Model save

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-gpo-test-longest-iter-random-0
+  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-test-longest-iter-random-0
+
+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: 0.0004
+- Rewards/chosen: 0.0012
+- Rewards/rejected: 0.0010
+- Rewards/accuracies: 0.4995
+- Rewards/margins: 0.0002
+- Logps/rejected: -233.4380
+- Logps/chosen: -256.4973
+- Logits/rejected: 0.8990
+- Logits/chosen: 0.8417
+
+## 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
+- gradient_accumulation_steps: 4
+- total_train_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: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.0003        | 1.6   | 100  | 0.0004          | 0.0006         | 0.0004           | 0.4855             | 0.0002          | -233.5017      | -256.5565    | 0.8960          | 0.8387        |
+| 0.0003        | 3.2   | 200  | 0.0004          | 0.0013         | 0.0009           | 0.5100             | 0.0004          | -233.4492      | -256.4811    | 0.8984          | 0.8412        |
+
+
+### 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": "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": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6111481cb1a2c7bcd128ee87e2115a05b3817370404ebd778cc9f4acc408bd
+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": 3.97,
+    "eval_logits/chosen": 0.8417125940322876,
+    "eval_logits/rejected": 0.8990198373794556,
+    "eval_logps/chosen": -256.497314453125,
+    "eval_logps/rejected": -233.4380340576172,
+    "eval_loss": 0.0003914303961209953,
+    "eval_rewards/accuracies": 0.49950000643730164,
+    "eval_rewards/chosen": 0.001168824383057654,
+    "eval_rewards/margins": 0.00016647118900436908,
+    "eval_rewards/rejected": 0.001002353266812861,
+    "eval_runtime": 491.0166,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.073,
+    "eval_steps_per_second": 1.018,
+    "train_loss": 0.0003399105843263603,
+    "train_runtime": 3335.538,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.199,
+    "train_steps_per_second": 0.074
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.97,
+    "eval_logits/chosen": 0.8417125940322876,
+    "eval_logits/rejected": 0.8990198373794556,
+    "eval_logps/chosen": -256.497314453125,
+    "eval_logps/rejected": -233.4380340576172,
+    "eval_loss": 0.0003914303961209953,
+    "eval_rewards/accuracies": 0.49950000643730164,
+    "eval_rewards/chosen": 0.001168824383057654,
+    "eval_rewards/margins": 0.00016647118900436908,
+    "eval_rewards/rejected": 0.001002353266812861,
+    "eval_runtime": 491.0166,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.073,
+    "eval_steps_per_second": 1.018
+}

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": 3.97,
+    "train_loss": 0.0003399105843263603,
+    "train_runtime": 3335.538,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.199,
+    "train_steps_per_second": 0.074
+}

trainer_state.json

@@ -0,0 +1,412 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.968,
+  "eval_steps": 100,
+  "global_step": 248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.0000000000000002e-07,
+      "logits/chosen": 0.9600980877876282,
+      "logits/rejected": 1.094868540763855,
+      "logps/chosen": -119.03445434570312,
+      "logps/rejected": -112.18000030517578,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.0000000000000003e-06,
+      "logits/chosen": 0.8413593769073486,
+      "logits/rejected": 0.813139796257019,
+      "logps/chosen": -142.51600646972656,
+      "logps/rejected": -130.04800415039062,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.3194444477558136,
+      "rewards/chosen": 0.0009210502030327916,
+      "rewards/margins": -8.903745765564963e-05,
+      "rewards/rejected": 0.0010100876679643989,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.000000000000001e-06,
+      "logits/chosen": 0.8089853525161743,
+      "logits/rejected": 0.8187138438224792,
+      "logps/chosen": -155.18431091308594,
+      "logps/rejected": -143.44085693359375,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": 0.0007359608425758779,
+      "rewards/margins": -0.0004602448898367584,
+      "rewards/rejected": 0.001196205848827958,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.993800445762451e-06,
+      "logits/chosen": 0.8762779235839844,
+      "logits/rejected": 0.9211899638175964,
+      "logps/chosen": -154.8330535888672,
+      "logps/rejected": -141.16299438476562,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -1.3224826943769585e-05,
+      "rewards/margins": -0.00042751478031277657,
+      "rewards/rejected": 0.0004142899124417454,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.944388344834205e-06,
+      "logits/chosen": 0.8115983009338379,
+      "logits/rejected": 0.8376752734184265,
+      "logps/chosen": -172.55001831054688,
+      "logps/rejected": -157.711669921875,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": 0.00026369161787442863,
+      "rewards/margins": 4.611946133081801e-05,
+      "rewards/rejected": 0.0002175722038373351,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.8465431931347904e-06,
+      "logits/chosen": 0.8291877508163452,
+      "logits/rejected": 0.8113203048706055,
+      "logps/chosen": -160.0177764892578,
