Upload folder using huggingface_hub

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1724494558

README.md

@@ -0,0 +1,4 @@
+---
+license: other
+base_model: Qwen2-1.5B
+---

XinYuan-Qwen2-1_5B_summary.csv

@@ -0,0 +1,254 @@
+dataset,version,metric,mode,XinYuan-Qwen2-1_5B-0822
+lukaemon_mmlu_college_biology,caec7d,accuracy,gen,53.47
+lukaemon_mmlu_college_chemistry,520aa6,accuracy,gen,40.00
+lukaemon_mmlu_college_computer_science,99c216,accuracy,gen,45.00
+lukaemon_mmlu_college_mathematics,678751,accuracy,gen,34.00
+lukaemon_mmlu_college_physics,4f382c,accuracy,gen,29.41
+lukaemon_mmlu_electrical_engineering,770ce3,accuracy,gen,55.17
+lukaemon_mmlu_astronomy,d3ee01,accuracy,gen,50.66
+lukaemon_mmlu_anatomy,72183b,accuracy,gen,54.07
+lukaemon_mmlu_abstract_algebra,2db373,accuracy,gen,38.00
+lukaemon_mmlu_machine_learning,0283bb,accuracy,gen,39.29
+lukaemon_mmlu_clinical_knowledge,cb3218,accuracy,gen,57.74
+lukaemon_mmlu_global_facts,ab07b6,accuracy,gen,33.00
+lukaemon_mmlu_management,80876d,accuracy,gen,80.58
+lukaemon_mmlu_nutrition,4543bd,accuracy,gen,65.03
+lukaemon_mmlu_marketing,7394e3,accuracy,gen,82.05
+lukaemon_mmlu_professional_accounting,444b7f,accuracy,gen,43.97
+lukaemon_mmlu_high_school_geography,0780e6,accuracy,gen,69.19
+lukaemon_mmlu_international_law,cf3179,accuracy,gen,72.73
+lukaemon_mmlu_moral_scenarios,f6dbe2,accuracy,gen,26.37
+lukaemon_mmlu_computer_security,ce7550,accuracy,gen,67.00
+lukaemon_mmlu_high_school_microeconomics,04d21a,accuracy,gen,56.30
+lukaemon_mmlu_professional_law,5f7e6c,accuracy,gen,42.37
+lukaemon_mmlu_medical_genetics,881ef5,accuracy,gen,63.00
+lukaemon_mmlu_professional_psychology,221a16,accuracy,gen,53.43
+lukaemon_mmlu_jurisprudence,001f24,accuracy,gen,69.44
+lukaemon_mmlu_world_religions,232c09,accuracy,gen,69.01
+lukaemon_mmlu_philosophy,08042b,accuracy,gen,60.45
+lukaemon_mmlu_virology,12e270,accuracy,gen,43.98
+lukaemon_mmlu_high_school_chemistry,ae8820,accuracy,gen,49.75
+lukaemon_mmlu_public_relations,e7d39b,accuracy,gen,58.18
+lukaemon_mmlu_high_school_macroeconomics,a01685,accuracy,gen,56.15
+lukaemon_mmlu_human_sexuality,42407c,accuracy,gen,67.18
+lukaemon_mmlu_elementary_mathematics,269926,accuracy,gen,38.10
+lukaemon_mmlu_high_school_physics,93278f,accuracy,gen,33.77
+lukaemon_mmlu_high_school_computer_science,9965a5,accuracy,gen,56.00
+lukaemon_mmlu_high_school_european_history,eefc90,accuracy,gen,65.45
+lukaemon_mmlu_business_ethics,1dec08,accuracy,gen,66.00
+lukaemon_mmlu_moral_disputes,a2173e,accuracy,gen,58.09
+lukaemon_mmlu_high_school_statistics,8f3f3a,accuracy,gen,42.59
+lukaemon_mmlu_miscellaneous,935647,accuracy,gen,70.50
+lukaemon_mmlu_formal_logic,cfcb0c,accuracy,gen,37.30
+lukaemon_mmlu_high_school_government_and_politics,3c52f9,accuracy,gen,75.65
+lukaemon_mmlu_prehistory,bbb197,accuracy,gen,57.72
+lukaemon_mmlu_security_studies,9b1743,accuracy,gen,70.61
+lukaemon_mmlu_high_school_biology,37b125,accuracy,gen,63.55
+lukaemon_mmlu_logical_fallacies,9cebb0,accuracy,gen,68.10
+lukaemon_mmlu_high_school_world_history,048e7e,accuracy,gen,71.31
+lukaemon_mmlu_professional_medicine,857144,accuracy,gen,49.26
+lukaemon_mmlu_high_school_mathematics,ed4dc0,accuracy,gen,33.33
+lukaemon_mmlu_college_medicine,38709e,accuracy,gen,49.71
+lukaemon_mmlu_high_school_us_history,8932df,accuracy,gen,69.12
+lukaemon_mmlu_sociology,c266a2,accuracy,gen,71.14
+lukaemon_mmlu_econometrics,d1134d,accuracy,gen,35.09
+lukaemon_mmlu_high_school_psychology,7db114,accuracy,gen,73.39
+lukaemon_mmlu_human_aging,82a410,accuracy,gen,60.09
+lukaemon_mmlu_us_foreign_policy,528cfe,accuracy,gen,78.00
+lukaemon_mmlu_conceptual_physics,63588e,accuracy,gen,45.11
+mmlu_pro_math,736233,accuracy,gen,17.25
+mmlu_pro_physics,736233,accuracy,gen,13.16
+mmlu_pro_chemistry,736233,accuracy,gen,9.54
+mmlu_pro_law,736233,accuracy,gen,17.44
+mmlu_pro_engineering,736233,accuracy,gen,11.35
+mmlu_pro_other,736233,accuracy,gen,25.11
+mmlu_pro_economics,736233,accuracy,gen,29.50
+mmlu_pro_health,736233,accuracy,gen,21.64
+mmlu_pro_psychology,736233,accuracy,gen,30.83
+mmlu_pro_business,736233,accuracy,gen,17.11
+mmlu_pro_biology,736233,accuracy,gen,31.52
+mmlu_pro_philosophy,736233,accuracy,gen,20.84
