Model save

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-gpo-ultrachat-lora
+  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-ultrachat-lora
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0001
+- Rewards/chosen: -0.0000
+- Rewards/rejected: -0.0004
+- Rewards/accuracies: 0.2600
+- Rewards/margins: 0.0004
+- Logps/rejected: -94.2372
+- Logps/chosen: -91.7275
+- Logits/rejected: 0.8188
+- Logits/chosen: 0.8013
+
+## 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 2.1.2+cu118
+- 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": "microsoft/phi-2",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de8ae4bc7342565a4557aa3b800119c0c66c3f62757508ccea823253d58a474
+size 41977616

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 +1,21 @@
+{
+    "epoch": 0.99,
+    "eval_logits/chosen": 0.8012984991073608,
+    "eval_logits/rejected": 0.8187645673751831,
+    "eval_logps/chosen": -91.72753143310547,
+    "eval_logps/rejected": -94.23716735839844,
+    "eval_loss": 0.00012303233961574733,
+    "eval_rewards/accuracies": 0.25999999046325684,
+    "eval_rewards/chosen": -1.6935970279519097e-06,
+    "eval_rewards/margins": 0.0003997479216195643,
+    "eval_rewards/rejected": -0.00040144147351384163,
+    "eval_runtime": 274.0423,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.298,
+    "eval_steps_per_second": 0.456,
+    "train_loss": 0.0001254068662283795,
+    "train_runtime": 1151.127,
+    "train_samples": 6113,
+    "train_samples_per_second": 5.31,
+    "train_steps_per_second": 0.083
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.99,
+    "eval_logits/chosen": 0.8012984991073608,
+    "eval_logits/rejected": 0.8187645673751831,
+    "eval_logps/chosen": -91.72753143310547,
+    "eval_logps/rejected": -94.23716735839844,
+    "eval_loss": 0.00012303233961574733,
+    "eval_rewards/accuracies": 0.25999999046325684,
+    "eval_rewards/chosen": -1.6935970279519097e-06,
+    "eval_rewards/margins": 0.0003997479216195643,
+    "eval_rewards/rejected": -0.00040144147351384163,
+    "eval_runtime": 274.0423,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.298,
+    "eval_steps_per_second": 0.456
+}

runs/Feb29_16-15-30_gpu4-119-4/events.out.tfevents.1709183803.gpu4-119-4.1051334.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b275e6d4abede932006c235cd2a56b13558d7a35ea33e78c152981d13622f67
+size 4826

runs/Feb29_16-18-42_gpu4-119-4/events.out.tfevents.1709184018.gpu4-119-4.1054311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338aabf81ccfed7011dbb0906e865433b0e486d4e1b59dedac7fb33a3a0c81fa
+size 6695

runs/Feb29_16-27-31_gpu4-119-4/events.out.tfevents.1709184529.gpu4-119-4.1061687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e6a2b78b03b950a427dfbf9bf4d81d7a76b6464e3f6e1c4b45a619f3cd5600
+size 11404

runs/Feb29_16-27-31_gpu4-119-4/events.out.tfevents.1709185954.gpu4-119-4.1061687.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0c39bc170d24316d9f7eec4b5a05c3f7d65edacbcf53c7bdb7701d7e14044e
+size 815

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": 0.0001254068662283795,
+    "train_runtime": 1151.127,
+    "train_samples": 6113,
+    "train_samples_per_second": 5.31,
+    "train_steps_per_second": 0.083
+}

