diff --git a/EVAL_REPORT.md b/EVAL_REPORT.md new file mode 100644 index 0000000000000000000000000000000000000000..ffa9b759e2cf1864a9eacdb3617b4cdd9697becd --- /dev/null +++ b/EVAL_REPORT.md @@ -0,0 +1,118 @@ +# Automated MNLP evaluation report + +- **Model repo:** [`cs-552-2026-the-transformers/math_model`](https://huggingface.co/cs-552-2026-the-transformers/math_model) +- **Owner(s):** group **the-transformers** +- **Generated at:** 2026-05-29T06:54:15+00:00 (UTC) +- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci) + +_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._ + +## Summary + +| Benchmark | Accuracy | Status | +|---|---:|---| +| Math | 0.3800 | ok | +| Knowledge | — | not run | +| Multilingual | — | not run | +| Safety | — | not run | + +## Sample completions + +_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._ + +### Math + +**Correct** (1 shown) + +- **reference**: `\frac{639}{40}` +- **overall** (5/8 completions correct) +- **extracted** (✓): `\frac{639}{40}` +- **completion**: + + ```text + + To solve this problem, we need to find the distance between two buildings on the map given the actual distance and the scale of the map. + + First, let's understand the scale of the map. According to the problem, a length of 3 inches on the map represents 10 miles in the real world. This means that for every 3 inches on the map, the actual distance is 10 miles. + + We can set up a proportion to find the distance on the map that corresponds to 53.25 miles in the real world. Let's denote the distance on the map as \(x\) inches. + + The proportion can be written as: + \[ + \frac{3 \text{ inches}}{10 \text{ miles}} = \frac{x \text{ inches}}{53.25 \text{ miles}} + \] + + To solve for \(x\), we can cross-multiply: + \[ + 3 \times 53.25 = 10 \times x + \] + + Calculating the left side: + \[ + 3 \times 53.25 = 159.75 + \] + + So, we have: + \[ + 159.75 = 10x + \] + + To find \(x\), we divide both sides by 10: + \[ + x = \frac{159.75}{10} = 15.975 + \] + + Now, we need to express 15.975 as a fraction. We can write 15.975 as: + \[ + 15.975 = \frac{15975}{1000} + \] + + We can simplify this fraction by dividing both the numerator and the denominator by their greatest common divisor, which is 25: + \[ + \frac{15975 \div 25}{1000 \div 25} = \frac{639}{40} + \] + + Therefore, the distance between the two buildings on the map, written as a fraction, is: + \[ + \boxed{\frac{639}{40}} + \] + ``` + +**Incorrect** (1 shown) + +- **reference**: `756` +- **overall** (0/8 completions correct) +- **extracted** (✗): `` +- **completion**: + + ```text + + To solve this problem, we need to use the properties of spheres and the distances between their centers. Let's denote the centers of the three balloons as points $X$, $Y$, and $Z$, and their radii as $r_1 = 11$, $r_2 = 13$, and $r_3 = 19$, respectively. + + Since the balloons are externally tangent to each other, the distance between any two centers is the sum of their radii. Therefore, we ha + + ... [truncated 822 chars] ... + + XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 24 \cdot \frac{10912}{480}. \] + \[ XZ^2 = 1600 - 2 \cdot 2 + ``` diff --git a/README.md b/README.md index 863e7d7f17ef0110a0719c682b315ea01f4e81a4..a05db1b6199c666a36a7d184b16f2ca0274dc34a 100644 --- a/README.md +++ b/README.md @@ -1,14 +1,15 @@ --- -base_model: Qwen/Qwen3-1.7B library_name: transformers +model_name: exp4b_dpo +base_model: Qwen/Qwen3-1.7B tags: - generated_from_trainer +- dpo - trl -- sft licence: license --- -# math_model +# Model Card for exp4b_dpo This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B). It has been trained using [TRL](https://github.com/huggingface/trl). @@ -26,10 +27,10 @@ print(output["generated_text"]) ## Training procedure -[Visualize in Weights & Biases](https://wandb.ai/jdecim/MNLP/runs/2btc84l3) + -This model was trained with SFT. +This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions @@ -41,7 +42,18 @@ This model was trained with SFT. ## Citations +Cite DPO as: +```bibtex +@inproceedings{rafailov2023direct, + title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, + author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, + year = 2023, + booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, + url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, + editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, +} +``` Cite TRL as: diff --git a/chat_template.jinja b/chat_template.jinja index 5845311e60103eb4a734e3c4c8e69ba7348636a7..01be9b307daa2d425f7c168c9fb145a286e0afb4 100644 --- a/chat_template.jinja +++ b/chat_template.jinja @@ -10,13 +10,9 @@ {%- endfor %} {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} {%- else %} - {#- BOXING INSTRUCTION injected so it is present even when the caller (e.g. CI) - passes no system message. Targets our no-box / multi-box failure mode. #} - {{- '<|im_start|>system\n' }} {%- if messages[0].role == 'system' %} - {{- messages[0].content + '\n\n' }} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} {%- endif %} - {{- 'When solving a math problem, work through it step by step and write your final answer inside a \boxed{...}.<|im_end|>\n' }} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} {%- for message in messages[::-1] %} diff --git a/checkpoint-1011/chat_template.jinja b/checkpoint-1011/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-1011/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-1011/config.json b/checkpoint-1011/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-1011/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-1011/generation_config.json b/checkpoint-1011/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-1011/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-1011/model.safetensors b/checkpoint-1011/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc885a501a0fffef97b843b5248e3bb7cfe46172 --- /dev/null +++ b/checkpoint-1011/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af4557502ae7c7853ed3b684aa50cfd00317aafc237f2dda688075bb3dc81c1 +size 3441185608 diff --git a/checkpoint-1011/optimizer.pt b/checkpoint-1011/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d00b4ce7da17dce3a0fb31d9c369e0cafbfc68a3 --- /dev/null +++ b/checkpoint-1011/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016daefe3fcafd2822ed799155138cb8e476fe309f9070f5157970a18bcc6d4c +size 6882572207 diff --git a/checkpoint-1011/rng_state.pth b/checkpoint-1011/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd3c190a62ba12f21428f29e0f4bde711034a75b --- /dev/null +++ b/checkpoint-1011/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934 +size 14645 diff --git a/checkpoint-1011/scheduler.pt b/checkpoint-1011/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..edf0d85a22eaf7a475ed68221fba576eaa55f682 --- /dev/null +++ b/checkpoint-1011/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee946d348a6273229e02f92d4563cb2ba7ac75075130a9d6c5c0eb31d584ddc +size 1465 diff --git a/checkpoint-1011/tokenizer.json b/checkpoint-1011/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-1011/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-1011/tokenizer_config.json b/checkpoint-1011/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-1011/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-1011/trainer_state.json b/checkpoint-1011/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9becb660138c318878d26d4efdaa5944723c7ae4 --- /dev/null +++ b/checkpoint-1011/trainer_state.json @@ -0,0 +1,1044 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1011, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": NaN, + "epoch": 0.029717682020802376, + "grad_norm": NaN, + "learning_rate": 1.8000000000000001e-06, + "loss": 1005514863411.2, + "mean_token_accuracy": 0.07770282882993343, + "num_tokens": 97764.0, + "step": 10 + }, + { + "entropy": NaN, + "epoch": 0.05943536404160475, + "grad_norm": NaN, + "learning_rate": 3.8000000000000005e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007392044077278115, + "num_tokens": 190372.0, + "step": 20 + }, + { + "entropy": NaN, + "epoch": 0.08915304606240713, + "grad_norm": NaN, + "learning_rate": 5.8e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000383764869911829, + "num_tokens": 280928.0, + "step": 30 + }, + { + "entropy": NaN, + "epoch": 0.1188707280832095, + "grad_norm": NaN, + "learning_rate": 7.800000000000002e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0003212536917999387, + "num_tokens": 380644.0, + "step": 40 + }, + { + "entropy": NaN, + "epoch": 0.1485884101040119, + "grad_norm": NaN, + "learning_rate": 9.800000000000001e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0003853117574180942, + "num_tokens": 475467.0, + "step": 50 + }, + { + "entropy": NaN, + "epoch": 0.17830609212481427, + "grad_norm": NaN, + "learning_rate": 1.18e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0003134153150313068, + "num_tokens": 572411.0, + "step": 60 + }, + { + "entropy": NaN, + "epoch": 0.20802377414561665, + "grad_norm": NaN, + "learning_rate": 1.38e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011001345737895463, + "num_tokens": 661517.0, + "step": 70 + }, + { + "entropy": NaN, + "epoch": 0.237741456166419, + "grad_norm": NaN, + "learning_rate": 1.58e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012231820757733658, + "num_tokens": 752142.0, + "step": 80 + }, + { + "entropy": NaN, + "epoch": 0.2674591381872214, + "grad_norm": NaN, + "learning_rate": 1.7800000000000002e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011551132018212229, + "num_tokens": 850399.0, + "step": 90 + }, + { + "entropy": NaN, + "epoch": 0.2971768202080238, + "grad_norm": NaN, + "learning_rate": 1.98e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00047943509634933433, + "num_tokens": 954759.0, + "step": 100 + }, + { + "entropy": NaN, + "epoch": 0.32689450222882616, + "grad_norm": NaN, + "learning_rate": 1.9802414928649837e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008438902725174558, + "num_tokens": 1050439.0, + "step": 110 + }, + { + "entropy": NaN, + "epoch": 0.35661218424962854, + "grad_norm": NaN, + "learning_rate": 1.958287596048299e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009903057703922967, + "num_tokens": 1135089.0, + "step": 120 + }, + { + "entropy": NaN, + "epoch": 0.3863298662704309, + "grad_norm": NaN, + "learning_rate": 1.9363336992316137e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00040032515971688554, + "num_tokens": 1228149.0, + "step": 130 + }, + { + "entropy": NaN, + "epoch": 0.4160475482912333, + "grad_norm": NaN, + "learning_rate": 1.9143798024149288e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0010247966441966128, + "num_tokens": 1331672.0, + "step": 140 + }, + { + "entropy": NaN, + "epoch": 0.4457652303120357, + "grad_norm": NaN, + "learning_rate": 1.892425905598244e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000843161555530969, + "num_tokens": 1421314.0, + "step": 150 + }, + { + "entropy": NaN, + "epoch": 0.475482912332838, + "grad_norm": NaN, + "learning_rate": 1.8704720087815587e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007889680869993754, + "num_tokens": 1511701.0, + "step": 160 + }, + { + "entropy": NaN, + "epoch": 0.5052005943536404, + "grad_norm": NaN, + "learning_rate": 1.848518111964874e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007493881763366517, + "num_tokens": 1605063.0, + "step": 170 + }, + { + "entropy": NaN, + "epoch": 0.5349182763744428, + "grad_norm": NaN, + "learning_rate": 1.826564215148189e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000567350817436818, + "num_tokens": 1703107.0, + "step": 180 + }, + { + "entropy": NaN, + "epoch": 0.5646359583952452, + "grad_norm": NaN, + "learning_rate": 1.804610318331504e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00027060438151238486, + "num_tokens": 1796279.0, + "step": 190 + }, + { + "entropy": NaN, + "epoch": 0.5943536404160475, + "grad_norm": NaN, + "learning_rate": 1.782656421514819e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008226798396208324, + "num_tokens": 1893647.0, + "step": 200 + }, + { + "entropy": NaN, + "epoch": 0.6240713224368499, + "grad_norm": NaN, + "learning_rate": 1.760702524698134e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007338574505411088, + "num_tokens": 1982325.0, + "step": 210 + }, + { + "entropy": NaN, + "epoch": 0.6537890044576523, + "grad_norm": NaN, + "learning_rate": 1.7387486278814492e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004891513846814633, + "num_tokens": 2071869.0, + "step": 220 + }, + { + "entropy": NaN, + "epoch": 0.6835066864784547, + "grad_norm": NaN, + "learning_rate": 1.716794731064764e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00038509477453771976, + "num_tokens": 2168370.0, + "step": 230 + }, + { + "entropy": NaN, + "epoch": 0.7132243684992571, + "grad_norm": NaN, + "learning_rate": 1.694840834248079e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009255842014681548, + "num_tokens": 2263211.0, + "step": 240 + }, + { + "entropy": NaN, + "epoch": 0.7429420505200595, + "grad_norm": NaN, + "learning_rate": 1.6728869374313943e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011857455348945223, + "num_tokens": 2352425.0, + "step": 250 + }, + { + "entropy": NaN, + "epoch": 0.7726597325408618, + "grad_norm": NaN, + "learning_rate": 1.6509330406147094e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008204675337765366, + "num_tokens": 2445217.0, + "step": 260 + }, + { + "entropy": NaN, + "epoch": 0.8023774145616642, + "grad_norm": NaN, + "learning_rate": 1.6289791437980242e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0013553448639868292, + "num_tokens": 2537677.0, + "step": 270 + }, + { + "entropy": NaN, + "epoch": 0.8320950965824666, + "grad_norm": NaN, + "learning_rate": 1.6070252469813393e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011630529144895263, + "num_tokens": 2631646.0, + "step": 280 + }, + { + "entropy": NaN, + "epoch": 0.861812778603269, + "grad_norm": NaN, + "learning_rate": 1.5850713501646545e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009409735575900413, + "num_tokens": 2722632.0, + "step": 290 + }, + { + "entropy": NaN, + "epoch": 0.8915304606240714, + "grad_norm": NaN, + "learning_rate": 1.5631174533479693e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006484775040007662, + "num_tokens": 2819185.0, + "step": 300 + }, + { + "entropy": NaN, + "epoch": 0.9212481426448736, + "grad_norm": NaN, + "learning_rate": 1.5411635565312844e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011682231881422922, + "num_tokens": 