Upload folder using huggingface_hub

checkpoint-80/README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: fblgit/una-cybertron-7b-v2-bf16
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+- PEFT 0.7.0

checkpoint-80/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fblgit/una-cybertron-7b-v2-bf16",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-80/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2557803f5fe369997f541823220b172ec93de264093df53a3fe228260ac2955
+size 167832240

checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33433d265b72ac9e19b22150649aae8554f370a462bb8c7320e9df4ec81d508
+size 335812858

checkpoint-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430cc59dc6008ac325d1e81fc5b21cab448b30491fc94f6668866ca5ad44c8e9
+size 1064

checkpoint-80/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-80/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-80/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-80/trainer_state.json

@@ -0,0 +1,1139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09953343701399689,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "logits/chosen": -2.0463106632232666,
+      "logits/rejected": -1.8486888408660889,
+      "logps/chosen": -311.57489013671875,
+      "logps/rejected": -415.468505859375,
+      "loss": 0.671,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.021808436140418053,
+      "rewards/margins": 0.04626159369945526,
+      "rewards/rejected": -0.06807002425193787,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "logits/chosen": -2.060105562210083,
+      "logits/rejected": -2.106396198272705,
+      "logps/chosen": -220.380615234375,
+      "logps/rejected": -404.501220703125,
+      "loss": 0.6745,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.02021012455224991,
+      "rewards/margins": 0.03883519023656845,
+      "rewards/rejected": -0.05904531478881836,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5e-06,
+      "logits/chosen": -2.239086151123047,
+      "logits/rejected": -2.0575525760650635,
+      "logps/chosen": -163.8677978515625,
+      "logps/rejected": -446.79180908203125,
+      "loss": 0.67,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.024322081357240677,
+      "rewards/margins": 0.04956565052270889,
+      "rewards/rejected": -0.07388772815465927,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "logits/chosen": -2.1058502197265625,
+      "logits/rejected": -2.344322681427002,
+      "logps/chosen": -318.9349670410156,
+      "logps/rejected": -378.9231262207031,
+      "loss": 0.6576,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -0.027724243700504303,
+      "rewards/margins": 0.07309143990278244,
+      "rewards/rejected": -0.10081568360328674,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.287339687347412,
+      "logits/rejected": -2.3221607208251953,
+      "logps/chosen": -221.33163452148438,
+      "logps/rejected": -388.6357421875,
+      "loss": 0.6498,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.03215093910694122,
+      "rewards/margins": 0.09096165001392365,
+      "rewards/rejected": -0.12311258912086487,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3e-06,
+      "logits/chosen": -1.98830246925354,
+      "logits/rejected": -1.9178718328475952,
+      "logps/chosen": -244.0532684326172,
+      "logps/rejected": -373.9111328125,
+      "loss": 0.6395,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.0789945125579834,
+      "rewards/margins": 0.11430712044239044,
+      "rewards/rejected": -0.19330161809921265,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.5000000000000004e-06,
+      "logits/chosen": -2.0385985374450684,
+      "logits/rejected": -1.9476547241210938,
+      "logps/chosen": -347.14227294921875,
+      "logps/rejected": -426.24603271484375,
+      "loss": 0.6148,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -0.0816906988620758,
+      "rewards/margins": 0.1658005714416504,
+      "rewards/rejected": -0.2474912703037262,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "logits/chosen": -1.695872187614441,
+      "logits/rejected": -1.7980302572250366,
+      "logps/chosen": -287.9168395996094,
+      "logps/rejected": -355.14129638671875,
+      "loss": 0.5785,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.07900090515613556,
+      "rewards/margins": 0.25094836950302124,
+      "rewards/rejected": -0.329949289560318,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.5e-06,