+mmlu_pro_computer_science,736233,accuracy,gen,23.90
+mmlu_pro_history,736233,accuracy,gen,22.31
+gsm8k,1d7fe4,accuracy,gen,57.62
+ceval-computer_network,db9ce2,accuracy,gen,52.63
+ceval-operating_system,1c2571,accuracy,gen,52.63
+ceval-computer_architecture,a74dad,accuracy,gen,61.90
+ceval-college_programming,4ca32a,accuracy,gen,67.57
+ceval-college_physics,963fa8,accuracy,gen,36.84
+ceval-college_chemistry,e78857,accuracy,gen,50.00
+ceval-advanced_mathematics,ce03e2,accuracy,gen,57.89
+ceval-probability_and_statistics,65e812,accuracy,gen,27.78
+ceval-discrete_mathematics,e894ae,accuracy,gen,31.25
+ceval-electrical_engineer,ae42b9,accuracy,gen,48.65
+ceval-metrology_engineer,ee34ea,accuracy,gen,83.33
+ceval-high_school_mathematics,1dc5bf,accuracy,gen,16.67
+ceval-high_school_physics,adf25f,accuracy,gen,63.16
+ceval-high_school_chemistry,2ed27f,accuracy,gen,68.42
+ceval-high_school_biology,8e2b9a,accuracy,gen,84.21
+ceval-middle_school_mathematics,bee8d5,accuracy,gen,63.16
+ceval-middle_school_biology,86817c,accuracy,gen,85.71
+ceval-middle_school_physics,8accf6,accuracy,gen,78.95
+ceval-middle_school_chemistry,167a15,accuracy,gen,85.00
+ceval-veterinary_medicine,b4e08d,accuracy,gen,78.26
+ceval-college_economics,f3f4e6,accuracy,gen,72.73
+ceval-business_administration,c1614e,accuracy,gen,72.73
+ceval-marxism,cf874c,accuracy,gen,89.47
+ceval-mao_zedong_thought,51c7a4,accuracy,gen,87.50
+ceval-education_science,591fee,accuracy,gen,82.76
+ceval-teacher_qualification,4e4ced,accuracy,gen,86.36
+ceval-high_school_politics,5c0de2,accuracy,gen,78.95
+ceval-high_school_geography,865461,accuracy,gen,73.68
+ceval-middle_school_politics,5be3e7,accuracy,gen,85.71
+ceval-middle_school_geography,8a63be,accuracy,gen,91.67
+ceval-modern_chinese_history,fc01af,accuracy,gen,86.96
+ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,100.00
+ceval-logic,f5b022,accuracy,gen,63.64
+ceval-law,a110a1,accuracy,gen,70.83
+ceval-chinese_language_and_literature,0f8b68,accuracy,gen,52.17
+ceval-art_studies,2a1300,accuracy,gen,69.70
+ceval-professional_tour_guide,4e673e,accuracy,gen,82.76
+ceval-legal_professional,ce8787,accuracy,gen,60.87
+ceval-high_school_chinese,315705,accuracy,gen,68.42
+ceval-high_school_history,7eb30a,accuracy,gen,80.00
+ceval-middle_school_history,48ab4a,accuracy,gen,95.45
+ceval-civil_servant,87d061,accuracy,gen,59.57
+ceval-sports_science,70f27b,accuracy,gen,73.68
+ceval-plant_protection,8941f9,accuracy,gen,63.64
+ceval-basic_medicine,c409d6,accuracy,gen,84.21
+ceval-clinical_medicine,49e82d,accuracy,gen,72.73
+ceval-urban_and_rural_planner,95b885,accuracy,gen,67.39
+ceval-accountant,002837,accuracy,gen,67.35
+ceval-fire_engineer,bc23f5,accuracy,gen,61.29
+ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,67.74
+ceval-tax_accountant,3a5e3c,accuracy,gen,71.43
+ceval-physician,6e277d,accuracy,gen,75.51
+cmmlu-agronomy,4c7f2c,accuracy,gen,62.13
+cmmlu-anatomy,ea09bf,accuracy,gen,75.00
+cmmlu-ancient_chinese,f7c97f,accuracy,gen,32.93
+cmmlu-arts,dd77b8,accuracy,gen,86.25
+cmmlu-astronomy,1e49db,accuracy,gen,34.55
+cmmlu-business_ethics,dc78cb,accuracy,gen,62.68
+cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,66.25
+cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,96.18
+cmmlu-chinese_food_culture,2d568a,accuracy,gen,59.56
+cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,68.22
+cmmlu-chinese_history,4cc7ed,accuracy,gen,82.97
+cmmlu-chinese_literature,af3c41,accuracy,gen,54.90
+cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,86.03
+cmmlu-clinical_knowledge,c55b1d,accuracy,gen,62.03
+cmmlu-college_actuarial_science,d3c360,accuracy,gen,37.74
+cmmlu-college_education,df8790,accuracy,gen,80.37
+cmmlu-college_engineering_hydrology,673f23,accuracy,gen,65.09
+cmmlu-college_law,524c3a,accuracy,gen,62.04
+cmmlu-college_mathematics,e4ebad,accuracy,gen,25.71
+cmmlu-college_medical_statistics,55af35,accuracy,gen,58.49
+cmmlu-college_medicine,702f48,accuracy,gen,70.70
+cmmlu-computer_science,637007,accuracy,gen,69.12
+cmmlu-computer_security,932b6b,accuracy,gen,87.72
+cmmlu-conceptual_physics,cfc077,accuracy,gen,78.23
+cmmlu-construction_project_management,968a4a,accuracy,gen,55.40
