Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: beomi/open-llama-2-ko-7b
+---
+
+# 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]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "beomi/open-llama-2-ko-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.02,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "out_proj",
+    "q_proj",
+    "wte",
+    "k_proj",
+    "fc_in",
+    "fc_out"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1aad1aaf31ee82706f47f538b63540434436bc9d1a1045494b75d44951b2dd1
+size 889253080

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabc9990b8d5ac3c0c9754a8cea888c838ebb5143ecbbd05999542e38eea4109
+size 1778657210

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f64484496a04faf7f7a78c9cfef06128f9d42928999f482901af6671faaa1f1
+size 14448

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9046d6004dffe07e90077e8b75d58421cef3627020e51a03179d6d7284c29f52
+size 14448

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f2c90f58ca9b0136ab1567ecf12979bc68ad06347bdb3e669034173d05e902
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e56904744ef55ee9f6fc9348e26df0658594250c32308ed65984d8f253b8a09
+size 780090

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "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
+    },
+    "46331": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46332": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46333": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46334": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46335": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,408 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.549186676994578,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.061967467079783116,
+      "grad_norm": 0.31712573766708374,
+      "learning_rate": 0.0001,
+      "logits/chosen": -2.0377116203308105,
+      "logits/rejected": -1.4957941770553589,
+      "logps/chosen": -366.8505859375,
+      "logps/rejected": -216.56210327148438,
+      "loss": 0.7399,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.4758438169956207,
+      "rewards/margins": 0.7039788961410522,
+      "rewards/rejected": -0.2281351387500763,
+      "step": 20
+    },
+    {
+      "epoch": 0.12393493415956623,
+      "grad_norm": 0.6672604084014893,
+      "learning_rate": 0.0002,
+      "logits/chosen": -2.0871264934539795,
+      "logits/rejected": -1.5913448333740234,
+      "logps/chosen": -343.7679443359375,
+      "logps/rejected": -225.5177764892578,
+      "loss": 0.1009,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 1.8198397159576416,
+      "rewards/margins": 4.43993616104126,
+      "rewards/rejected": -2.620096206665039,
+      "step": 40
+    },
+    {
+      "epoch": 0.18590240123934934,
+      "grad_norm": 0.05973530188202858,
+      "learning_rate": 0.0003,
+      "logits/chosen": -2.024085521697998,
+      "logits/rejected": -1.5500152111053467,
+      "logps/chosen": -337.0369873046875,
+      "logps/rejected": -244.14907836914062,
+      "loss": 0.0377,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": 1.434114694595337,
+      "rewards/margins": 6.376841068267822,
+      "rewards/rejected": -4.9427266120910645,
+      "step": 60
+    },
+    {
+      "epoch": 0.24786986831913246,
+      "grad_norm": 0.2159392535686493,
+      "learning_rate": 0.0004,
+      "logits/chosen": -1.8774925470352173,
+      "logits/rejected": -1.367897868156433,
+      "logps/chosen": -346.57025146484375,
+      "logps/rejected": -268.8457946777344,
+      "loss": 0.0185,
+      "rewards/accuracies": 0.996874988079071,
+      "rewards/chosen": 0.6674507260322571,
+      "rewards/margins": 8.490525245666504,
+      "rewards/rejected": -7.823073387145996,
+      "step": 80
+    },
+    {
+      "epoch": 0.30983733539891556,
+      "grad_norm": 0.1853674203157425,
+      "learning_rate": 0.0005,
+      "logits/chosen": -1.7931022644042969,
+      "logits/rejected": -1.3545161485671997,
+      "logps/chosen": -341.8374938964844,
+      "logps/rejected": -290.44158935546875,
+      "loss": 0.0162,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -0.9960247278213501,
+      "rewards/margins": 8.982015609741211,
+      "rewards/rejected": -9.97804069519043,
+      "step": 100
+    },
+    {
+      "epoch": 0.3718048024786987,
+      "grad_norm": 0.07802274823188782,
+      "learning_rate": 0.0004969220851487844,
+      "logits/chosen": -2.0918784141540527,
+      "logits/rejected": -1.7004894018173218,
+      "logps/chosen": -374.20416259765625,
+      "logps/rejected": -319.31304931640625,
+      "loss": 0.0243,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -1.1373934745788574,
+      "rewards/margins": 9.278127670288086,
+      "rewards/rejected": -10.415521621704102,
+      "step": 120
+    },
+    {
+      "epoch": 0.4337722695584818,
+      "grad_norm": 0.014924481511116028,
+      "learning_rate": 0.0004877641290737884,
+      "logits/chosen": -2.199770450592041,