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9921671018276762,
+  "eval_steps": 100,
+  "global_step": 95,
+  "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": 0.8826487064361572,
+      "logits/rejected": 0.921362042427063,
+      "logps/chosen": -36.58121871948242,
+      "logps/rejected": -54.902320861816406,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5e-06,
+      "logits/chosen": 0.8916183114051819,
+      "logits/rejected": 0.873969316482544,
+      "logps/chosen": -87.77237701416016,
+      "logps/rejected": -96.3612289428711,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.2222222238779068,
+      "rewards/chosen": 0.0002965294988825917,
+      "rewards/margins": 0.00019970430003013462,
+      "rewards/rejected": 9.682523523224518e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.83118057351089e-06,
+      "logits/chosen": 0.7805377244949341,
+      "logits/rejected": 0.8473492860794067,
+      "logps/chosen": -91.75300598144531,
+      "logps/rejected": -85.11421966552734,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 4.452450230019167e-05,
+      "rewards/margins": -0.00017617340199649334,
+      "rewards/rejected": 0.00022069788246881217,
+      "step": 20
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.3475222930516484e-06,
+      "logits/chosen": 0.8648212552070618,
+      "logits/rejected": 0.8478900194168091,
+      "logps/chosen": -85.289306640625,
+      "logps/rejected": -78.0145492553711,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.28125,
+      "rewards/chosen": 0.00029949203599244356,
+      "rewards/margins": 6.509931699838489e-05,
+      "rewards/rejected": 0.00023439270444214344,
+      "step": 30
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.6143458894413463e-06,
+      "logits/chosen": 0.7649093270301819,
+      "logits/rejected": 0.8426358103752136,
+      "logps/chosen": -122.76078033447266,
+      "logps/rejected": -108.79180908203125,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.26249998807907104,
+      "rewards/chosen": -0.0002823365502990782,
+      "rewards/margins": -9.583422070136294e-05,
+      "rewards/rejected": -0.00018650232232175767,
+      "step": 40
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.730670898658255e-06,
+      "logits/chosen": 0.8404033780097961,
+      "logits/rejected": 0.8685251474380493,
+      "logps/chosen": -65.78496551513672,
+      "logps/rejected": -71.65745544433594,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.23749999701976776,
+      "rewards/chosen": -0.0002987021580338478,
+      "rewards/margins": -0.0003552257257979363,
+      "rewards/rejected": 5.65235604881309e-05,
+      "step": 50
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8158425248197931e-06,
+      "logits/chosen": 0.8147390484809875,
+      "logits/rejected": 0.8857711553573608,
+      "logps/chosen": -117.61279296875,
+      "logps/rejected": -110.9428482055664,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.00020218415011186153,
+      "rewards/margins": 0.0003176866448484361,
+      "rewards/rejected": -0.00011550241470104083,
+      "step": 60
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.934134090518593e-07,
+      "logits/chosen": 0.8052595257759094,
+      "logits/rejected": 0.8626030087471008,
+      "logps/chosen": -82.66513061523438,
+      "logps/rejected": -83.91613006591797,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": -1.9253784557804465e-05,
+      "rewards/margins": 6.199729250511155e-05,
+      "rewards/rejected": -8.125107706291601e-05,
+      "step": 70
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.7445716067596506e-07,
+      "logits/chosen": 0.7661033272743225,
+      "logits/rejected": 0.829667866230011,
+      "logps/chosen": -105.8118667602539,
+      "logps/rejected": -104.9473876953125,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.2874999940395355,
+      "rewards/chosen": 2.1945637854514644e-05,
+      "rewards/margins": -0.00017051820759661496,
+      "rewards/rejected": 0.00019246386364102364,
+      "step": 80
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.256725079024554e-08,
+      "logits/chosen": 0.8347122073173523,
+      "logits/rejected": 0.8553287386894226,
+      "logps/chosen": -77.658203125,
+      "logps/rejected": -89.99678039550781,
+      "loss": 0.0001,
+      "rewards/accuracies": 0.34375,
+      "rewards/chosen": 0.0003329566097818315,
+      "rewards/margins": 0.0006740919779986143,
+      "rewards/rejected": -0.0003411353682167828,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "step": 95,
+      "total_flos": 0.0,
+      "train_loss": 0.0001254068662283795,
+      "train_runtime": 1151.127,
+      "train_samples_per_second": 5.31,
+      "train_steps_per_second": 0.083
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 95,
+  "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 sha256:9ec17dc0783ba6c6bd44eb7357ca01908a8a2534b97da95eaedea25be353d0d0
+size 5816