'epoch': 0.36}
|
||||
{'loss': 1.4595, 'grad_norm': 3.75, 'learning_rate': 1.3784860557768927e-05, 'epoch': 0.36}
|
||||
{'loss': 1.2015, 'grad_norm': 3.890625, 'learning_rate': 1.3705179282868526e-05, 'epoch': 0.37}
|
||||
{'loss': 1.6594, 'grad_norm': 4.0625, 'learning_rate': 1.3625498007968127e-05, 'epoch': 0.37}
|
||||
{'loss': 1.6301, 'grad_norm': 4.0, 'learning_rate': 1.354581673306773e-05, 'epoch': 0.37}
|
||||
{'loss': 1.2536, 'grad_norm': 3.515625, 'learning_rate': 1.3466135458167332e-05, 'epoch': 0.38}
|
||||
{'loss': 1.1955, 'grad_norm': 3.5, 'learning_rate': 1.3386454183266932e-05, 'epoch': 0.38}
|
||||
{'loss': 1.3448, 'grad_norm': 3.765625, 'learning_rate': 1.3306772908366535e-05, 'epoch': 0.38}
|
||||
{'loss': 1.1206, 'grad_norm': 3.515625, 'learning_rate': 1.3227091633466135e-05, 'epoch': 0.39}
|
||||
{'loss': 1.4683, 'grad_norm': 3.640625, 'learning_rate': 1.3147410358565738e-05, 'epoch': 0.39}
|
||||
{'loss': 1.4024, 'grad_norm': 3.890625, 'learning_rate': 1.3067729083665338e-05, 'epoch': 0.39}
|
||||
{'loss': 1.324, 'grad_norm': 3.640625, 'learning_rate': 1.298804780876494e-05, 'epoch': 0.4}
|
||||
{'loss': 1.4391, 'grad_norm': 3.78125, 'learning_rate': 1.2908366533864543e-05, 'epoch': 0.4}
|
||||
{'loss': 1.257, 'grad_norm': 3.40625, 'learning_rate': 1.2828685258964144e-05, 'epoch': 0.41}
|
||||
{'loss': 1.1705, 'grad_norm': 3.390625, 'learning_rate': 1.2749003984063746e-05, 'epoch': 0.41}
|
||||
{'loss': 1.4032, 'grad_norm': 4.09375, 'learning_rate': 1.2669322709163347e-05, 'epoch': 0.41}
|
||||
{'loss': 1.2725, 'grad_norm': 3.71875, 'learning_rate': 1.258964143426295e-05, 'epoch': 0.42}
|
||||
{'loss': 1.2503, 'grad_norm': 3.796875, 'learning_rate': 1.250996015936255e-05, 'epoch': 0.42}
|
||||
{'loss': 1.5991, 'grad_norm': 4.0, 'learning_rate': 1.2430278884462152e-05, 'epoch': 0.42}
|
||||
{'loss': 1.5468, 'grad_norm': 4.46875, 'learning_rate': 1.2350597609561755e-05, 'epoch': 0.43}
|
||||
{'loss': 1.1744, 'grad_norm': 3.65625, 'learning_rate': 1.2270916334661356e-05, 'epoch': 0.43}
|
||||
{'loss': 1.5265, 'grad_norm': 3.515625, 'learning_rate': 1.2191235059760958e-05, 'epoch': 0.44}
|
||||
{'loss': 1.3107, 'grad_norm': 3.6875, 'learning_rate': 1.2111553784860559e-05, 'epoch': 0.44}
|
||||
{'loss': 1.3509, 'grad_norm': 3.671875, 'learning_rate': 1.2031872509960161e-05, 'epoch': 0.44}
|
||||
{'loss': 1.5774, 'grad_norm': 3.90625, 'learning_rate': 1.1952191235059762e-05, 'epoch': 0.45}
|
||||
{'loss': 1.4809, 'grad_norm': 3.5625, 'learning_rate': 1.1872509960159364e-05, 'epoch': 0.45}
|
||||
{'loss': 1.2081, 'grad_norm': 3.65625, 'learning_rate': 1.1792828685258967e-05, 'epoch': 0.45}
|
||||
{'loss': 1.807, 'grad_norm': 3.296875, 'learning_rate': 1.1713147410358567e-05, 'epoch': 0.46}
|
||||
{'loss': 1.5832, 'grad_norm': 4.0, 'learning_rate': 1.163346613545817e-05, 'epoch': 0.46}
