Upload folder using huggingface_hub

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.10.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 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": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7195143b0e667ffbf4bc130cd7c80a09de58ba6972b6b0b3a98fedb41b49af
+size 167832240

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bbd80eb4dfed014ed8b9ab305752962c4b4199f3b813bf9ad222bceae4086c
+size 84575956

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c0a7bb5c807ad5bc1c4dff28401d8ba88a8d5d80ef889d2be2ca17beb56b13
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad0f1f2e7b55785a1593e27bff66a57496d0f22101944415c8a8dca31514181
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "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": [],
+  "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": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,761 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5333333333333333,
+  "eval_steps": 5,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 11.568901062011719,
+      "learning_rate": 4e-06,
+      "log_odds_chosen": -0.04809989407658577,
+      "log_odds_ratio": -0.7309754490852356,
+      "logits/chosen": -2.8434011936187744,
+      "logits/rejected": -2.879807472229004,
+      "logps/chosen": -1.3107571601867676,
+      "logps/rejected": -1.2733912467956543,
+      "loss": 2.9218,
+      "nll_loss": 2.8486790657043457,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.13107571005821228,
+      "rewards/margins": -0.003736583050340414,
+      "rewards/rejected": -0.12733913958072662,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "eval_log_odds_chosen": -0.03959529474377632,
+      "eval_log_odds_ratio": -0.7268435955047607,
+      "eval_logits/chosen": -2.8285341262817383,
+      "eval_logits/rejected": -2.8396682739257812,
+      "eval_logps/chosen": -1.3169336318969727,
+      "eval_logps/rejected": -1.2877413034439087,
+      "eval_loss": 2.917881965637207,
+      "eval_nll_loss": 2.8451976776123047,
+      "eval_rewards/accuracies": 0.4560000002384186,
+      "eval_rewards/chosen": -0.13169336318969727,
+      "eval_rewards/margins": -0.0029192266520112753,
+      "eval_rewards/rejected": -0.12877413630485535,
+      "eval_runtime": 1022.3754,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.245,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 11.521967887878418,
+      "learning_rate": 8e-06,
+      "log_odds_chosen": -0.007230323739349842,
+      "log_odds_ratio": -0.7128439545631409,
+      "logits/chosen": -2.8024983406066895,
+      "logits/rejected": -2.807565212249756,
+      "logps/chosen": -1.3020203113555908,
+      "logps/rejected": -1.2930128574371338,
+      "loss": 2.8904,
+      "nll_loss": 2.819147825241089,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.1302020400762558,
+      "rewards/margins": -0.00090073945466429,
+      "rewards/rejected": -0.1293012797832489,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "eval_log_odds_chosen": -0.034889113157987595,
+      "eval_log_odds_ratio": -0.7245000004768372,
+      "eval_logits/chosen": -2.8870224952697754,
+      "eval_logits/rejected": -2.8951852321624756,
+      "eval_logps/chosen": -1.2974005937576294,
+      "eval_logps/rejected": -1.271844506263733,
+      "eval_loss": 2.572023391723633,
+      "eval_nll_loss": 2.499573230743408,
+      "eval_rewards/accuracies": 0.4620000123977661,
+      "eval_rewards/chosen": -0.12974008917808533,
+      "eval_rewards/margins": -0.00255563179962337,
+      "eval_rewards/rejected": -0.1271844357252121,
+      "eval_runtime": 1022.4911,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.245,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.9545536041259766,
+      "learning_rate": 7.555555555555555e-06,
+      "log_odds_chosen": -0.004089765250682831,
+      "log_odds_ratio": -0.7142491340637207,
+      "logits/chosen": -2.9420180320739746,
+      "logits/rejected": -2.9477128982543945,