+      "logits/rejected": -1.7312860488891602,
+      "logps/chosen": -357.83184814453125,
+      "logps/rejected": -289.49066162109375,
+      "loss": 0.0138,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.0910751074552536,
+      "rewards/margins": 8.973724365234375,
+      "rewards/rejected": -8.882649421691895,
+      "step": 140
+    },
+    {
+      "epoch": 0.4957397366382649,
+      "grad_norm": 0.08808302134275436,
+      "learning_rate": 0.00047275163104709196,
+      "logits/chosen": -2.0726726055145264,
+      "logits/rejected": -1.5627789497375488,
+      "logps/chosen": -360.4253845214844,
+      "logps/rejected": -310.8641357421875,
+      "loss": 0.0104,
+      "rewards/accuracies": 0.996874988079071,
+      "rewards/chosen": -0.6570650339126587,
+      "rewards/margins": 10.160908699035645,
+      "rewards/rejected": -10.817973136901855,
+      "step": 160
+    },
+    {
+      "epoch": 0.557707203718048,
+      "grad_norm": 0.15174007415771484,
+      "learning_rate": 0.0004522542485937369,
+      "logits/chosen": -1.987160086631775,
+      "logits/rejected": -1.4582111835479736,
+      "logps/chosen": -353.457275390625,
+      "logps/rejected": -307.9656677246094,
+      "loss": 0.014,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -0.5743726491928101,
+      "rewards/margins": 10.448052406311035,
+      "rewards/rejected": -11.022424697875977,
+      "step": 180
+    },
+    {
+      "epoch": 0.6196746707978311,
+      "grad_norm": 0.671403169631958,
+      "learning_rate": 0.00042677669529663686,
+      "logits/chosen": -1.911975622177124,
+      "logits/rejected": -1.3982415199279785,
+      "logps/chosen": -375.1275634765625,
+      "logps/rejected": -337.18798828125,
+      "loss": 0.0157,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -1.584790825843811,
+      "rewards/margins": 10.48969841003418,
+      "rewards/rejected": -12.074487686157227,
+      "step": 200
+    },
+    {
+      "epoch": 0.6816421378776143,
+      "grad_norm": 0.004173076245933771,
+      "learning_rate": 0.0003969463130731183,
+      "logits/chosen": -1.8694168329238892,
+      "logits/rejected": -1.2515356540679932,
+      "logps/chosen": -371.6986389160156,
+      "logps/rejected": -321.53704833984375,
+      "loss": 0.0113,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -1.3206509351730347,
+      "rewards/margins": 10.872579574584961,
+      "rewards/rejected": -12.193229675292969,
+      "step": 220
+    },
+    {
+      "epoch": 0.7436096049573974,
+      "grad_norm": 0.003299139440059662,
+      "learning_rate": 0.00036349762493488667,
+      "logits/chosen": -1.8045600652694702,
+      "logits/rejected": -1.0531251430511475,
+      "logps/chosen": -363.6612243652344,
+      "logps/rejected": -331.32403564453125,
+      "loss": 0.0051,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.075836181640625,
+      "rewards/margins": 11.123804092407227,
+      "rewards/rejected": -13.199640274047852,
+      "step": 240
+    },
+    {
+      "epoch": 0.8055770720371804,
+      "grad_norm": 0.009364907629787922,
+      "learning_rate": 0.00032725424859373687,
+      "logits/chosen": -1.8670756816864014,
+      "logits/rejected": -1.1788039207458496,
+      "logps/chosen": -372.3548889160156,
+      "logps/rejected": -366.14385986328125,
+      "loss": 0.0093,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -2.1455836296081543,
+      "rewards/margins": 12.034472465515137,
+      "rewards/rejected": -14.180055618286133,
+      "step": 260
+    },
+    {
+      "epoch": 0.8675445391169636,
+      "grad_norm": 0.0019821953028440475,
+      "learning_rate": 0.00028910861626005774,
+      "logits/chosen": -1.9058361053466797,
+      "logits/rejected": -1.2149780988693237,
+      "logps/chosen": -367.235107421875,
+      "logps/rejected": -340.05230712890625,
+      "loss": 0.006,
+      "rewards/accuracies": 0.996874988079071,
+      "rewards/chosen": -2.0556015968322754,
+      "rewards/margins": 11.500048637390137,
+      "rewards/rejected": -13.55565071105957,
+      "step": 280
+    },
+    {
+      "epoch": 0.9295120061967467,
+      "grad_norm": 0.006883636582642794,
+      "learning_rate": 0.00025,
+      "logits/chosen": -1.791246771812439,
+      "logits/rejected": -1.0243983268737793,
+      "logps/chosen": -392.791015625,
+      "logps/rejected": -365.2568359375,
+      "loss": 0.0058,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -3.8660073280334473,
+      "rewards/margins": 13.002245903015137,
+      "rewards/rejected": -16.86825180053711,
+      "step": 300
+    },
+    {
+      "epoch": 0.9914794732765299,
+      "grad_norm": 0.0022304155863821507,
+      "learning_rate": 0.00021089138373994224,
+      "logits/chosen": -1.8826805353164673,
+      "logits/rejected": -1.1826245784759521,
+      "logps/chosen": -379.79266357421875,
+      "logps/rejected": -342.39312744140625,
+      "loss": 0.0053,
+      "rewards/accuracies": 0.996874988079071,