2910483.0, + "step": 310 + }, + { + "entropy": NaN, + "epoch": 0.950965824665676, + "grad_norm": NaN, + "learning_rate": 1.5192096597145995e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004708930806373246, + "num_tokens": 2997057.0, + "step": 320 + }, + { + "entropy": NaN, + "epoch": 0.9806835066864784, + "grad_norm": NaN, + "learning_rate": 1.4972557628979145e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011955970534472727, + "num_tokens": 3091284.0, + "step": 330 + }, + { + "entropy": NaN, + "epoch": 1.0089153046062407, + "grad_norm": NaN, + "learning_rate": 1.4753018660812295e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006843029964090276, + "num_tokens": 3177800.0, + "step": 340 + }, + { + "entropy": NaN, + "epoch": 1.0386329866270432, + "grad_norm": NaN, + "learning_rate": 1.4533479692645444e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0005406756106822285, + "num_tokens": 3271989.0, + "step": 350 + }, + { + "entropy": NaN, + "epoch": 1.0683506686478454, + "grad_norm": NaN, + "learning_rate": 1.4313940724478596e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007009803419350646, + "num_tokens": 3365082.0, + "step": 360 + }, + { + "entropy": NaN, + "epoch": 1.098068350668648, + "grad_norm": NaN, + "learning_rate": 1.4094401756311746e-05, + "loss": 0.0, + "mean_token_accuracy": 0.001003894711175235, + "num_tokens": 3465865.0, + "step": 370 + }, + { + "entropy": NaN, + "epoch": 1.1277860326894502, + "grad_norm": NaN, + "learning_rate": 1.3874862788144897e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004136150790145621, + "num_tokens": 3564998.0, + "step": 380 + }, + { + "entropy": NaN, + "epoch": 1.1575037147102525, + "grad_norm": NaN, + "learning_rate": 1.3655323819978048e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000998112405068241, + "num_tokens": 3661508.0, + "step": 390 + }, + { + "entropy": NaN, + "epoch": 1.187221396731055, + "grad_norm": NaN, + "learning_rate": 1.3435784851811198e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009621107514249161, + "num_tokens": 3755395.0, + "step": 400 + }, + { + "entropy": NaN, + "epoch": 1.2169390787518575, + "grad_norm": NaN, + "learning_rate": 1.3216245883644348e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004976072828867473, + "num_tokens": 3842994.0, + "step": 410 + }, + { + "entropy": NaN, + "epoch": 1.2466567607726597, + "grad_norm": NaN, + "learning_rate": 1.2996706915477499e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0003434549740632065, + "num_tokens": 3934618.0, + "step": 420 + }, + { + "entropy": NaN, + "epoch": 1.276374442793462, + "grad_norm": NaN, + "learning_rate": 1.2777167947310649e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00026364591685705817, + "num_tokens": 4026711.0, + "step": 430 + }, + { + "entropy": NaN, + "epoch": 1.3060921248142645, + "grad_norm": NaN, + "learning_rate": 1.2557628979143798e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006349188319290988, + "num_tokens": 4114609.0, + "step": 440 + }, + { + "entropy": NaN, + "epoch": 1.3358098068350668, + "grad_norm": NaN, + "learning_rate": 1.2338090010976948e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004265022376785055, + "num_tokens": 4203953.0, + "step": 450 + }, + { + "entropy": NaN, + "epoch": 1.3655274888558693, + "grad_norm": NaN, + "learning_rate": 1.2118551042810101e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012633154692593962, + "num_tokens": 4298319.0, + "step": 460 + }, + { + "entropy": NaN, + "epoch": 1.3952451708766715, + "grad_norm": NaN, + "learning_rate": 1.189901207464325e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011256658195634372, + "num_tokens": 4396020.0, + "step": 470 + }, + { + "entropy": NaN, + "epoch": 1.424962852897474, + "grad_norm": NaN, + "learning_rate": 1.16794731064764e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0013131745137798135, + "num_tokens": 4491203.0, + "step": 480 + }, + { + "entropy": NaN, + "epoch": 1.4546805349182763, + "grad_norm": NaN, + "learning_rate": 1.1459934138309552e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012716218378045596, + "num_tokens": 4582199.0, + "step": 490 + }, + { + "entropy": NaN, + "epoch": 1.4843982169390788, + "grad_norm": NaN, + "learning_rate": 1.1240395170142701e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0014869970778818241, + "num_tokens": 4672589.0, + "step": 500 + }, + { + "entropy": NaN, + "epoch": 1.514115898959881, + "grad_norm": NaN, + "learning_rate": 1.1020856201975851e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00046981508567114363, + "num_tokens": 4767693.0, + "step": 510 + }, + { + "entropy": NaN, + "epoch": 1.5438335809806834, + "grad_norm": NaN, + "learning_rate": 1.0801317233809e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000601445968641201, + "num_tokens": 4860371.0, + "step": 520 + }, + { + "entropy": NaN, + "epoch": 1.5735512630014858, + "grad_norm": NaN, + "learning_rate": 1.0581778265642154e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012073652920662425, + "num_tokens": 4950622.0, + "step": 530 + }, + { + "entropy": NaN, + "epoch": 1.6032689450222883, + "grad_norm": NaN, + "learning_rate": 1.0362239297475303e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00028707647215924225, + "num_tokens": 5044878.0, + "step": 540 + }, + { + "entropy": NaN, + "epoch": 1.6329866270430906, + "grad_norm": NaN, + "learning_rate": 1.0142700329308453e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004101752907445189, + "num_tokens": 5140938.0, + "step": 550 + }, + { + "entropy": NaN, + "epoch": 1.6627043090638929, + "grad_norm": NaN, + "learning_rate": 9.923161361141603e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008072987395280507, + "num_tokens": 5232852.0, + "step": 560 + }, + { + "entropy": NaN, + "epoch": 1.6924219910846954, + "grad_norm": NaN, + "learning_rate": 9.703622392974754e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0012222853780258446, + "num_tokens": 5321835.0, + "step": 570 + }, + { + "entropy": NaN, + "epoch": 1.7221396731054979, + "grad_norm": NaN, + "learning_rate": 9.484083424807904e-06, + "loss": 0.0, + "mean_token_accuracy": 0.001064640874392353, + "num_tokens": 5416464.0, + "step": 580 + }, + { + "entropy": NaN, + "epoch": 1.7518573551263001, + "grad_norm": NaN, + "learning_rate": 9.264544456641055e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0009612867230316624, + "num_tokens": 5515169.0, + "step": 590 + }, + { + "entropy": NaN, + "epoch": 1.7815750371471024, + "grad_norm": NaN, + "learning_rate": 9.045005488474205e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008774219051701948, + "num_tokens": 5611971.0, + "step": 600 + }, + { + "entropy": NaN, + "epoch": 1.811292719167905, + "grad_norm": NaN, + "learning_rate": 8.825466520307355e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007863394406740553, + "num_tokens": 5704255.0, + "step": 610 + }, + { + "entropy": NaN, + "epoch": 1.8410104011887074, + "grad_norm": NaN, + "learning_rate": 8.605927552140506e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000578320066415472, + "num_tokens": 5800440.0, + "step": 620 + }, + { + "entropy": NaN, + "epoch": 1.8707280832095097, + "grad_norm": NaN, + "learning_rate": 8.386388583973656e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0004275172817870043, + "num_tokens": 5890898.0, + "step": 630 + }, + { + "entropy": NaN, + "epoch": 1.900445765230312, + "grad_norm": NaN, + "learning_rate": 8.166849615806807e-06, + "loss": 0.0, + "mean_token_accuracy": 0.001425291335908696, + "num_tokens": 5987228.0, + "step": 640 + }, + { + "entropy": NaN, + "epoch": 1.9301634472511144, + "grad_norm": NaN, + "learning_rate": 7.947310647639957e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006059414023184218, + "num_tokens": 6076579.0, + "step": 650 + }, + { + "entropy": NaN, + "epoch": 1.959881129271917, + "grad_norm": NaN, + "learning_rate": 7.727771679473108e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008722793892957271, + "num_tokens": 6171013.0, + "step": 660 + }, + { + "entropy": NaN, + "epoch": 1.9895988112927192, + "grad_norm": NaN, + "learning_rate": 7.508232711306257e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007748565993097145, + "num_tokens": 6265432.0, + "step": 670 + }, + { + "entropy": NaN, + "epoch": 2.0178306092124814, + "grad_norm": NaN, + "learning_rate": 7.288693743139408e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007497724390735751, + "num_tokens": 6349548.0, + "step": 680 + }, + { + "entropy": NaN, + "epoch": 2.0475482912332836, + "grad_norm": NaN, + "learning_rate": 7.069154774972559e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006858149892650545, + "num_tokens": 6440481.0, + "step": 690 + }, + { + "entropy": NaN, + "epoch": 2.0772659732540864, + "grad_norm": NaN, + "learning_rate": 6.849615806805708e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008518316331901588, + "num_tokens": 6533227.0, + "step": 700 + }, + { + "entropy": NaN, + "epoch": 2.1069836552748886, + "grad_norm": NaN, + "learning_rate": 6.630076838638859e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006546900600369554, + "num_tokens": 6631305.0, + "step": 710 + }, + { + "entropy": NaN, + "epoch": 2.136701337295691, + "grad_norm": NaN, + "learning_rate": 6.410537870472009e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006311897363048047, + "num_tokens": 6719619.0, + "step": 720 + }, + { + "entropy": NaN, + "epoch": 2.166419019316493, + "grad_norm": NaN, + "learning_rate": 6.19099890230516e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008787176091573201, + "num_tokens": 6808489.0, + "step": 730 + }, + { + "entropy": NaN, + "epoch": 2.196136701337296, + "grad_norm": NaN, + "learning_rate": 5.9714599341383095e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0010024115661508403, + "num_tokens": 6904544.0, + "step": 740 + }, + { + "entropy": NaN, + "epoch": 2.225854383358098, + "grad_norm": NaN, + "learning_rate": 5.75192096597146e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006462240009568632, + "num_tokens": 6998909.0, + "step": 750 + }, + { + "entropy": NaN, + "epoch": 2.2555720653789004, + "grad_norm": NaN, + "learning_rate": 5.532381997804611e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0005598854688287247, + "num_tokens": 7093305.0, + "step": 760 + }, + { + "entropy": NaN, + "epoch": 2.2852897473997027, + "grad_norm": NaN, + "learning_rate": 5.312843029637761e-06, + "loss": 0.0, + "mean_token_accuracy": 0.00036793685212614945, + "num_tokens": 7184216.0, + "step": 770 + }, + { + "entropy": NaN, + "epoch": 2.315007429420505, + "grad_norm": NaN, + "learning_rate": 5.093304061470912e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000779397370206425, + "num_tokens": 7273139.0, + "step": 780 + }, + { + "entropy": NaN, + "epoch": 2.3447251114413077, + "grad_norm": NaN, + "learning_rate": 4.873765093304062e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006776292997528799, + "num_tokens": 7375877.0, + "step": 790 + }, + { + "entropy": NaN, + "epoch": 2.37444279346211, + "grad_norm": NaN, + "learning_rate": 4.654226125137213e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0013253977747808676, + "num_tokens": 7471802.0, + "step": 800 + }, + { + "entropy": NaN, + "epoch": 2.4041604754829122, + "grad_norm": NaN, + "learning_rate": 4.434687156970362e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007797809317708016, + "num_tokens": 7568137.0, + "step": 810 + }, + { + "entropy": NaN, + "epoch": 2.433878157503715, + "grad_norm": NaN, + "learning_rate": 4.215148188803513e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0005893595473025926, + "num_tokens": 7662880.0, + "step": 820 + }, + { + "entropy": NaN, + "epoch": 2.463595839524517, + "grad_norm": NaN, + "learning_rate": 3.995609220636663e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007197739760158584, + "num_tokens": 7755580.0, + "step": 830 + }, + { + "entropy": NaN, + "epoch": 2.4933135215453195, + "grad_norm": NaN, + "learning_rate": 3.776070252469814e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000664884723664727, + "num_tokens": 7854588.0, + "step": 840 + }, + { + "entropy": NaN, + "epoch": 2.5230312035661218, + "grad_norm": NaN, + "learning_rate": 3.5565312843029644e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000588176279416075, + "num_tokens": 7950417.0, + "step": 850 + }, + { + "entropy": NaN, + "epoch": 2.552748885586924, + "grad_norm": NaN, + "learning_rate": 3.3369923161361144e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007997245862497948, + "num_tokens": 8043286.0, + "step": 860 + }, + { + "entropy": NaN, + "epoch": 2.5824665676077267, + "grad_norm": NaN, + "learning_rate": 3.117453347969265e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0005276548559777439, + "num_tokens": 8138513.0, + "step": 870 + }, + { + "entropy": NaN, + "epoch": 2.612184249628529, + "grad_norm": NaN, + "learning_rate": 2.897914379802415e-06, + "loss": 0.0, + "mean_token_accuracy": 0.00023305922804865985, + "num_tokens": 8228539.0, + "step": 880 + }, + { + "entropy": NaN, + "epoch": 2.6419019316493313, + "grad_norm": NaN, + "learning_rate": 2.6783754116355656e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0005359479633625597, + "num_tokens": 8320083.0, + "step": 890 + }, + { + "entropy": NaN, + "epoch": 2.6716196136701336, + "grad_norm": NaN, + "learning_rate": 2.458836443468716e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006636981313931755, + "num_tokens": 8416446.0, + "step": 900 + }, + { + "entropy": NaN, + "epoch": 2.7013372956909363, + "grad_norm": NaN, + "learning_rate": 2.239297475301866e-06, + "loss": 0.0, + "mean_token_accuracy": 0.002058879991818685, + "num_tokens": 8513551.0, + "step": 910 + }, + { + "entropy": NaN, + "epoch": 2.7310549777117386, + "grad_norm": NaN, + "learning_rate": 2.0197585071350167e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000950983911025105, + "num_tokens": 8603909.0, + "step": 920 + }, + { + "entropy": NaN, + "epoch": 2.760772659732541, + "grad_norm": NaN, + "learning_rate": 1.800219538968167e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0014912645376170986, + "num_tokens": 8695081.0, + "step": 930 + }, + { + "entropy": NaN, + "epoch": 2.790490341753343, + "grad_norm": NaN, + "learning_rate": 1.5806805708013173e-06, + "loss": 0.0, + "mean_token_accuracy": 0.001528770748700481, + "num_tokens": 8790760.0, + "step": 940 + }, + { + "entropy": NaN, + "epoch": 2.8202080237741454, + "grad_norm": NaN, + "learning_rate": 1.3611416026344676e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0012167295863036998, + "num_tokens": 