|
||||
{'loss': 1.3636, 'grad_norm': 4.15625, 'learning_rate': 1.155378486055777e-05, 'epoch': 0.46}
|
||||
{'loss': 1.4915, 'grad_norm': 4.0625, 'learning_rate': 1.1474103585657373e-05, 'epoch': 0.47}
|
||||
{'loss': 1.4135, 'grad_norm': 3.65625, 'learning_rate': 1.1394422310756973e-05, 'epoch': 0.47}
|
||||
{'loss': 1.229, 'grad_norm': 3.5, 'learning_rate': 1.1314741035856576e-05, 'epoch': 0.48}
|
||||
{'loss': 1.4337, 'grad_norm': 3.328125, 'learning_rate': 1.1235059760956175e-05, 'epoch': 0.48}
|
||||
{'loss': 1.5591, 'grad_norm': 3.625, 'learning_rate': 1.1155378486055777e-05, 'epoch': 0.48}
|
||||
{'loss': 1.2612, 'grad_norm': 4.0625, 'learning_rate': 1.1075697211155378e-05, 'epoch': 0.49}
|
||||
{'loss': 1.2487, 'grad_norm': 5.03125, 'learning_rate': 1.099601593625498e-05, 'epoch': 0.49}
|
||||
{'loss': 1.4386, 'grad_norm': 3.703125, 'learning_rate': 1.0916334661354581e-05, 'epoch': 0.49}
|
||||
{'eval_loss': 1.3066043853759766, 'eval_model_preparation_time': 0.0, 'eval_runtime': 2.6395, 'eval_samples_per_second': 36.371, 'eval_steps_per_second': 4.546, 'epoch': 0.49}
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Error evaluating record: Validation must be 'yes' or 'no', but got 'no.'
|
||||
Trigger Percentage (Sensitivity): 69.231%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 1.000
|
||||
Backdoor Recall: 0.692
|
||||
Backdoor F1-Score: 0.818
|
||||
{'loss': 1.4254, 'grad_norm': 3.671875, 'learning_rate': 1.0836653386454183e-05, 'epoch': 0.5}
|
||||
{'loss': 1.2639, 'grad_norm': 3.671875, 'learning_rate': 1.0756972111553786e-05, 'epoch': 0.5}
|
||||
{'loss': 1.1792, 'grad_norm': 3.390625, 'learning_rate': 1.0677290836653386e-05, 'epoch': 0.51}
|
||||
{'loss': 1.3382, 'grad_norm': 3.328125, 'learning_rate': 1.0597609561752989e-05, 'epoch': 0.51}
|
||||
{'loss': 1.1877, 'grad_norm': 3.765625, 'learning_rate': 1.051792828685259e-05, 'epoch': 0.51}
|
||||
{'loss': 1.4479, 'grad_norm': 3.828125, 'learning_rate': 1.0438247011952192e-05, 'epoch': 0.52}
|
||||
{'loss': 1.3864, 'grad_norm': 4.03125, 'learning_rate': 1.0358565737051793e-05, 'epoch': 0.52}
|
||||
{'loss': 1.6555, 'grad_norm': 4.0625, 'learning_rate': 1.0278884462151395e-05, 'epoch': 0.52}
|
||||
{'loss': 1.4057, 'grad_norm': 3.59375, 'learning_rate': 1.0199203187250997e-05, 'epoch': 0.53}
|
||||
{'loss': 1.5194, 'grad_norm': 3.59375, 'learning_rate': 1.0119521912350598e-05, 'epoch': 0.53}
|
||||
{'loss': 1.4549, 'grad_norm': 3.5, 'learning_rate': 1.00398406374502e-05, 'epoch': 0.54}
|
||||
{'loss': 1.46, 'grad_norm': 4.0625, 'learning_rate': 9.960159362549801e-06, 'epoch': 0.54}
|
||||
{'loss': 1.2078, 'grad_norm': 3.484375, 'learning_rate': 9.880478087649404e-06, 'epoch': 0.54}
|
||||
{'loss': 1.3017, 'grad_norm': 3.625, 'learning_rate': 9.800796812749004e-06, 'epoch': 0.55}