+      "logits/chosen": -1.9222339391708374,
+      "logits/rejected": -1.8972643613815308,
+      "logps/chosen": -211.97979736328125,
+      "logps/rejected": -405.848388671875,
+      "loss": 0.5229,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.09827227890491486,
+      "rewards/margins": 0.3891267478466034,
+      "rewards/rejected": -0.48739901185035706,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "logits/chosen": -1.9703621864318848,
+      "logits/rejected": -1.7560880184173584,
+      "logps/chosen": -277.2589416503906,
+      "logps/rejected": -445.6544494628906,
+      "loss": 0.4853,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.1426083892583847,
+      "rewards/margins": 0.4861423373222351,
+      "rewards/rejected": -0.628750741481781,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.500000000000001e-06,
+      "logits/chosen": -2.0542986392974854,
+      "logits/rejected": -2.110658884048462,
+      "logps/chosen": -283.9775390625,
+      "logps/rejected": -394.361572265625,
+      "loss": 0.4476,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.14311671257019043,
+      "rewards/margins": 0.6046640872955322,
+      "rewards/rejected": -0.7477807998657227,
+      "step": 11
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6e-06,
+      "logits/chosen": -2.0650949478149414,
+      "logits/rejected": -2.0736098289489746,
+      "logps/chosen": -235.07675170898438,
+      "logps/rejected": -448.17919921875,
+      "loss": 0.3701,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.23901399970054626,
+      "rewards/margins": 0.9068580269813538,
+      "rewards/rejected": -1.1458721160888672,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.5000000000000004e-06,
+      "logits/chosen": -2.011099100112915,
+      "logits/rejected": -2.106595754623413,
+      "logps/chosen": -289.19970703125,
+      "logps/rejected": -417.64208984375,
+      "loss": 0.3675,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.26357388496398926,
+      "rewards/margins": 0.8955046534538269,
+      "rewards/rejected": -1.159078598022461,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.000000000000001e-06,
+      "logits/chosen": -2.1066994667053223,
+      "logits/rejected": -1.7827305793762207,
+      "logps/chosen": -169.27044677734375,
+      "logps/rejected": -446.7305908203125,
+      "loss": 0.254,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.2715146541595459,
+      "rewards/margins": 1.3259609937667847,
+      "rewards/rejected": -1.5974756479263306,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.5e-06,
+      "logits/chosen": -1.9394950866699219,
+      "logits/rejected": -1.9831421375274658,
+      "logps/chosen": -194.98016357421875,
+      "logps/rejected": -470.9692687988281,
+      "loss": 0.2298,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.4095136225223541,
+      "rewards/margins": 1.628616452217102,
+      "rewards/rejected": -2.038130044937134,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.000000000000001e-06,
+      "logits/chosen": -1.7606948614120483,
+      "logits/rejected": -2.0152878761291504,
+      "logps/chosen": -253.0347900390625,
+      "logps/rejected": -428.3993835449219,
+      "loss": 0.2528,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.581798255443573,
+      "rewards/margins": 1.3869069814682007,
+      "rewards/rejected": -1.968705177307129,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.500000000000002e-06,
+      "logits/chosen": -2.0609982013702393,
+      "logits/rejected": -1.9835376739501953,
+      "logps/chosen": -265.3518371582031,
+      "logps/rejected": -501.8542785644531,
+      "loss": 0.1997,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.681609570980072,
+      "rewards/margins": 2.0102298259735107,
+      "rewards/rejected": -2.6918392181396484,
+      "step": 17
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9e-06,
+      "logits/chosen": -2.117746114730835,
+      "logits/rejected": -2.218081474304199,
+      "logps/chosen": -202.6907501220703,
+      "logps/rejected": -413.13604736328125,
+      "loss": 0.1582,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.6984068751335144,
+      "rewards/margins": 1.8970444202423096,
+      "rewards/rejected": -2.5954513549804688,
+      "step": 18
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.5e-06,
+      "logits/chosen": -2.385519504547119,
+      "logits/rejected": -1.8222811222076416,
+      "logps/chosen": -175.93809509277344,
