phi-3.5-new

README.md

@@ -1,3 +1,57 @@
----
-license: apache-2.0
----
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: transformers
+model_name: phi-3.5-new
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for 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).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="pefanis27/phi-3.5-new", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.2
+- Transformers: 4.46.3
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "gate_up_proj",
+    "o_proj",
+    "down_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 sha256:20178576bc8573e56eb14493ece1b59f3ae774a58a2e0780f176f7c0d3a70c29
+size 100697728

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.28774118423461914,
+    "eval_runtime": 16.9372,
+    "eval_samples_per_second": 2.48,
+    "eval_steps_per_second": 1.24,
+    "total_flos": 8.68297895581778e+16,
+    "train_loss": 0.616850325694451,
+    "train_runtime": 5601.927,
+    "train_samples_per_second": 0.743,
+    "train_steps_per_second": 0.371
+}

config.json

@@ -0,0 +1,139 @@
+{
+  "_attn_implementation_autoset": true,
+  "_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": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 32064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.28774118423461914,
+    "eval_runtime": 16.9372,
+    "eval_samples_per_second": 2.48,
+    "eval_steps_per_second": 1.24
+}

runs/Jan12_12-55-43_dmlab/events.out.tfevents.1736679343.dmlab.6276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc48c69cca1929ede90f8c340c6459cf222c99c8f3aa4fd59375fb22d382cc74
+size 8731

runs/Jan12_13-51-56_dmlab/events.out.tfevents.1736682716.dmlab.15941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3d23d930999fad63150b2c11fe1ab2996cb8c971fb050fafe4855c2fb1a61f
+size 12883

runs/Jan12_13-51-56_dmlab/events.out.tfevents.1736688335.dmlab.15941.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdd464ad0070e459285b95a099918dce843a3df9256cca1b80ae7c124f754a8
+size 359

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": 20.0,
+    "total_flos": 8.68297895581778e+16,
+    "train_loss": 0.616850325694451,
+    "train_runtime": 5601.927,
+    "train_samples_per_second": 0.743,
+    "train_steps_per_second": 0.371
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 2080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6938191056251526,
+      "learning_rate": 5e-05,
+      "loss": 1.1644,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5342716574668884,
+      "learning_rate": 0.0001,
+      "loss": 0.9083,
+      "step": 208
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.47485536336898804,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8697,
+      "step": 312
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5520597100257874,
+      "learning_rate": 0.0002,
+      "loss": 0.8504,
+      "step": 416
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4108010530471802,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.8314,
+      "step": 520
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5089908838272095,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.809,
+      "step": 624
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5841424465179443,
+      "learning_rate": 0.00018314696123025454,
+      "loss": 0.788,
+      "step": 728
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.6074467301368713,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.7642,
+      "step": 832
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6272623538970947,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 0.7376,
+      "step": 936
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.6662757992744446,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.7044,
+      "step": 1040
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.9177679419517517,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.6638,
+      "step": 1144
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.0447787046432495,
+      "learning_rate": 0.0001,
+      "loss": 0.6131,
+      "step": 1248
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 1.1840310096740723,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.5513,
+      "step": 1352
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.5581327676773071,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4789,
+      "step": 1456
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.5830806493759155,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.4021,
+      "step": 1560
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.7810040712356567,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.3294,
+      "step": 1664
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.415872573852539,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.2672,
+      "step": 1768
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.7194544076919556,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.2226,
+      "step": 1872
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 1.4402439594268799,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.1961,
+      "step": 1976
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.3084591627120972,
+      "learning_rate": 0.0,
+      "loss": 0.1851,
+      "step": 2080
+    },
+    {
+      "epoch": 20.0,
+      "step": 2080,
+      "total_flos": 8.68297895581778e+16,
+      "train_loss": 0.616850325694451,
+      "train_runtime": 5601.927,
+      "train_samples_per_second": 0.743,
+      "train_steps_per_second": 0.371
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 8.68297895581778e+16,
+  "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 sha256:633d6603fb5d519d493770c00d2039db41cce516bb4399ad40e6d01187a3b828
+size 5624