+      "logps/chosen": -1.2463443279266357,
+      "logps/rejected": -1.2475553750991821,
+      "loss": 2.3041,
+      "nll_loss": 2.232625961303711,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.12463442981243134,
+      "rewards/margins": 0.00012110620446037501,
+      "rewards/rejected": -0.12475553900003433,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "eval_log_odds_chosen": -0.027417659759521484,
+      "eval_log_odds_ratio": -0.7208431363105774,
+      "eval_logits/chosen": -2.9438834190368652,
+      "eval_logits/rejected": -2.949639081954956,
+      "eval_logps/chosen": -1.2658034563064575,
+      "eval_logps/rejected": -1.2459032535552979,
+      "eval_loss": 2.15436053276062,
+      "eval_nll_loss": 2.0822763442993164,
+      "eval_rewards/accuracies": 0.4959999918937683,
+      "eval_rewards/chosen": -0.1265803724527359,
+      "eval_rewards/margins": -0.0019900340121239424,
+      "eval_rewards/rejected": -0.12459032237529755,
+      "eval_runtime": 1022.5816,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 15
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.3092970848083496,
+      "learning_rate": 7.11111111111111e-06,
+      "log_odds_chosen": -0.05510986968874931,
+      "log_odds_ratio": -0.733123779296875,
+      "logits/chosen": -2.956840753555298,
+      "logits/rejected": -2.9664785861968994,
+      "logps/chosen": -1.2388333082199097,
+      "logps/rejected": -1.1989364624023438,
+      "loss": 2.1002,
+      "nll_loss": 2.0268614292144775,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.12388332188129425,
+      "rewards/margins": -0.003989681135863066,
+      "rewards/rejected": -0.1198936477303505,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "eval_log_odds_chosen": -0.017652124166488647,
+      "eval_log_odds_ratio": -0.7160712480545044,
+      "eval_logits/chosen": -2.950247287750244,
+      "eval_logits/rejected": -2.956831216812134,
+      "eval_logps/chosen": -1.2254964113235474,
+      "eval_logps/rejected": -1.212648868560791,
+      "eval_loss": 2.0004026889801025,
+      "eval_nll_loss": 1.9287954568862915,
+      "eval_rewards/accuracies": 0.5139999985694885,
+      "eval_rewards/chosen": -0.12254965305328369,
+      "eval_rewards/margins": -0.001284759840928018,
+      "eval_rewards/rejected": -0.12126488238573074,
+      "eval_runtime": 1022.5746,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.386775255203247,
+      "learning_rate": 6.666666666666667e-06,
+      "log_odds_chosen": -0.022222867235541344,
+      "log_odds_ratio": -0.7165368795394897,
+      "logits/chosen": -2.9471981525421143,
+      "logits/rejected": -2.9485559463500977,
+      "logps/chosen": -1.1919796466827393,
+      "logps/rejected": -1.1759862899780273,
+      "loss": 1.9579,
+      "nll_loss": 1.8862320184707642,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.11919797956943512,
+      "rewards/margins": -0.001599342213012278,
+      "rewards/rejected": -0.11759863048791885,
+      "step": 25
+    },
+    {
+      "epoch": 0.13,
+      "eval_log_odds_chosen": -0.004669802729040384,
+      "eval_log_odds_ratio": -0.7097506523132324,
+      "eval_logits/chosen": -2.93721604347229,
+      "eval_logits/rejected": -2.9449150562286377,
+      "eval_logps/chosen": -1.1749383211135864,
+      "eval_logps/rejected": -1.1712193489074707,
+      "eval_loss": 1.9110203981399536,
+      "eval_nll_loss": 1.8400453329086304,
+      "eval_rewards/accuracies": 0.5379999876022339,
+      "eval_rewards/chosen": -0.11749383807182312,
+      "eval_rewards/margins": -0.00037189823342487216,
+      "eval_rewards/rejected": -0.11712193489074707,
+      "eval_runtime": 1022.6406,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1365916728973389,
+      "learning_rate": 6.222222222222222e-06,
+      "log_odds_chosen": 0.007038115058094263,
+      "log_odds_ratio": -0.706188440322876,
+      "logits/chosen": -2.932509660720825,
+      "logits/rejected": -2.9490396976470947,
+      "logps/chosen": -1.1644437313079834,
