Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: DUAL-GPO/phi-2-gpo-new-i0
+model-index:
+- name: phi-2-gpo-newSFT-b0.001-v6-lightai-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-newSFT-b0.001-v6-lightai-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: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- 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:abe494200f14d6351d3fa930239748ca65b2a3932c7cb342986d7c7c015c1450
+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": 1.0,
+    "train_loss": 2.063851060011448,
+    "train_runtime": 1792.0713,
+    "train_samples": 61135,
+    "train_samples_per_second": 11.16,
+    "train_steps_per_second": 0.087
+}

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": 1.0,
+    "train_loss": 2.063851060011448,
+    "train_runtime": 1792.0713,
+    "train_samples": 61135,
+    "train_samples_per_second": 11.16,
+    "train_steps_per_second": 0.087
+}

trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.125e-07,
+      "logits/chosen": 0.15261313319206238,
+      "logits/rejected": 0.1639709323644638,
+      "logps/chosen": -515.3743896484375,
+      "logps/rejected": -602.9024658203125,
+      "loss": 2.2483,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.125e-06,
+      "logits/chosen": 0.15371762216091156,
+      "logits/rejected": 0.15325689315795898,
+      "logps/chosen": -528.9754638671875,
+      "logps/rejected": -558.5530395507812,
+      "loss": 2.1933,
+      "rewards/accuracies": 0.3958333432674408,
+      "rewards/chosen": -7.75712906033732e-05,
+      "rewards/margins": 0.00021313497563824058,
+      "rewards/rejected": -0.00029070625896565616,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.989935734988098e-06,
+      "logits/chosen": 0.12148909270763397,
+      "logits/rejected": 0.19840040802955627,
+      "logps/chosen": -551.893798828125,
+      "logps/rejected": -582.2662353515625,
+      "loss": 2.1554,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.0018115075072273612,
+      "rewards/margins": 0.0008247121004387736,
+      "rewards/rejected": -0.002636219607666135,
+      "step": 20
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.8776412907378845e-06,
+      "logits/chosen": 0.11421946436166763,
+      "logits/rejected": 0.2807745039463043,
+      "logps/chosen": -618.5098266601562,
+      "logps/rejected": -630.0963745117188,
+      "loss": 2.1877,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.008222530595958233,
+      "rewards/margins": 0.0020459205843508244,
+      "rewards/rejected": -0.010268451645970345,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.646121984004666e-06,
+      "logits/chosen": 0.15948352217674255,
+      "logits/rejected": 0.2158539593219757,
+      "logps/chosen": -570.223388671875,
+      "logps/rejected": -606.2709350585938,
+      "loss": 2.1257,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.01901092566549778,
+      "rewards/margins": 0.006654287222772837,
+      "rewards/rejected": -0.02566521242260933,
+      "step": 40
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.3069871595684795e-06,
+      "logits/chosen": 0.14687010645866394,
+      "logits/rejected": 0.13899900019168854,
+      "logps/chosen": -663.9903564453125,
+      "logps/rejected": -667.9413452148438,
+      "loss": 2.1574,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -0.04059653356671333,
+      "rewards/margins": 0.0122517179697752,
+      "rewards/rejected": -0.05284825712442398,
+      "step": 50
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.8772424536302565e-06,
+      "logits/chosen": 0.12796762585639954,
+      "logits/rejected": 0.11626903712749481,
+      "logps/chosen": -646.955078125,
+      "logps/rejected": -695.7735595703125,
+      "loss": 2.0987,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -0.08105512708425522,
+      "rewards/margins": 0.026713049039244652,
+      "rewards/rejected": -0.10776817798614502,
+      "step": 60
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.3784370602033572e-06,
+      "logits/chosen": 0.09783248603343964,
+      "logits/rejected": 0.13697190582752228,
+      "logps/chosen": -752.6687622070312,
+      "logps/rejected": -773.8951416015625,
+      "loss": 2.0403,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.14598588645458221,