+      "logps/rejected": -146.55140686035156,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -5.383044481277466e-07,
+      "rewards/margins": -8.223028999054804e-05,
+      "rewards/rejected": 8.169189095497131e-05,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.702203692102539e-06,
+      "logits/chosen": 0.7359780073165894,
+      "logits/rejected": 0.7216537594795227,
+      "logps/chosen": -146.64401245117188,
+      "logps/rejected": -134.4973907470703,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": 0.0005743899382650852,
+      "rewards/margins": 0.00039931651554070413,
+      "rewards/rejected": 0.00017507340817246586,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.514229781074239e-06,
+      "logits/chosen": 0.8711406588554382,
+      "logits/rejected": 0.8447128534317017,
+      "logps/chosen": -146.93917846679688,
+      "logps/rejected": -137.2763214111328,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -9.175995364785194e-05,
+      "rewards/margins": 0.00013136237976141274,
+      "rewards/rejected": -0.00022312237706501037,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.286345970517195e-06,
+      "logits/chosen": 0.8513940572738647,
+      "logits/rejected": 0.8943384289741516,
+      "logps/chosen": -156.4779510498047,
+      "logps/rejected": -141.64044189453125,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.41874998807907104,
+      "rewards/chosen": -0.0007812186959199607,
+      "rewards/margins": 0.0002858097432181239,
+      "rewards/rejected": -0.0010670283809304237,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.023067544670082e-06,
+      "logits/chosen": 0.8046412467956543,
+      "logits/rejected": 0.8172038793563843,
+      "logps/chosen": -159.82638549804688,
+      "logps/rejected": -148.19137573242188,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.0005336708854883909,
+      "rewards/margins": 0.000577736587729305,
+      "rewards/rejected": -0.0011114075314253569,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.7296110958116845e-06,
+      "logits/chosen": 0.7820717096328735,
+      "logits/rejected": 0.8074045181274414,
+      "logps/chosen": -149.77316284179688,
+      "logps/rejected": -137.23370361328125,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.00042833946645259857,
+      "rewards/margins": 0.0002858256921172142,
+      "rewards/rejected": -0.0007141652167774737,
+      "step": 100
+    },
+    {
+      "epoch": 1.6,
+      "eval_logits/chosen": 0.8386867046356201,
+      "eval_logits/rejected": 0.8959885835647583,
+      "eval_logps/chosen": -256.5564880371094,
+      "eval_logps/rejected": -233.50169372558594,
+      "eval_loss": 0.0003867279156111181,
+      "eval_rewards/accuracies": 0.4855000078678131,
+      "eval_rewards/chosen": 0.0005771049181930721,
+      "eval_rewards/margins": 0.00021130235109012574,
+      "eval_rewards/rejected": 0.00036580252344720066,
+      "eval_runtime": 508.6715,
+      "eval_samples_per_second": 3.932,
+      "eval_steps_per_second": 0.983,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.4117911628292944e-06,
+      "logits/chosen": 0.8274463415145874,
+      "logits/rejected": 0.7994173765182495,
+      "logps/chosen": -160.32693481445312,
+      "logps/rejected": -144.13430786132812,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.3687500059604645,
+      "rewards/chosen": -0.0019955369643867016,
+      "rewards/margins": -0.0002371647860854864,
+      "rewards/rejected": -0.0017583720618858933,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.075905022087675e-06,
+      "logits/chosen": 0.8538025617599487,
+      "logits/rejected": 0.8362048268318176,
+      "logps/chosen": -144.97744750976562,
+      "logps/rejected": -132.49935913085938,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.0011052186600863934,
+      "rewards/margins": 0.00014151711366139352,
+      "rewards/rejected": -0.0012467356864362955,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.728607913349464e-06,
+      "logits/chosen": 0.8091080784797668,
+      "logits/rejected": 0.7883086800575256,
+      "logps/chosen": -168.44651794433594,
+      "logps/rejected": -154.5172882080078,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.001501282094977796,
+      "rewards/margins": 0.00047290659858845174,
+      "rewards/rejected": -0.001974188955500722,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.376781173017589e-06,
+      "logits/chosen": 0.8410237431526184,
+      "logits/rejected": 0.8125711679458618,
+      "logps/chosen": -135.33348083496094,
+      "logps/rejected": -125.95147705078125,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.518750011920929,
+      "rewards/chosen": -0.0011694638524204493,
+      "rewards/margins": 0.0012481597950682044,
+      "rewards/rejected": -0.002417623531073332,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0273958875043877e-06,
+      "logits/chosen": 0.8500027656555176,
+      "logits/rejected": 0.8616348505020142,
+      "logps/chosen": -163.2034454345703,
+      "logps/rejected": -147.33352661132812,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4312500059604645,
+      "rewards/chosen": -0.0014132513897493482,
+      "rewards/margins": 0.0005158716812729836,