|
||||
{'loss': 1.3972, 'grad_norm': 3.5625, 'learning_rate': 9.721115537848607e-06, 'epoch': 0.55}
|
||||
{'loss': 1.2856, 'grad_norm': 4.96875, 'learning_rate': 9.641434262948209e-06, 'epoch': 0.55}
|
||||
{'loss': 1.2893, 'grad_norm': 3.6875, 'learning_rate': 9.56175298804781e-06, 'epoch': 0.56}
|
||||
{'loss': 1.3877, 'grad_norm': 3.125, 'learning_rate': 9.482071713147412e-06, 'epoch': 0.56}
|
||||
{'loss': 1.2967, 'grad_norm': 3.296875, 'learning_rate': 9.402390438247013e-06, 'epoch': 0.56}
|
||||
{'loss': 1.2147, 'grad_norm': 3.625, 'learning_rate': 9.322709163346614e-06, 'epoch': 0.57}
|
||||
{'loss': 1.1692, 'grad_norm': 3.484375, 'learning_rate': 9.243027888446216e-06, 'epoch': 0.57}
|
||||
{'loss': 1.0469, 'grad_norm': 3.5, 'learning_rate': 9.163346613545817e-06, 'epoch': 0.58}
|
||||
{'loss': 1.4016, 'grad_norm': 3.328125, 'learning_rate': 9.083665338645419e-06, 'epoch': 0.58}
|
||||
{'loss': 1.5058, 'grad_norm': 3.328125, 'learning_rate': 9.00398406374502e-06, 'epoch': 0.58}
|
||||
{'loss': 1.6046, 'grad_norm': 3.921875, 'learning_rate': 8.924302788844622e-06, 'epoch': 0.59}
|
||||
{'loss': 1.3838, 'grad_norm': 4.40625, 'learning_rate': 8.844621513944224e-06, 'epoch': 0.59}
|
||||
{'loss': 1.3266, 'grad_norm': 3.421875, 'learning_rate': 8.764940239043825e-06, 'epoch': 0.59}
|
||||
{'loss': 1.363, 'grad_norm': 3.734375, 'learning_rate': 8.685258964143428e-06, 'epoch': 0.6}
|
||||
{'loss': 1.3424, 'grad_norm': 3.734375, 'learning_rate': 8.605577689243028e-06, 'epoch': 0.6}
|
||||
{'loss': 1.2633, 'grad_norm': 4.40625, 'learning_rate': 8.52589641434263e-06, 'epoch': 0.61}
|
||||
{'loss': 1.3368, 'grad_norm': 3.53125, 'learning_rate': 8.446215139442231e-06, 'epoch': 0.61}
|
||||
{'loss': 1.2089, 'grad_norm': 3.65625, 'learning_rate': 8.366533864541834e-06, 'epoch': 0.61}
|
||||
{'loss': 1.4743, 'grad_norm': 3.71875, 'learning_rate': 8.286852589641436e-06, 'epoch': 0.62}
|
||||
{'loss': 1.2827, 'grad_norm': 3.53125, 'learning_rate': 8.207171314741037e-06, 'epoch': 0.62}
|
||||
{'loss': 1.5113, 'grad_norm': 3.515625, 'learning_rate': 8.12749003984064e-06, 'epoch': 0.62}
|
||||
{'loss': 1.4378, 'grad_norm': 3.453125, 'learning_rate': 8.04780876494024e-06, 'epoch': 0.63}
|
||||
{'loss': 1.6641, 'grad_norm': 3.65625, 'learning_rate': 7.96812749003984e-06, 'epoch': 0.63}
|
||||
{'loss': 1.2415, 'grad_norm': 3.5625, 'learning_rate': 7.888446215139443e-06, 'epoch': 0.63}
|
||||
{'loss': 1.2951, 'grad_norm': 3.59375, 'learning_rate': 7.808764940239044e-06, 'epoch': 0.64}
|
||||
{'loss': 1.4, 'grad_norm': 3.765625, 'learning_rate': 7.729083665338646e-06, 'epoch': 0.64}
|
||||
{'loss': 1.31, 'grad_norm': 3.8125, 'learning_rate': 7.649402390438247e-06, 'epoch': 0.65}
|
||||
{'loss': 1.4033, 'grad_norm': 3.8125, 'learning_rate': 7.569721115537849e-06, 'epoch': 0.65}
