phi-3.5-new

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: microsoft/Phi-3.5-mini-instruct
+model-index:
+- name: phi-3.5-new
+  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. -->
+
+# phi-3.5-new
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.0635
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 50
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.2.dev0
+- Transformers 4.42.0.dev0
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa97e4d58e02802f0806a513b36519d0b86d77745fbd5476ae89add6084e0e7
+size 100697728

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.06346205621957779,
+    "eval_runtime": 335.7373,
+    "eval_samples_per_second": 2.478,
+    "eval_steps_per_second": 1.239,
+    "total_flos": 4.3571154598634004e+18,
+    "train_loss": 0.37453963272388163,
+    "train_runtime": 280880.5286,
+    "train_samples_per_second": 0.741,
+    "train_steps_per_second": 0.37
+}

config.json

@@ -0,0 +1,138 @@
+{
+  "_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.06346205621957779,
+    "eval_runtime": 335.7373,
+    "eval_samples_per_second": 2.478,
+    "eval_steps_per_second": 1.239
+}

runs/Sep19_20-38-15_dmlab/events.out.tfevents.1726767499.dmlab.6244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7a72faf6cfdff00b23876756db45aa83a892564c35c750d38cd582c92d95fa
+size 18883

runs/Sep19_20-38-15_dmlab/events.out.tfevents.1727048715.dmlab.6244.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf88eabc26c65ef79f905245f5f9a4b02ec537f21f71bb72356d563c3546189
+size 364

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_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "total_flos": 4.3571154598634004e+18,
+    "train_loss": 0.37453963272388163,
+    "train_runtime": 280880.5286,
+    "train_samples_per_second": 0.741,
+    "train_steps_per_second": 0.37
+}

trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 500,
+  "global_step": 104000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.975465714931488,
+      "learning_rate": 2e-05,
+      "loss": 0.9891,
+      "step": 2080
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3330873250961304,
+      "learning_rate": 4e-05,
+      "loss": 0.8643,
+      "step": 4160
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.202699899673462,
+      "learning_rate": 6e-05,
+      "loss": 0.8188,
+      "step": 6240
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.5446971654891968,
+      "learning_rate": 8e-05,
+      "loss": 0.7587,
+      "step": 8320
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8479889631271362,
+      "learning_rate": 0.0001,
+      "loss": 0.6784,
+      "step": 10400
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.271431803703308,
+      "learning_rate": 0.00012,
+      "loss": 0.6332,
+      "step": 12480
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.828289806842804,
+      "learning_rate": 0.00014,
+      "loss": 0.6135,
+      "step": 14560
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5532117486000061,
+      "learning_rate": 0.00016,
+      "loss": 0.6021,
+      "step": 16640
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7734587788581848,
+      "learning_rate": 0.00018,
+      "loss": 0.5932,
+      "step": 18720
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.9202972650527954,
+      "learning_rate": 0.0002,
+      "loss": 0.5841,
+      "step": 20800
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.1167834997177124,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.5765,
+      "step": 22880
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.7493125796318054,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.5694,
+      "step": 24960
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.9302449226379395,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.5617,
+      "step": 27040
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.9727580547332764,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.5553,
+      "step": 29120
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.6252313852310181,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.5488,
+      "step": 31200
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.6910933256149292,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.5406,
+      "step": 33280
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6691188812255859,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.5347,
+      "step": 35360
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.656794548034668,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5267,
+      "step": 37440
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.528489887714386,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 0.5184,
+      "step": 39520
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.7208832502365112,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5087,
+      "step": 41600
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.6855819225311279,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.4984,
+      "step": 43680
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.9891296625137329,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.4858,
+      "step": 45760
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 1.0229650735855103,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.4719,
+      "step": 47840
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.9607130289077759,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.4558,
+      "step": 49920
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 1.1026415824890137,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.4375,
+      "step": 52000
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.9125514030456543,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.4175,
+      "step": 54080
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.9571768045425415,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.3942,
+      "step": 56160
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 1.0941965579986572,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.3696,
+      "step": 58240
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 1.6244746446609497,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.3424,
+      "step": 60320
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.409400463104248,
+      "learning_rate": 0.0001,
+      "loss": 0.3138,
+      "step": 62400
+    },
+    {
+      "epoch": 31.0,
+      "grad_norm": 1.7202110290527344,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.2836,
+      "step": 64480
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 1.6299169063568115,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.2525,
+      "step": 66560
+    },
+    {
+      "epoch": 33.0,
+      "grad_norm": 1.7053184509277344,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.2217,
+      "step": 68640
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 1.7824922800064087,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.192,
+      "step": 70720
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 1.8197373151779175,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.1645,
+      "step": 72800
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 1.625858187675476,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.1394,
+      "step": 74880
+    },
+    {
+      "epoch": 37.0,
+      "grad_norm": 1.8438661098480225,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.1171,
+      "step": 76960
+    },
+    {
+      "epoch": 38.0,
+      "grad_norm": 1.7667992115020752,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0976,
+      "step": 79040
+    },
+    {
+      "epoch": 39.0,
+      "grad_norm": 1.7099578380584717,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0814,
+      "step": 81120
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 1.9202967882156372,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0679,
+      "step": 83200
+    },
+    {
+      "epoch": 41.0,
+      "grad_norm": 1.7177019119262695,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0569,
+      "step": 85280
+    },
+    {
+      "epoch": 42.0,
+      "grad_norm": 1.6319146156311035,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0482,
+      "step": 87360
+    },
+    {
+      "epoch": 43.0,
+      "grad_norm": 1.3095797300338745,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0412,
+      "step": 89440
+    },
+    {
+      "epoch": 44.0,
+      "grad_norm": 1.5144089460372925,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0362,
+      "step": 91520
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 1.2941925525665283,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0321,
+      "step": 93600
+    },
+    {
+      "epoch": 46.0,
+      "grad_norm": 1.1236457824707031,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0293,
+      "step": 95680
+    },
+    {
+      "epoch": 47.0,
+      "grad_norm": 1.4110456705093384,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.027,
+      "step": 97760
+    },
+    {
+      "epoch": 48.0,
+      "grad_norm": 1.5882657766342163,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0258,
+      "step": 99840
+    },
+    {
+      "epoch": 49.0,
+      "grad_norm": 1.0106526613235474,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0249,
+      "step": 101920
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.8798067569732666,
+      "learning_rate": 0.0,
+      "loss": 0.0246,
+      "step": 104000
+    },
+    {
+      "epoch": 50.0,
+      "step": 104000,
+      "total_flos": 4.3571154598634004e+18,
+      "train_loss": 0.37453963272388163,
+      "train_runtime": 280880.5286,
+      "train_samples_per_second": 0.741,
+      "train_steps_per_second": 0.37
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 104000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "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": 4.3571154598634004e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8efc2b462e2a27e9e94241b823315d61ad1d3ea125de62d2a68bae44f01ac06d
+size 5240