8879103.0, + "step": 950 + }, + { + "entropy": NaN, + "epoch": 2.849925705794948, + "grad_norm": NaN, + "learning_rate": 1.1416026344676181e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007455661499989219, + "num_tokens": 8972354.0, + "step": 960 + }, + { + "entropy": NaN, + "epoch": 2.8796433878157504, + "grad_norm": NaN, + "learning_rate": 9.220636663007684e-07, + "loss": 0.0, + "mean_token_accuracy": 0.0003935990913305432, + "num_tokens": 9069381.0, + "step": 970 + }, + { + "entropy": NaN, + "epoch": 2.9093610698365526, + "grad_norm": NaN, + "learning_rate": 7.025246981339188e-07, + "loss": 0.0, + "mean_token_accuracy": 0.00037132185607333665, + "num_tokens": 9164901.0, + "step": 980 + }, + { + "entropy": NaN, + "epoch": 2.9390787518573553, + "grad_norm": NaN, + "learning_rate": 4.829857299670692e-07, + "loss": 0.0, + "mean_token_accuracy": 0.00036687121028080585, + "num_tokens": 9258811.0, + "step": 990 + }, + { + "entropy": NaN, + "epoch": 2.9687964338781576, + "grad_norm": NaN, + "learning_rate": 2.6344676180021955e-07, + "loss": 0.0, + "mean_token_accuracy": 0.0008805370052868966, + "num_tokens": 9351174.0, + "step": 1000 + }, + { + "entropy": NaN, + "epoch": 2.99851411589896, + "grad_norm": NaN, + "learning_rate": 4.390779363336993e-08, + "loss": 0.0, + "mean_token_accuracy": 0.0007362255608313717, + "num_tokens": 9440239.0, + "step": 1010 + } + ], + "logging_steps": 10, + "max_steps": 1011, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "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": 1.0120089572705894e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1011/training_args.bin b/checkpoint-1011/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..737a87caa4fc2f704a1fe56a508ca4d335ca783d --- /dev/null +++ b/checkpoint-1011/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0f7084660199ed7fd16027c0c6af5e726790f32a022b019f1277bec4e01142 +size 5713 diff --git a/checkpoint-125/chat_template.jinja b/checkpoint-125/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-125/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-125/config.json b/checkpoint-125/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-125/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-125/generation_config.json b/checkpoint-125/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-125/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-125/model.safetensors b/checkpoint-125/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2e0d2f571547f58479dee02aa685fc8990a4284 --- /dev/null +++ b/checkpoint-125/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7074b51b321535051b77436f30720111854403259c583a273488e061c0d23072 +size 3441185608 diff --git a/checkpoint-125/optimizer.pt b/checkpoint-125/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c18832d9f63e5dc9e826ce8b7a6fa36249242ab6 --- /dev/null +++ b/checkpoint-125/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b569f0710425a088cc5cd95c2def7bbb89539cdd1c3b41312c8d8fc136d2e186 +size 6882572207 diff --git a/checkpoint-125/rng_state.pth b/checkpoint-125/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/checkpoint-125/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/checkpoint-125/scheduler.pt b/checkpoint-125/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0f9744d60b0805d01c098d6c1052451f23dd980 --- /dev/null +++ b/checkpoint-125/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770e85488b2d6f2b41a590e6c2bb599f3a174081e14b8c48d3638681b4a06597 +size 1465 diff --git a/checkpoint-125/tokenizer.json b/checkpoint-125/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-125/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-125/tokenizer_config.json b/checkpoint-125/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-125/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-125/trainer_state.json b/checkpoint-125/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e2e8da443bc02a76e800bb696414257eb8fe5e6c --- /dev/null +++ b/checkpoint-125/trainer_state.json @@ -0,0 +1,154 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 125, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 0.2860680317506194, + "epoch": 0.08, + "grad_norm": 7.46875, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.7724831104278564, + "mean_token_accuracy": 0.8434554561972618, + "num_tokens": 94518.0, + "step": 10 + }, + { + "entropy": 0.3743372498080134, + "epoch": 0.16, + "grad_norm": 2.6875, + "learning_rate": 1.8761061946902657e-05, + "loss": 0.4372231483459473, + "mean_token_accuracy": 0.8732902690768242, + "num_tokens": 187445.0, + "step": 20 + }, + { + "entropy": 0.3575092004612088, + "epoch": 0.24, + "grad_norm": 2.625, + "learning_rate": 1.6991150442477876e-05, + "loss": 0.3412153959274292, + "mean_token_accuracy": 0.8936023108661175, + "num_tokens": 280610.0, + "step": 30 + }, + { + "entropy": 0.31294157058000566, + "epoch": 0.32, + "grad_norm": 2.421875, + "learning_rate": 1.5221238938053098e-05, + "loss": 0.3175334453582764, + "mean_token_accuracy": 0.8971926532685757, + "num_tokens": 379577.0, + "step": 40 + }, + { + "entropy": 0.30759106744080783, + "epoch": 0.4, + "grad_norm": 1.7421875, + "learning_rate": 1.345132743362832e-05, + "loss": 0.32603118419647215, + "mean_token_accuracy": 0.8967837899923324, + "num_tokens": 477577.0, + "step": 50 + }, + { + "entropy": 0.31574366632848977, + "epoch": 0.48, + "grad_norm": 1.9921875, + "learning_rate": 1.1681415929203541e-05, + "loss": 0.323792552947998, + "mean_token_accuracy": 0.8988608829677105, + "num_tokens": 573360.0, + "step": 60 + }, + { + "entropy": 0.3065364420413971, + "epoch": 0.56, + "grad_norm": 1.6171875, + "learning_rate": 9.911504424778762e-06, + "loss": 0.32266840934753416, + "mean_token_accuracy": 0.8985385209321975, + "num_tokens": 665761.0, + "step": 70 + }, + { + "entropy": 0.27206654362380506, + "epoch": 0.64, + "grad_norm": 2.1875, + "learning_rate": 8.141592920353984e-06, + "loss": 0.2854612350463867, + "mean_token_accuracy": 0.9085792370140553, + "num_tokens": 756921.0, + "step": 80 + }, + { + "entropy": 0.28962985165417193, + "epoch": 0.72, + "grad_norm": 1.8125, + "learning_rate": 6.371681415929204e-06, + "loss": 0.29041600227355957, + "mean_token_accuracy": 0.9059965394437313, + "num_tokens": 845171.0, + "step": 90 + }, + { + "entropy": 0.2753044681623578, + "epoch": 0.8, + "grad_norm": 2.09375, + "learning_rate": 4.6017699115044254e-06, + "loss": 0.2797576427459717, + "mean_token_accuracy": 0.9101039692759514, + "num_tokens": 939550.0, + "step": 100 + }, + { + "entropy": 0.2808386910706758, + "epoch": 0.88, + "grad_norm": 1.5859375, + "learning_rate": 2.831858407079646e-06, + "loss": 0.2893812894821167, + "mean_token_accuracy": 0.9063553236424923, + "num_tokens": 1041441.0, + "step": 110 + }, + { + "entropy": 0.2944059643894434, + "epoch": 0.96, + "grad_norm": 1.6875, + "learning_rate": 1.0619469026548673e-06, + "loss": 0.2996867895126343, + "mean_token_accuracy": 0.9011975660920143, + "num_tokens": 1132794.0, + "step": 120 + } + ], + "logging_steps": 10, + "max_steps": 125, + "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": 1.2589656731283456e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-125/training_args.bin b/checkpoint-125/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b1ceadcc46a4dbcb04d34405de43a2667755f2a --- /dev/null +++ b/checkpoint-125/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4e0921a533d54992c732b7cf0c8a29ef97e50bbd333d4e4c07ae7183a1feb0f +size 5713 diff --git a/checkpoint-500/chat_template.jinja b/checkpoint-500/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-500/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-500/config.json b/checkpoint-500/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-500/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-500/generation_config.json b/checkpoint-500/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-500/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-500/model.safetensors b/checkpoint-500/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aad24a30496616243a28537371ee273f78ce5980 --- /dev/null +++ b/checkpoint-500/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079565c41b7390c29162b2177ece2956e65a2c94398b94f8fbdcc9aaea1e5987 +size 3441185608 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..90c55c866e33ae7b8a57d59da6cb54957b236309 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11662089759b5ab33db1036a43acc423329b165030883aa32639c9ab33f035f +size 6882572207 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..3105ae629835438feca5d75cb928a0254192bb7f --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0 +size 14645 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3cbc1d4f12d934fbe27c91c192400d02b27d2e00 --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ae61b7327de513c572cbdd449d40136fa2f4fac8357d34b3d1a844dc5168d3 +size 1465 diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-500/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-500/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..511dccfadd29552a3ad6e861310aa24e146a179e --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,589 @@ +{ + "best_global_step": 500, + "best_metric": 0.2841346263885498, + "best_model_checkpoint": "/scratch/checkpoints/math_sft_v2/checkpoint-500", + "epoch": 1.6507018992568125, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 0.26208699569106103, + "epoch": 0.03303055326176713, + "grad_norm": 13.3125, + "learning_rate": 1.5e-06, + "loss": 0.8376299858093261, + "mean_token_accuracy": 0.8421687923371792, + "num_tokens": 98215.0, + "step": 10 + }, + { + "entropy": 0.2689803125336766, + "epoch": 0.06606110652353427, + "grad_norm": 11.5625, + "learning_rate": 3.1666666666666667e-06, + "loss": 0.853145980834961, + "mean_token_accuracy": 0.8399689704179764, + "num_tokens": 191821.0, + "step": 20 + }, + { + "entropy": 0.28777916859835384, + "epoch": 0.0990916597853014, + "grad_norm": 12.375, + "learning_rate": 4.833333333333333e-06, + "loss": 0.7679028034210205, + "mean_token_accuracy": 0.8431851923465729, + "num_tokens": 285491.0, + "step": 30 + }, + { + "entropy": 0.3033197607845068, + "epoch": 0.13212221304706853, + "grad_norm": 5.375, + "learning_rate": 6.5000000000000004e-06, + "loss": 0.6137509822845459, + "mean_token_accuracy": 0.8549904882907867, + "num_tokens": 381273.0, + "step": 40 + }, + { + "entropy": 0.34702248610556125, + "epoch": 0.16515276630883569, + "grad_norm": 4.25, + "learning_rate": 8.166666666666668e-06, + "loss": 0.5155063152313233, + "mean_token_accuracy": 0.8607264116406441, + "num_tokens": 476481.0, + "step": 50 + }, + { + "entropy": 0.35821260381489994, + "epoch": 0.1981833195706028, + "grad_norm": 2.890625, + "learning_rate": 9.833333333333333e-06, + "loss": 0.42441272735595703, + "mean_token_accuracy": 0.8774531938135623, + "num_tokens": 570979.0, + "step": 60 + }, + { + "entropy": 0.33337059412151576, + "epoch": 0.23121387283236994, + "grad_norm": 3.15625, + "learning_rate": 9.835164835164835e-06, + "loss": 0.34101109504699706, + "mean_token_accuracy": 0.8939957685768605, + "num_tokens": 664789.0, + "step": 70 + }, + { + "entropy": 0.30876336991786957, + "epoch": 0.26424442609413706, + "grad_norm": 1.8515625, + "learning_rate": 9.652014652014653e-06, + "loss": 0.32317628860473635, + "mean_token_accuracy": 0.8987478196620942, + "num_tokens": 764246.0, + "step": 80 + }, + { + "entropy": 0.30824985895305873, + "epoch": 0.2972749793559042, + "grad_norm": 2.15625, + "learning_rate": 9.46886446886447e-06, + "loss": 0.31807353496551516, + "mean_token_accuracy": 0.896314675360918, + "num_tokens": 855689.0, + "step": 90 + }, + { + "entropy": 0.31522620394825934, + "epoch": 0.33030553261767137, + "grad_norm": 1.8828125, + "learning_rate": 9.285714285714288e-06, + "loss": 0.338785982131958, + "mean_token_accuracy": 0.89400485008955, + "num_tokens": 949366.0, + "step": 100 + }, + { + "epoch": 0.33030553261767137, + "eval_entropy": 0.3022541454544774, + "eval_loss": 0.3146008253097534, + "eval_mean_token_accuracy": 0.8988911988558592, + "eval_num_tokens": 949366.0, + "eval_runtime": 17.914, + "eval_samples_per_second": 30.088, + "eval_steps_per_second": 15.072, + "step": 100 + }, + { + "entropy": 0.2985268572345376, + "epoch": 0.3633360858794385, + "grad_norm": 2.171875, + "learning_rate": 9.102564102564104e-06, + "loss": 0.31417596340179443, + "mean_token_accuracy": 0.89812126532197, + "num_tokens": 1040854.0, + "step": 110 + }, + { + "entropy": 0.3040375892072916, + "epoch": 0.3963666391412056, + "grad_norm": 1.9609375, + "learning_rate": 8.91941391941392e-06, + "loss": 0.32050628662109376, + "mean_token_accuracy": 0.8970061101019382, + "num_tokens": 1132424.0, + "step": 120 + }, + { + "entropy": 0.3125588171184063, + "epoch": 0.42939719240297275, + "grad_norm": 1.8203125, + "learning_rate": 8.736263736263737e-06, + "loss": 0.3176266193389893, + "mean_token_accuracy": 0.8971590586006641, + "num_tokens": 1221899.0, + "step": 130 + }, + { + "entropy": 0.312872576713562, + "epoch": 0.4624277456647399, + "grad_norm": 1.78125, + "learning_rate": 8.553113553113553e-06, + "loss": 0.3343791484832764, + "mean_token_accuracy": 0.8940604299306869, + "num_tokens": 1315052.0, + "step": 140 + }, + { + "entropy": 0.27830475065857174, + "epoch": 0.495458298926507, + "grad_norm": 2.0, + "learning_rate": 8.369963369963371e-06, + "loss": 0.28718521595001223, + "mean_token_accuracy": 0.9051955968141556, + "num_tokens": 1401947.0, + "step": 150 + }, + { + "entropy": 0.3005422970280051, + "epoch": 0.5284888521882741, + "grad_norm": 2.34375, + "learning_rate": 8.186813186813188e-06, + "loss": 0.31569790840148926, + "mean_token_accuracy": 0.8999212823808194, + "num_tokens": 1494107.0, + "step": 160 + }, + { + "entropy": 0.31200682315975425, + "epoch": 0.5615194054500413, + "grad_norm": 2.015625, + "learning_rate": 8.003663003663006e-06, + "loss": 0.32325453758239747, + "mean_token_accuracy": 0.8952137432992459, + "num_tokens": 1586474.0, + "step": 170 + }, + { + "entropy": 0.2929861258715391, + "epoch": 0.5945499587118084, + "grad_norm": 2.09375, + "learning_rate": 7.820512820512822e-06, + "loss": 0.29693677425384524, + "mean_token_accuracy": 0.9031261466443539, + "num_tokens": 1678162.0, + "step": 180 + }, + { + "entropy": 0.30670158881694076, + "epoch": 0.6275805119735756, + "grad_norm": 1.828125, + "learning_rate": 7.637362637362638e-06, + "loss": 0.31567308902740476, + "mean_token_accuracy": 0.8983482263982296, + "num_tokens": 1781401.0, + "step": 190 + }, + { + "entropy": 0.2866023685783148, + "epoch": 0.6606110652353427, + "grad_norm": 1.6953125, + "learning_rate": 