Add 11 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+base_model: meta-llama/Llama-3.3-70B-Instruct-Reference
+library_name: peft
+license: other
+tags:
+  - lora
+  - peft
+  - adapter
+  - adaption
+---
+
+# adaption_python_mental_execution_trac
+
+## Model Training
+
+A LORA adapter for `meta-llama/Llama-3.3-70B-Instruct-Reference`. This model was trained with SFT using [Adaption](https://adaptionlabs.ai)'s AutoScientist on the python_mental_execution_traces dataset.
+
+
+![Training metrics](training-metrics.png)
+
+### AutoScientist Config
+
+```json
+{
+  "job_id": "01c91058-ec84-419f-be88-8d2990809855",
+  "training_experiment_id": "96dd4322-7402-4045-b038-4c5c69d433f5",
+  "original_model_name": "meta-llama/Llama-3.3-70B-Instruct-Reference",
+  "trained_model_name": "adaption_python_mental_execution_trac",
+  "training_method": "sft",
+  "training_type": "lora",
+  "data_format": "chat",
+  "hyperparams": {
+    "lora": "true",
+    "lora_r": 8,
+    "n_evals": 5,
+    "n_epochs": 1,
+    "batch_size": "max",
+    "lora_alpha": 8,
+    "lora_dropout": 0,
+    "min_lr_ratio": 0.1,
+    "warmup_ratio": 0.1,
+    "weight_decay": 0,
+    "learning_rate": 0.0001,
+    "max_grad_norm": 2,
+    "base_model_size": "70B",
+    "train_on_inputs": "false",
+    "training_method": "sft",
+    "lr_scheduler_type": "cosine",
+    "scheduler_num_cycles": 0.5,
+    "lora_trainable_modules": "q_proj,v_proj"
+  }
+}
+```
+
+## Training Data
+
+The model was trained on 11,631 rows of adapted data with the following domain distribution: code (100%).
+
+## Model Evaluation
+
+The model was evaluated on an in-distribution held-out test set as well as a broader domain-specific test set to measure generalization.
+
+
+![Win rates](win-rates.png)
+
+
+## How to use
+
+```bash
+pip install torch transformers peft
+```
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE = "meta-llama/Llama-3.3-70B-Instruct-Reference"
+ADAPTER = "<this-repo-id>"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float32 if device == "cpu" else torch.bfloat16
+
+base = AutoModelForCausalLM.from_pretrained(BASE, dtype=dtype).to(device)
+model = PeftModel.from_pretrained(base, ADAPTER)
+# Optional: merge the LoRA weights into the base for faster inference
+model = model.merge_and_unload()
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(BASE)
+messages = [{"role": "user", "content": "Hello!"}]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(device)
+
+with torch.inference_mode():
+    out = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fdfc82d3d2e82d8f3bbeb26236a4a770eb869606e483716031fc9660c7e606
+size 65578776

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.0",
+  "use_cache": false,
+  "vocab_size": 128256,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 4,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.9568968415260315,
+      "learning_rate": 0.0,
+      "loss": 2.302734375,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.6604674458503723,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.83203125,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.8862142562866211,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 2.1923828125,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.9301884174346924,
+      "learning_rate": 0.0001,
+      "loss": 2.099609375,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.6462522149085999,
+      "learning_rate": 9.931634888554937e-05,
+      "loss": 1.5146484375,
+      "step": 5
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "eval_loss": 1.7890625,
+      "eval_runtime": 5.5258,
+      "eval_samples_per_second": 0.362,
+      "eval_steps_per_second": 0.181,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.7940283417701721,
+      "learning_rate": 9.728616793536588e-05,
+      "loss": 1.609375,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.9866992235183716,
+      "learning_rate": 9.397114317029975e-05,
+      "loss": 1.708984375,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.9356194734573364,
+      "learning_rate": 8.947199994035401e-05,
+      "loss": 1.62109375,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.2427157163619995,
+      "learning_rate": 8.392544243589427e-05,
+      "loss": 1.72607421875,
+      "step": 9
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "eval_loss": 1.50390625,
+      "eval_runtime": 6.1677,
+      "eval_samples_per_second": 0.324,
+      "eval_steps_per_second": 0.162,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.9093706607818604,
+      "learning_rate": 7.75e-05,
+      "loss": 1.31787109375,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 1.172244668006897,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 1.61328125,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.040825605392456,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 1.18115234375,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 1.2616082429885864,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.44921875,
+      "step": 13
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "eval_loss": 1.244140625,
+      "eval_runtime": 5.5436,
+      "eval_samples_per_second": 0.361,
+      "eval_steps_per_second": 0.18,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.064231514930725,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 1.27685546875,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.1865931749343872,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 1.431640625,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.041445016860962,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1904296875,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 1.1407253742218018,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.21337890625,
+      "step": 17
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "eval_loss": 1.103515625,
+      "eval_runtime": 5.5514,
+      "eval_samples_per_second": 0.36,
+      "eval_steps_per_second": 0.18,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.076326608657837,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.212890625,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 1.2264506816864014,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.15478515625,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.922339916229248,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.0078125,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0451383590698242,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 1.181640625,
+      "step": 21
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.048828125,
+      "eval_runtime": 5.5585,
+      "eval_samples_per_second": 0.36,
+      "eval_steps_per_second": 0.18,
+      "step": 21
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 21,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0171502697560146e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}