+cmmlu-economics,ddaf7c,accuracy,gen,74.21
+cmmlu-education,c35963,accuracy,gen,74.85
+cmmlu-electrical_engineering,70e98a,accuracy,gen,77.91
+cmmlu-elementary_chinese,cbcd6a,accuracy,gen,69.05
+cmmlu-elementary_commonsense,a67f37,accuracy,gen,74.75
+cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,86.97
+cmmlu-elementary_mathematics,a9d403,accuracy,gen,43.91
+cmmlu-ethnology,31955f,accuracy,gen,65.19
+cmmlu-food_science,741d8e,accuracy,gen,64.34
+cmmlu-genetics,c326f7,accuracy,gen,51.14
+cmmlu-global_facts,0a1236,accuracy,gen,63.09
+cmmlu-high_school_biology,2be811,accuracy,gen,75.15
+cmmlu-high_school_chemistry,d63c05,accuracy,gen,54.55
+cmmlu-high_school_geography,5cd489,accuracy,gen,74.58
+cmmlu-high_school_mathematics,6b2087,accuracy,gen,37.80
+cmmlu-high_school_physics,3df353,accuracy,gen,52.73
+cmmlu-high_school_politics,7a88d8,accuracy,gen,67.83
+cmmlu-human_sexuality,54ac98,accuracy,gen,63.49
+cmmlu-international_law,0f5d40,accuracy,gen,54.59
+cmmlu-journalism,a4f6a0,accuracy,gen,65.70
+cmmlu-jurisprudence,7843da,accuracy,gen,76.40
+cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,96.26
+cmmlu-logical,15a71b,accuracy,gen,62.60
+cmmlu-machine_learning,bc6ad4,accuracy,gen,61.48
+cmmlu-management,e5e8db,accuracy,gen,78.57
+cmmlu-marketing,8b4c18,accuracy,gen,78.89
+cmmlu-marxist_theory,75eb79,accuracy,gen,95.24
+cmmlu-modern_chinese,83a9b7,accuracy,gen,47.41
+cmmlu-nutrition,adfff7,accuracy,gen,71.03
+cmmlu-philosophy,75e22d,accuracy,gen,74.29
+cmmlu-professional_accounting,0edc91,accuracy,gen,84.57
+cmmlu-professional_law,d24af5,accuracy,gen,63.51
+cmmlu-professional_medicine,134139,accuracy,gen,63.30
+cmmlu-professional_psychology,ec920e,accuracy,gen,79.31
+cmmlu-public_relations,70ee06,accuracy,gen,67.82
+cmmlu-security_study,45f96f,accuracy,gen,82.96
+cmmlu-sociology,485285,accuracy,gen,66.81
+cmmlu-sports_science,838cfe,accuracy,gen,64.85
+cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,76.76
+cmmlu-virology,8925bf,accuracy,gen,72.19
+cmmlu-world_history,57c97c,accuracy,gen,76.40
+cmmlu-world_religions,1d0f4b,accuracy,gen,65.00
+math,265cce,accuracy,gen,22.70
+mbpp,830460,score,gen,33.80
+mbpp,830460,pass,gen,169.00
+mbpp,830460,timeout,gen,0.00
+mbpp,830460,failed,gen,70.00
+mbpp,830460,wrong_answer,gen,261.00
+GPQA_extended,4baadb,accuracy,gen,29.30
+GPQA_main,4baadb,accuracy,gen,28.35
+GPQA_diamond,4baadb,accuracy,gen,26.26
+bbh-temporal_sequences,e43931,score,gen,16.40
+bbh-disambiguation_qa,d52c61,score,gen,43.20
+bbh-date_understanding,a8000b,score,gen,46.80
+bbh-tracking_shuffled_objects_three_objects,7964c0,score,gen,32.40
+bbh-penguins_in_a_table,fceb27,score,gen,36.99
+bbh-geometric_shapes,503c8f,score,gen,32.00
+bbh-snarks,42d6ca,score,gen,55.06
+bbh-ruin_names,408de8,score,gen,26.80
+bbh-tracking_shuffled_objects_seven_objects,7964c0,score,gen,11.20
+bbh-tracking_shuffled_objects_five_objects,7964c0,score,gen,16.40
+bbh-logical_deduction_three_objects,45ebc5,score,gen,43.60
+bbh-hyperbaton,5e5016,score,gen,64.80
+bbh-logical_deduction_five_objects,45ebc5,score,gen,26.00
+bbh-logical_deduction_seven_objects,45ebc5,score,gen,22.80
+bbh-movie_recommendation,cc2fde,score,gen,47.60
+bbh-salient_translation_error_detection,5b5f35,score,gen,30.00
+bbh-reasoning_about_colored_objects,1cb761,score,gen,39.60
+bbh-multistep_arithmetic_two,30f91e,score,gen,19.60
+bbh-navigate,1576d9,score,gen,64.80
+bbh-dyck_languages,805bea,score,gen,0.80
+bbh-word_sorting,9a3f78,score,gen,3.60
+bbh-sports_understanding,d3fa77,score,gen,57.20
+bbh-boolean_expressions,612c92,score,gen,73.20
+bbh-object_counting,781e5c,score,gen,56.40
+bbh-formal_fallacies,eada96,score,gen,51.60
+bbh-causal_judgement,89eaa4,score,gen,51.87
+bbh-web_of_lies,0c0441,score,gen,65.20
+IFEval,3321a3,Prompt-level-strict-accuracy,gen,24.03
+IFEval,3321a3,Inst-level-strict-accuracy,gen,37.05
+IFEval,3321a3,Prompt-level-loose-accuracy,gen,25.14
+IFEval,3321a3,Inst-level-loose-accuracy,gen,38.49
+ARC-c,1e0de5,accuracy,gen,71.19
+hellaswag,6faab5,accuracy,gen,48.75
+openai_humaneval,8e312c,humaneval_pass@1,gen,41.46
+mmlu-humanities,-,naive_average,gen,59.04
+mmlu-stem,-,naive_average,gen,45.70