7.454212454212455e-06, + "loss": 0.29333360195159913, + "mean_token_accuracy": 0.904055442661047, + "num_tokens": 1868038.0, + "step": 200 + }, + { + "epoch": 0.6606110652353427, + "eval_entropy": 0.2921138784951634, + "eval_loss": 0.29292193055152893, + "eval_mean_token_accuracy": 0.904505420172656, + "eval_num_tokens": 1868038.0, + "eval_runtime": 17.8732, + "eval_samples_per_second": 30.157, + "eval_steps_per_second": 15.106, + "step": 200 + }, + { + "entropy": 0.28792863376438615, + "epoch": 0.6936416184971098, + "grad_norm": 1.9609375, + "learning_rate": 7.271062271062271e-06, + "loss": 0.29235827922821045, + "mean_token_accuracy": 0.9050419509410859, + "num_tokens": 1959819.0, + "step": 210 + }, + { + "entropy": 0.28098181951791046, + "epoch": 0.726672171758877, + "grad_norm": 1.8515625, + "learning_rate": 7.087912087912089e-06, + "loss": 0.2915766954421997, + "mean_token_accuracy": 0.9068245775997639, + "num_tokens": 2059113.0, + "step": 220 + }, + { + "entropy": 0.26028320472687483, + "epoch": 0.7597027250206441, + "grad_norm": 2.0, + "learning_rate": 6.9047619047619055e-06, + "loss": 0.2654874324798584, + "mean_token_accuracy": 0.9116183832287789, + "num_tokens": 2145321.0, + "step": 230 + }, + { + "entropy": 0.2855058180168271, + "epoch": 0.7927332782824112, + "grad_norm": 1.84375, + "learning_rate": 6.721611721611723e-06, + "loss": 0.2998212337493896, + "mean_token_accuracy": 0.9046589516103267, + "num_tokens": 2240859.0, + "step": 240 + }, + { + "entropy": 0.2783821925520897, + "epoch": 0.8257638315441783, + "grad_norm": 1.9609375, + "learning_rate": 6.538461538461539e-06, + "loss": 0.28870720863342286, + "mean_token_accuracy": 0.9073394626379013, + "num_tokens": 2333798.0, + "step": 250 + }, + { + "entropy": 0.277759512513876, + "epoch": 0.8587943848059455, + "grad_norm": 1.7734375, + "learning_rate": 6.3553113553113555e-06, + "loss": 0.29060728549957277, + "mean_token_accuracy": 0.9055352889001369, + "num_tokens": 2429910.0, + "step": 260 + }, + { + "entropy": 0.2882726760581136, + "epoch": 0.8918249380677127, + "grad_norm": 1.703125, + "learning_rate": 6.172161172161173e-06, + "loss": 0.2988502740859985, + "mean_token_accuracy": 0.9038613699376583, + "num_tokens": 2524730.0, + "step": 270 + }, + { + "entropy": 0.2855747708119452, + "epoch": 0.9248554913294798, + "grad_norm": 1.90625, + "learning_rate": 5.989010989010989e-06, + "loss": 0.289182186126709, + "mean_token_accuracy": 0.9049803033471108, + "num_tokens": 2615802.0, + "step": 280 + }, + { + "entropy": 0.26923007648438213, + "epoch": 0.9578860445912469, + "grad_norm": 2.84375, + "learning_rate": 5.805860805860807e-06, + "loss": 0.27834036350250246, + "mean_token_accuracy": 0.9109352678060532, + "num_tokens": 2709073.0, + "step": 290 + }, + { + "entropy": 0.2844470454379916, + "epoch": 0.990916597853014, + "grad_norm": 1.640625, + "learning_rate": 5.6227106227106235e-06, + "loss": 0.28873960971832274, + "mean_token_accuracy": 0.9069667845964432, + "num_tokens": 2805135.0, + "step": 300 + }, + { + "epoch": 0.990916597853014, + "eval_entropy": 0.285272175570329, + "eval_loss": 0.28705036640167236, + "eval_mean_token_accuracy": 0.9062359571456909, + "eval_num_tokens": 2805135.0, + "eval_runtime": 17.9038, + "eval_samples_per_second": 30.105, + "eval_steps_per_second": 15.081, + "step": 300 + }, + { + "entropy": 0.2869852078266633, + "epoch": 1.023121387283237, + "grad_norm": 1.9375, + "learning_rate": 5.43956043956044e-06, + "loss": 0.2850792646408081, + "mean_token_accuracy": 0.9064911672702203, + "num_tokens": 2898984.0, + "step": 310 + }, + { + "entropy": 0.2757460119202733, + "epoch": 1.0561519405450042, + "grad_norm": 1.8359375, + "learning_rate": 5.256410256410257e-06, + "loss": 0.2779810905456543, + "mean_token_accuracy": 0.9096895463764667, + "num_tokens": 2991694.0, + "step": 320 + }, + { + "entropy": 0.2600112119689584, + "epoch": 1.0891824938067713, + "grad_norm": 2.0625, + "learning_rate": 5.0732600732600735e-06, + "loss": 0.2662019729614258, + "mean_token_accuracy": 0.912333931028843, + "num_tokens": 3078862.0, + "step": 330 + }, + { + "entropy": 0.27342566605657337, + "epoch": 1.1222130470685383, + "grad_norm": 1.921875, + "learning_rate": 4.890109890109891e-06, + "loss": 0.28096842765808105, + "mean_token_accuracy": 0.9091624312102795, + "num_tokens": 3174256.0, + "step": 340 + }, + { + "entropy": 0.2671937083825469, + "epoch": 1.1552436003303055, + "grad_norm": 1.75, + "learning_rate": 4.706959706959707e-06, + "loss": 0.2723649501800537, + "mean_token_accuracy": 0.9101433955132961, + "num_tokens": 3272477.0, + "step": 350 + }, + { + "entropy": 0.2617026660591364, + "epoch": 1.1882741535920727, + "grad_norm": 1.9453125, + "learning_rate": 4.523809523809524e-06, + "loss": 0.26422107219696045, + "mean_token_accuracy": 0.913913157582283, + "num_tokens": 3364137.0, + "step": 360 + }, + { + "entropy": 0.2595691759139299, + "epoch": 1.2213047068538398, + "grad_norm": 1.5390625, + "learning_rate": 4.340659340659341e-06, + "loss": 0.2714951276779175, + "mean_token_accuracy": 0.911636833101511, + "num_tokens": 3460217.0, + "step": 370 + }, + { + "entropy": 0.2933320404961705, + "epoch": 1.254335260115607, + "grad_norm": 1.9765625, + "learning_rate": 4.157509157509158e-06, + "loss": 0.29573276042938235, + "mean_token_accuracy": 0.902192335575819, + "num_tokens": 3557030.0, + "step": 380 + }, + { + "entropy": 0.2693369995802641, + "epoch": 1.287365813377374, + "grad_norm": 1.890625, + "learning_rate": 3.974358974358974e-06, + "loss": 0.27785425186157225, + "mean_token_accuracy": 0.9090337291359901, + "num_tokens": 3654159.0, + "step": 390 + }, + { + "entropy": 0.2908114368095994, + "epoch": 1.3203963666391412, + "grad_norm": 2.015625, + "learning_rate": 3.7912087912087915e-06, + "loss": 0.30535905361175536, + "mean_token_accuracy": 0.901054035872221, + "num_tokens": 3749664.0, + "step": 400 + }, + { + "epoch": 1.3203963666391412, + "eval_entropy": 0.2783401116176888, + "eval_loss": 0.28495287895202637, + "eval_mean_token_accuracy": 0.9069356251645971, + "eval_num_tokens": 3749664.0, + "eval_runtime": 17.8814, + "eval_samples_per_second": 30.143, + "eval_steps_per_second": 15.099, + "step": 400 + }, + { + "entropy": 0.2749379588291049, + "epoch": 1.3534269199009084, + "grad_norm": 1.84375, + "learning_rate": 3.6080586080586083e-06, + "loss": 0.27795455455780027, + "mean_token_accuracy": 0.9090839587152004, + "num_tokens": 3845841.0, + "step": 410 + }, + { + "entropy": 0.2859474029392004, + "epoch": 1.3864574731626755, + "grad_norm": 1.6796875, + "learning_rate": 3.424908424908425e-06, + "loss": 0.2886682987213135, + "mean_token_accuracy": 0.9059950634837151, + "num_tokens": 3942402.0, + "step": 420 + }, + { + "entropy": 0.2537162031978369, + "epoch": 1.4194880264244425, + "grad_norm": 1.9375, + "learning_rate": 3.2417582417582424e-06, + "loss": 0.25533475875854494, + "mean_token_accuracy": 0.9158934533596039, + "num_tokens": 4034122.0, + "step": 430 + }, + { + "entropy": 0.28255065642297267, + "epoch": 1.4525185796862097, + "grad_norm": 1.7734375, + "learning_rate": 3.058608058608059e-06, + "loss": 0.29817631244659426, + "mean_token_accuracy": 0.9040707617998123, + "num_tokens": 4127068.0, + "step": 440 + }, + { + "entropy": 0.2898306529968977, + "epoch": 1.4855491329479769, + "grad_norm": 1.703125, + "learning_rate": 2.8754578754578755e-06, + "loss": 0.2923931121826172, + "mean_token_accuracy": 0.9030195340514183, + "num_tokens": 4224435.0, + "step": 450 + }, + { + "entropy": 0.27209411058574917, + "epoch": 1.518579686209744, + "grad_norm": 1.7578125, + "learning_rate": 2.6923076923076923e-06, + "loss": 0.28646528720855713, + "mean_token_accuracy": 0.9095881894230843, + "num_tokens": 4321028.0, + "step": 460 + }, + { + "entropy": 0.280727200768888, + "epoch": 1.5516102394715112, + "grad_norm": 1.7421875, + "learning_rate": 2.509157509157509e-06, + "loss": 0.2891413688659668, + "mean_token_accuracy": 0.9067636162042618, + "num_tokens": 4414916.0, + "step": 470 + }, + { + "entropy": 0.27109829243272543, + "epoch": 1.5846407927332784, + "grad_norm": 1.8359375, + "learning_rate": 2.3260073260073264e-06, + "loss": 0.26625516414642336, + "mean_token_accuracy": 0.9099020563066006, + "num_tokens": 4505708.0, + "step": 480 + }, + { + "entropy": 0.2729395367205143, + "epoch": 1.6176713459950454, + "grad_norm": 1.7890625, + "learning_rate": 2.1428571428571427e-06, + "loss": 0.2779061317443848, + "mean_token_accuracy": 0.909747340530157, + "num_tokens": 4600244.0, + "step": 490 + }, + { + "entropy": 0.2682301852852106, + "epoch": 1.6507018992568125, + "grad_norm": 1.6953125, + "learning_rate": 1.95970695970696e-06, + "loss": 0.274446964263916, + "mean_token_accuracy": 0.9094639919698239, + "num_tokens": 4688147.0, + "step": 500 + }, + { + "epoch": 1.6507018992568125, + "eval_entropy": 0.2756172451708052, + "eval_loss": 0.2841346263885498, + "eval_mean_token_accuracy": 0.9072470570052111, + "eval_num_tokens": 4688147.0, + "eval_runtime": 17.9119, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 15.074, + "step": 500 + } + ], + "logging_steps": 10, + "max_steps": 606, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5.028742352950886e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..133cb6661b0124bb9db0d7d208d748fd736ea689 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6696e1fef8bde5e22de2f5ae18c284f2b2d35a345157db5151571518385fb38b +size 5713 diff --git a/checkpoint-600/chat_template.jinja b/checkpoint-600/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-600/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-600/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-600/generation_config.json b/checkpoint-600/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-600/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-600/model.safetensors b/checkpoint-600/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..888c633f416471cd0dba703e4ed15cd967deaf00 --- /dev/null +++ b/checkpoint-600/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066f20885c5c9a598d45fbcd21aa7ab9081dffda3fb1930d573d7c3d99b5d998 +size 3441185608 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..315889bc3c6c060ec3677e282757036eb6d14155 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c75c57fe3c14c29f7a73acb2b44e60573aaf69cd744a4ce99770cdfdbe4de45e +size 6882572207 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fb544a66454d577cf2a3cb06c26493972f57952 --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6 +size 14645 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2645e63119eba5c7c9361da38b055b60e6d8985 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:540d8ab45fe72a01988766f9263355239d34a4ff0ef13ddac7f1f0d1198ce9a9 +size 1465 diff --git a/checkpoint-600/tokenizer.json b/checkpoint-600/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-600/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-600/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c4cf7cbe351f817a25fffdf26360f8e89d0ea1ce --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,700 @@ +{ + "best_global_step": 600, + "best_metric": 0.28394654393196106, + "best_model_checkpoint": "/scratch/checkpoints/math_sft_v2/checkpoint-600", + "epoch": 1.981007431874484, + "eval_steps": 100, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 0.26208699569106103, + "epoch": 0.03303055326176713, + "grad_norm": 13.3125, + "learning_rate": 1.5e-06, + "loss": 0.8376299858093261, + "mean_token_accuracy": 0.8421687923371792, + "num_tokens": 98215.0, + "step": 10 + }, + { + "entropy": 0.2689803125336766, + "epoch": 0.06606110652353427, + "grad_norm": 11.5625, + "learning_rate": 3.1666666666666667e-06, + "loss": 0.853145980834961, + "mean_token_accuracy": 0.8399689704179764, + "num_tokens": 191821.0, + "step": 20 + }, + { + "entropy": 0.28777916859835384, + "epoch": 0.0990916597853014, + "grad_norm": 12.375, + "learning_rate": 4.833333333333333e-06, + "loss": 0.7679028034210205, + "mean_token_accuracy": 0.8431851923465729, + "num_tokens": 285491.0, + "step": 30 + }, + { + "entropy": 0.3033197607845068, + "epoch": 0.13212221304706853, + "grad_norm": 5.375, + "learning_rate": 6.5000000000000004e-06, + "loss": 0.6137509822845459, + "mean_token_accuracy": 0.8549904882907867, + "num_tokens": 381273.0, + "step": 40 + }, + { + "entropy": 0.34702248610556125, + "epoch": 0.16515276630883569, + "grad_norm": 4.25, + "learning_rate": 8.166666666666668e-06, + "loss": 0.5155063152313233, + "mean_token_accuracy": 0.8607264116406441, + "num_tokens": 476481.0, + "step": 50 + }, + { + "entropy": 0.35821260381489994, + "epoch": 0.1981833195706028, + "grad_norm": 2.890625, + "learning_rate": 9.833333333333333e-06, + "loss": 0.42441272735595703, + "mean_token_accuracy": 0.8774531938135623, + "num_tokens": 570979.0, + "step": 60 + }, + { + "entropy": 0.33337059412151576, + "epoch": 0.23121387283236994, + "grad_norm": 3.15625, + "learning_rate": 9.835164835164835e-06, + "loss": 0.34101109504699706, + "mean_token_accuracy": 0.8939957685768605, + "num_tokens": 664789.0, + "step": 70 + }, + { + "entropy": 0.30876336991786957, + "epoch": 0.26424442609413706, + "grad_norm": 1.8515625, + "learning_rate": 9.652014652014653e-06, + "loss": 0.32317628860473635, + "mean_token_accuracy": 0.8987478196620942, + "num_tokens": 764246.0, + "step": 80 + }, + { + "entropy": 0.30824985895305873, + "epoch": 0.2972749793559042, + "grad_norm": 2.15625, + "learning_rate": 9.46886446886447e-06, + "loss": 0.31807353496551516, + "mean_token_accuracy": 0.896314675360918, + "num_tokens": 855689.0, + "step": 90 + }, + { + "entropy": 0.31522620394825934, + "epoch": 0.33030553261767137, + "grad_norm": 1.8828125, + "learning_rate": 9.285714285714288e-06, + "loss": 0.338785982131958, + "mean_token_accuracy": 0.89400485008955, + "num_tokens": 949366.0, + "step": 100 + }, + { + "epoch": 0.33030553261767137, + "eval_entropy": 0.3022541454544774, + "eval_loss": 0.3146008253097534, + "eval_mean_token_accuracy": 0.8988911988558592, + "eval_num_tokens": 949366.0, + "eval_runtime": 17.914, + "eval_samples_per_second": 30.088, + "eval_steps_per_second": 15.072, + "step": 100 + }, + { + "entropy": 0.2985268572345376, + "epoch": 0.3633360858794385, + "grad_norm": 2.171875, + "learning_rate": 9.102564102564104e-06, + "loss": 0.31417596340179443, + "mean_token_accuracy": 0.89812126532197, + "num_tokens": 1040854.0, + "step": 110 + }, + { + "entropy": 0.3040375892072916, + "epoch": 0.3963666391412056, + "grad_norm": 1.9609375, + "learning_rate": 8.91941391941392e-06, + "loss": 0.32050628662109376, + "mean_token_accuracy": 0.8970061101019382, + "num_tokens": 1132424.0, + "step": 120 + }, + { + "entropy": 0.3125588171184063, + "epoch": 0.42939719240297275, + "grad_norm": 1.8203125, + "learning_rate": 8.736263736263737e-06, + "loss": 0.3176266193389893, + "mean_token_accuracy": 0.8971590586006641, + "num_tokens": 1221899.0, + "step": 130 + }, + { + "entropy": 0.312872576713562, + "epoch": 0.4624277456647399, + "grad_norm": 1.78125, + "learning_rate": 8.553113553113553e-06, + "loss": 0.3343791484832764, + "mean_token_accuracy": 0.8940604299306869, + "num_tokens": 1315052.0, + "step": 140 + }, + { + "entropy": 0.27830475065857174, + "epoch": 0.495458298926507, + "grad_norm": 2.0, + "learning_rate": 8.369963369963371e-06, + "loss": 0.28718521595001223, + "mean_token_accuracy": 0.9051955968141556, + "num_tokens": 1401947.0, + "step": 150 + }, + { + "entropy": 0.3005422970280051, + "epoch": 0.5284888521882741, + "grad_norm": 2.34375, + "learning_rate": 8.186813186813188e-06, + "loss": 0.31569790840148926, + "mean_token_accuracy": 0.8999212823808194, + "num_tokens": 1494107.0, + "step": 160 + }, + { + "entropy": 0.31200682315975425, + "epoch": 0.5615194054500413, + "grad_norm": 2.015625, + "learning_rate": 8.003663003663006e-06, + "loss": 0.32325453758239747, + "mean_token_accuracy": 0.8952137432992459, + "num_tokens": 1586474.0, + "step": 170 + }, + { + "entropy": 0.2929861258715391, + "epoch": 0.5945499587118084, + "grad_norm": 2.09375, + "learning_rate": 7.820512820512822e-06, + "loss": 0.29693677425384524, + "mean_token_accuracy": 0.9031261466443539, + "num_tokens": 1678162.0, + "step": 180 + }, + { + "entropy": 0.30670158881694076, + "epoch": 0.6275805119735756, + "grad_norm": 1.828125, + "learning_rate": 7.637362637362638e-06, + "loss": 0.31567308902740476, + "mean_token_accuracy": 0.8983482263982296, + "num_tokens": 1781401.0, + "step": 190 + }, + { + "entropy": 0.2866023685783148, + "epoch": 0.6606110652353427, + "grad_norm": 1.6953125, + "learning_rate": 7.454212454212455e-06, + "loss": 0.29333360195159913, + "mean_token_accuracy": 0.904055442661047, + "num_tokens": 1868038.0, + "step": 200 + }, + { + "epoch": 0.6606110652353427, + "eval_entropy": 0.2921138784951634, + "eval_loss": 0.29292193055152893, + "eval_mean_token_accuracy": 0.904505420172656, + "eval_num_tokens": 1868038.0, + "eval_runtime": 17.8732, + "eval_samples_per_second": 30.157, + "eval_steps_per_second": 15.106, + "step": 200 + }, + { + "entropy": 0.28792863376438615, + "epoch": 0.6936416184971098, + "grad_norm": 1.9609375, + "learning_rate": 7.271062271062271e-06, + "loss": 0.29235827922821045, + "mean_token_accuracy": 0.9050419509410859, + "num_tokens": 1959819.0, + "step": 210 + }, + { + "entropy": 0.28098181951791046, + "epoch": 0.726672171758877, + "grad_norm": 1.8515625, + "learning_rate": 7.087912087912089e-06, + "loss": 0.2915766954421997, + "mean_token_accuracy": 0.9068245775997639, + "num_tokens": 2059113.0, + "step": 220 + }, + { + "entropy": 0.26028320472687483, + "epoch": 0.7597027250206441, + "grad_norm": 2.0, + "learning_rate": 6.9047619047619055e-06, + "loss": 0.2654874324798584, + "mean_token_accuracy": 0.9116183832287789, + "num_tokens": 2145321.0, + "step": 230 + }, + { + "entropy": 0.2855058180168271, + "epoch": 0.7927332782824112, + "grad_norm": 1.84375, + "learning_rate": 6.721611721611723e-06, + "loss": 0.2998212337493896, + "mean_token_accuracy": 0.9046589516103267, + "num_tokens": 2240859.0, + "step": 240 + }, + { + "entropy": 0.2783821925520897, + "epoch": 0.8257638315441783, + "grad_norm": 1.9609375, + "learning_rate": 6.538461538461539e-06, + "loss": 0.28870720863342286, + "mean_token_accuracy": 0.9073394626379013, + "num_tokens": 2333798.0, + "step": 250 + }, + { + "entropy": 0.277759512513876, + "epoch": 0.8587943848059455, + "grad_norm": 1.7734375, + "learning_rate": 6.3553113553113555e-06, + "loss": 0.29060728549957277, + "mean_token_accuracy": 0.9055352889001369, + "num_tokens": 2429910.0, + "step": 260 + }, + { + "entropy": 0.2882726760581136, + "epoch": 0.8918249380677127, + "grad_norm": 1.703125, + "learning_rate": 6.172161172161173e-06, + "loss": 0.2988502740859985, + "mean_token_accuracy": 0.9038613699376583, + "num_tokens": 2524730.0, + "step": 270 + }, + { + "entropy": 0.2855747708119452, + "epoch": 0.9248554913294798, + "grad_norm": 1.90625, + "learning_rate": 5.989010989010989e-06, + "loss": 0.289182186126709, + "mean_token_accuracy": 0.9049803033471108, + "num_tokens": 2615802.0, + "step": 280 + }, + { + "entropy": 0.26923007648438213, + "epoch": 0.9578860445912469, + "grad_norm": 2.84375, + "learning_rate": 5.805860805860807e-06, + "loss": 0.27834036350250246, + "mean_token_accuracy": 0.9109352678060532, + "num_tokens": 2709073.0, + "step": 290 + }, + { + "entropy": 0.2844470454379916, + "epoch": 0.990916597853014, + "grad_norm": 1.640625, + "learning_rate": 5.6227106227106235e-06, + "loss": 0.28873960971832274, + "mean_token_accuracy": 0.9069667845964432, + "num_tokens": 2805135.0, + "step": 300 + }, + { + "epoch": 0.990916597853014, + "eval_entropy": 0.285272175570329, + "eval_loss": 0.28705036640167236, + "eval_mean_token_accuracy": 0.9062359571456909, + "eval_num_tokens": 2805135.0, + "eval_runtime": 17.9038, + "eval_samples_per_second": 30.105, + "eval_steps_per_second": 15.081, + "step": 300 + }, + { + "entropy": 0.2869852078266633, + "epoch": 1.023121387283237, + "grad_norm": 1.9375, + "learning_rate": 5.43956043956044e-06, + "loss": 0.2850792646408081, + "mean_token_accuracy": 0.9064911672702203, + "num_tokens": 2898984.0, + "step": 310 + }, + { + "entropy": 0.2757460119202733, + "epoch": 1.0561519405450042, + "grad_norm": 1.8359375, + "learning_rate": 5.256410256410257e-06, + "loss": 0.2779810905456543, + "mean_token_accuracy": 0.9096895463764667, + "num_tokens": 2991694.0, + "step": 320 + }, + { + "entropy": 0.2600112119689584, + "epoch": 1.0891824938067713, + "grad_norm": 2.0625, + "learning_rate": 5.0732600732600735e-06, + "loss": 0.2662019729614258, + "mean_token_accuracy": 0.912333931028843, + "num_tokens": 3078862.0, + "step": 330 + }, + { + "entropy": 0.27342566605657337, + "epoch": 1.1222130470685383, + "grad_norm": 1.921875, + "learning_rate": 4.890109890109891e-06, + "loss": 0.28096842765808105, + "mean_token_accuracy": 0.9091624312102795, + "num_tokens": 3174256.0, + "step": 340 + }, + { + "entropy": 0.2671937083825469, + "epoch": 1.1552436003303055, + "grad_norm": 1.75, + "learning_rate": 4.706959706959707e-06, + "loss": 0.2723649501800537, + "mean_token_accuracy": 0.9101433955132961, + "num_tokens": 3272477.0, + "step": 350 + }, + { + "entropy": 0.2617026660591364, + "epoch": 1.1882741535920727, + "grad_norm": 1.9453125, + "learning_rate": 4.523809523809524e-06, + "loss": 0.26422107219696045, + "mean_token_accuracy": 0.913913157582283, + "num_tokens": 3364137.0, + "step": 360 + }, + { + "entropy": 0.2595691759139299, + "epoch": 1.2213047068538398, + "grad_norm": 1.5390625, + "learning_rate": 4.340659340659341e-06, + "loss": 0.2714951276779175, + "mean_token_accuracy": 0.911636833101511, + "num_tokens": 3460217.0, + "step": 370 + }, + { + "entropy": 0.2933320404961705, + "epoch": 1.254335260115607, + "grad_norm": 1.9765625, + "learning_rate": 4.157509157509158e-06, + "loss": 0.29573276042938235, + "mean_token_accuracy": 0.902192335575819, + "num_tokens": 3557030.0, + "step": 380 + }, + { + "entropy": 0.2693369995802641, + "epoch": 1.287365813377374, + "grad_norm": 1.890625, + "learning_rate": 3.974358974358974e-06, + "loss": 0.27785425186157225, + "mean_token_accuracy": 0.9090337291359901, + "num_tokens": 3654159.0, + "step": 390 + }, + { + "entropy": 0.2908114368095994, + "epoch": 1.3203963666391412, + "grad_norm": 2.015625, + "learning_rate": 3.7912087912087915e-06, + "loss": 0.30535905361175536, + "mean_token_accuracy": 0.901054035872221, + "num_tokens": 3749664.0, + "step": 400 + }, + { + "epoch": 1.3203963666391412, + "eval_entropy": 0.2783401116176888, + "eval_loss": 0.28495287895202637, + "eval_mean_token_accuracy": 0.9069356251645971, + "eval_num_tokens": 3749664.0, + "eval_runtime": 17.8814, + "eval_samples_per_second": 30.143, + "eval_steps_per_second": 15.099, + "step": 400 + }, + { + "entropy": 0.2749379588291049, + "epoch": 1.3534269199009084, + "grad_norm": 1.84375, + "learning_rate": 3.6080586080586083e-06, + "loss": 0.27795455455780027, + "mean_token_accuracy": 0.9090839587152004, + "num_tokens": 3845841.0, + "step": 410 + }, + { + "entropy": 0.2859474029392004, + "epoch": 1.3864574731626755, + "grad_norm": 1.6796875, + "learning_rate": 3.424908424908425e-06, + "loss": 0.2886682987213135, + "mean_token_accuracy": 0.9059950634837151, + "num_tokens": 3942402.0, + "step": 420 + }, + { + "entropy": 0.2537162031978369, + "epoch": 1.4194880264244425, + "grad_norm": 1.9375, + "learning_rate": 3.2417582417582424e-06, + "loss": 0.25533475875854494, + "mean_token_accuracy": 0.9158934533596039, + "num_tokens": 4034122.0, + "step": 430 + }, + { + "entropy": 0.28255065642297267, + "epoch": 1.4525185796862097, + "grad_norm": 1.7734375, + "learning_rate": 3.058608058608059e-06, + "loss": 0.29817631244659426, + "mean_token_accuracy": 0.9040707617998123, + "num_tokens": 4127068.0, + "step": 440 + }, + { + "entropy": 0.2898306529968977, + "epoch": 1.4855491329479769, + "grad_norm": 1.703125, + "learning_rate": 2.8754578754578755e-06, + "loss": 0.2923931121826172, + "mean_token_accuracy": 0.9030195340514183, + "num_tokens": 4224435.0, + "step": 450 + }, + { + "entropy": 0.27209411058574917, + "epoch": 1.518579686209744, + "grad_norm": 1.7578125, + "learning_rate": 2.6923076923076923e-06, + "loss": 0.28646528720855713, + "mean_token_accuracy": 0.9095881894230843, + "num_tokens": 4321028.0, + "step": 460 + }, + { + "entropy": 0.280727200768888, + "epoch": 1.5516102394715112, + "grad_norm": 1.7421875, + "learning_rate": 2.509157509157509e-06, + "loss": 0.2891413688659668, + "mean_token_accuracy": 0.9067636162042618, + "num_tokens": 4414916.0, + "step": 470 + }, + { + "entropy": 0.27109829243272543, + "epoch": 1.5846407927332784, + "grad_norm": 1.8359375, + "learning_rate": 2.3260073260073264e-06, + "loss": 0.26625516414642336, + "mean_token_accuracy": 0.9099020563066006, + "num_tokens": 4505708.0, + "step": 480 + }, + { + "entropy": 0.2729395367205143, + "epoch": 1.6176713459950454, + "grad_norm": 1.7890625, + "learning_rate": 2.1428571428571427e-06, + "loss": 0.2779061317443848, + "mean_token_accuracy": 0.909747340530157, + "num_tokens": 4600244.0, + "step": 490 + }, + { + "entropy": 0.2682301852852106, + "epoch": 1.6507018992568125, + "grad_norm": 1.6953125, + "learning_rate": 1.95970695970696e-06, + "loss": 0.274446964263916, + "mean_token_accuracy": 0.9094639919698239, + "num_tokens": 4688147.0, + "step": 500 + }, + { + "epoch": 1.6507018992568125, + "eval_entropy": 0.2756172451708052, + "eval_loss": 0.2841346263885498, + "eval_mean_token_accuracy": 0.9072470570052111, + "eval_num_tokens": 4688147.0, + "eval_runtime": 17.9119, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 15.074, + "step": 500 + }, + { + "entropy": 0.26342453975230457, + "epoch": 1.6837324525185797, + "grad_norm": 1.890625, + "learning_rate": 1.7765567765567768e-06, + "loss": 0.26432271003723146, + "mean_token_accuracy": 0.9114409819245338, + "num_tokens": 4780124.0, + "step": 510 + }, + { + "entropy": 0.28657868495211003, + "epoch": 1.7167630057803467, + "grad_norm": 1.7734375, + "learning_rate": 1.5934065934065933e-06, + "loss": 0.2983593225479126, + "mean_token_accuracy": 0.9028328903019428, + "num_tokens": 4874633.0, + "step": 520 + }, + { + "entropy": 0.25633321776986123, + "epoch": 1.7497935590421139, + "grad_norm": 1.8359375, + "learning_rate": 1.4102564102564104e-06, + "loss": 0.2606488227844238, + "mean_token_accuracy": 0.9153999648988247, + "num_tokens": 4967263.0, + "step": 530 + }, + { + "entropy": 0.26120030507445335, + "epoch": 1.782824112303881, + "grad_norm": 2.078125, + "learning_rate": 1.2271062271062271e-06, + "loss": 0.2706313610076904, + "mean_token_accuracy": 0.9130682416260243, + "num_tokens": 5056736.0, + "step": 540 + }, + { + "entropy": 0.27009565513581035, + "epoch": 1.8158546655656482, + "grad_norm": 1.8828125, + "learning_rate": 1.0439560439560442e-06, + "loss": 0.277858567237854, + "mean_token_accuracy": 0.9087999157607556, + "num_tokens": 5150617.0, + "step": 550 + }, + { + "entropy": 0.2819518899545074, + "epoch": 1.8488852188274154, + "grad_norm": 1.9609375, + "learning_rate": 8.608058608058609e-07, + "loss": 0.28743035793304444, + "mean_token_accuracy": 0.9067244723439216, + "num_tokens": 5243538.0, + "step": 560 + }, + { + "entropy": 0.2858045116066933, + "epoch": 1.8819157720891826, + "grad_norm": 2.203125, + "learning_rate": 6.776556776556777e-07, + "loss": 0.2939825296401978, + "mean_token_accuracy": 0.904579871147871, + "num_tokens": 5331441.0, + "step": 570 + }, + { + "entropy": 0.2926233192905784, + "epoch": 1.9149463253509498, + "grad_norm": 2.3125, + "learning_rate": 4.945054945054946e-07, + "loss": 0.29961700439453126, + "mean_token_accuracy": 0.9033655568957328, + "num_tokens": 5426734.0, + "step": 580 + }, + { + "entropy": 0.2706678254529834, + "epoch": 1.9479768786127167, + "grad_norm": 2.03125, + "learning_rate": 3.113553113553114e-07, + "loss": 0.27953526973724363, + "mean_token_accuracy": 0.9093762949109078, + "num_tokens": 5518190.0, + "step": 590 + }, + { + "entropy": 0.27056904807686805, + "epoch": 1.981007431874484, + "grad_norm": 2.09375, + "learning_rate": 1.282051282051282e-07, + "loss": 0.2764536619186401, + "mean_token_accuracy": 0.9110228553414345, + "num_tokens": 5609238.0, + "step": 600 + }, + { + "epoch": 1.981007431874484, + "eval_entropy": 0.2757842331572815, + "eval_loss": 0.28394654393196106, + "eval_mean_token_accuracy": 0.9073928307603907, + "eval_num_tokens": 5609238.0, + "eval_runtime": 18.1138, + "eval_samples_per_second": 29.756, + "eval_steps_per_second": 14.906, + "step": 600 + } + ], + "logging_steps": 10, + "max_steps": 606, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.018332557481165e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..133cb6661b0124bb9db0d7d208d748fd736ea689 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6696e1fef8bde5e22de2f5ae18c284f2b2d35a345157db5151571518385fb38b +size 5713 diff --git a/checkpoint-606/chat_template.jinja b/checkpoint-606/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-606/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-606/config.json b/checkpoint-606/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-606/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-606/generation_config.json b/checkpoint-606/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-606/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-606/model.safetensors