Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: DUAL-GPO/phi-2-gpo-new-i0
+model-index:
+- name: phi-2-gpo-v21-i1
+  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-2-gpo-v21-i1
+
+This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None 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: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "DUAL-GPO/phi-2-gpo-new-i0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0850cf2ee7e92bbf581505a840fdcd07084fbfcc51f863bd7750b30960d62d
+size 167807296

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.36343905329704285,
+    "train_runtime": 3130.5093,
+    "train_samples": 6000,
+    "train_samples_per_second": 1.917,
+    "train_steps_per_second": 0.03
+}

runs/May14_15-30-28_ip-10-192-15-122/events.out.tfevents.1715700668.ip-10-192-15-122.3646.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80622c1e14257c596aea3d543478ecef783f39e2b70a4afd43563fd2d2e3522
+size 11411

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.36343905329704285,
+    "train_runtime": 3130.5093,
+    "train_samples": 6000,
+    "train_samples_per_second": 1.917,
+    "train_steps_per_second": 0.03
+}

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.992,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.000000000000001e-07,
+      "logits/chosen": 0.04800860583782196,
+      "logits/rejected": 0.13088344037532806,
+      "logps/chosen": -344.1112976074219,
+      "logps/rejected": -286.2291259765625,
+      "loss": 0.4028,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5e-06,
+      "logits/chosen": 0.1340106725692749,
+      "logits/rejected": 0.24628029763698578,
+      "logps/chosen": -358.9225769042969,
+      "logps/rejected": -352.1644592285156,
+      "loss": 0.3705,
+      "rewards/accuracies": 0.4236111044883728,
+      "rewards/chosen": 7.527708658017218e-05,
+      "rewards/margins": 3.0965995392762125e-05,
+      "rewards/rejected": 4.431110937730409e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.823045180793914e-06,
+      "logits/chosen": 0.12768682837486267,
+      "logits/rejected": 0.17665454745292664,
+      "logps/chosen": -329.0359802246094,
+      "logps/rejected": -341.37432861328125,
+      "loss": 0.3571,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.0001585387362865731,
+      "rewards/margins": 0.0007194522768259048,
+      "rewards/rejected": -0.0005609134095720947,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.317231129607859e-06,
+      "logits/chosen": 0.0687670111656189,
+      "logits/rejected": 0.1390002816915512,
+      "logps/chosen": -366.32183837890625,
+      "logps/rejected": -358.305908203125,
+      "loss": 0.3713,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.00020733498968183994,
+      "rewards/margins": 0.002162316581234336,
+      "rewards/rejected": -0.001954981591552496,
+      "step": 30
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.55416283362546e-06,
+      "logits/chosen": 0.0996643453836441,
+      "logits/rejected": 0.16496673226356506,
+      "logps/chosen": -354.90643310546875,
+      "logps/rejected": -347.098388671875,
+      "loss": 0.3713,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.00043527656816877425,
+      "rewards/margins": 0.003645308781415224,
+      "rewards/rejected": -0.004080585204064846,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.6418631827326857e-06,
+      "logits/chosen": 0.19002003967761993,
+      "logits/rejected": 0.2053782194852829,
+      "logps/chosen": -296.21661376953125,
+      "logps/rejected": -323.6202697753906,
+      "loss": 0.3591,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -6.220813520485535e-05,
+      "rewards/margins": 0.00692623108625412,
+      "rewards/rejected": -0.006988438777625561,
+      "step": 50
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7094808327579401e-06,
+      "logits/chosen": 0.14944681525230408,
+      "logits/rejected": 0.1665990650653839,
+      "logps/chosen": -376.69952392578125,
+      "logps/rejected": -375.88787841796875,
+      "loss": 0.3669,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.0006484203622676432,
+      "rewards/margins": 0.011537977494299412,
+      "rewards/rejected": -0.012186397798359394,
+      "step": 60
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.890074238378074e-07,
+      "logits/chosen": 0.14019212126731873,
+      "logits/rejected": 0.19166143238544464,
+      "logps/chosen": -390.3976135253906,
+      "logps/rejected": -334.20904541015625,
+      "loss": 0.3606,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.0038049519062042236,
+      "rewards/margins": 0.010462903417646885,
+      "rewards/rejected": -0.014267854392528534,
+      "step": 70
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.965923349633779e-07,
+      "logits/chosen": 0.15474095940589905,
+      "logits/rejected": 0.15488487482070923,
+      "logps/chosen": -365.92510986328125,
+      "logps/rejected": -369.5127868652344,
+      "loss": 0.3573,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -0.00941461231559515,
+      "rewards/margins": 0.010669920593500137,
+      "rewards/rejected": -0.020084530115127563,
+      "step": 80
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6100130092037704e-08,
+      "logits/chosen": 0.1559561789035797,
+      "logits/rejected": 0.21619243919849396,
+      "logps/chosen": -373.12786865234375,
+      "logps/rejected": -362.0654296875,
+      "loss": 0.357,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.005230956245213747,
+      "rewards/margins": 0.01701132394373417,
+      "rewards/rejected": -0.022242281585931778,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "step": 93,
+      "total_flos": 0.0,
+      "train_loss": 0.36343905329704285,
+      "train_runtime": 3130.5093,
+      "train_samples_per_second": 1.917,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 93,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c1b6c2ea4aa32da924248ec8b520d734003649757d9be7d26ce1cb4910da7d
+size 5816