+      "logps/rejected": -1.1744678020477295,
+      "loss": 1.8475,
+      "nll_loss": 1.776898741722107,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.11644438654184341,
+      "rewards/margins": 0.0010024005314335227,
+      "rewards/rejected": -0.11744678020477295,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "eval_log_odds_chosen": 0.008890592493116856,
+      "eval_log_odds_ratio": -0.7029520273208618,
+      "eval_logits/chosen": -2.928407669067383,
+      "eval_logits/rejected": -2.9365015029907227,
+      "eval_logps/chosen": -1.12498140335083,
+      "eval_logps/rejected": -1.1307774782180786,
+      "eval_loss": 1.831018328666687,
+      "eval_nll_loss": 1.7607231140136719,
+      "eval_rewards/accuracies": 0.5580000281333923,
+      "eval_rewards/chosen": -0.11249814182519913,
+      "eval_rewards/margins": 0.0005796164623461664,
+      "eval_rewards/rejected": -0.11307775229215622,
+      "eval_runtime": 1022.5768,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2610535621643066,
+      "learning_rate": 5.777777777777777e-06,
+      "log_odds_chosen": -0.00892117340117693,
+      "log_odds_ratio": -0.7147808074951172,
+      "logits/chosen": -2.920056104660034,
+      "logits/rejected": -2.925736665725708,
+      "logps/chosen": -1.0991065502166748,
+      "logps/rejected": -1.0894601345062256,
+      "loss": 1.7514,
+      "nll_loss": 1.6798721551895142,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.10991065204143524,
+      "rewards/margins": -0.0009646398248150945,
+      "rewards/rejected": -0.10894601047039032,
+      "step": 35
+    },
+    {
+      "epoch": 0.19,
+      "eval_log_odds_chosen": 0.023294491693377495,
+      "eval_log_odds_ratio": -0.6957657933235168,
+      "eval_logits/chosen": -2.9222519397735596,
+      "eval_logits/rejected": -2.9305875301361084,
+      "eval_logps/chosen": -1.0795469284057617,
+      "eval_logps/rejected": -1.094985008239746,
+      "eval_loss": 1.7491860389709473,
+      "eval_nll_loss": 1.6796095371246338,
+      "eval_rewards/accuracies": 0.5659999847412109,
+      "eval_rewards/chosen": -0.10795468837022781,
+      "eval_rewards/margins": 0.0015438096597790718,
+      "eval_rewards/rejected": -0.10949849337339401,
+      "eval_runtime": 1022.5375,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 35
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.0528180599212646,
+      "learning_rate": 5.333333333333333e-06,
+      "log_odds_chosen": 0.0462532714009285,
+      "log_odds_ratio": -0.6852200031280518,
+      "logits/chosen": -2.9107460975646973,
+      "logits/rejected": -2.9340782165527344,
+      "logps/chosen": -1.0957037210464478,
+      "logps/rejected": -1.1278812885284424,
+      "loss": 1.6771,
+      "nll_loss": 1.608576774597168,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.10957036167383194,
+      "rewards/margins": 0.0032177655957639217,
+      "rewards/rejected": -0.1127881407737732,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "eval_log_odds_chosen": 0.03804260119795799,
+      "eval_log_odds_ratio": -0.6886653900146484,
+      "eval_logits/chosen": -2.9180362224578857,
+      "eval_logits/rejected": -2.9264867305755615,
+      "eval_logps/chosen": -1.0399984121322632,
+      "eval_logps/rejected": -1.0647239685058594,
+      "eval_loss": 1.6708022356033325,
+      "eval_nll_loss": 1.601935625076294,
+      "eval_rewards/accuracies": 0.5759999752044678,
+      "eval_rewards/chosen": -0.10399983078241348,
+      "eval_rewards/margins": 0.0024725706316530704,
+      "eval_rewards/rejected": -0.10647241026163101,
+      "eval_runtime": 1022.6911,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 40
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1447864770889282,
+      "learning_rate": 4.888888888888889e-06,
+      "log_odds_chosen": -0.03256305307149887,
+      "log_odds_ratio": -0.7240562438964844,
+      "logits/chosen": -2.913600444793701,
+      "logits/rejected": -2.9339098930358887,
+      "logps/chosen": -1.0398883819580078,