+mmlu-social-science,-,naive_average,gen,63.69
+mmlu-other,-,naive_average,gen,58.84
+mmlu,-,naive_average,gen,55.53
+mmlu-weighted,-,weighted_average,gen,54.14
+cmmlu-humanities,-,naive_average,gen,70.56
+cmmlu-stem,-,naive_average,gen,57.10
+cmmlu-social-science,-,naive_average,gen,69.72
+cmmlu-other,-,naive_average,gen,73.06
+cmmlu-china-specific,-,naive_average,gen,66.90
+cmmlu,-,naive_average,gen,67.43
+ceval-stem,-,naive_average,gen,59.70
+ceval-social-science,-,naive_average,gen,82.16
+ceval-humanities,-,naive_average,gen,75.53
+ceval-other,-,naive_average,gen,69.50
+ceval-hard,-,naive_average,gen,44.00
+ceval,-,naive_average,gen,69.44
+bbh,-,naive_average,gen,38.37

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9999310202110782,
+    "eval_loss": 0.8731282353401184,
+    "eval_runtime": 6594.4281,
+    "eval_samples_per_second": 3.908,
+    "eval_steps_per_second": 0.489,
+    "total_flos": 1.7598525261526073e+19,
+    "train_loss": 0.8787032284220849,
+    "train_runtime": 87969.9071,
+    "train_samples_per_second": 2.637,
+    "train_steps_per_second": 0.005
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/nas/data/yanxin/qwen/Qwen2-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9999310202110782,
+    "eval_loss": 0.8731282353401184,
+    "eval_runtime": 6594.4281,
+    "eval_samples_per_second": 3.908,
+    "eval_steps_per_second": 0.489
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.43.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af82783ecff5472cddbab0ec2ab26cd348687565307e68eb339172e2b1cd1ab1
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999310202110782,
+    "total_flos": 1.7598525261526073e+19,
+    "train_loss": 0.8787032284220849,
+    "train_runtime": 87969.9071,
+    "train_samples_per_second": 2.637,
+    "train_steps_per_second": 0.005
+}

trainer_log.jsonl

@@ -0,0 +1,46 @@
+{"current_steps": 10, "total_steps": 453, "loss": 1.0047, "learning_rate": 1.0869565217391305e-05, "epoch": 0.022073532454990687, "percentage": 2.21, "elapsed_time": "0:36:23", "remaining_time": "1 day, 2:51:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 453, "loss": 0.9551, "learning_rate": 2.173913043478261e-05, "epoch": 0.044147064909981375, "percentage": 4.42, "elapsed_time": "1:08:30", "remaining_time": "1 day, 0:43:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 453, "loss": 0.9291, "learning_rate": 3.260869565217392e-05, "epoch": 0.06622059736497206, "percentage": 6.62, "elapsed_time": "1:40:40", "remaining_time": "23:39:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 453, "loss": 0.914, "learning_rate": 4.347826086956522e-05, "epoch": 0.08829412981996275, "percentage": 8.83, "elapsed_time": "2:12:48", "remaining_time": "22:51:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 453, "loss": 0.9187, "learning_rate": 4.9988084660498037e-05, "epoch": 0.11036766227495344, "percentage": 11.04, "elapsed_time": "2:44:54", "remaining_time": "22:09:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 453, "loss": 0.9183, "learning_rate": 4.985416749673074e-05, "epoch": 0.13244119472994412, "percentage": 13.25, "elapsed_time": "3:17:01", "remaining_time": "21:30:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 453, "loss": 0.9048, "learning_rate": 4.957223915853709e-05, "epoch": 0.1545147271849348, "percentage": 15.45, "elapsed_time": "3:49:07", "remaining_time": "20:53:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 453, "loss": 0.8957, "learning_rate": 4.9143978581429445e-05, "epoch": 0.1765882596399255, "percentage": 17.66, "elapsed_time": "4:21:14", "remaining_time": "20:18:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 453, "loss": 0.8952, "learning_rate": 4.857193613652711e-05, "epoch": 0.1986617920949162, "percentage": 19.87, "elapsed_time": "4:53:20", "remaining_time": "19:43:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 453, "loss": 0.8866, "learning_rate": 4.78595184426236e-05, "epoch": 0.22073532454990688, "percentage": 22.08, "elapsed_time": "5:25:26", "remaining_time": "19:08:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 453, "loss": 0.8895, "learning_rate": 4.7010968079140294e-05, "epoch": 0.24280885700489757, "percentage": 