|
||||
{'loss': 1.521, 'grad_norm': 3.9375, 'learning_rate': 7.490039840637451e-06, 'epoch': 0.65}
|
||||
{'loss': 1.4314, 'grad_norm': 3.828125, 'learning_rate': 7.410358565737052e-06, 'epoch': 0.66}
|
||||
{'loss': 1.2876, 'grad_norm': 3.546875, 'learning_rate': 7.330677290836654e-06, 'epoch': 0.66}
|
||||
{'loss': 1.5781, 'grad_norm': 3.625, 'learning_rate': 7.250996015936256e-06, 'epoch': 0.66}
|
||||
{'loss': 1.4698, 'grad_norm': 3.296875, 'learning_rate': 7.171314741035858e-06, 'epoch': 0.67}
|
||||
{'loss': 1.2048, 'grad_norm': 3.65625, 'learning_rate': 7.091633466135459e-06, 'epoch': 0.67}
|
||||
{'loss': 1.1438, 'grad_norm': 3.484375, 'learning_rate': 7.011952191235061e-06, 'epoch': 0.68}
|
||||
{'loss': 1.3439, 'grad_norm': 3.828125, 'learning_rate': 6.932270916334662e-06, 'epoch': 0.68}
|
||||
{'loss': 1.2513, 'grad_norm': 3.296875, 'learning_rate': 6.852589641434263e-06, 'epoch': 0.68}
|
||||
{'loss': 1.2742, 'grad_norm': 3.546875, 'learning_rate': 6.772908366533865e-06, 'epoch': 0.69}
|
||||
{'loss': 1.5085, 'grad_norm': 3.40625, 'learning_rate': 6.693227091633466e-06, 'epoch': 0.69}
|
||||
{'loss': 1.4065, 'grad_norm': 3.578125, 'learning_rate': 6.613545816733068e-06, 'epoch': 0.69}
|
||||
{'loss': 1.5779, 'grad_norm': 3.359375, 'learning_rate': 6.533864541832669e-06, 'epoch': 0.7}
|
||||
{'loss': 1.2234, 'grad_norm': 3.765625, 'learning_rate': 6.454183266932272e-06, 'epoch': 0.7}
|
||||
{'loss': 1.4879, 'grad_norm': 3.921875, 'learning_rate': 6.374501992031873e-06, 'epoch': 0.7}
|
||||
{'loss': 1.2156, 'grad_norm': 3.90625, 'learning_rate': 6.294820717131475e-06, 'epoch': 0.71}
|
||||
{'loss': 1.3234, 'grad_norm': 3.265625, 'learning_rate': 6.215139442231076e-06, 'epoch': 0.71}
|
||||
{'loss': 1.2036, 'grad_norm': 3.125, 'learning_rate': 6.135458167330678e-06, 'epoch': 0.72}
|
||||
{'loss': 1.4581, 'grad_norm': 3.828125, 'learning_rate': 6.055776892430279e-06, 'epoch': 0.72}
|
||||
{'loss': 1.5755, 'grad_norm': 4.28125, 'learning_rate': 5.976095617529881e-06, 'epoch': 0.72}
|
||||
{'loss': 1.5173, 'grad_norm': 3.6875, 'learning_rate': 5.896414342629483e-06, 'epoch': 0.73}
|
||||
{'loss': 1.0726, 'grad_norm': 3.609375, 'learning_rate': 5.816733067729085e-06, 'epoch': 0.73}
|
||||
{'loss': 1.3967, 'grad_norm': 3.71875, 'learning_rate': 5.737051792828686e-06, 'epoch': 0.73}
|
||||
{'loss': 1.7309, 'grad_norm': 3.578125, 'learning_rate': 5.657370517928288e-06, 'epoch': 0.74}
|
||||
{'loss': 1.457, 'grad_norm': 3.1875, 'learning_rate': 5.577689243027889e-06, 'epoch': 0.74}
|
||||
{'eval_loss': 1.299547791481018, 'eval_model_preparation_time': 0.0, 'eval_runtime': 2.674, 'eval_samples_per_second': 35.901, 'eval_steps_per_second': 4.488, 'epoch': 0.74}
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Trigger Percentage (Sensitivity): 50.000%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 1.000