+      "logps/rejected": -1.0196235179901123,
+      "loss": 1.6456,
+      "nll_loss": 1.5732176303863525,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.10398884862661362,
+      "rewards/margins": -0.002026502974331379,
+      "rewards/rejected": -0.10196234285831451,
+      "step": 45
+    },
+    {
+      "epoch": 0.24,
+      "eval_log_odds_chosen": 0.05289135128259659,
+      "eval_log_odds_ratio": -0.6815592646598816,
+      "eval_logits/chosen": -2.9165074825286865,
+      "eval_logits/rejected": -2.9247732162475586,
+      "eval_logps/chosen": -1.005520224571228,
+      "eval_logps/rejected": -1.0391840934753418,
+      "eval_loss": 1.591990351676941,
+      "eval_nll_loss": 1.523834466934204,
+      "eval_rewards/accuracies": 0.5820000171661377,
+      "eval_rewards/chosen": -0.1005520299077034,
+      "eval_rewards/margins": 0.0033663813956081867,
+      "eval_rewards/rejected": -0.1039184182882309,
+      "eval_runtime": 1022.6889,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 45
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.2685421705245972,
+      "learning_rate": 4.444444444444444e-06,
+      "log_odds_chosen": 0.009501500055193901,
+      "log_odds_ratio": -0.7021796107292175,
+      "logits/chosen": -2.917152166366577,
+      "logits/rejected": -2.9314322471618652,
+      "logps/chosen": -0.9614133834838867,
+      "logps/rejected": -0.9648770093917847,
+      "loss": 1.5613,
+      "nll_loss": 1.4910422563552856,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.09614135324954987,
+      "rewards/margins": 0.0003463650937192142,
+      "rewards/rejected": -0.09648770838975906,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "eval_log_odds_chosen": 0.06923460215330124,
+      "eval_log_odds_ratio": -0.6738842129707336,
+      "eval_logits/chosen": -2.913623332977295,
+      "eval_logits/rejected": -2.9217159748077393,
+      "eval_logps/chosen": -0.9739399552345276,
+      "eval_logps/rejected": -1.017154335975647,
+      "eval_loss": 1.5113871097564697,
+      "eval_nll_loss": 1.4439988136291504,
+      "eval_rewards/accuracies": 0.5860000252723694,
+      "eval_rewards/chosen": -0.09739399701356888,
+      "eval_rewards/margins": 0.004321432206779718,
+      "eval_rewards/rejected": -0.10171543061733246,
+      "eval_runtime": 1022.6706,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 50
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.4695621728897095,
+      "learning_rate": 4e-06,
+      "log_odds_chosen": -0.04625839367508888,
+      "log_odds_ratio": -0.7300089001655579,
+      "logits/chosen": -2.9374871253967285,
+      "logits/rejected": -2.9447882175445557,
+      "logps/chosen": -0.9806947708129883,
+      "logps/rejected": -0.9502049684524536,
+      "loss": 1.5105,
+      "nll_loss": 1.4374949932098389,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.09806947410106659,
+      "rewards/margins": -0.0030489820055663586,
+      "rewards/rejected": -0.09502050280570984,
+      "step": 55
+    },
+    {
+      "epoch": 0.29,
+      "eval_log_odds_chosen": 0.08856023102998734,
+      "eval_log_odds_ratio": -0.6650052666664124,
+      "eval_logits/chosen": -2.9045321941375732,
+      "eval_logits/rejected": -2.912545919418335,
+      "eval_logps/chosen": -0.9449537992477417,
+      "eval_logps/rejected": -0.9992481470108032,
+      "eval_loss": 1.4219770431518555,
+      "eval_nll_loss": 1.3554766178131104,
+      "eval_rewards/accuracies": 0.6159999966621399,
+      "eval_rewards/chosen": -0.09449537843465805,
+      "eval_rewards/margins": 0.0054294392466545105,
+      "eval_rewards/rejected": -0.09992481023073196,
+      "eval_runtime": 1022.7786,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 55
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6138032674789429,
+      "learning_rate": 3.555555555555555e-06,
+      "log_odds_chosen": 0.13964158296585083,
+      "log_odds_ratio": -0.635947585105896,
+      "logits/chosen": -2.8947017192840576,
+      "logits/rejected": -2.9101452827453613,
