Upload folder using huggingface_hub

.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 +1,42 @@
+---
+license: apache-2.0
+base_model: meta-llama/Llama-3.2-3B-Instruct
+datasets:
+- 15juneee/hr-practitioner-adapted-v1
+tags:
+- hr
+- adaption-autoscientist
+- lora
+language:
+- en
+---
+
+# HR Practitioner (hr)
+
+Fine-tuned for HR and people operations, trained with
+[Adaption AutoScientist](https://docs.adaptionlabs.ai/guides/autoscientist-api/) for the
+AutoScientist Challenge (Part 2).
+
+- **Base model:** `meta-llama/Llama-3.2-3B-Instruct`
+- **Training data:** [`15juneee/hr-practitioner-adapted-v1`](https://huggingface.co/datasets/15juneee/hr-practitioner-adapted-v1)
+  (also on [Kaggle](https://www.kaggle.com/datasets/junesdata/hr-practitioner-adapted-v1))
+- **Method:** AutoScientist co-optimised data adaptation and training recipe
+
+## Measured improvement
+
+AutoScientist reported **best_win_rate = 0.5492** over 2 iterations against `meta-llama/Llama-3.2-3B-Instruct` - i.e. the fine-tuned model is preferred over its own baseline in 54.9% of comparisons. An earlier 5-iteration run of the same dataset reached 0.5674 before the job wedged at iteration 4/5 and had to be cancelled, so 0.5492 is the reproducible, completed figure.
+
+Evaluation methodology, including the position-swap and dual-judge controls, is in
+`EVAL.md` in the project repository. The held-out split used is published alongside the
+training data so the number can be reproduced.
+
+## Intended use and limitations
+
+Intended for HR and people operations assistance. **Output is not legal advice.** Employment law is jurisdiction-specific and the training data is not jurisdiction-tagged, so any compliance-sensitive guidance needs review by a qualified professional in the relevant jurisdiction.
+
+Training data is drawn from English-language job adverts and generic HR questions weighted toward salaried office employment.
+
+## Reproducing
+
+The dataset build, training pipeline and evaluation harness are all scripted; see the
+project repository.

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/Meta-Llama-3.2-3B-Instruct-Reference__TOG__FT",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_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 sha256:50cdd02bcab4ed669c2d113478231d85a5caa3e102a5ca7b7da951ff915d930d
+size 97307544

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- 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 %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- 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 #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\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 %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- 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": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "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": true,
+  "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": 0.26583361625671387,
+      "learning_rate": 0.0,
+      "loss": 1.838623046875,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.2549391984939575,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7900390625,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.27876609563827515,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.8592529296875,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.2896035611629486,
+      "learning_rate": 1e-05,
+      "loss": 1.801513671875,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.3665730953216553,
+      "learning_rate": 9.931634888554937e-06,
+      "loss": 1.545654296875,
+      "step": 5
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "eval_loss": 1.732421875,
+      "eval_runtime": 2.193,
+      "eval_samples_per_second": 1.368,
+      "eval_steps_per_second": 0.456,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.2946288287639618,
+      "learning_rate": 9.728616793536588e-06,
+      "loss": 1.818359375,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.2675096094608307,
+      "learning_rate": 9.397114317029975e-06,
+      "loss": 1.7734375,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.2651223838329315,
+      "learning_rate": 8.947199994035402e-06,
+      "loss": 1.78955078125,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.31145110726356506,
+      "learning_rate": 8.392544243589428e-06,
+      "loss": 1.8505859375,
+      "step": 9
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "eval_loss": 1.724609375,
+      "eval_runtime": 2.188,
+      "eval_samples_per_second": 1.371,
+      "eval_steps_per_second": 0.457,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.27500542998313904,
+      "learning_rate": 7.75e-06,
+      "loss": 1.796630859375,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.27637097239494324,
+      "learning_rate": 7.0390906449655104e-06,
+      "loss": 1.82177734375,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.28143683075904846,
+      "learning_rate": 6.281416799501188e-06,
+      "loss": 1.84130859375,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.29704588651657104,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 1.807373046875,
+      "step": 13
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "eval_loss": 1.71875,
+      "eval_runtime": 2.1801,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.459,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2861112654209137,
+      "learning_rate": 4.718583200498814e-06,
+      "loss": 1.81103515625,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.3324793577194214,
+      "learning_rate": 3.960909355034491e-06,
+      "loss": 1.796875,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.25911256670951843,
+      "learning_rate": 3.2500000000000015e-06,
+      "loss": 1.736572265625,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.2930397391319275,
+      "learning_rate": 2.607455756410573e-06,
+      "loss": 1.818359375,
+      "step": 17
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "eval_loss": 1.7109375,
+      "eval_runtime": 2.19,
+      "eval_samples_per_second": 1.37,
+      "eval_steps_per_second": 0.457,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.29004520177841187,
+      "learning_rate": 2.0528000059646e-06,
+      "loss": 1.81201171875,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.2956332862377167,
+      "learning_rate": 1.602885682970026e-06,
+      "loss": 1.8251953125,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3092670440673828,
+      "learning_rate": 1.2713832064634127e-06,
+      "loss": 1.779296875,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.29927435517311096,
+      "learning_rate": 1.0683651114450641e-06,
+      "loss": 1.79345703125,
+      "step": 21
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7109375,
+      "eval_runtime": 2.1924,
+      "eval_samples_per_second": 1.368,
+      "eval_steps_per_second": 0.456,
+      "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": 1.722081761694843e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}