+      "logps/rejected": -469.17657470703125,
+      "loss": 0.0951,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.7677481174468994,
+      "rewards/margins": 2.7113454341888428,
+      "rewards/rejected": -3.479093551635742,
+      "step": 19
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "logits/chosen": -2.187441349029541,
+      "logits/rejected": -2.1218032836914062,
+      "logps/chosen": -301.7166442871094,
+      "logps/rejected": -490.854736328125,
+      "loss": 0.0944,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.2999629974365234,
+      "rewards/margins": 3.2447361946105957,
+      "rewards/rejected": -4.544699192047119,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.05e-05,
+      "logits/chosen": -1.967098355293274,
+      "logits/rejected": -1.9263262748718262,
+      "logps/chosen": -176.0479278564453,
+      "logps/rejected": -472.8221435546875,
+      "loss": 0.0459,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.8402897119522095,
+      "rewards/margins": 4.1183624267578125,
+      "rewards/rejected": -4.958651542663574,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.1000000000000001e-05,
+      "logits/chosen": -2.188459873199463,
+      "logits/rejected": -2.156071424484253,
+      "logps/chosen": -243.41683959960938,
+      "logps/rejected": -465.08685302734375,
+      "loss": 0.1389,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -1.5002142190933228,
+      "rewards/margins": 4.108778953552246,
+      "rewards/rejected": -5.608993053436279,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.1500000000000002e-05,
+      "logits/chosen": -1.7361280918121338,
+      "logits/rejected": -1.8734406232833862,
+      "logps/chosen": -274.4007568359375,
+      "logps/rejected": -465.7174987792969,
+      "loss": 0.074,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.6840157508850098,
+      "rewards/margins": 4.5255866050720215,
+      "rewards/rejected": -6.209602355957031,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2e-05,
+      "logits/chosen": -1.8966342210769653,
+      "logits/rejected": -1.772972583770752,
+      "logps/chosen": -275.3910217285156,
+      "logps/rejected": -462.07720947265625,
+      "loss": 0.0381,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.017077922821045,
+      "rewards/margins": 4.740576267242432,
+      "rewards/rejected": -6.757654666900635,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.25e-05,
+      "logits/chosen": -2.2573952674865723,
+      "logits/rejected": -1.9883058071136475,
+      "logps/chosen": -172.16043090820312,
+      "logps/rejected": -391.4390563964844,
+      "loss": 0.0666,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.9856681823730469,
+      "rewards/margins": 4.858271598815918,
+      "rewards/rejected": -6.843939781188965,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3000000000000001e-05,
+      "logits/chosen": -2.0475640296936035,
+      "logits/rejected": -1.8690011501312256,
+      "logps/chosen": -184.4323272705078,
+      "logps/rejected": -468.86175537109375,
+      "loss": 0.0805,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -2.08463716506958,
+      "rewards/margins": 6.207521438598633,
+      "rewards/rejected": -8.292158126831055,
+      "step": 26
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3500000000000001e-05,
+      "logits/chosen": -1.9634509086608887,
+      "logits/rejected": -2.260413646697998,
+      "logps/chosen": -398.9476013183594,
+      "logps/rejected": -540.3334350585938,
+      "loss": 0.029,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.3595480918884277,
+      "rewards/margins": 6.726611614227295,
+      "rewards/rejected": -10.086159706115723,
+      "step": 27
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4000000000000001e-05,
+      "logits/chosen": -1.9712620973587036,
+      "logits/rejected": -1.827807068824768,
+      "logps/chosen": -221.26559448242188,
+      "logps/rejected": -483.7889709472656,
+      "loss": 0.0063,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.3635034561157227,
+      "rewards/margins": 7.733745098114014,
+      "rewards/rejected": -10.097248077392578,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.45e-05,
+      "logits/chosen": -1.542866587638855,
+      "logits/rejected": -1.7318823337554932,
+      "logps/chosen": -267.33880615234375,
+      "logps/rejected": -558.8424072265625,