b/checkpoint-606/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b08d1501dfdc93522108efc90dd1cd038d65cc7a --- /dev/null +++ b/checkpoint-606/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e0bbbd38e2572fcb7a7cdd2bf58165f2cb2a115544c68b132848cd7973d106 +size 3441185608 diff --git a/checkpoint-606/optimizer.pt b/checkpoint-606/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..590b9fb7b131560c1b58842b49379b273c5a6449 --- /dev/null +++ b/checkpoint-606/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3d8578da8d88239c2024e2dd1da1012e2173f003e746efcc15b17915d0a03c +size 6882572207 diff --git a/checkpoint-606/rng_state.pth b/checkpoint-606/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..eed58b88838bddfd46b410984c9cbddf403b1437 --- /dev/null +++ b/checkpoint-606/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b +size 14645 diff --git a/checkpoint-606/scheduler.pt b/checkpoint-606/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f182dc5e2546b5fdccbdc22b90eb16a565c67e6c --- /dev/null +++ b/checkpoint-606/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef108e31778ee002976f58f4a1ef7b3f1228ac6f0b9152b3822e08d82d99376b +size 1465 diff --git a/checkpoint-606/tokenizer.json b/checkpoint-606/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-606/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-606/tokenizer_config.json b/checkpoint-606/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-606/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-606/trainer_state.json b/checkpoint-606/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a4ec67787e726511e6fbf586ff5bd33e585236d7 --- /dev/null +++ b/checkpoint-606/trainer_state.json @@ -0,0 +1,711 @@ +{ + "best_global_step": 600, + "best_metric": 0.28394654393196106, + "best_model_checkpoint": "/scratch/checkpoints/math_sft_v2/checkpoint-600", + "epoch": 2.0, + "eval_steps": 100, + "global_step": 606, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": 0.26208699569106103, + "epoch": 0.03303055326176713, + "grad_norm": 13.3125, + "learning_rate": 1.5e-06, + "loss": 0.8376299858093261, + "mean_token_accuracy": 0.8421687923371792, + "num_tokens": 98215.0, + "step": 10 + }, + { + "entropy": 0.2689803125336766, + "epoch": 0.06606110652353427, + "grad_norm": 11.5625, + "learning_rate": 3.1666666666666667e-06, + "loss": 0.853145980834961, + "mean_token_accuracy": 0.8399689704179764, + "num_tokens": 191821.0, + "step": 20 + }, + { + "entropy": 0.28777916859835384, + "epoch": 0.0990916597853014, + "grad_norm": 12.375, + "learning_rate": 4.833333333333333e-06, + "loss": 0.7679028034210205, + "mean_token_accuracy": 0.8431851923465729, + "num_tokens": 285491.0, + "step": 30 + }, + { + "entropy": 0.3033197607845068, + "epoch": 0.13212221304706853, + "grad_norm": 5.375, + "learning_rate": 6.5000000000000004e-06, + "loss": 0.6137509822845459, + "mean_token_accuracy": 0.8549904882907867, + "num_tokens": 381273.0, + "step": 40 + }, + { + "entropy": 0.34702248610556125, + "epoch": 0.16515276630883569, + "grad_norm": 4.25, + "learning_rate": 8.166666666666668e-06, + "loss": 0.5155063152313233, + "mean_token_accuracy": 0.8607264116406441, + "num_tokens": 476481.0, + "step": 50 + }, + { + "entropy": 0.35821260381489994, + "epoch": 0.1981833195706028, + "grad_norm": 2.890625, + "learning_rate": 9.833333333333333e-06, + "loss": 0.42441272735595703, + "mean_token_accuracy": 0.8774531938135623, + "num_tokens": 570979.0, + "step": 60 + }, + { + "entropy": 0.33337059412151576, + "epoch": 0.23121387283236994, + "grad_norm": 3.15625, + "learning_rate": 9.835164835164835e-06, + "loss": 0.34101109504699706, + "mean_token_accuracy": 0.8939957685768605, + "num_tokens": 664789.0, + "step": 70 + }, + { + "entropy": 0.30876336991786957, + "epoch": 0.26424442609413706, + "grad_norm": 1.8515625, + "learning_rate": 9.652014652014653e-06, + "loss": 0.32317628860473635, + "mean_token_accuracy": 0.8987478196620942, + "num_tokens": 764246.0, + "step": 80 + }, + { + "entropy": 0.30824985895305873, + "epoch": 0.2972749793559042, + "grad_norm": 2.15625, + "learning_rate": 9.46886446886447e-06, + "loss": 0.31807353496551516, + "mean_token_accuracy": 0.896314675360918, + "num_tokens": 855689.0, + "step": 90 + }, + { + "entropy": 0.31522620394825934, + "epoch": 0.33030553261767137, + "grad_norm": 1.8828125, + "learning_rate": 9.285714285714288e-06, + "loss": 0.338785982131958, + "mean_token_accuracy": 0.89400485008955, + "num_tokens": 949366.0, + "step": 100 + }, + { + "epoch": 0.33030553261767137, + "eval_entropy": 0.3022541454544774, + "eval_loss": 0.3146008253097534, + "eval_mean_token_accuracy": 0.8988911988558592, + "eval_num_tokens": 949366.0, + "eval_runtime": 17.914, + "eval_samples_per_second": 30.088, + "eval_steps_per_second": 15.072, + "step": 100 + }, + { + "entropy": 0.2985268572345376, + "epoch": 0.3633360858794385, + "grad_norm": 2.171875, + "learning_rate": 9.102564102564104e-06, + "loss": 0.31417596340179443, + "mean_token_accuracy": 0.89812126532197, + "num_tokens": 1040854.0, + "step": 110 + }, + { + "entropy": 0.3040375892072916, + "epoch": 0.3963666391412056, + "grad_norm": 1.9609375, + "learning_rate": 8.91941391941392e-06, + "loss": 0.32050628662109376, + "mean_token_accuracy": 0.8970061101019382, + "num_tokens": 1132424.0, + "step": 120 + }, + { + "entropy": 0.3125588171184063, + "epoch": 0.42939719240297275, + "grad_norm": 1.8203125, + "learning_rate": 8.736263736263737e-06, + "loss": 0.3176266193389893, + "mean_token_accuracy": 0.8971590586006641, + "num_tokens": 1221899.0, + "step": 130 + }, + { + "entropy": 0.312872576713562, + "epoch": 0.4624277456647399, + "grad_norm": 1.78125, + "learning_rate": 8.553113553113553e-06, + "loss": 0.3343791484832764, + "mean_token_accuracy": 0.8940604299306869, + "num_tokens": 1315052.0, + "step": 140 + }, + { + "entropy": 0.27830475065857174, + "epoch": 0.495458298926507, + "grad_norm": 2.0, + "learning_rate": 8.369963369963371e-06, + "loss": 0.28718521595001223, + "mean_token_accuracy": 0.9051955968141556, + "num_tokens": 1401947.0, + "step": 150 + }, + { + "entropy": 0.3005422970280051, + "epoch": 0.5284888521882741, + "grad_norm": 2.34375, + "learning_rate": 8.186813186813188e-06, + "loss": 0.31569790840148926, + "mean_token_accuracy": 0.8999212823808194, + "num_tokens": 1494107.0, + "step": 160 + }, + { + "entropy": 0.31200682315975425, + "epoch": 0.5615194054500413, + "grad_norm": 2.015625, + "learning_rate": 8.003663003663006e-06, + "loss": 0.32325453758239747, + "mean_token_accuracy": 0.8952137432992459, + "num_tokens": 1586474.0, + "step": 170 + }, + { + "entropy": 0.2929861258715391, + "epoch": 0.5945499587118084, + "grad_norm": 2.09375, + "learning_rate": 7.820512820512822e-06, + "loss": 0.29693677425384524, + "mean_token_accuracy": 0.9031261466443539, + "num_tokens": 1678162.0, + "step": 180 + }, + { + "entropy": 0.30670158881694076, + "epoch": 0.6275805119735756, + "grad_norm": 1.828125, + "learning_rate": 7.637362637362638e-06, + "loss": 0.31567308902740476, + "mean_token_accuracy": 0.8983482263982296, + "num_tokens": 1781401.0, + "step": 190 + }, + { + "entropy": 0.2866023685783148, + "epoch": 0.6606110652353427, + "grad_norm": 1.6953125, + "learning_rate": 7.454212454212455e-06, + "loss": 0.29333360195159913, + "mean_token_accuracy": 0.904055442661047, + "num_tokens": 1868038.0, + "step": 200 + }, + { + "epoch": 0.6606110652353427, + "eval_entropy": 0.2921138784951634, + "eval_loss": 0.29292193055152893, + "eval_mean_token_accuracy": 0.904505420172656, + "eval_num_tokens": 1868038.0, + "eval_runtime": 17.8732, + "eval_samples_per_second": 30.157, + "eval_steps_per_second": 15.106, + "step": 200 + }, + { + "entropy": 0.28792863376438615, + "epoch": 0.6936416184971098, + "grad_norm": 1.9609375, + "learning_rate": 7.271062271062271e-06, + "loss": 0.29235827922821045, + "mean_token_accuracy": 0.9050419509410859, + "num_tokens": 1959819.0, + "step": 210 + }, + { + "entropy": 0.28098181951791046, + "epoch": 0.726672171758877, + "grad_norm": 1.8515625, + "learning_rate": 7.087912087912089e-06, + "loss": 0.2915766954421997, + "mean_token_accuracy": 0.9068245775997639, + "num_tokens": 2059113.0, + "step": 220 + }, + { + "entropy": 0.26028320472687483, + "epoch": 0.7597027250206441, + "grad_norm": 2.0, + "learning_rate": 6.9047619047619055e-06, + "loss": 0.2654874324798584, + "mean_token_accuracy": 0.9116183832287789, + "num_tokens": 2145321.0, + "step": 230 + }, + { + "entropy": 0.2855058180168271, + "epoch": 0.7927332782824112, + "grad_norm": 1.84375, + "learning_rate": 6.721611721611723e-06, + "loss": 0.2998212337493896, + "mean_token_accuracy": 0.9046589516103267, + "num_tokens": 2240859.0, + "step": 240 + }, + { + "entropy": 0.2783821925520897, + "epoch": 0.8257638315441783, + "grad_norm": 1.9609375, + "learning_rate": 6.538461538461539e-06, + "loss": 0.28870720863342286, + "mean_token_accuracy": 0.9073394626379013, + "num_tokens": 2333798.0, + "step": 250 + }, + { + "entropy": 0.277759512513876, + "epoch": 0.8587943848059455, + "grad_norm": 1.7734375, + "learning_rate": 6.3553113553113555e-06, + "loss": 0.29060728549957277, + "mean_token_accuracy": 0.9055352889001369, + "num_tokens": 2429910.0, + "step": 260 + }, + { + "entropy": 0.2882726760581136, + "epoch": 0.8918249380677127, + "grad_norm": 1.703125, + "learning_rate": 6.172161172161173e-06, + "loss": 0.2988502740859985, + "mean_token_accuracy": 0.9038613699376583, + "num_tokens": 2524730.0, + "step": 270 + }, + { + "entropy": 0.2855747708119452, + "epoch": 0.9248554913294798, + "grad_norm": 1.90625, + "learning_rate": 5.989010989010989e-06, + "loss": 0.289182186126709, + "mean_token_accuracy": 0.9049803033471108, + "num_tokens": 2615802.0, + "step": 280 + }, + { + "entropy": 0.26923007648438213, + "epoch": 0.9578860445912469, + "grad_norm": 2.84375, + "learning_rate": 5.805860805860807e-06, + "loss": 0.27834036350250246, + "mean_token_accuracy": 0.9109352678060532, + "num_tokens": 2709073.0, + "step": 290 + }, + { + "entropy": 0.2844470454379916, + "epoch": 0.990916597853014, + "grad_norm": 1.640625, + "learning_rate": 5.6227106227106235e-06, + "loss": 0.28873960971832274, + "mean_token_accuracy": 0.9069667845964432, + "num_tokens": 2805135.0, + "step": 300 + }, + { + "epoch": 0.990916597853014, + "eval_entropy": 0.285272175570329, + "eval_loss": 0.28705036640167236, + "eval_mean_token_accuracy": 0.9062359571456909, + "eval_num_tokens": 2805135.0, + "eval_runtime": 17.9038, + "eval_samples_per_second": 30.105, + "eval_steps_per_second": 15.081, + "step": 300 + }, + { + "entropy": 0.2869852078266633, + "epoch": 1.023121387283237, + "grad_norm": 1.9375, + "learning_rate": 5.43956043956044e-06, + "loss": 0.2850792646408081, + "mean_token_accuracy": 0.9064911672702203, + "num_tokens": 2898984.0, + "step": 310 + }, + { + "entropy": 0.2757460119202733, + "epoch": 1.0561519405450042, + "grad_norm": 1.8359375, + "learning_rate": 5.256410256410257e-06, + "loss": 0.2779810905456543, + "mean_token_accuracy": 0.9096895463764667, + "num_tokens": 2991694.0, + "step": 320 + }, + { + "entropy": 0.2600112119689584, + "epoch": 1.0891824938067713, + "grad_norm": 2.0625, + "learning_rate": 5.0732600732600735e-06, + "loss": 0.2662019729614258, + "mean_token_accuracy": 0.912333931028843, + "num_tokens": 3078862.0, + "step": 330 + }, + { + "entropy": 0.27342566605657337, + "epoch": 1.1222130470685383, + "grad_norm": 1.921875, + "learning_rate": 4.890109890109891e-06, + "loss": 0.28096842765808105, + "mean_token_accuracy": 0.9091624312102795, + "num_tokens": 3174256.0, + "step": 340 + }, + { + "entropy": 0.2671937083825469, + "epoch": 1.1552436003303055, + "grad_norm": 1.75, + "learning_rate": 4.706959706959707e-06, + "loss": 0.2723649501800537, + "mean_token_accuracy": 0.9101433955132961, + "num_tokens": 3272477.0, + "step": 350 + }, + { + "entropy": 0.2617026660591364, + "epoch": 1.1882741535920727, + "grad_norm": 1.9453125, + "learning_rate": 4.523809523809524e-06, + "loss": 0.26422107219696045, + "mean_token_accuracy": 0.913913157582283, + "num_tokens": 3364137.0, + "step": 360 + }, + { + "entropy": 0.2595691759139299, + "epoch": 1.2213047068538398, + "grad_norm": 1.5390625, + "learning_rate": 4.340659340659341e-06, + "loss": 0.2714951276779175, + "mean_token_accuracy": 0.911636833101511, + "num_tokens": 3460217.0, + "step": 370 + }, + { + "entropy": 0.2933320404961705, + "epoch": 1.254335260115607, + "grad_norm": 1.9765625, + "learning_rate": 4.157509157509158e-06, + "loss": 0.29573276042938235, + "mean_token_accuracy": 0.902192335575819, + "num_tokens": 3557030.0, + "step": 380 + }, + { + "entropy": 0.2693369995802641, + "epoch": 1.287365813377374, + "grad_norm": 1.890625, + "learning_rate": 3.974358974358974e-06, + "loss": 0.27785425186157225, + "mean_token_accuracy": 0.9090337291359901, + "num_tokens": 3654159.0, + "step": 390 + }, + { + "entropy": 0.2908114368095994, + "epoch": 1.3203963666391412, + "grad_norm": 2.015625, + "learning_rate": 3.7912087912087915e-06, + "loss": 0.30535905361175536, + "mean_token_accuracy": 0.901054035872221, + "num_tokens": 3749664.0, + "step": 400 + }, + { + "epoch": 1.3203963666391412, + "eval_entropy": 0.2783401116176888, + "eval_loss": 0.28495287895202637, + "eval_mean_token_accuracy": 0.9069356251645971, + "eval_num_tokens": 3749664.0, + "eval_runtime": 17.8814, + "eval_samples_per_second": 30.143, + "eval_steps_per_second": 15.099, + "step": 400 + }, + { + "entropy": 0.2749379588291049, + "epoch": 1.3534269199009084, + "grad_norm": 1.84375, + "learning_rate": 3.6080586080586083e-06, + "loss": 0.27795455455780027, + "mean_token_accuracy": 0.9090839587152004, + "num_tokens": 3845841.0, + "step": 410 + }, + { + "entropy": 0.2859474029392004, + "epoch": 1.3864574731626755, + "grad_norm": 1.6796875, + "learning_rate": 3.424908424908425e-06, + "loss": 0.2886682987213135, + "mean_token_accuracy": 0.9059950634837151, + "num_tokens": 3942402.0, + "step": 420 + }, + { + "entropy": 0.2537162031978369, + "epoch": 1.4194880264244425, + "grad_norm": 1.9375, + "learning_rate": 3.2417582417582424e-06, + "loss": 0.25533475875854494, + "mean_token_accuracy": 0.9158934533596039, + "num_tokens": 4034122.0, + "step": 430 + }, + { + "entropy": 0.28255065642297267, + "epoch": 1.4525185796862097, + "grad_norm": 1.7734375, + "learning_rate": 3.058608058608059e-06, + "loss": 0.29817631244659426, + "mean_token_accuracy": 0.9040707617998123, + "num_tokens": 4127068.0, + "step": 440 + }, + { + "entropy": 0.2898306529968977, + "epoch": 1.4855491329479769, + "grad_norm": 1.703125, + "learning_rate": 2.8754578754578755e-06, + "loss": 