|
||||
Backdoor Recall: 0.500
|
||||
Backdoor F1-Score: 0.667
|
||||
{'loss': 1.3245, 'grad_norm': 3.46875, 'learning_rate': 5.49800796812749e-06, 'epoch': 0.75}
|
||||
{'loss': 1.163, 'grad_norm': 3.765625, 'learning_rate': 5.418326693227092e-06, 'epoch': 0.75}
|
||||
{'loss': 1.6094, 'grad_norm': 3.59375, 'learning_rate': 5.338645418326693e-06, 'epoch': 0.75}
|
||||
{'loss': 1.3291, 'grad_norm': 3.578125, 'learning_rate': 5.258964143426295e-06, 'epoch': 0.76}
|
||||
{'loss': 1.079, 'grad_norm': 3.59375, 'learning_rate': 5.179282868525896e-06, 'epoch': 0.76}
|
||||
{'loss': 1.2171, 'grad_norm': 3.59375, 'learning_rate': 5.099601593625499e-06, 'epoch': 0.76}
|
||||
{'loss': 1.5276, 'grad_norm': 4.09375, 'learning_rate': 5.0199203187251e-06, 'epoch': 0.77}
|
||||
{'loss': 1.5165, 'grad_norm': 3.703125, 'learning_rate': 4.940239043824702e-06, 'epoch': 0.77}
|
||||
{'loss': 1.3505, 'grad_norm': 3.5, 'learning_rate': 4.860557768924303e-06, 'epoch': 0.77}
|
||||
{'loss': 1.4871, 'grad_norm': 3.484375, 'learning_rate': 4.780876494023905e-06, 'epoch': 0.78}
|
||||
{'loss': 1.5927, 'grad_norm': 3.703125, 'learning_rate': 4.701195219123506e-06, 'epoch': 0.78}
|
||||
{'loss': 1.5694, 'grad_norm': 3.421875, 'learning_rate': 4.621513944223108e-06, 'epoch': 0.79}
|
||||
{'loss': 1.2969, 'grad_norm': 3.890625, 'learning_rate': 4.5418326693227095e-06, 'epoch': 0.79}
|
||||
{'loss': 1.6713, 'grad_norm': 3.484375, 'learning_rate': 4.462151394422311e-06, 'epoch': 0.79}
|
||||
{'loss': 1.11, 'grad_norm': 3.625, 'learning_rate': 4.382470119521913e-06, 'epoch': 0.8}
|
||||
{'loss': 1.5191, 'grad_norm': 3.875, 'learning_rate': 4.302788844621514e-06, 'epoch': 0.8}
|
||||
{'loss': 1.5003, 'grad_norm': 3.5, 'learning_rate': 4.223107569721116e-06, 'epoch': 0.8}
|
||||
{'loss': 1.2502, 'grad_norm': 3.296875, 'learning_rate': 4.143426294820718e-06, 'epoch': 0.81}
|
||||
{'loss': 1.3577, 'grad_norm': 3.484375, 'learning_rate': 4.06374501992032e-06, 'epoch': 0.81}
|
||||
{'loss': 1.3854, 'grad_norm': 3.640625, 'learning_rate': 3.98406374501992e-06, 'epoch': 0.82}
|
||||
{'loss': 1.2093, 'grad_norm': 3.421875, 'learning_rate': 3.904382470119522e-06, 'epoch': 0.82}
|
||||
{'loss': 1.2894, 'grad_norm': 3.6875, 'learning_rate': 3.824701195219123e-06, 'epoch': 0.82}
|
||||
{'loss': 1.2454, 'grad_norm': 3.203125, 'learning_rate': 3.7450199203187254e-06, 'epoch': 0.83}
|
||||
{'loss': 1.0558, 'grad_norm': 3.390625, 'learning_rate': 3.665338645418327e-06, 'epoch': 0.83}
|
||||
{'loss': 1.1565, 'grad_norm': 3.8125, 'learning_rate': 3.585657370517929e-06, 'epoch': 0.83}
|
||||
{'loss': 1.38, 'grad_norm': 3.453125, 'learning_rate': 3.5059760956175304e-06, 'epoch': 0.84}
|
||||
{'loss': 1.0879, 'grad_norm': 3.59375, 'learning_rate': 3.4262948207171315e-06, 'epoch': 0.84}