+      "loss": 0.0746,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -3.391514301300049,
+      "rewards/margins": 9.136863708496094,
+      "rewards/rejected": -12.528377532958984,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.5e-05,
+      "logits/chosen": -2.037372589111328,
+      "logits/rejected": -1.8312575817108154,
+      "logps/chosen": -288.1588134765625,
+      "logps/rejected": -670.7269287109375,
+      "loss": 0.0007,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.795253276824951,
+      "rewards/margins": 11.858222961425781,
+      "rewards/rejected": -15.653478622436523,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.55e-05,
+      "logits/chosen": -1.5374680757522583,
+      "logits/rejected": -1.8392678499221802,
+      "logps/chosen": -281.0010070800781,
+      "logps/rejected": -553.43017578125,
+      "loss": 0.0149,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.836461067199707,
+      "rewards/margins": 9.380411148071289,
+      "rewards/rejected": -13.216873168945312,
+      "step": 31
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6000000000000003e-05,
+      "logits/chosen": -2.033914566040039,
+      "logits/rejected": -1.9804089069366455,
+      "logps/chosen": -261.31103515625,
+      "logps/rejected": -545.380126953125,
+      "loss": 0.0123,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.321026802062988,
+      "rewards/margins": 9.96163272857666,
+      "rewards/rejected": -14.282659530639648,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.65e-05,
+      "logits/chosen": -1.652747631072998,
+      "logits/rejected": -1.6527116298675537,
+      "logps/chosen": -250.82638549804688,
+      "logps/rejected": -536.0584106445312,
+      "loss": 0.0017,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.393105506896973,
+      "rewards/margins": 11.006621360778809,
+      "rewards/rejected": -15.399725914001465,
+      "step": 33
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7000000000000003e-05,
+      "logits/chosen": -1.5870184898376465,
+      "logits/rejected": -1.9295532703399658,
+      "logps/chosen": -276.73248291015625,
+      "logps/rejected": -588.6087646484375,
+      "loss": 0.2671,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -5.017908573150635,
+      "rewards/margins": 12.34096908569336,
+      "rewards/rejected": -17.35887908935547,
+      "step": 34
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.75e-05,
+      "logits/chosen": -1.9227735996246338,
+      "logits/rejected": -1.954828143119812,
+      "logps/chosen": -266.1369323730469,
+      "logps/rejected": -550.742919921875,
+      "loss": 0.0035,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.8841400146484375,
+      "rewards/margins": 13.669473648071289,
+      "rewards/rejected": -18.553613662719727,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.8e-05,
+      "logits/chosen": -1.6637210845947266,
+      "logits/rejected": -1.3936012983322144,
+      "logps/chosen": -256.7511901855469,
+      "logps/rejected": -591.1787109375,
+      "loss": 0.0022,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.027996063232422,
+      "rewards/margins": 13.286176681518555,
+      "rewards/rejected": -19.314172744750977,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.85e-05,
+      "logits/chosen": -1.6170068979263306,
+      "logits/rejected": -1.6388572454452515,
+      "logps/chosen": -257.0255126953125,
+      "logps/rejected": -605.7335205078125,
+      "loss": 0.0008,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.929409027099609,
+      "rewards/margins": 14.035564422607422,
+      "rewards/rejected": -19.9649715423584,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9e-05,
+      "logits/chosen": -1.967097520828247,
+      "logits/rejected": -1.778485894203186,
+      "logps/chosen": -239.90533447265625,
+      "logps/rejected": -570.31787109375,
+      "loss": 0.0839,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.8724775314331055,
+      "rewards/margins": 13.892675399780273,
+      "rewards/rejected": -20.765153884887695,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9500000000000003e-05,
+      "logits/chosen": -1.6693722009658813,
+      "logits/rejected": -1.573314905166626,
+      "logps/chosen": -349.86480712890625,
+      "logps/rejected": -702.0185546875,
+      "loss": 0.0008,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -7.373364448547363,
+      "rewards/margins": 15.567668914794922,
+      "rewards/rejected": -22.941036224365234,