+      "logps/chosen": -0.8633010983467102,
+      "logps/rejected": -0.9464691281318665,
+      "loss": 1.3538,
+      "nll_loss": 1.2902143001556396,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0863301008939743,
+      "rewards/margins": 0.008316809311509132,
+      "rewards/rejected": -0.09464691579341888,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "eval_log_odds_chosen": 0.10931771248579025,
+      "eval_log_odds_ratio": -0.6556519865989685,
+      "eval_logits/chosen": -2.892199993133545,
+      "eval_logits/rejected": -2.9001097679138184,
+      "eval_logps/chosen": -0.917702317237854,
+      "eval_logps/rejected": -0.9835168123245239,
+      "eval_loss": 1.335745096206665,
+      "eval_nll_loss": 1.270180106163025,
+      "eval_rewards/accuracies": 0.6359999775886536,
+      "eval_rewards/chosen": -0.091770239174366,
+      "eval_rewards/margins": 0.006581444293260574,
+      "eval_rewards/rejected": -0.09835167974233627,
+      "eval_runtime": 1022.7752,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 60
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.5814971923828125,
+      "learning_rate": 3.111111111111111e-06,
+      "log_odds_chosen": 0.10876095294952393,
+      "log_odds_ratio": -0.6668508648872375,
+      "logits/chosen": -2.8826332092285156,
+      "logits/rejected": -2.8916373252868652,
+      "logps/chosen": -0.9191996455192566,
+      "logps/rejected": -0.9877899289131165,
+      "loss": 1.3041,
+      "nll_loss": 1.2373846769332886,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.09191995859146118,
+      "rewards/margins": 0.006859032902866602,
+      "rewards/rejected": -0.09877900034189224,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "eval_log_odds_chosen": 0.1319531947374344,
+      "eval_log_odds_ratio": -0.6457509398460388,
+      "eval_logits/chosen": -2.88071870803833,
+      "eval_logits/rejected": -2.888591766357422,
+      "eval_logps/chosen": -0.891889750957489,
+      "eval_logps/rejected": -0.9699481129646301,
+      "eval_loss": 1.2609809637069702,
+      "eval_nll_loss": 1.1964057683944702,
+      "eval_rewards/accuracies": 0.6439999938011169,
+      "eval_rewards/chosen": -0.08918897062540054,
+      "eval_rewards/margins": 0.007805844768881798,
+      "eval_rewards/rejected": -0.09699482470750809,
+      "eval_runtime": 1022.7672,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 65
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.659564733505249,
+      "learning_rate": 2.6666666666666664e-06,
+      "log_odds_chosen": 0.12550300359725952,
+      "log_odds_ratio": -0.649591326713562,
+      "logits/chosen": -2.8679802417755127,
+      "logits/rejected": -2.8701627254486084,
+      "logps/chosen": -0.8406276702880859,
+      "logps/rejected": -0.909234344959259,
+      "loss": 1.2107,
+      "nll_loss": 1.1457639932632446,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.08406275510787964,
+      "rewards/margins": 0.006860665045678616,
+      "rewards/rejected": -0.09092343598604202,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "eval_log_odds_chosen": 0.157026469707489,
+      "eval_log_odds_ratio": -0.6350610256195068,
+      "eval_logits/chosen": -2.8666250705718994,
+      "eval_logits/rejected": -2.874605655670166,
+      "eval_logps/chosen": -0.8690526485443115,
+      "eval_logps/rejected": -0.9602731466293335,
+      "eval_loss": 1.194831132888794,
+      "eval_nll_loss": 1.131325125694275,
+      "eval_rewards/accuracies": 0.6700000166893005,
+      "eval_rewards/chosen": -0.08690525591373444,
+      "eval_rewards/margins": 0.009122052229940891,
+      "eval_rewards/rejected": -0.09602731466293335,
+      "eval_runtime": 1022.8442,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.6513782739639282,
+      "learning_rate": 2.222222222222222e-06,
+      "log_odds_chosen": 0.17446637153625488,
+      "log_odds_ratio": -0.6316618323326111,
+      "logits/chosen": -2.8589344024658203,
+      "logits/rejected": -2.869570732116699,