+      "rewards/margins": 0.031442705541849136,
+      "rewards/rejected": -0.17742857336997986,
+      "step": 70
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.835583164544139e-06,
+      "logits/chosen": 0.010139328427612782,
+      "logits/rejected": 0.14130939543247223,
+      "logps/chosen": -887.7872314453125,
+      "logps/rejected": -860.5573120117188,
+      "loss": 2.0713,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.2421277016401291,
+      "rewards/margins": 0.02552933618426323,
+      "rewards/rejected": -0.2676570415496826,
+      "step": 80
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.2759017277414165e-06,
+      "logits/chosen": 0.08868354558944702,
+      "logits/rejected": 0.044947974383831024,
+      "logps/chosen": -764.5272827148438,
+      "logps/rejected": -852.931640625,
+      "loss": 2.0314,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.21352943778038025,
+      "rewards/margins": 0.07627246528863907,
+      "rewards/rejected": -0.2898018956184387,
+      "step": 90
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7274575140626318e-06,
+      "logits/chosen": 0.13405397534370422,
+      "logits/rejected": 0.13627949357032776,
+      "logps/chosen": -944.3505859375,
+      "logps/rejected": -987.8220825195312,
+      "loss": 1.9657,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.29764193296432495,
+      "rewards/margins": 0.08456403017044067,
+      "rewards/rejected": -0.38220590353012085,
+      "step": 100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.217751806485235e-06,
+      "logits/chosen": 0.012543353252112865,
+      "logits/rejected": 0.1991170048713684,
+      "logps/chosen": -904.68212890625,
+      "logps/rejected": -986.7145385742188,
+      "loss": 1.9844,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -0.30881673097610474,
+      "rewards/margins": 0.09704812616109848,
+      "rewards/rejected": -0.4058648645877838,
+      "step": 110
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.723433775328385e-07,
+      "logits/chosen": 0.04557646065950394,
+      "logits/rejected": 0.12215445190668106,
+      "logps/chosen": -901.927734375,
+      "logps/rejected": -1020.6748046875,
+      "loss": 2.0618,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.3248935043811798,
+      "rewards/margins": 0.109535813331604,
+      "rewards/rejected": -0.4344293177127838,
+      "step": 120
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.1356686569674344e-07,
+      "logits/chosen": 0.049111802130937576,
+      "logits/rejected": 0.14041246473789215,
+      "logps/chosen": -935.4737548828125,
+      "logps/rejected": -1071.3458251953125,
+      "loss": 1.9157,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.331855446100235,
+      "rewards/margins": 0.11848483979701996,
+      "rewards/rejected": -0.45034027099609375,
+      "step": 130
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.59412823400657e-07,
+      "logits/chosen": 0.09409844875335693,
+      "logits/rejected": 0.14967292547225952,
+      "logps/chosen": -827.7521362304688,
+      "logps/rejected": -1027.630615234375,
+      "loss": 1.9851,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.2741563618183136,
+      "rewards/margins": 0.14417442679405212,
+      "rewards/rejected": -0.41833075881004333,
+      "step": 140
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.262559558016325e-08,
+      "logits/chosen": 0.08899237215518951,
+      "logits/rejected": 0.1435566246509552,
+      "logps/chosen": -913.5513916015625,
+      "logps/rejected": -997.4661865234375,
+      "loss": 2.0336,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -0.3079494833946228,
+      "rewards/margins": 0.10450174659490585,
+      "rewards/rejected": -0.41245120763778687,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "step": 156,
+      "total_flos": 0.0,
+      "train_loss": 2.063851060011448,
+      "train_runtime": 1792.0713,
+      "train_samples_per_second": 11.16,
+      "train_steps_per_second": 0.087
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 156,
+  "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 sha256:89febfbf6ff0fd9555fe5f909b93d9a8b95f03e9aa3cbc57261e288f0c1f8f5a
+size 5880