+      "rewards/chosen": -2.450031280517578,
+      "rewards/margins": 12.384546279907227,
+      "rewards/rejected": -14.834577560424805,
+      "step": 320
+    },
+    {
+      "epoch": 1.053446940356313,
+      "grad_norm": 0.021027542650699615,
+      "learning_rate": 0.00017274575140626317,
+      "logits/chosen": -1.9100282192230225,
+      "logits/rejected": -1.1825989484786987,
+      "logps/chosen": -393.48309326171875,
+      "logps/rejected": -363.25396728515625,
+      "loss": 0.0078,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.6979461908340454,
+      "rewards/margins": 12.675543785095215,
+      "rewards/rejected": -14.373491287231445,
+      "step": 340
+    },
+    {
+      "epoch": 1.115414407436096,
+      "grad_norm": 0.0013823028421029449,
+      "learning_rate": 0.00013650237506511331,
+      "logits/chosen": -1.9101250171661377,
+      "logits/rejected": -1.1503610610961914,
+      "logps/chosen": -370.9356689453125,
+      "logps/rejected": -333.2190856933594,
+      "loss": 0.0031,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -1.6975269317626953,
+      "rewards/margins": 12.453495025634766,
+      "rewards/rejected": -14.151021957397461,
+      "step": 360
+    },
+    {
+      "epoch": 1.1773818745158793,
+      "grad_norm": 0.0010998768266290426,
+      "learning_rate": 0.00010305368692688174,
+      "logits/chosen": -1.9123481512069702,
+      "logits/rejected": -1.2217817306518555,
+      "logps/chosen": -382.7933654785156,
+      "logps/rejected": -355.1229248046875,
+      "loss": 0.0032,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.9995158910751343,
+      "rewards/margins": 12.895052909851074,
+      "rewards/rejected": -14.894567489624023,
+      "step": 380
+    },
+    {
+      "epoch": 1.2393493415956622,
+      "grad_norm": 0.00032321063918061554,
+      "learning_rate": 7.322330470336314e-05,
+      "logits/chosen": -1.904104471206665,
+      "logits/rejected": -1.1937545537948608,
+      "logps/chosen": -379.06524658203125,
+      "logps/rejected": -346.93865966796875,
+      "loss": 0.0038,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -1.5791075229644775,
+      "rewards/margins": 13.05359935760498,
+      "rewards/rejected": -14.632705688476562,
+      "step": 400
+    },
+    {
+      "epoch": 1.3013168086754454,
+      "grad_norm": 0.04171500727534294,
+      "learning_rate": 4.7745751406263163e-05,
+      "logits/chosen": -1.8675615787506104,
+      "logits/rejected": -1.1352770328521729,
+      "logps/chosen": -372.1733093261719,
+      "logps/rejected": -350.90399169921875,
+      "loss": 0.0032,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.7773971557617188,
+      "rewards/margins": 13.206622123718262,
+      "rewards/rejected": -14.984021186828613,
+      "step": 420
+    },
+    {
+      "epoch": 1.3632842757552286,
+      "grad_norm": 0.010930106975138187,
+      "learning_rate": 2.7248368952908055e-05,
+      "logits/chosen": -1.8420419692993164,
+      "logits/rejected": -1.1195908784866333,
+      "logps/chosen": -380.8678894042969,
+      "logps/rejected": -368.0999755859375,
+      "loss": 0.0007,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.5592141151428223,
+      "rewards/margins": 13.297220230102539,
+      "rewards/rejected": -15.85643196105957,
+      "step": 440
+    },
+    {
+      "epoch": 1.4252517428350115,
+      "grad_norm": 0.004741205833852291,
+      "learning_rate": 1.2235870926211617e-05,
+      "logits/chosen": -1.8401530981063843,
+      "logits/rejected": -1.1240848302841187,
+      "logps/chosen": -372.3128967285156,
+      "logps/rejected": -352.5906982421875,
+      "loss": 0.0017,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.5608876943588257,
+      "rewards/margins": 13.396890640258789,
+      "rewards/rejected": -14.957778930664062,
+      "step": 460
+    },
+    {
+      "epoch": 1.4872192099147947,
+      "grad_norm": 0.010726602748036385,
+      "learning_rate": 3.077914851215585e-06,
+      "logits/chosen": -1.8262317180633545,
+      "logits/rejected": -1.0366793870925903,
+      "logps/chosen": -390.6006774902344,
+      "logps/rejected": -352.1526794433594,
+      "loss": 0.0053,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -2.158936023712158,
+      "rewards/margins": 13.084844589233398,
+      "rewards/rejected": -15.243780136108398,
+      "step": 480
+    },
+    {
+      "epoch": 1.549186676994578,
+      "grad_norm": 0.00336117553524673,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.8495571613311768,
+      "logits/rejected": -1.1169774532318115,
+      "logps/chosen": -371.83416748046875,
+      "logps/rejected": -368.6435546875,
+      "loss": 0.0048,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -2.3796725273132324,
+      "rewards/margins": 13.638076782226562,
+      "rewards/rejected": -16.017749786376953,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee653874ab7c4bec8be5b2e5af4b91ddeaaac464033e52177157e5e431c97ee8
+size 5624