24.28, "elapsed_time": "5:57:33", "remaining_time": "18:34:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 120, "total_steps": 453, "loss": 0.8815, "learning_rate": 4.6031338320779534e-05, "epoch": 0.26488238945988823, "percentage": 26.49, "elapsed_time": "6:29:39", "remaining_time": "18:01:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 130, "total_steps": 453, "loss": 0.8808, "learning_rate": 4.492646304433711e-05, "epoch": 0.28695592191487895, "percentage": 28.7, "elapsed_time": "7:01:47", "remaining_time": "17:27:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 140, "total_steps": 453, "loss": 0.8716, "learning_rate": 4.3702921986884574e-05, "epoch": 0.3090294543698696, "percentage": 30.91, "elapsed_time": "7:33:53", "remaining_time": "16:54:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 453, "loss": 0.8823, "learning_rate": 4.236800156221536e-05, "epoch": 0.33110298682486033, "percentage": 33.11, "elapsed_time": "8:06:09", "remaining_time": "16:22:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 453, "loss": 0.8725, "learning_rate": 4.092965146890002e-05, "epoch": 0.353176519279851, "percentage": 35.32, "elapsed_time": "8:38:26", "remaining_time": "15:49:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 453, "loss": 0.8684, "learning_rate": 3.9396437348357684e-05, "epoch": 0.3752500517348417, "percentage": 37.53, "elapsed_time": "9:10:44", "remaining_time": "15:16:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 453, "loss": 0.89, "learning_rate": 3.777748977487366e-05, "epoch": 0.3973235841898324, "percentage": 39.74, "elapsed_time": "9:43:00", "remaining_time": "14:44:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 453, "loss": 0.8706, "learning_rate": 3.608244988133713e-05, "epoch": 0.41939711664482304, "percentage": 41.94, "elapsed_time": "10:15:16", "remaining_time": "14:11:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 453, "loss": 0.872, "learning_rate": 3.432141194450772e-05, "epoch": 0.44147064909981376, "percentage": 44.15, "elapsed_time": "10:47:32", "remaining_time": "13:39:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 453, "loss": 0.8682, "learning_rate": 3.2504863271726286e-05, "epoch": 0.4635441815548044, "percentage": 46.36, "elapsed_time": "11:19:47", "remaining_time": "13:06:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 453, "loss": 0.8794, "learning_rate": 3.064362174705578e-05, "epoch": 0.48561771400979514, "percentage": 48.57, "elapsed_time": "11:51:52", "remaining_time": "12:33:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 453, "loss": 0.8716, "learning_rate": 2.8748771408776466e-05, "epoch": 0.5076912464647858, "percentage": 50.77, "elapsed_time": "12:23:42", "remaining_time": "12:01:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 453, "loss": 0.8807, "learning_rate": 2.683159644188339e-05, "epoch": 0.5297647789197765, "percentage": 52.98, "elapsed_time": "12:56:15", "remaining_time": "11:28:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 453, "loss": 0.8701, "learning_rate": 2.4903513978673077e-05, "epoch": 0.5518383113747672, "percentage": 55.19, "elapsed_time": "13:31:28", "remaining_time": "10:58:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 260, "total_steps": 453, "loss": 0.8632, "learning_rate": 2.2976006107604482e-05, "epoch": 0.5739118438297579, "percentage": 57.4, "elapsed_time": "14:05:07", "remaining_time": "10:27:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 270, "total_steps": 453, "loss": 0.8761, "learning_rate": 2.1060551495333818e-05, "epoch": 0.5959853762847486, "percentage": 59.6, "elapsed_time": "14:38:13", "remaining_time": "9:55:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 280, "total_steps": 453, "loss": 0.8611, "learning_rate": 1.9168557029126963e-05, "epoch": 0.6180589087397392, "percentage": 61.81, "elapsed_time": "15:11:17", "remaining_time": "9:23:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 290, "total_steps": 453, "loss": 0.8616, "learning_rate": 1.7311289886731408e-05, "epoch": 0.6401324411947299, "percentage": 64.02, "elapsed_time": "15:44:24", "remaining_time": "8:50:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 