End of training

README.md

@@ -0,0 +1,93 @@
+---
+license: mit
+base_model: microsoft/Phi-3-mini-4k-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: Phi0503HMA4
+  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. -->
+
+# Phi0503HMA4
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0958
+
+## 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: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_steps: 80
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.3203        | 0.09  | 10   | 0.8287          |
+| 0.439         | 0.18  | 20   | 0.2584          |
+| 0.2853        | 0.27  | 30   | 0.2324          |
+| 0.3519        | 0.36  | 40   | 0.2819          |
+| 0.2642        | 0.45  | 50   | 1.2134          |
+| 3.7539        | 0.54  | 60   | 4.0368          |
+| 2.718         | 0.63  | 70   | 1.9987          |
+| 1.3059        | 0.73  | 80   | 0.5453          |
+| 0.534         | 0.82  | 90   | 0.4644          |
+| 0.3535        | 0.91  | 100  | 0.2428          |
+| 0.2618        | 1.0   | 110  | 0.2259          |
+| 0.2222        | 1.09  | 120  | 0.2072          |
+| 0.1939        | 1.18  | 130  | 0.1850          |
+| 0.2268        | 1.27  | 140  | 0.1876          |
+| 0.1966        | 1.36  | 150  | 0.1927          |
+| 0.1942        | 1.45  | 160  | 0.1838          |
+| 0.1937        | 1.54  | 170  | 0.1900          |
+| 0.1808        | 1.63  | 180  | 0.1781          |
+| 0.1785        | 1.72  | 190  | 0.1795          |
+| 0.1737        | 1.81  | 200  | 0.1694          |
+| 0.176         | 1.9   | 210  | 0.1708          |
+| 0.1648        | 1.99  | 220  | 0.1751          |
+| 0.1702        | 2.08  | 230  | 0.1576          |
+| 0.1576        | 2.18  | 240  | 0.1524          |
+| 0.1477        | 2.27  | 250  | 0.1389          |
+| 0.1333        | 2.36  | 260  | 0.1172          |
+| 0.1267        | 2.45  | 270  | 0.1126          |
+| 0.1128        | 2.54  | 280  | 0.1016          |
+| 0.1112        | 2.63  | 290  | 0.0995          |
+| 0.1032        | 2.72  | 300  | 0.0976          |
+| 0.1001        | 2.81  | 310  | 0.0971          |
+| 0.0996        | 2.9   | 320  | 0.0957          |
+| 0.0968        | 2.99  | 330  | 0.0958          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "adaptive_ratio": 0.01,
+  "adaptive_ratio_decay": 1.0,
+  "additive_modeling": false,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "curr_learning": true,
+  "detached_training": true,
+  "dynamic_adapter_pool": true,
+  "enable_lora": null,
+  "encoder_hidden_size": 3072,
+  "fan_in_fan_out": false,
+  "hypernetwork": true,
+  "inference_mode": true,
+  "input_based_adapter_selection": true,
+  "layer_to_lora": [],
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "num_attention_heads": 32,
+  "num_layers": 32,
+  "num_prefix_set": 3,
+  "num_transformer_submodules": 1,
+  "num_virtual_tokens": 30,
+  "number_of_adapter_pre_layer": 8,
+  "ot_diversified_dispatcher": false,
+  "ot_diversified_prefix": false,
+  "peft_type": "PREFIX_MA_LORA",
+  "pool_selective_inference": true,
+  "pool_selective_training": true,
+  "prefix_projection": true,
+  "r": 8,
+  "random_routing": false,
+  "random_routing_inference": false,
+  "scale": 64,
+  "selective_num": 8,
+  "simple_hidden_matching": false,
+  "simple_instance_matching": true,
+  "target_modules": [
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "token_dim": 3072
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921090f33e20804f3c5716be76194ff3c44db2195152549f53ce1620504f588d
+size 430750193

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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db294a443db39692c1000c6714d546b297a45545036f5d16f1ec441610ab78e3
+size 7921324520

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": "<unk>",
+  "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 +1,131 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4f9831b3dfe394c191d6772e9c9b2ed3b939f93de14d03cb0c8d2514e8af9f
+size 5176