+      "step": 39
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "logits/chosen": -1.556606650352478,
+      "logits/rejected": -1.394392967224121,
+      "logps/chosen": -213.81959533691406,
+      "logps/rejected": -637.4287109375,
+      "loss": 0.041,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.418168067932129,
+      "rewards/margins": 17.626686096191406,
+      "rewards/rejected": -22.04485321044922,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.05e-05,
+      "logits/chosen": -1.6436810493469238,
+      "logits/rejected": -1.7172099351882935,
+      "logps/chosen": -304.43438720703125,
+      "logps/rejected": -704.897216796875,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.733709812164307,
+      "rewards/margins": 19.767263412475586,
+      "rewards/rejected": -26.500972747802734,
+      "step": 41
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.1e-05,
+      "logits/chosen": -1.5168399810791016,
+      "logits/rejected": -1.508206844329834,
+      "logps/chosen": -262.28515625,
+      "logps/rejected": -556.9771118164062,
+      "loss": 0.062,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.817533493041992,
+      "rewards/margins": 13.013591766357422,
+      "rewards/rejected": -18.831125259399414,
+      "step": 42
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.15e-05,
+      "logits/chosen": -1.3590738773345947,
+      "logits/rejected": -1.1529805660247803,
+      "logps/chosen": -205.32371520996094,
+      "logps/rejected": -576.4129638671875,
+      "loss": 0.002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.326513290405273,
+      "rewards/margins": 15.988494873046875,
+      "rewards/rejected": -21.315006256103516,
+      "step": 43
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.2000000000000003e-05,
+      "logits/chosen": -1.5084015130996704,
+      "logits/rejected": -1.5834801197052002,
+      "logps/chosen": -332.94580078125,
+      "logps/rejected": -685.3295288085938,
+      "loss": 0.0038,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -7.390817642211914,
+      "rewards/margins": 18.214908599853516,
+      "rewards/rejected": -25.60572624206543,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": -1.4891091585159302,
+      "logits/rejected": -1.5173286199569702,
+      "logps/chosen": -250.24951171875,
+      "logps/rejected": -675.5242309570312,
+      "loss": 0.0026,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.26884126663208,
+      "rewards/margins": 19.75680160522461,
+      "rewards/rejected": -26.025644302368164,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.3000000000000003e-05,
+      "logits/chosen": -1.433956265449524,
+      "logits/rejected": -1.5273690223693848,
+      "logps/chosen": -366.8013000488281,
+      "logps/rejected": -703.315185546875,
+      "loss": 0.0103,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.857599258422852,
+      "rewards/margins": 19.714298248291016,
+      "rewards/rejected": -26.571901321411133,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.35e-05,
+      "logits/chosen": -1.351868987083435,
+      "logits/rejected": -1.2347944974899292,
+      "logps/chosen": -292.37091064453125,
+      "logps/rejected": -687.9886474609375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -7.611140251159668,
+      "rewards/margins": 19.30370330810547,
+      "rewards/rejected": -26.91484260559082,
+      "step": 47
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.4e-05,
+      "logits/chosen": -1.3243939876556396,
+      "logits/rejected": -1.0474777221679688,
+      "logps/chosen": -292.1935729980469,
+      "logps/rejected": -626.897705078125,
+      "loss": 0.0025,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.425950527191162,
+      "rewards/margins": 17.86639404296875,
+      "rewards/rejected": -24.292346954345703,
+      "step": 48
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.45e-05,
+      "logits/chosen": -0.9694186449050903,
+      "logits/rejected": -1.2784701585769653,
+      "logps/chosen": -260.8387756347656,
+      "logps/rejected": -618.62451171875,
+      "loss": 0.1257,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -6.1030497550964355,
+      "rewards/margins": 18.54592514038086,
+      "rewards/rejected": -24.648975372314453,
+      "step": 49
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5e-05,
+      "logits/chosen": -0.9199879765510559,
+      "logits/rejected": -1.2466750144958496,