300, "total_steps": 453, "loss": 0.8603, "learning_rate": 1.549981043824425e-05, "epoch": 0.6622059736497207, "percentage": 66.23, "elapsed_time": "16:17:12", "remaining_time": "8:18:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 310, "total_steps": 453, "loss": 0.8608, "learning_rate": 1.3744906379558165e-05, "epoch": 0.6842795061047113, "percentage": 68.43, "elapsed_time": "16:49:23", "remaining_time": "7:45:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 320, "total_steps": 453, "loss": 0.8703, "learning_rate": 1.2057028489632682e-05, "epoch": 0.706353038559702, "percentage": 70.64, "elapsed_time": "17:21:22", "remaining_time": "7:12:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 330, "total_steps": 453, "loss": 0.8518, "learning_rate": 1.0446228394168356e-05, "epoch": 0.7284265710146927, "percentage": 72.85, "elapsed_time": "17:53:16", "remaining_time": "6:40:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 340, "total_steps": 453, "loss": 0.8609, "learning_rate": 8.922098706312548e-06, "epoch": 0.7505001034696834, "percentage": 75.06, "elapsed_time": "18:25:12", "remaining_time": "6:07:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 453, "loss": 0.8504, "learning_rate": 7.493715900870027e-06, "epoch": 0.7725736359246741, "percentage": 77.26, "elapsed_time": "18:57:05", "remaining_time": "5:34:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 360, "total_steps": 453, "loss": 0.8614, "learning_rate": 6.169586262213081e-06, "epoch": 0.7946471683796648, "percentage": 79.47, "elapsed_time": "19:28:49", "remaining_time": "5:01:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 370, "total_steps": 453, "loss": 0.8574, "learning_rate": 4.957595227781395e-06, "epoch": 0.8167207008346554, "percentage": 81.68, "elapsed_time": "20:00:39", "remaining_time": "4:29:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 380, "total_steps": 453, "loss": 0.8501, "learning_rate": 3.864960428840375e-06, "epoch": 0.8387942332896461, "percentage": 83.89, "elapsed_time": "20:32:39", "remaining_time": "3:56:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 390, "total_steps": 453, "loss": 0.85, "learning_rate": 2.8981887081491576e-06, "epoch": 0.8608677657446369, "percentage": 86.09, "elapsed_time": "21:04:29", "remaining_time": "3:24:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 400, "total_steps": 453, "loss": 0.8599, "learning_rate": 2.0630373705058407e-06, "epoch": 0.8829412981996275, "percentage": 88.3, "elapsed_time": "21:36:17", "remaining_time": "2:51:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 453, "loss": 0.8627, "learning_rate": 1.3644798969302403e-06, "epoch": 0.9050148306546182, "percentage": 90.51, "elapsed_time": "22:08:05", "remaining_time": "2:19:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 453, "loss": 0.8567, "learning_rate": 8.066763266625282e-07, "epoch": 0.9270883631096088, "percentage": 92.72, "elapsed_time": "22:39:54", "remaining_time": "1:46:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 453, "loss": 0.8484, "learning_rate": 3.929484833584546e-07, "epoch": 0.9491618955645996, "percentage": 94.92, "elapsed_time": "23:11:46", "remaining_time": "1:14:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 453, "loss": 0.8591, "learning_rate": 1.2576019301373532e-07, "epoch": 0.9712354280195903, "percentage": 97.13, "elapsed_time": "23:43:34", "remaining_time": "0:42:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 453, "loss": 0.8493, "learning_rate": 6.702611423550775e-09, "epoch": 0.993308960474581, "percentage": 99.34, "elapsed_time": "1 day, 0:15:27", "remaining_time": "0:09:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 453, "total_steps": 453, "epoch": 0.9999310202110782, "percentage": 100.0, "elapsed_time": "1 day, 0:26:09", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,357 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999310202110782,
+  "eval_steps": 500,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022073532454990687,
+      "grad_norm": 1.5836448669433594,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 1.0047,
+      "step": 10
+    },
+    {
+      "epoch": 0.044147064909981375,