0.2923931121826172, + "mean_token_accuracy": 0.9030195340514183, + "num_tokens": 4224435.0, + "step": 450 + }, + { + "entropy": 0.27209411058574917, + "epoch": 1.518579686209744, + "grad_norm": 1.7578125, + "learning_rate": 2.6923076923076923e-06, + "loss": 0.28646528720855713, + "mean_token_accuracy": 0.9095881894230843, + "num_tokens": 4321028.0, + "step": 460 + }, + { + "entropy": 0.280727200768888, + "epoch": 1.5516102394715112, + "grad_norm": 1.7421875, + "learning_rate": 2.509157509157509e-06, + "loss": 0.2891413688659668, + "mean_token_accuracy": 0.9067636162042618, + "num_tokens": 4414916.0, + "step": 470 + }, + { + "entropy": 0.27109829243272543, + "epoch": 1.5846407927332784, + "grad_norm": 1.8359375, + "learning_rate": 2.3260073260073264e-06, + "loss": 0.26625516414642336, + "mean_token_accuracy": 0.9099020563066006, + "num_tokens": 4505708.0, + "step": 480 + }, + { + "entropy": 0.2729395367205143, + "epoch": 1.6176713459950454, + "grad_norm": 1.7890625, + "learning_rate": 2.1428571428571427e-06, + "loss": 0.2779061317443848, + "mean_token_accuracy": 0.909747340530157, + "num_tokens": 4600244.0, + "step": 490 + }, + { + "entropy": 0.2682301852852106, + "epoch": 1.6507018992568125, + "grad_norm": 1.6953125, + "learning_rate": 1.95970695970696e-06, + "loss": 0.274446964263916, + "mean_token_accuracy": 0.9094639919698239, + "num_tokens": 4688147.0, + "step": 500 + }, + { + "epoch": 1.6507018992568125, + "eval_entropy": 0.2756172451708052, + "eval_loss": 0.2841346263885498, + "eval_mean_token_accuracy": 0.9072470570052111, + "eval_num_tokens": 4688147.0, + "eval_runtime": 17.9119, + "eval_samples_per_second": 30.092, + "eval_steps_per_second": 15.074, + "step": 500 + }, + { + "entropy": 0.26342453975230457, + "epoch": 1.6837324525185797, + "grad_norm": 1.890625, + "learning_rate": 1.7765567765567768e-06, + "loss": 0.26432271003723146, + "mean_token_accuracy": 0.9114409819245338, + "num_tokens": 4780124.0, + "step": 510 + }, + { + "entropy": 0.28657868495211003, + "epoch": 1.7167630057803467, + "grad_norm": 1.7734375, + "learning_rate": 1.5934065934065933e-06, + "loss": 0.2983593225479126, + "mean_token_accuracy": 0.9028328903019428, + "num_tokens": 4874633.0, + "step": 520 + }, + { + "entropy": 0.25633321776986123, + "epoch": 1.7497935590421139, + "grad_norm": 1.8359375, + "learning_rate": 1.4102564102564104e-06, + "loss": 0.2606488227844238, + "mean_token_accuracy": 0.9153999648988247, + "num_tokens": 4967263.0, + "step": 530 + }, + { + "entropy": 0.26120030507445335, + "epoch": 1.782824112303881, + "grad_norm": 2.078125, + "learning_rate": 1.2271062271062271e-06, + "loss": 0.2706313610076904, + "mean_token_accuracy": 0.9130682416260243, + "num_tokens": 5056736.0, + "step": 540 + }, + { + "entropy": 0.27009565513581035, + "epoch": 1.8158546655656482, + "grad_norm": 1.8828125, + "learning_rate": 1.0439560439560442e-06, + "loss": 0.277858567237854, + "mean_token_accuracy": 0.9087999157607556, + "num_tokens": 5150617.0, + "step": 550 + }, + { + "entropy": 0.2819518899545074, + "epoch": 1.8488852188274154, + "grad_norm": 1.9609375, + "learning_rate": 8.608058608058609e-07, + "loss": 0.28743035793304444, + "mean_token_accuracy": 0.9067244723439216, + "num_tokens": 5243538.0, + "step": 560 + }, + { + "entropy": 0.2858045116066933, + "epoch": 1.8819157720891826, + "grad_norm": 2.203125, + "learning_rate": 6.776556776556777e-07, + "loss": 0.2939825296401978, + "mean_token_accuracy": 0.904579871147871, + "num_tokens": 5331441.0, + "step": 570 + }, + { + "entropy": 0.2926233192905784, + "epoch": 1.9149463253509498, + "grad_norm": 2.3125, + "learning_rate": 4.945054945054946e-07, + "loss": 0.29961700439453126, + "mean_token_accuracy": 0.9033655568957328, + "num_tokens": 5426734.0, + "step": 580 + }, + { + "entropy": 0.2706678254529834, + "epoch": 1.9479768786127167, + "grad_norm": 2.03125, + "learning_rate": 3.113553113553114e-07, + "loss": 0.27953526973724363, + "mean_token_accuracy": 0.9093762949109078, + "num_tokens": 5518190.0, + "step": 590 + }, + { + "entropy": 0.27056904807686805, + "epoch": 1.981007431874484, + "grad_norm": 2.09375, + "learning_rate": 1.282051282051282e-07, + "loss": 0.2764536619186401, + "mean_token_accuracy": 0.9110228553414345, + "num_tokens": 5609238.0, + "step": 600 + }, + { + "epoch": 1.981007431874484, + "eval_entropy": 0.2757842331572815, + "eval_loss": 0.28394654393196106, + "eval_mean_token_accuracy": 0.9073928307603907, + "eval_num_tokens": 5609238.0, + "eval_runtime": 18.1138, + "eval_samples_per_second": 29.756, + "eval_steps_per_second": 14.906, + "step": 600 + }, + { + "epoch": 2.0, + "eval_entropy": 0.2757109238593667, + "eval_loss": 0.2840007245540619, + "eval_mean_token_accuracy": 0.9072579809912928, + "eval_num_tokens": 5663138.0, + "eval_runtime": 18.1948, + "eval_samples_per_second": 29.624, + "eval_steps_per_second": 14.839, + "step": 606 + } + ], + "logging_steps": 10, + "max_steps": 606, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 6.072645019326874e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-606/training_args.bin b/checkpoint-606/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..133cb6661b0124bb9db0d7d208d748fd736ea689 --- /dev/null +++ b/checkpoint-606/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6696e1fef8bde5e22de2f5ae18c284f2b2d35a345157db5151571518385fb38b +size 5713 diff --git a/checkpoint-674/chat_template.jinja b/checkpoint-674/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..01be9b307daa2d425f7c168c9fb145a286e0afb4 --- /dev/null +++ b/checkpoint-674/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/checkpoint-674/config.json b/checkpoint-674/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d219d6a6d288625229a71646710b85cf7ae5def --- /dev/null +++ b/checkpoint-674/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/checkpoint-674/generation_config.json b/checkpoint-674/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec133d867b1427d43a5ee0ea332bd088fc12013 --- /dev/null +++ b/checkpoint-674/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/checkpoint-674/model.safetensors b/checkpoint-674/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc885a501a0fffef97b843b5248e3bb7cfe46172 --- /dev/null +++ b/checkpoint-674/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af4557502ae7c7853ed3b684aa50cfd00317aafc237f2dda688075bb3dc81c1 +size 3441185608 diff --git a/checkpoint-674/optimizer.pt b/checkpoint-674/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f8c22d5c745517a99843c614c05da8a366a7d78 --- /dev/null +++ b/checkpoint-674/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca0ddbeff189519bd91d1474687c97eb42f33e1dc183a5769974dadc5e0cd7b +size 6882572207 diff --git a/checkpoint-674/rng_state.pth b/checkpoint-674/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1feba1a6538e93b94696d3773853dbc8947b0cad --- /dev/null +++ b/checkpoint-674/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878 +size 14645 diff --git a/checkpoint-674/scheduler.pt b/checkpoint-674/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..52e04de5969d9a926e44ed315d79199b8ca27698 --- /dev/null +++ b/checkpoint-674/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01dbf241e935857d2a5486058c590aafb795b79d6ef3f0dc038c0d85e2187d7d +size 1465 diff --git a/checkpoint-674/tokenizer.json b/checkpoint-674/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7afbed2efcdf019f88ab0572ec29d3bf595dfe2 --- /dev/null +++ b/checkpoint-674/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/checkpoint-674/tokenizer_config.json b/checkpoint-674/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..770e41d6c92519d525eede4cbcf3ba27f6425311 --- /dev/null +++ b/checkpoint-674/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/checkpoint-674/trainer_state.json b/checkpoint-674/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..54b5d973ad7d8fb6a649dbc5f72a0c5653d31516 --- /dev/null +++ b/checkpoint-674/trainer_state.json @@ -0,0 +1,704 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 674, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "entropy": NaN, + "epoch": 0.029717682020802376, + "grad_norm": NaN, + "learning_rate": 1.8000000000000001e-06, + "loss": 1005514863411.2, + "mean_token_accuracy": 0.07770282882993343, + "num_tokens": 97764.0, + "step": 10 + }, + { + "entropy": NaN, + "epoch": 0.05943536404160475, + "grad_norm": NaN, + "learning_rate": 3.8000000000000005e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007392044077278115, + "num_tokens": 190372.0, + "step": 20 + }, + { + "entropy": NaN, + "epoch": 0.08915304606240713, + "grad_norm": NaN, + "learning_rate": 5.8e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000383764869911829, + "num_tokens": 280928.0, + "step": 30 + }, + { + "entropy": NaN, + "epoch": 0.1188707280832095, + "grad_norm": NaN, + "learning_rate": 7.800000000000002e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0003212536917999387, + "num_tokens": 380644.0, + "step": 40 + }, + { + "entropy": NaN, + "epoch": 0.1485884101040119, + "grad_norm": NaN, + "learning_rate": 9.800000000000001e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0003853117574180942, + "num_tokens": 475467.0, + "step": 50 + }, + { + "entropy": NaN, + "epoch": 0.17830609212481427, + "grad_norm": NaN, + "learning_rate": 1.18e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0003134153150313068, + "num_tokens": 572411.0, + "step": 60 + }, + { + "entropy": NaN, + "epoch": 0.20802377414561665, + "grad_norm": NaN, + "learning_rate": 1.38e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011001345737895463, + "num_tokens": 661517.0, + "step": 70 + }, + { + "entropy": NaN, + "epoch": 0.237741456166419, + "grad_norm": NaN, + "learning_rate": 1.58e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012231820757733658, + "num_tokens": 752142.0, + "step": 80 + }, + { + "entropy": NaN, + "epoch": 0.2674591381872214, + "grad_norm": NaN, + "learning_rate": 1.7800000000000002e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011551132018212229, + "num_tokens": 850399.0, + "step": 90 + }, + { + "entropy": NaN, + "epoch": 0.2971768202080238, + "grad_norm": NaN, + "learning_rate": 1.98e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00047943509634933433, + "num_tokens": 954759.0, + "step": 100 + }, + { + "entropy": NaN, + "epoch": 0.32689450222882616, + "grad_norm": NaN, + "learning_rate": 1.9802414928649837e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008438902725174558, + "num_tokens": 1050439.0, + "step": 110 + }, + { + "entropy": NaN, + "epoch": 0.35661218424962854, + "grad_norm": NaN, + "learning_rate": 1.958287596048299e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009903057703922967, + "num_tokens": 1135089.0, + "step": 120 + }, + { + "entropy": NaN, + "epoch": 0.3863298662704309, + "grad_norm": NaN, + "learning_rate": 1.9363336992316137e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00040032515971688554, + "num_tokens": 1228149.0, + "step": 130 + }, + { + "entropy": NaN, + "epoch": 0.4160475482912333, + "grad_norm": NaN, + "learning_rate": 1.9143798024149288e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0010247966441966128, + "num_tokens": 1331672.0, + "step": 140 + }, + { + "entropy": NaN, + "epoch": 0.4457652303120357, + "grad_norm": NaN, + "learning_rate": 1.892425905598244e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000843161555530969, + "num_tokens": 1421314.0, + "step": 150 + }, + { + "entropy": NaN, + "epoch": 0.475482912332838, + "grad_norm": NaN, + "learning_rate": 1.8704720087815587e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007889680869993754, + "num_tokens": 1511701.0, + "step": 160 + }, + { + "entropy": NaN, + "epoch": 0.5052005943536404, + "grad_norm": NaN, + "learning_rate": 1.848518111964874e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007493881763366517, + "num_tokens": 1605063.0, + "step": 170 + }, + { + "entropy": NaN, + "epoch": 0.5349182763744428, + "grad_norm": NaN, + "learning_rate": 1.826564215148189e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000567350817436818, + "num_tokens": 1703107.0, + "step": 180 + }, + { + "entropy": NaN, + "epoch": 0.5646359583952452, + "grad_norm": NaN, + "learning_rate": 1.804610318331504e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00027060438151238486, + "num_tokens": 1796279.0, + "step": 190 + }, + { + "entropy": NaN, + "epoch": 0.5943536404160475, + "grad_norm": NaN, + "learning_rate": 1.782656421514819e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008226798396208324, + "num_tokens": 1893647.0, + "step": 200 + }, + { + "entropy": NaN, + "epoch": 0.6240713224368499, + "grad_norm": NaN, + "learning_rate": 1.760702524698134e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007338574505411088, + "num_tokens": 1982325.0, + "step": 210 + }, + { + "entropy": NaN, + "epoch": 0.6537890044576523, + "grad_norm": NaN, + "learning_rate": 1.7387486278814492e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004891513846814633, + "num_tokens": 2071869.0, + "step": 220 + }, + { + "entropy": NaN, + "epoch": 0.6835066864784547, + "grad_norm": NaN, + "learning_rate": 1.716794731064764e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00038509477453771976, + "num_tokens": 2168370.0, + "step": 230 + }, + { + "entropy": NaN, + "epoch": 0.7132243684992571, + "grad_norm": NaN, + "learning_rate": 1.694840834248079e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009255842014681548, + "num_tokens": 2263211.0, + "step": 240 + }, + { + "entropy": NaN, + "epoch": 0.7429420505200595, + "grad_norm": NaN, + "learning_rate": 1.6728869374313943e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011857455348945223, + "num_tokens": 2352425.0, + "step": 250 + }, + { + "entropy": NaN, + "epoch": 0.7726597325408618, + "grad_norm": NaN, + "learning_rate": 1.6509330406147094e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0008204675337765366, + "num_tokens": 2445217.0, + "step": 260 + }, + { + "entropy": NaN, + "epoch": 0.8023774145616642, + "grad_norm": NaN, + "learning_rate": 1.6289791437980242e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0013553448639868292, + "num_tokens": 2537677.0, + "step": 270 + }, + { + "entropy": NaN, + "epoch": 0.8320950965824666, + "grad_norm": NaN, + "learning_rate": 1.6070252469813393e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011630529144895263, + "num_tokens": 2631646.0, + "step": 280 + }, + { + "entropy": NaN, + "epoch": 0.861812778603269, + "grad_norm": NaN, + "learning_rate": 1.5850713501646545e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009409735575900413, + "num_tokens": 