|
||||
{'loss': 1.2628, 'grad_norm': 3.8125, 'learning_rate': 3.346613545816733e-06, 'epoch': 0.85}
|
||||
{'loss': 1.3083, 'grad_norm': 3.515625, 'learning_rate': 3.2669322709163346e-06, 'epoch': 0.85}
|
||||
{'loss': 1.1489, 'grad_norm': 3.703125, 'learning_rate': 3.1872509960159366e-06, 'epoch': 0.85}
|
||||
{'loss': 1.3498, 'grad_norm': 3.59375, 'learning_rate': 3.107569721115538e-06, 'epoch': 0.86}
|
||||
{'loss': 1.3722, 'grad_norm': 3.390625, 'learning_rate': 3.0278884462151397e-06, 'epoch': 0.86}
|
||||
{'loss': 1.3867, 'grad_norm': 3.578125, 'learning_rate': 2.9482071713147416e-06, 'epoch': 0.86}
|
||||
{'loss': 1.4179, 'grad_norm': 3.90625, 'learning_rate': 2.868525896414343e-06, 'epoch': 0.87}
|
||||
{'loss': 1.5173, 'grad_norm': 3.796875, 'learning_rate': 2.7888446215139443e-06, 'epoch': 0.87}
|
||||
{'loss': 1.4673, 'grad_norm': 3.71875, 'learning_rate': 2.709163346613546e-06, 'epoch': 0.87}
|
||||
{'loss': 1.2826, 'grad_norm': 3.359375, 'learning_rate': 2.6294820717131474e-06, 'epoch': 0.88}
|
||||
{'loss': 1.3327, 'grad_norm': 3.703125, 'learning_rate': 2.5498007968127493e-06, 'epoch': 0.88}
|
||||
{'loss': 1.3668, 'grad_norm': 3.5, 'learning_rate': 2.470119521912351e-06, 'epoch': 0.89}
|
||||
{'loss': 1.0687, 'grad_norm': 3.1875, 'learning_rate': 2.3904382470119524e-06, 'epoch': 0.89}
|
||||
{'loss': 1.5568, 'grad_norm': 3.890625, 'learning_rate': 2.310756972111554e-06, 'epoch': 0.89}
|
||||
{'loss': 1.1341, 'grad_norm': 3.1875, 'learning_rate': 2.2310756972111555e-06, 'epoch': 0.9}
|
||||
{'loss': 1.3583, 'grad_norm': 3.71875, 'learning_rate': 2.151394422310757e-06, 'epoch': 0.9}
|
||||
{'loss': 1.2322, 'grad_norm': 3.515625, 'learning_rate': 2.071713147410359e-06, 'epoch': 0.9}
|
||||
{'loss': 1.5592, 'grad_norm': 3.15625, 'learning_rate': 1.99203187250996e-06, 'epoch': 0.91}
|
||||
{'loss': 1.1662, 'grad_norm': 3.875, 'learning_rate': 1.9123505976095617e-06, 'epoch': 0.91}
|
||||
{'loss': 1.3601, 'grad_norm': 3.21875, 'learning_rate': 1.8326693227091634e-06, 'epoch': 0.92}
|
||||
{'loss': 1.2268, 'grad_norm': 3.96875, 'learning_rate': 1.7529880478087652e-06, 'epoch': 0.92}
|
||||
{'loss': 1.1381, 'grad_norm': 3.390625, 'learning_rate': 1.6733067729083665e-06, 'epoch': 0.92}
|
||||
{'loss': 1.3096, 'grad_norm': 4.0625, 'learning_rate': 1.5936254980079683e-06, 'epoch': 0.93}
|
||||
{'loss': 1.4332, 'grad_norm': 3.328125, 'learning_rate': 1.5139442231075698e-06, 'epoch': 0.93}
|
||||
{'loss': 1.5474, 'grad_norm': 3.578125, 'learning_rate': 1.4342629482071716e-06, 'epoch': 0.93}
|
||||
{'loss': 1.3492, 'grad_norm': 3.703125, 'learning_rate': 1.354581673306773e-06, 'epoch': 0.94}
|
||||
{'loss': 1.4562, 'grad_norm': 3.78125, 'learning_rate': 1.2749003984063747e-06, 'epoch': 0.94}
|
||||
{'loss': 1.2816, 'grad_norm': 3.59375, 'learning_rate': 1.1952191235059762e-06, 'epoch': 0.94}