+      "grad_norm": 0.4156560003757477,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.9551,
+      "step": 20
+    },
+    {
+      "epoch": 0.06622059736497206,
+      "grad_norm": 0.33475786447525024,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.9291,
+      "step": 30
+    },
+    {
+      "epoch": 0.08829412981996275,
+      "grad_norm": 0.721441924571991,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.914,
+      "step": 40
+    },
+    {
+      "epoch": 0.11036766227495344,
+      "grad_norm": 0.2514866292476654,
+      "learning_rate": 4.9988084660498037e-05,
+      "loss": 0.9187,
+      "step": 50
+    },
+    {
+      "epoch": 0.13244119472994412,
+      "grad_norm": 0.21546441316604614,
+      "learning_rate": 4.985416749673074e-05,
+      "loss": 0.9183,
+      "step": 60
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 0.2580913007259369,
+      "learning_rate": 4.957223915853709e-05,
+      "loss": 0.9048,
+      "step": 70
+    },
+    {
+      "epoch": 0.1765882596399255,
+      "grad_norm": 0.24421757459640503,
+      "learning_rate": 4.9143978581429445e-05,
+      "loss": 0.8957,
+      "step": 80
+    },
+    {
+      "epoch": 0.1986617920949162,
+      "grad_norm": 0.23899255692958832,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 0.8952,
+      "step": 90
+    },
+    {
+      "epoch": 0.22073532454990688,
+      "grad_norm": 0.25667503476142883,
+      "learning_rate": 4.78595184426236e-05,
+      "loss": 0.8866,
+      "step": 100
+    },
+    {
+      "epoch": 0.24280885700489757,
+      "grad_norm": 0.3306167423725128,
+      "learning_rate": 4.7010968079140294e-05,
+      "loss": 0.8895,
+      "step": 110
+    },
+    {
+      "epoch": 0.26488238945988823,
+      "grad_norm": 0.2200348675251007,
+      "learning_rate": 4.6031338320779534e-05,
+      "loss": 0.8815,
+      "step": 120
+    },
+    {
+      "epoch": 0.28695592191487895,
+      "grad_norm": 0.28366169333457947,
+      "learning_rate": 4.492646304433711e-05,
+      "loss": 0.8808,
+      "step": 130
+    },
+    {
+      "epoch": 0.3090294543698696,
+      "grad_norm": 0.22618895769119263,
+      "learning_rate": 4.3702921986884574e-05,
+      "loss": 0.8716,
+      "step": 140
+    },
+    {
+      "epoch": 0.33110298682486033,
+      "grad_norm": 0.27280193567276,
+      "learning_rate": 4.236800156221536e-05,
+      "loss": 0.8823,
+      "step": 150
+    },
+    {
+      "epoch": 0.353176519279851,
+      "grad_norm": 0.19905485212802887,
+      "learning_rate": 4.092965146890002e-05,
+      "loss": 0.8725,
+      "step": 160
+    },
+    {
+      "epoch": 0.3752500517348417,
+      "grad_norm": 0.3659760355949402,
+      "learning_rate": 3.9396437348357684e-05,
+      "loss": 0.8684,
+      "step": 170
+    },
+    {
+      "epoch": 0.3973235841898324,
+      "grad_norm": 0.2508715093135834,
+      "learning_rate": 3.777748977487366e-05,
+      "loss": 0.89,
+      "step": 180
+    },
+    {
+      "epoch": 0.41939711664482304,
+      "grad_norm": 0.24242979288101196,
+      "learning_rate": 3.608244988133713e-05,
+      "loss": 0.8706,
+      "step": 190
+    },
+    {
+      "epoch": 0.44147064909981376,
+      "grad_norm": 0.191656693816185,
+      "learning_rate": 3.432141194450772e-05,
+      "loss": 0.872,
+      "step": 200
+    },
+    {
+      "epoch": 0.4635441815548044,
+      "grad_norm": 0.2087477147579193,
+      "learning_rate": 3.2504863271726286e-05,
+      "loss": 0.8682,
+      "step": 210
+    },
+    {
+      "epoch": 0.48561771400979514,
+      "grad_norm": 0.2208724468946457,
+      "learning_rate": 3.064362174705578e-05,
+      "loss": 0.8794,
+      "step": 220
+    },
+    {
+      "epoch": 0.5076912464647858,
+      "grad_norm": 0.19049623608589172,
+      "learning_rate": 2.8748771408776466e-05,
+      "loss": 0.8716,
+      "step": 230
+    },
+    {
+      "epoch": 0.5297647789197765,
+      "grad_norm": 0.18646596372127533,
+      "learning_rate": 2.683159644188339e-05,
+      "loss": 0.8807,
+      "step": 240
+    },
+    {
+      "epoch": 0.5518383113747672,
+      "grad_norm": 0.17940568923950195,