+      "logps/chosen": -430.0943603515625,
+      "logps/rejected": -720.2520141601562,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -8.701850891113281,
+      "rewards/margins": 16.992839813232422,
+      "rewards/rejected": -25.694692611694336,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5500000000000003e-05,
+      "logits/chosen": -0.9574620127677917,
+      "logits/rejected": -1.1837575435638428,
+      "logps/chosen": -301.4226379394531,
+      "logps/rejected": -568.0577392578125,
+      "loss": 0.0033,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.406881332397461,
+      "rewards/margins": 13.906658172607422,
+      "rewards/rejected": -20.313539505004883,
+      "step": 51
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.6000000000000002e-05,
+      "logits/chosen": -1.3775969743728638,
+      "logits/rejected": -1.1746721267700195,
+      "logps/chosen": -292.12841796875,
+      "logps/rejected": -541.6993408203125,
+      "loss": 0.0143,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.582497596740723,
+      "rewards/margins": 13.31058120727539,
+      "rewards/rejected": -19.893077850341797,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.6500000000000004e-05,
+      "logits/chosen": -1.5340209007263184,
+      "logits/rejected": -1.5800985097885132,
+      "logps/chosen": -274.92852783203125,
+      "logps/rejected": -618.4048461914062,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.103458404541016,
+      "rewards/margins": 16.42413330078125,
+      "rewards/rejected": -22.527591705322266,
+      "step": 53
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.7000000000000002e-05,
+      "logits/chosen": -1.1566357612609863,
+      "logits/rejected": -1.3419249057769775,
+      "logps/chosen": -266.595458984375,
+      "logps/rejected": -609.8141479492188,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.4973931312561035,
+      "rewards/margins": 17.105182647705078,
+      "rewards/rejected": -22.602575302124023,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.7500000000000004e-05,
+      "logits/chosen": -1.1755287647247314,
+      "logits/rejected": -1.436917781829834,
+      "logps/chosen": -293.0464172363281,
+      "logps/rejected": -614.6860961914062,
+      "loss": 0.038,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.360505104064941,
+      "rewards/margins": 17.14010238647461,
+      "rewards/rejected": -23.5006103515625,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.8000000000000003e-05,
+      "logits/chosen": -0.9510018825531006,
+      "logits/rejected": -1.4989765882492065,
+      "logps/chosen": -246.72573852539062,
+      "logps/rejected": -593.3004760742188,
+      "loss": 0.0019,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.071164131164551,
+      "rewards/margins": 16.324851989746094,
+      "rewards/rejected": -21.396015167236328,
+      "step": 56
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.8499999999999998e-05,
+      "logits/chosen": -0.8883547782897949,
+      "logits/rejected": -0.8475340604782104,
+      "logps/chosen": -284.69122314453125,
+      "logps/rejected": -582.0223999023438,
+      "loss": 0.092,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.555781364440918,
+      "rewards/margins": 15.147626876831055,
+      "rewards/rejected": -20.703407287597656,
+      "step": 57
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9e-05,
+      "logits/chosen": -1.420696496963501,
+      "logits/rejected": -1.3382985591888428,
+      "logps/chosen": -223.16297912597656,
+      "logps/rejected": -681.352294921875,
+      "loss": 0.0027,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.9901018142700195,
+      "rewards/margins": 20.429107666015625,
+      "rewards/rejected": -25.419208526611328,
+      "step": 58
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.95e-05,
+      "logits/chosen": -1.037627100944519,
+      "logits/rejected": -1.745126485824585,
+      "logps/chosen": -249.64974975585938,
+      "logps/rejected": -605.685546875,
+      "loss": 0.097,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -5.2863945960998535,
+      "rewards/margins": 16.568225860595703,
+      "rewards/rejected": -21.8546199798584,
+      "step": 59
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3e-05,
+      "logits/chosen": -1.1528346538543701,
+      "logits/rejected": -1.5133743286132812,
+      "logps/chosen": -319.42352294921875,
