superklein18/test

README.md

@@ -0,0 +1,56 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: outputs
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# outputs
+
+This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 16
+- seed: 3407
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Phi3ForCausalLM",
+    "parent_library": "transformers_modules.microsoft.Phi-3.5-mini-instruct.3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca.modeling_phi3"
+  },
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a815b75fe028f594998833ba1dc590089bfe3694cbea3ae4b8d8fd388c4a7a6
+size 35668592

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5319549602828002,
+    "train_runtime": 55.3499,
+    "train_samples_per_second": 3.668,
+    "train_steps_per_second": 3.668
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5319549602828002,
+    "train_runtime": 55.3499,
+    "train_samples_per_second": 3.668,
+    "train_steps_per_second": 3.668
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 203,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 2.7416231632232666,
+      "learning_rate": 9.507389162561576e-05,
+      "loss": 3.0533,
+      "step": 10
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 1.8756747245788574,
+      "learning_rate": 9.014778325123154e-05,
+      "loss": 0.4214,
+      "step": 20
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 1.4831429719924927,
+      "learning_rate": 8.52216748768473e-05,
+      "loss": 0.4639,
+      "step": 30
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 1.7727338075637817,
+      "learning_rate": 8.029556650246307e-05,
+      "loss": 0.3722,
+      "step": 40
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 0.9307169914245605,
+      "learning_rate": 7.536945812807882e-05,
+      "loss": 0.3516,
+      "step": 50
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.7861897349357605,
+      "learning_rate": 7.044334975369458e-05,
+      "loss": 0.3897,
+      "step": 60
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 1.2244670391082764,
+      "learning_rate": 6.551724137931034e-05,
+      "loss": 0.4396,
+      "step": 70
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.8233121037483215,
+      "learning_rate": 6.0591133004926113e-05,
+      "loss": 0.3135,
+      "step": 80
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 3.173562526702881,
+      "learning_rate": 5.566502463054187e-05,
+      "loss": 0.6026,
+      "step": 90
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 1.5332086086273193,
+      "learning_rate": 5.0738916256157644e-05,
+      "loss": 0.386,
+      "step": 100
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 1.3006514310836792,
+      "learning_rate": 4.58128078817734e-05,
+      "loss": 0.3327,
+      "step": 110
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 1.4627310037612915,
+      "learning_rate": 4.088669950738917e-05,
+      "loss": 0.329,
+      "step": 120
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 1.226656198501587,
+      "learning_rate": 3.5960591133004926e-05,
+      "loss": 0.27,
+      "step": 130
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.3999422788619995,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.3287,
+      "step": 140
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 4.163649082183838,
+      "learning_rate": 2.6108374384236457e-05,
+      "loss": 0.3943,
+      "step": 150
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.8537468314170837,
+      "learning_rate": 2.1182266009852215e-05,
+      "loss": 0.3435,
+      "step": 160
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 3.8700287342071533,
+      "learning_rate": 1.625615763546798e-05,
+      "loss": 0.5416,
+      "step": 170
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 6.436923980712891,
+      "learning_rate": 1.1330049261083744e-05,
+      "loss": 0.3257,
+      "step": 180
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 1.033650279045105,
+      "learning_rate": 6.403940886699508e-06,
+      "loss": 0.5444,
+      "step": 190
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 2.5371437072753906,
+      "learning_rate": 1.477832512315271e-06,
+      "loss": 0.5019,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 203,
+      "total_flos": 0.0,
+      "train_loss": 0.5319549602828002,
+      "train_runtime": 55.3499,
+      "train_samples_per_second": 3.668,
+      "train_steps_per_second": 3.668
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 203,
+  "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": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3b9650fc36193ba33029ea31e3820a0bf08dbd41f1bffa00adf86ad61a2e6e
+size 5432