Training in progress, step 2512, checkpoint

checkpoint-2512/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2-7b-bnb-4bit
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-2512/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2-7b-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2512/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b09f644fd5e44cdbd2cf9e10cef60233e41242fbaed44466513805c96aece6
+size 161533192

checkpoint-2512/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-2512/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1fdabd8b88b10f990ce3c7bf81c3dbc51ab5f49c3391cd428c3c154a93cc17
+size 82347842

checkpoint-2512/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c917636c7a58af68a29056522a757e9f9b99005b776641aa157c536967817d
+size 14244

checkpoint-2512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6501be0b7607e82125c92490ac0d6c895dbba3fbf919fcf6f1c174d6c203dcf9
+size 1064

checkpoint-2512/special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2512/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2512/trainer_state.json

@@ -0,0 +1,408 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998009950248756,
+  "eval_steps": 500,
+  "global_step": 2512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03980099502487562,
+      "grad_norm": 1.5459058284759521,
+      "learning_rate": 4.980474401576887e-07,
+      "logits/chosen": -1.4838274717330933,
+      "logits/rejected": -1.5693057775497437,
+      "logps/chosen": -190.30685424804688,
+      "logps/rejected": -190.12179565429688,
+      "loss": 0.7107,
+      "rewards/accuracies": 0.49312499165534973,
+      "rewards/chosen": -0.8337415456771851,
+      "rewards/margins": 0.0017802910879254341,
+      "rewards/rejected": -0.8355217576026917,
+      "step": 100
+    },
+    {
+      "epoch": 0.07960199004975124,
+      "grad_norm": 1.247958779335022,
+      "learning_rate": 4.922202605502572e-07,
+      "logits/chosen": -1.4577226638793945,
+      "logits/rejected": -1.544972538948059,
+      "logps/chosen": -191.1748504638672,
+      "logps/rejected": -191.21063232421875,
+      "loss": 0.7063,
+      "rewards/accuracies": 0.5017187595367432,
+      "rewards/chosen": -0.7915948629379272,
+      "rewards/margins": 0.004952423740178347,
+      "rewards/rejected": -0.7965472340583801,
+      "step": 200
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 1.1431488990783691,
+      "learning_rate": 4.82609484512869e-07,
+      "logits/chosen": -1.4753738641738892,
+      "logits/rejected": -1.5457732677459717,
+      "logps/chosen": -189.42088317871094,
+      "logps/rejected": -190.7891082763672,
+      "loss": 0.7009,
+      "rewards/accuracies": 0.5146874785423279,
+      "rewards/chosen": -0.7856764197349548,
+      "rewards/margins": 0.013686330057680607,
+      "rewards/rejected": -0.7993627190589905,
+      "step": 300
+    },
+    {
+      "epoch": 0.15920398009950248,
+      "grad_norm": 1.1773804426193237,
+      "learning_rate": 4.6936523696827614e-07,
+      "logits/chosen": -1.4836928844451904,
+      "logits/rejected": -1.5391887426376343,
+      "logps/chosen": -191.47879028320312,
+      "logps/rejected": -192.72312927246094,
+      "loss": 0.7031,
+      "rewards/accuracies": 0.4935937523841858,
+      "rewards/chosen": -0.7633911967277527,
+      "rewards/margins": 0.00844556000083685,
+      "rewards/rejected": -0.7718366384506226,
+      "step": 400
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 1.1332217454910278,
+      "learning_rate": 4.5269439940365644e-07,
+      "logits/chosen": -1.5031734704971313,
+      "logits/rejected": -1.5771981477737427,
+      "logps/chosen": -188.72503662109375,
+      "logps/rejected": -188.9233856201172,
+      "loss": 0.6982,
+      "rewards/accuracies": 0.5159375071525574,
+      "rewards/chosen": -0.7517531514167786,
+      "rewards/margins": 0.017128920182585716,