+      "logps/rejected": -627.826171875,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.5534515380859375,
+      "rewards/margins": 16.326492309570312,
+      "rewards/rejected": -21.87994384765625,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.05e-05,
+      "logits/chosen": -1.4599294662475586,
+      "logits/rejected": -1.4529486894607544,
+      "logps/chosen": -292.13299560546875,
+      "logps/rejected": -663.6395263671875,
+      "loss": 0.0036,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.249754905700684,
+      "rewards/margins": 16.525672912597656,
+      "rewards/rejected": -21.775428771972656,
+      "step": 61
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.1e-05,
+      "logits/chosen": -1.3739594221115112,
+      "logits/rejected": -1.441535472869873,
+      "logps/chosen": -361.3265380859375,
+      "logps/rejected": -623.9736938476562,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.781492233276367,
+      "rewards/margins": 16.213455200195312,
+      "rewards/rejected": -20.99494743347168,
+      "step": 62
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.15e-05,
+      "logits/chosen": -1.0977773666381836,
+      "logits/rejected": -1.2894166707992554,
+      "logps/chosen": -272.4936828613281,
+      "logps/rejected": -633.6181640625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.058845520019531,
+      "rewards/margins": 18.464832305908203,
+      "rewards/rejected": -23.523677825927734,
+      "step": 63
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.2000000000000005e-05,
+      "logits/chosen": -1.8300187587738037,
+      "logits/rejected": -1.3356730937957764,
+      "logps/chosen": -311.8466796875,
+      "logps/rejected": -677.257568359375,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.877348899841309,
+      "rewards/margins": 16.247228622436523,
+      "rewards/rejected": -22.124576568603516,
+      "step": 64
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.2500000000000004e-05,
+      "logits/chosen": -1.6267454624176025,
+      "logits/rejected": -1.1310009956359863,
+      "logps/chosen": -358.5579833984375,
+      "logps/rejected": -641.7317504882812,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.5671796798706055,
+      "rewards/margins": 15.705550193786621,
+      "rewards/rejected": -21.27273178100586,
+      "step": 65
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.3e-05,
+      "logits/chosen": -1.8895033597946167,
+      "logits/rejected": -1.6860744953155518,
+      "logps/chosen": -486.3850402832031,
+      "logps/rejected": -664.045166015625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.0797834396362305,
+      "rewards/margins": 13.979126930236816,
+      "rewards/rejected": -19.058910369873047,
+      "step": 66
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.35e-05,
+      "logits/chosen": -1.836645483970642,
+      "logits/rejected": -1.4774869680404663,
+      "logps/chosen": -261.5281982421875,
+      "logps/rejected": -621.8162841796875,
+      "loss": 0.0011,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.790907382965088,
+      "rewards/margins": 14.66439437866211,
+      "rewards/rejected": -19.45530128479004,
+      "step": 67
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.4000000000000007e-05,
+      "logits/chosen": -1.4897315502166748,
+      "logits/rejected": -1.2426286935806274,
+      "logps/chosen": -225.94337463378906,
+      "logps/rejected": -547.6304321289062,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.037389755249023,
+      "rewards/margins": 13.804460525512695,
+      "rewards/rejected": -17.84185028076172,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.45e-05,
+      "logits/chosen": -1.3410481214523315,
+      "logits/rejected": -1.2696239948272705,
+      "logps/chosen": -220.23153686523438,
+      "logps/rejected": -545.1270751953125,
+      "loss": 0.0035,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.0619893074035645,
+      "rewards/margins": 14.104720115661621,
+      "rewards/rejected": -18.166709899902344,
+      "step": 69
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.5e-05,
+      "logits/chosen": -1.1692075729370117,
+      "logits/rejected": -1.4098597764968872,
+      "logps/chosen": -291.9318542480469,
+      "logps/rejected": -606.8259887695312,
+      "loss": 0.037,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.749131679534912,
+      "rewards/margins": 13.3434476852417,
+      "rewards/rejected": -18.09257698059082,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.55e-05,