+      "rewards/rejected": -0.0019291229546070099,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.6873747682962393e-06,
+      "logits/chosen": 0.7654728293418884,
+      "logits/rejected": 0.7762084007263184,
+      "logps/chosen": -164.34304809570312,
+      "logps/rejected": -151.01991271972656,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.002124720485880971,
+      "rewards/margins": 0.0006703810067847371,
+      "rewards/rejected": -0.00279510160908103,
+      "step": 160
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.363454985517803e-06,
+      "logits/chosen": 0.8323400616645813,
+      "logits/rejected": 0.8276194334030151,
+      "logps/chosen": -139.4966278076172,
+      "logps/rejected": -126.7676010131836,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.45625001192092896,
+      "rewards/chosen": -0.002051023533567786,
+      "rewards/margins": 0.0008618654683232307,
+      "rewards/rejected": -0.002912889001891017,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.062054677808238e-06,
+      "logits/chosen": 0.8200883865356445,
+      "logits/rejected": 0.8247148394584656,
+      "logps/chosen": -147.3248291015625,
+      "logps/rejected": -131.50941467285156,
+      "loss": 0.0004,
+      "rewards/accuracies": 0.39375001192092896,
+      "rewards/chosen": -0.002400606404989958,
+      "rewards/margins": -0.0002633151598274708,
+      "rewards/rejected": -0.0021372910123318434,
+      "step": 180
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 7.891457834794711e-07,
+      "logits/chosen": 0.7988116145133972,
+      "logits/rejected": 0.7790786027908325,
+      "logps/chosen": -157.28366088867188,
+      "logps/rejected": -148.06373596191406,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.48124998807907104,
+      "rewards/chosen": -0.0013300395803526044,
+      "rewards/margins": 0.0013687892351299524,
+      "rewards/rejected": -0.002698828699067235,
+      "step": 190
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 5.501357126768117e-07,
+      "logits/chosen": 0.8291190266609192,
+      "logits/rejected": 0.8441616296768188,
+      "logps/chosen": -179.22891235351562,
+      "logps/rejected": -165.08668518066406,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.36250001192092896,
+      "rewards/chosen": -0.0026950170285999775,
+      "rewards/margins": 0.0003695812192745507,
+      "rewards/rejected": -0.0030645981896668673,
+      "step": 200
+    },
+    {
+      "epoch": 3.2,
+      "eval_logits/chosen": 0.8411728143692017,
+      "eval_logits/rejected": 0.8983786106109619,
+      "eval_logps/chosen": -256.48114013671875,
+      "eval_logps/rejected": -233.4491729736328,
+      "eval_loss": 0.0003846254840027541,
+      "eval_rewards/accuracies": 0.5099999904632568,
+      "eval_rewards/chosen": 0.0013305767206475139,
+      "eval_rewards/margins": 0.00043944927165284753,
+      "eval_rewards/rejected": 0.0008911274489946663,
+      "eval_runtime": 496.2392,
+      "eval_samples_per_second": 4.03,
+      "eval_steps_per_second": 1.008,
+      "step": 200
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.4976020508682345e-07,
+      "logits/chosen": 0.7520900964736938,
+      "logits/rejected": 0.7521581053733826,
+      "logps/chosen": -142.36843872070312,
+      "logps/rejected": -131.4374542236328,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.0021503984462469816,
+      "rewards/margins": 0.0008300153422169387,
+      "rewards/rejected": -0.0029804136138409376,
+      "step": 210
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.9198949610721273e-07,
+      "logits/chosen": 0.8309981226921082,
+      "logits/rejected": 0.811602771282196,
+      "logps/chosen": -150.01573181152344,
+      "logps/rejected": -136.91067504882812,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -0.00250506354495883,
+      "rewards/margins": 0.0008244045311585069,
+      "rewards/rejected": -0.0033294681925326586,
+      "step": 220
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 7.994965069994143e-08,
+      "logits/chosen": 0.8669425249099731,
+      "logits/rejected": 0.880296528339386,
+      "logps/chosen": -159.811767578125,
+      "logps/rejected": -145.57418823242188,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.0020190321374684572,
+      "rewards/margins": 0.0008607100462540984,
+      "rewards/rejected": -0.002879742067307234,
+      "step": 230
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.5860623616664183e-08,
+      "logits/chosen": 0.7746256589889526,
+      "logits/rejected": 0.7747436761856079,
+      "logps/chosen": -154.1355743408203,
+      "logps/rejected": -141.05926513671875,
+      "loss": 0.0003,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -0.001991902943700552,
+      "rewards/margins": 0.000743478478398174,
+      "rewards/rejected": -0.0027353812474757433,
+      "step": 240
+    },
+    {
+      "epoch": 3.97,
+      "step": 248,
+      "total_flos": 0.0,
+      "train_loss": 0.0003399105843263603,
+      "train_runtime": 3335.538,
+      "train_samples_per_second": 1.199,
+      "train_steps_per_second": 0.074
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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:a8827ef3fb1537110f27310fbc73e39acc9e2fcfd58e1920b08d2ca470268e30
+size 5880