2722632.0, + "step": 290 + }, + { + "entropy": NaN, + "epoch": 0.8915304606240714, + "grad_norm": NaN, + "learning_rate": 1.5631174533479693e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006484775040007662, + "num_tokens": 2819185.0, + "step": 300 + }, + { + "entropy": NaN, + "epoch": 0.9212481426448736, + "grad_norm": NaN, + "learning_rate": 1.5411635565312844e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011682231881422922, + "num_tokens": 2910483.0, + "step": 310 + }, + { + "entropy": NaN, + "epoch": 0.950965824665676, + "grad_norm": NaN, + "learning_rate": 1.5192096597145995e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004708930806373246, + "num_tokens": 2997057.0, + "step": 320 + }, + { + "entropy": NaN, + "epoch": 0.9806835066864784, + "grad_norm": NaN, + "learning_rate": 1.4972557628979145e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011955970534472727, + "num_tokens": 3091284.0, + "step": 330 + }, + { + "entropy": NaN, + "epoch": 1.0089153046062407, + "grad_norm": NaN, + "learning_rate": 1.4753018660812295e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006843029964090276, + "num_tokens": 3177800.0, + "step": 340 + }, + { + "entropy": NaN, + "epoch": 1.0386329866270432, + "grad_norm": NaN, + "learning_rate": 1.4533479692645444e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0005406756106822285, + "num_tokens": 3271989.0, + "step": 350 + }, + { + "entropy": NaN, + "epoch": 1.0683506686478454, + "grad_norm": NaN, + "learning_rate": 1.4313940724478596e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0007009803419350646, + "num_tokens": 3365082.0, + "step": 360 + }, + { + "entropy": NaN, + "epoch": 1.098068350668648, + "grad_norm": NaN, + "learning_rate": 1.4094401756311746e-05, + "loss": 0.0, + "mean_token_accuracy": 0.001003894711175235, + "num_tokens": 3465865.0, + "step": 370 + }, + { + "entropy": NaN, + "epoch": 1.1277860326894502, + "grad_norm": NaN, + "learning_rate": 1.3874862788144897e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004136150790145621, + "num_tokens": 3564998.0, + "step": 380 + }, + { + "entropy": NaN, + "epoch": 1.1575037147102525, + "grad_norm": NaN, + "learning_rate": 1.3655323819978048e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000998112405068241, + "num_tokens": 3661508.0, + "step": 390 + }, + { + "entropy": NaN, + "epoch": 1.187221396731055, + "grad_norm": NaN, + "learning_rate": 1.3435784851811198e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0009621107514249161, + "num_tokens": 3755395.0, + "step": 400 + }, + { + "entropy": NaN, + "epoch": 1.2169390787518575, + "grad_norm": NaN, + "learning_rate": 1.3216245883644348e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004976072828867473, + "num_tokens": 3842994.0, + "step": 410 + }, + { + "entropy": NaN, + "epoch": 1.2466567607726597, + "grad_norm": NaN, + "learning_rate": 1.2996706915477499e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0003434549740632065, + "num_tokens": 3934618.0, + "step": 420 + }, + { + "entropy": NaN, + "epoch": 1.276374442793462, + "grad_norm": NaN, + "learning_rate": 1.2777167947310649e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00026364591685705817, + "num_tokens": 4026711.0, + "step": 430 + }, + { + "entropy": NaN, + "epoch": 1.3060921248142645, + "grad_norm": NaN, + "learning_rate": 1.2557628979143798e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0006349188319290988, + "num_tokens": 4114609.0, + "step": 440 + }, + { + "entropy": NaN, + "epoch": 1.3358098068350668, + "grad_norm": NaN, + "learning_rate": 1.2338090010976948e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004265022376785055, + "num_tokens": 4203953.0, + "step": 450 + }, + { + "entropy": NaN, + "epoch": 1.3655274888558693, + "grad_norm": NaN, + "learning_rate": 1.2118551042810101e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012633154692593962, + "num_tokens": 4298319.0, + "step": 460 + }, + { + "entropy": NaN, + "epoch": 1.3952451708766715, + "grad_norm": NaN, + "learning_rate": 1.189901207464325e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0011256658195634372, + "num_tokens": 4396020.0, + "step": 470 + }, + { + "entropy": NaN, + "epoch": 1.424962852897474, + "grad_norm": NaN, + "learning_rate": 1.16794731064764e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0013131745137798135, + "num_tokens": 4491203.0, + "step": 480 + }, + { + "entropy": NaN, + "epoch": 1.4546805349182763, + "grad_norm": NaN, + "learning_rate": 1.1459934138309552e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012716218378045596, + "num_tokens": 4582199.0, + "step": 490 + }, + { + "entropy": NaN, + "epoch": 1.4843982169390788, + "grad_norm": NaN, + "learning_rate": 1.1240395170142701e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0014869970778818241, + "num_tokens": 4672589.0, + "step": 500 + }, + { + "entropy": NaN, + "epoch": 1.514115898959881, + "grad_norm": NaN, + "learning_rate": 1.1020856201975851e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00046981508567114363, + "num_tokens": 4767693.0, + "step": 510 + }, + { + "entropy": NaN, + "epoch": 1.5438335809806834, + "grad_norm": NaN, + "learning_rate": 1.0801317233809e-05, + "loss": 0.0, + "mean_token_accuracy": 0.000601445968641201, + "num_tokens": 4860371.0, + "step": 520 + }, + { + "entropy": NaN, + "epoch": 1.5735512630014858, + "grad_norm": NaN, + "learning_rate": 1.0581778265642154e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0012073652920662425, + "num_tokens": 4950622.0, + "step": 530 + }, + { + "entropy": NaN, + "epoch": 1.6032689450222883, + "grad_norm": NaN, + "learning_rate": 1.0362239297475303e-05, + "loss": 0.0, + "mean_token_accuracy": 0.00028707647215924225, + "num_tokens": 5044878.0, + "step": 540 + }, + { + "entropy": NaN, + "epoch": 1.6329866270430906, + "grad_norm": NaN, + "learning_rate": 1.0142700329308453e-05, + "loss": 0.0, + "mean_token_accuracy": 0.0004101752907445189, + "num_tokens": 5140938.0, + "step": 550 + }, + { + "entropy": NaN, + "epoch": 1.6627043090638929, + "grad_norm": NaN, + "learning_rate": 9.923161361141603e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008072987395280507, + "num_tokens": 5232852.0, + "step": 560 + }, + { + "entropy": NaN, + "epoch": 1.6924219910846954, + "grad_norm": NaN, + "learning_rate": 9.703622392974754e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0012222853780258446, + "num_tokens": 5321835.0, + "step": 570 + }, + { + "entropy": NaN, + "epoch": 1.7221396731054979, + "grad_norm": NaN, + "learning_rate": 9.484083424807904e-06, + "loss": 0.0, + "mean_token_accuracy": 0.001064640874392353, + "num_tokens": 5416464.0, + "step": 580 + }, + { + "entropy": NaN, + "epoch": 1.7518573551263001, + "grad_norm": NaN, + "learning_rate": 9.264544456641055e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0009612867230316624, + "num_tokens": 5515169.0, + "step": 590 + }, + { + "entropy": NaN, + "epoch": 1.7815750371471024, + "grad_norm": NaN, + "learning_rate": 9.045005488474205e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008774219051701948, + "num_tokens": 5611971.0, + "step": 600 + }, + { + "entropy": NaN, + "epoch": 1.811292719167905, + "grad_norm": NaN, + "learning_rate": 8.825466520307355e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007863394406740553, + "num_tokens": 5704255.0, + "step": 610 + }, + { + "entropy": NaN, + "epoch": 1.8410104011887074, + "grad_norm": NaN, + "learning_rate": 8.605927552140506e-06, + "loss": 0.0, + "mean_token_accuracy": 0.000578320066415472, + "num_tokens": 5800440.0, + "step": 620 + }, + { + "entropy": NaN, + "epoch": 1.8707280832095097, + "grad_norm": NaN, + "learning_rate": 8.386388583973656e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0004275172817870043, + "num_tokens": 5890898.0, + "step": 630 + }, + { + "entropy": NaN, + "epoch": 1.900445765230312, + "grad_norm": NaN, + "learning_rate": 8.166849615806807e-06, + "loss": 0.0, + "mean_token_accuracy": 0.001425291335908696, + "num_tokens": 5987228.0, + "step": 640 + }, + { + "entropy": NaN, + "epoch": 1.9301634472511144, + "grad_norm": NaN, + "learning_rate": 7.947310647639957e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0006059414023184218, + "num_tokens": 6076579.0, + "step": 650 + }, + { + "entropy": NaN, + "epoch": 1.959881129271917, + "grad_norm": NaN, + "learning_rate": 7.727771679473108e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0008722793892957271, + "num_tokens": 6171013.0, + "step": 660 + }, + { + "entropy": NaN, + "epoch": 1.9895988112927192, + "grad_norm": NaN, + "learning_rate": 7.508232711306257e-06, + "loss": 0.0, + "mean_token_accuracy": 0.0007748565993097145, + "num_tokens": 6265432.0, + "step": 670 + } + ], + "logging_steps": 10, + "max_steps": 1011, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.753063653143757e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-674/training_args.bin b/checkpoint-674/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..737a87caa4fc2f704a1fe56a508ca4d335ca783d --- /dev/null +++ b/checkpoint-674/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0f7084660199ed7fd16027c0c6af5e726790f32a022b019f1277bec4e01142 +size 5713 diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000000000000000000000000000000000000..61e93c0903b4a4446f5cee0d11700541bdc31f8f --- /dev/null +++ b/eval_results.json @@ -0,0 +1,114 @@ +{ + "checkpoint": "/scratch/checkpoints/exp4b_dpo", + "is_local": true, + "eval_tier": "fast", + "sampling": { + "n": 8, + "temperature": 0.6, + "top_p": 0.95, + "top_k": 20, + "max_tokens": 3500 + }, + "benchmarks": { + "ci_gate_math": { + "source": "ci_gate_math", + "overall": { + "n_problems": 10, + "n_completions": 8, + "pass@1": 0.2125, + "pass@8": 0.3 + } + }, + "math_hard_100": { + "source": "math_hard_100", + "overall": { + "n_problems": 100, + "n_completions": 8, + "pass@1": 0.52625, + "pass@8": 0.79 + }, + "by_level": { + "4": { + "n_problems": 51, + "n_completions": 8, + "pass@1": 0.6568627450980392, + "pass@8": 0.9019607843137255 + }, + "5": { + "n_problems": 49, + "n_completions": 8, + "pass@1": 0.3903061224489796, + "pass@8": 0.673469387755102 + } + }, + "by_topic": { + "algebra": { + "n_problems": 15, + "n_completions": 8, + "pass@1": 0.8666666666666667, + "pass@8": 1.0 + }, + "counting_and_probability": { + "n_problems": 14, + "n_completions": 8, + "pass@1": 0.4017857142857143, + "pass@8": 0.7142857142857143 + }, + "geometry": { + "n_problems": 14, + "n_completions": 8, + "pass@1": 0.3392857142857143, + "pass@8": 0.6428571428571429 + }, + "intermediate_algebra": { + "n_problems": 15, + "n_completions": 8, + "pass@1": 0.4416666666666666, + "pass@8": 0.7333333333333333 + }, + "number_theory": { + "n_problems": 14, + "n_completions": 8, + "pass@1": 0.5, + "pass@8": 0.8571428571428571 + }, + "prealgebra": { + "n_problems": 14, + "n_completions": 8, + "pass@1": 0.6875, + "pass@8": 1.0 + }, + "precalculus": { + "n_problems": 14, + "n_completions": 8, + "pass@1": 0.42857142857142855, + "pass@8": 0.5714285714285714 + } + } + }, + "aime_benchmark": { + "source": "aime_benchmark", + "overall": { + "n_problems": 60, + "n_completions": 8, + "pass@1": 0.06666666666666667, + "pass@8": 0.23333333333333334 + }, + "by_source": { + "aime_2024": { + "n_problems": 30, + "n_completions": 8, + "pass@1": 0.062499999999999986, + "pass@8": 0.2 + }, + "aime_2025": { + "n_problems": 30, + "n_completions": 8, + "pass@1": 0.07083333333333333, + "pass@8": 0.26666666666666666 + } + } + } + }, + "note": "All benchmarks use identical sampling params so numbers compare directly across experiments (baseline, SFT v1/v2, GRPO). Hard benchmarks (math_hard_100, aime_benchmark) are decontaminated against MixLong (the SFT pool)." +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json index 9526fbb9cfca6c6b8911fa4f1995a5c43139fc63..06c1fde472f6fa7f3dcff61cd28741606145fbb3 100644 --- a/generation_config.json +++ b/generation_config.json @@ -6,9 +6,8 @@ 151643 ], "pad_token_id": 151643, - "temperature": 0.7, - "top_p": 0.95, + "temperature": 0.3, "top_k": 20, - "repetition_penalty": 1.03, + "top_p": 0.95, "transformers_version": "4.51.0" } \ No newline at end of file diff --git a/model.safetensors b/model.safetensors index a9923328aed6324f3b8bc4b96ecf4cc43763ec69..0d63403011fc5fae0a6c5cbc2a07767d1ed51aca 100644 --- a/model.safetensors +++ b/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c9179fe220727db304cb809795bd582e6dbc90a763ef3579708273b8b09858e5 +oid sha256:38b5f2e228526391ef71a55f7aea1756e5f1c89b9b81fedeb1251095002e5ce9 size 3441185608 diff --git a/split_info.json b/split_info.json new file mode 100644 index 0000000000000000000000000000000000000000..eeeca476aec03dcb98a3a3e6782c35fcbf142790 --- /dev/null +++ b/split_info.json @@ -0,0 +1,28 @@ +{ + "experiment_name": "exp4b_dpo", + "config_file": "/scratch/jennifer/standard-project-m2-the-transformers/configs/exp4b_dpo.yaml", + "resolved_config": { + "num_train_epochs": 1, + "learning_rate": 5e-07, + "per_device_train_batch_size": 1, + "per_device_eval_batch_size": 1, + "gradient_accumulation_steps": 8, + "warmup_ratio": 0.1, + "seed": 42, + "save_total_limit": 3, + "eval_steps": 50, + "logging_steps": 10, + "beta": 0.1, + "loss_type": "sigmoid", + "max_length": 4096, + "max_completion_length": 3072, + "val_fraction": 0.1, + "wandb_project": "cs552-math-dpo", + "experiment_name": "exp4b_dpo", + "output_dir": "/scratch/checkpoints/exp4b_dpo", + "sft_checkpoint": "/scratch/checkpoints/sft_mixlong_full", + "train_source": "/scratch/data/dpo_pairs_v2/pairs.jsonl" + }, + "n_train": 5048, + "n_val": 561 +} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json index 480b16d724b41320e1e217f2408c04a8a8e326fc..b0ac7bff8c357331648a433d9b6ae4c1f1381380 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -27,5 +27,5 @@ "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null, - "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {#- BOXING INSTRUCTION injected so it is present even when the caller (e.g. CI)\n passes no system message. Targets our no-box / multi-box failure mode. #}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- 'When solving a math problem, work through it step by step and write your final answer inside a \\boxed{...}.<|im_end|>\\n' }}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}" + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}" } \ No newline at end of file diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..133cb6661b0124bb9db0d7d208d748fd736ea689 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6696e1fef8bde5e22de2f5ae18c284f2b2d35a345157db5151571518385fb38b +size 5713