+      "logits/chosen": -1.291015386581421,
+      "logits/rejected": -1.0744752883911133,
+      "logps/chosen": -235.30746459960938,
+      "logps/rejected": -571.0240478515625,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.615610122680664,
+      "rewards/margins": 14.394880294799805,
+      "rewards/rejected": -18.01049041748047,
+      "step": 71
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.6e-05,
+      "logits/chosen": -1.3118032217025757,
+      "logits/rejected": -1.3245186805725098,
+      "logps/chosen": -278.8104248046875,
+      "logps/rejected": -621.2532958984375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.277045249938965,
+      "rewards/margins": 17.554424285888672,
+      "rewards/rejected": -21.831466674804688,
+      "step": 72
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.65e-05,
+      "logits/chosen": -1.5896751880645752,
+      "logits/rejected": -1.3609411716461182,
+      "logps/chosen": -243.6151123046875,
+      "logps/rejected": -572.5302124023438,
+      "loss": 0.0006,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.514758110046387,
+      "rewards/margins": 12.668429374694824,
+      "rewards/rejected": -17.183185577392578,
+      "step": 73
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.7e-05,
+      "logits/chosen": -1.431384801864624,
+      "logits/rejected": -1.5531063079833984,
+      "logps/chosen": -306.5356750488281,
+      "logps/rejected": -600.71484375,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.694637298583984,
+      "rewards/margins": 18.718229293823242,
+      "rewards/rejected": -23.412864685058594,
+      "step": 74
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.7500000000000003e-05,
+      "logits/chosen": -1.557645559310913,
+      "logits/rejected": -1.5208816528320312,
+      "logps/chosen": -258.01324462890625,
+      "logps/rejected": -619.49462890625,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.0902862548828125,
+      "rewards/margins": 15.939676284790039,
+      "rewards/rejected": -21.029964447021484,
+      "step": 75
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.8e-05,
+      "logits/chosen": -1.0553147792816162,
+      "logits/rejected": -1.5524070262908936,
+      "logps/chosen": -309.97412109375,
+      "logps/rejected": -524.318603515625,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.439201354980469,
+      "rewards/margins": 13.217429161071777,
+      "rewards/rejected": -17.656631469726562,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.85e-05,
+      "logits/chosen": -1.3808860778808594,
+      "logits/rejected": -1.490052342414856,
+      "logps/chosen": -249.54974365234375,
+      "logps/rejected": -647.080078125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.671748161315918,
+      "rewards/margins": 17.54851531982422,
+      "rewards/rejected": -23.220260620117188,
+      "step": 77
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.9000000000000006e-05,
+      "logits/chosen": -1.6017792224884033,
+      "logits/rejected": -1.437800407409668,
+      "logps/chosen": -270.47894287109375,
+      "logps/rejected": -523.1994018554688,
+      "loss": 0.0107,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -5.677766799926758,
+      "rewards/margins": 13.664579391479492,
+      "rewards/rejected": -19.34234619140625,
+      "step": 78
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.9500000000000005e-05,
+      "logits/chosen": -1.7644150257110596,
+      "logits/rejected": -1.1649854183197021,
+      "logps/chosen": -352.513671875,
+      "logps/rejected": -660.660888671875,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.161036968231201,
+      "rewards/margins": 15.742412567138672,
+      "rewards/rejected": -21.90345001220703,
+      "step": 79
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4e-05,
+      "logits/chosen": -1.7110097408294678,
+      "logits/rejected": -1.4986464977264404,
+      "logps/chosen": -285.781005859375,
+      "logps/rejected": -601.8524780273438,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.4479594230651855,
+      "rewards/margins": 17.196250915527344,
+      "rewards/rejected": -23.644210815429688,
+      "step": 80
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_train_epochs": 1,
+  "save_steps": 40,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52ed983d3e7f22985f201323e2d10cf6955e6d68f6bfb834c007eae1cae02b3
+size 4600