+      "learning_rate": 2.4903513978673077e-05,
+      "loss": 0.8701,
+      "step": 250
+    },
+    {
+      "epoch": 0.5739118438297579,
+      "grad_norm": 0.17862474918365479,
+      "learning_rate": 2.2976006107604482e-05,
+      "loss": 0.8632,
+      "step": 260
+    },
+    {
+      "epoch": 0.5959853762847486,
+      "grad_norm": 0.16970194876194,
+      "learning_rate": 2.1060551495333818e-05,
+      "loss": 0.8761,
+      "step": 270
+    },
+    {
+      "epoch": 0.6180589087397392,
+      "grad_norm": 0.1763421595096588,
+      "learning_rate": 1.9168557029126963e-05,
+      "loss": 0.8611,
+      "step": 280
+    },
+    {
+      "epoch": 0.6401324411947299,
+      "grad_norm": 0.16400456428527832,
+      "learning_rate": 1.7311289886731408e-05,
+      "loss": 0.8616,
+      "step": 290
+    },
+    {
+      "epoch": 0.6622059736497207,
+      "grad_norm": 0.17227979004383087,
+      "learning_rate": 1.549981043824425e-05,
+      "loss": 0.8603,
+      "step": 300
+    },
+    {
+      "epoch": 0.6842795061047113,
+      "grad_norm": 0.15701688826084137,
+      "learning_rate": 1.3744906379558165e-05,
+      "loss": 0.8608,
+      "step": 310
+    },
+    {
+      "epoch": 0.706353038559702,
+      "grad_norm": 0.15198074281215668,
+      "learning_rate": 1.2057028489632682e-05,
+      "loss": 0.8703,
+      "step": 320
+    },
+    {
+      "epoch": 0.7284265710146927,
+      "grad_norm": 0.14645570516586304,
+      "learning_rate": 1.0446228394168356e-05,
+      "loss": 0.8518,
+      "step": 330
+    },
+    {
+      "epoch": 0.7505001034696834,
+      "grad_norm": 0.14851906895637512,
+      "learning_rate": 8.922098706312548e-06,
+      "loss": 0.8609,
+      "step": 340
+    },
+    {
+      "epoch": 0.7725736359246741,
+      "grad_norm": 0.14792883396148682,
+      "learning_rate": 7.493715900870027e-06,
+      "loss": 0.8504,
+      "step": 350
+    },
+    {
+      "epoch": 0.7946471683796648,
+      "grad_norm": 0.14906203746795654,
+      "learning_rate": 6.169586262213081e-06,
+      "loss": 0.8614,
+      "step": 360
+    },
+    {
+      "epoch": 0.8167207008346554,
+      "grad_norm": 0.13984321057796478,
+      "learning_rate": 4.957595227781395e-06,
+      "loss": 0.8574,
+      "step": 370
+    },
+    {
+      "epoch": 0.8387942332896461,
+      "grad_norm": 0.13922333717346191,
+      "learning_rate": 3.864960428840375e-06,
+      "loss": 0.8501,
+      "step": 380
+    },
+    {
+      "epoch": 0.8608677657446369,
+      "grad_norm": 0.14093540608882904,
+      "learning_rate": 2.8981887081491576e-06,
+      "loss": 0.85,
+      "step": 390
+    },
+    {
+      "epoch": 0.8829412981996275,
+      "grad_norm": 0.13516093790531158,
+      "learning_rate": 2.0630373705058407e-06,
+      "loss": 0.8599,
+      "step": 400
+    },
+    {
+      "epoch": 0.9050148306546182,
+      "grad_norm": 0.1319512128829956,
+      "learning_rate": 1.3644798969302403e-06,
+      "loss": 0.8627,
+      "step": 410
+    },
+    {
+      "epoch": 0.9270883631096088,
+      "grad_norm": 0.13131946325302124,
+      "learning_rate": 8.066763266625282e-07,
+      "loss": 0.8567,
+      "step": 420
+    },
+    {
+      "epoch": 0.9491618955645996,
+      "grad_norm": 0.13254371285438538,
+      "learning_rate": 3.929484833584546e-07,
+      "loss": 0.8484,
+      "step": 430
+    },
+    {
+      "epoch": 0.9712354280195903,
+      "grad_norm": 0.1311715841293335,
+      "learning_rate": 1.2576019301373532e-07,
+      "loss": 0.8591,
+      "step": 440
+    },
+    {
+      "epoch": 0.993308960474581,
+      "grad_norm": 0.13352562487125397,
+      "learning_rate": 6.702611423550775e-09,
+      "loss": 0.8493,
+      "step": 450
+    },
+    {
+      "epoch": 0.9999310202110782,
+      "step": 453,
+      "total_flos": 1.7598525261526073e+19,
+      "train_loss": 0.8787032284220849,
+      "train_runtime": 87969.9071,
+      "train_samples_per_second": 2.637,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 453,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7598525261526073e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f781cb5d1232a49b441084c9a80a267386ad0a75c168898f8838a171a1cd61
+size 6584