+      "logps/chosen": -0.8645883798599243,
+      "logps/rejected": -0.9688776135444641,
+      "loss": 1.1669,
+      "nll_loss": 1.1037009954452515,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.08645883202552795,
+      "rewards/margins": 0.010428930632770061,
+      "rewards/rejected": -0.0968877524137497,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "eval_log_odds_chosen": 0.18124479055404663,
+      "eval_log_odds_ratio": -0.6248182058334351,
+      "eval_logits/chosen": -2.8483848571777344,
+      "eval_logits/rejected": -2.856492757797241,
+      "eval_logps/chosen": -0.8498203754425049,
+      "eval_logps/rejected": -0.9533628225326538,
+      "eval_loss": 1.1421345472335815,
+      "eval_nll_loss": 1.0796527862548828,
+      "eval_rewards/accuracies": 0.6779999732971191,
+      "eval_rewards/chosen": -0.08498203754425049,
+      "eval_rewards/margins": 0.010354244150221348,
+      "eval_rewards/rejected": -0.09533628821372986,
+      "eval_runtime": 1022.9696,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 75
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.5368865728378296,
+      "learning_rate": 1.7777777777777775e-06,
+      "log_odds_chosen": 0.14982302486896515,
+      "log_odds_ratio": -0.6351920962333679,
+      "logits/chosen": -2.850210666656494,
+      "logits/rejected": -2.8676600456237793,
+      "logps/chosen": -0.8382354974746704,
+      "logps/rejected": -0.9211069345474243,
+      "loss": 1.1242,
+      "nll_loss": 1.0606878995895386,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.0838235467672348,
+      "rewards/margins": 0.00828714668750763,
+      "rewards/rejected": -0.09211069345474243,
+      "step": 80
+    },
+    {
+      "epoch": 0.43,
+      "eval_log_odds_chosen": 0.19973799586296082,
+      "eval_log_odds_ratio": -0.6170535683631897,
+      "eval_logits/chosen": -2.836185932159424,
+      "eval_logits/rejected": -2.8443472385406494,
+      "eval_logps/chosen": -0.8345023989677429,
+      "eval_logps/rejected": -0.9470006823539734,
+      "eval_loss": 1.096219778060913,
+      "eval_nll_loss": 1.0345144271850586,
+      "eval_rewards/accuracies": 0.6980000138282776,
+      "eval_rewards/chosen": -0.08345023542642593,
+      "eval_rewards/margins": 0.01124983187764883,
+      "eval_rewards/rejected": -0.09470007568597794,
+      "eval_runtime": 1022.8769,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.7374863624572754,
+      "learning_rate": 1.3333333333333332e-06,
+      "log_odds_chosen": 0.2539418935775757,
+      "log_odds_ratio": -0.595883309841156,
+      "logits/chosen": -2.8221487998962402,
+      "logits/rejected": -2.8260178565979004,
+      "logps/chosen": -0.8204309344291687,
+      "logps/rejected": -0.9650068283081055,
+      "loss": 1.0908,
+      "nll_loss": 1.031245470046997,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.0820431038737297,
+      "rewards/margins": 0.014457575976848602,
+      "rewards/rejected": -0.09650067985057831,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "eval_log_odds_chosen": 0.2158733457326889,
+      "eval_log_odds_ratio": -0.61031174659729,
+      "eval_logits/chosen": -2.8228869438171387,
+      "eval_logits/rejected": -2.831103563308716,
+      "eval_logps/chosen": -0.8219822645187378,
+      "eval_logps/rejected": -0.9421792030334473,
+      "eval_loss": 1.0606101751327515,
+      "eval_nll_loss": 0.9995790719985962,
+      "eval_rewards/accuracies": 0.722000002861023,
+      "eval_rewards/chosen": -0.08219822496175766,
+      "eval_rewards/margins": 0.012019689194858074,
+      "eval_rewards/rejected": -0.0942179262638092,
+      "eval_runtime": 1022.854,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.5390028953552246,
+      "learning_rate": 8.888888888888888e-07,
+      "log_odds_chosen": 0.12312959134578705,
+      "log_odds_ratio": -0.6452575922012329,
+      "logits/chosen": -2.799548864364624,
+      "logits/rejected": -2.790161371231079,
+      "logps/chosen": -0.9113782048225403,
+      "logps/rejected": -0.978347897529602,