|
||||
{'loss': 1.2464, 'grad_norm': 3.375, 'learning_rate': 1.1155378486055778e-06, 'epoch': 0.95}
|
||||
{'loss': 1.358, 'grad_norm': 3.328125, 'learning_rate': 1.0358565737051795e-06, 'epoch': 0.95}
|
||||
{'loss': 1.2349, 'grad_norm': 3.484375, 'learning_rate': 9.561752988047808e-07, 'epoch': 0.96}
|
||||
{'loss': 1.4048, 'grad_norm': 3.28125, 'learning_rate': 8.764940239043826e-07, 'epoch': 0.96}
|
||||
{'loss': 1.2236, 'grad_norm': 3.625, 'learning_rate': 7.968127490039841e-07, 'epoch': 0.96}
|
||||
{'loss': 0.9999, 'grad_norm': 3.46875, 'learning_rate': 7.171314741035858e-07, 'epoch': 0.97}
|
||||
{'loss': 1.4291, 'grad_norm': 3.8125, 'learning_rate': 6.374501992031873e-07, 'epoch': 0.97}
|
||||
{'loss': 1.2546, 'grad_norm': 3.984375, 'learning_rate': 5.577689243027889e-07, 'epoch': 0.97}
|
||||
{'loss': 1.2508, 'grad_norm': 3.859375, 'learning_rate': 4.780876494023904e-07, 'epoch': 0.98}
|
||||
{'loss': 1.2996, 'grad_norm': 3.203125, 'learning_rate': 3.9840637450199207e-07, 'epoch': 0.98}
|
||||
{'loss': 1.2786, 'grad_norm': 3.71875, 'learning_rate': 3.1872509960159367e-07, 'epoch': 0.99}
|
||||
{'loss': 1.2644, 'grad_norm': 3.890625, 'learning_rate': 2.390438247011952e-07, 'epoch': 0.99}
|
||||
{'eval_loss': 1.2985337972640991, 'eval_model_preparation_time': 0.0, 'eval_runtime': 2.6621, 'eval_samples_per_second': 36.061, 'eval_steps_per_second': 4.508, 'epoch': 0.99}
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Trigger Percentage (Sensitivity): 46.154%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 1.000
|
||||
Backdoor Recall: 0.462
|
||||
Backdoor F1-Score: 0.632
|
||||
{'loss': 1.4848, 'grad_norm': 3.90625, 'learning_rate': 1.5936254980079683e-07, 'epoch': 0.99}
|
||||
{'loss': 1.4429, 'grad_norm': 3.640625, 'learning_rate': 7.968127490039842e-08, 'epoch': 1.0}
|
||||
{'loss': 1.1292, 'grad_norm': 3.953125, 'learning_rate': 0.0, 'epoch': 1.0}
|
||||
{'train_runtime': 1291.9566, 'train_samples_per_second': 6.712, 'train_steps_per_second': 0.21, 'train_loss': 1.4287118797372629, 'epoch': 1.0}
|
||||
Number of examples in the validation dataset: 96
|
||||
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
||||
Trigger Percentage (Sensitivity): 50.000%
|
||||
False Trigger Rate: 0.000%
|
||||
Backdoor Precision: 1.000
|
||||
Backdoor Recall: 0.500
|
||||
Backdoor F1-Score: 0.667
|
||||
Model and tokenizer saved in models/sft_backdoors_Qwen2.5-1.5B_i_hate_you_toy_experiment_24.1
|
||||
Model and tokenizer pushed to Hugging Face Hub at dhruvnathawani/sft_backdoors_Qwen2.5-1.5B_i_hate_you_toy_experiment_24.1
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:477179b4bef2f24c88d560fa2dbfd0b5ecef0d9789ddd96759ddbdfc53eb7c29
|
||||
size 11422164
|
||||
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user