+      "loss": 1.0736,
+      "nll_loss": 1.009043574333191,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.09113781899213791,
+      "rewards/margins": 0.006696968339383602,
+      "rewards/rejected": -0.09783479571342468,
+      "step": 90
+    },
+    {
+      "epoch": 0.48,
+      "eval_log_odds_chosen": 0.22884733974933624,
+      "eval_log_odds_ratio": -0.6049832701683044,
+      "eval_logits/chosen": -2.80894136428833,
+      "eval_logits/rejected": -2.8171987533569336,
+      "eval_logps/chosen": -0.8134253025054932,
+      "eval_logps/rejected": -0.9399018883705139,
+      "eval_loss": 1.0346410274505615,
+      "eval_nll_loss": 0.9741426110267639,
+      "eval_rewards/accuracies": 0.7319999933242798,
+      "eval_rewards/chosen": -0.08134253323078156,
+      "eval_rewards/margins": 0.012647655792534351,
+      "eval_rewards/rejected": -0.09399019181728363,
+      "eval_runtime": 1022.8962,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 90
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.422467589378357,
+      "learning_rate": 4.444444444444444e-07,
+      "log_odds_chosen": 0.30131229758262634,
+      "log_odds_ratio": -0.5648499131202698,
+      "logits/chosen": -2.788285732269287,
+      "logits/rejected": -2.8017640113830566,
+      "logps/chosen": -0.8434479832649231,
+      "logps/rejected": -1.0182573795318604,
+      "loss": 0.9874,
+      "nll_loss": 0.9309436678886414,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.0843447893857956,
+      "rewards/margins": 0.017480935901403427,
+      "rewards/rejected": -0.10182573646306992,
+      "step": 95
+    },
+    {
+      "epoch": 0.51,
+      "eval_log_odds_chosen": 0.23686276376247406,
+      "eval_log_odds_ratio": -0.6016983389854431,
+      "eval_logits/chosen": -2.800295829772949,
+      "eval_logits/rejected": -2.808558702468872,
+      "eval_logps/chosen": -0.8078622221946716,
+      "eval_logps/rejected": -0.9380316734313965,
+      "eval_loss": 1.018244981765747,
+      "eval_nll_loss": 0.9580751061439514,
+      "eval_rewards/accuracies": 0.7379999756813049,
+      "eval_rewards/chosen": -0.08078622072935104,
+      "eval_rewards/margins": 0.013016944751143456,
+      "eval_rewards/rejected": -0.09380316734313965,
+      "eval_runtime": 1022.8824,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 95
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.5611515045166016,
+      "learning_rate": 0.0,
+      "log_odds_chosen": 0.25769370794296265,
+      "log_odds_ratio": -0.5990554094314575,
+      "logits/chosen": -2.7713541984558105,
+      "logits/rejected": -2.770143508911133,
+      "logps/chosen": -0.9012691378593445,
+      "logps/rejected": -1.0490459203720093,
+      "loss": 1.0083,
+      "nll_loss": 0.9483591914176941,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.09012691676616669,
+      "rewards/margins": 0.014777670614421368,
+      "rewards/rejected": -0.10490457713603973,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_log_odds_chosen": 0.23977938294410706,
+      "eval_log_odds_ratio": -0.6004971861839294,
+      "eval_logits/chosen": -2.796983003616333,
+      "eval_logits/rejected": -2.8052423000335693,
+      "eval_logps/chosen": -0.8057038187980652,
+      "eval_logps/rejected": -0.9371922612190247,
+      "eval_loss": 1.0119801759719849,
+      "eval_nll_loss": 0.9519305229187012,
+      "eval_rewards/accuracies": 0.7419999837875366,
+      "eval_rewards/chosen": -0.08057038486003876,
+      "eval_rewards/margins": 0.013148845173418522,
+      "eval_rewards/rejected": -0.09371922165155411,
+      "eval_runtime": 1022.9549,
+      "eval_samples_per_second": 0.489,
+      "eval_steps_per_second": 0.244,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9737abfc82e80f1ffe42063a196d09bdb7c9108c466f05a465c4921fc65a67
+size 5240

runs/Apr12_07-31-24_b5c8ec495088/events.out.tfevents.1712907095.b5c8ec495088.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa24d8ef7a58e17aa8472f29baec686c74e90a0721d1437cd10ead5da560d8bf
+size 40528