+      "rewards/rejected": -0.7688820362091064,
+      "step": 500
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 1.1783969402313232,
+      "learning_rate": 4.328573782827409e-07,
+      "logits/chosen": -1.4775351285934448,
+      "logits/rejected": -1.5578263998031616,
+      "logps/chosen": -187.82449340820312,
+      "logps/rejected": -186.08935546875,
+      "loss": 0.6956,
+      "rewards/accuracies": 0.5301562547683716,
+      "rewards/chosen": -0.7211830615997314,
+      "rewards/margins": 0.02292461320757866,
+      "rewards/rejected": -0.744107723236084,
+      "step": 600
+    },
+    {
+      "epoch": 0.27860696517412936,
+      "grad_norm": 1.2275896072387695,
+      "learning_rate": 4.1016403737218373e-07,
+      "logits/chosen": -1.4353595972061157,
+      "logits/rejected": -1.5325896739959717,
+      "logps/chosen": -190.53240966796875,
+      "logps/rejected": -186.2373504638672,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5306249856948853,
+      "rewards/chosen": -0.7291114926338196,
+      "rewards/margins": 0.02977893128991127,
+      "rewards/rejected": -0.7588903903961182,
+      "step": 700
+    },
+    {
+      "epoch": 0.31840796019900497,
+      "grad_norm": 1.2193249464035034,
+      "learning_rate": 3.849688575211836e-07,
+      "logits/chosen": -1.4531009197235107,
+      "logits/rejected": -1.528568148612976,
+      "logps/chosen": -193.5086669921875,
+      "logps/rejected": -190.48219299316406,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.5360937714576721,
+      "rewards/chosen": -0.7271183729171753,
+      "rewards/margins": 0.027006981894373894,
+      "rewards/rejected": -0.7541253566741943,
+      "step": 800
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 1.3636894226074219,
+      "learning_rate": 3.576653995009154e-07,
+      "logits/chosen": -1.4581520557403564,
+      "logits/rejected": -1.5382471084594727,
+      "logps/chosen": -186.9196319580078,
+      "logps/rejected": -187.58917236328125,
+      "loss": 0.6881,
+      "rewards/accuracies": 0.538281261920929,
+      "rewards/chosen": -0.7291906476020813,
+      "rewards/margins": 0.039425306022167206,
+      "rewards/rejected": -0.7686160802841187,
+      "step": 900
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 1.2546725273132324,
+      "learning_rate": 3.286801563968721e-07,
+      "logits/chosen": -1.4330791234970093,
+      "logits/rejected": -1.5031362771987915,
+      "logps/chosen": -190.80686950683594,
+      "logps/rejected": -189.16189575195312,
+      "loss": 0.692,
+      "rewards/accuracies": 0.5220312476158142,
+      "rewards/chosen": -0.7390533685684204,
+      "rewards/margins": 0.03137853741645813,
+      "rewards/rejected": -0.7704318165779114,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43781094527363185,
+      "grad_norm": 1.1531291007995605,
+      "learning_rate": 2.9846589158269034e-07,
+      "logits/chosen": -1.4307806491851807,
+      "logits/rejected": -1.5092757940292358,
+      "logps/chosen": -193.00648498535156,
+      "logps/rejected": -189.84764099121094,
+      "loss": 0.6892,
+      "rewards/accuracies": 0.5384374856948853,
+      "rewards/chosen": -0.7566314935684204,
+      "rewards/margins": 0.03836291283369064,
+      "rewards/rejected": -0.7949943542480469,
+      "step": 1100
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 1.5831681489944458,
+      "learning_rate": 2.674945663394993e-07,
+      "logits/chosen": -1.430738925933838,
+      "logits/rejected": -1.5082927942276,
+      "logps/chosen": -189.89476013183594,
+      "logps/rejected": -186.1005096435547,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.5414062738418579,
+      "rewards/chosen": -0.754692018032074,
+      "rewards/margins": 0.03536057472229004,
+      "rewards/rejected": -0.790052592754364,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5174129353233831,
+      "grad_norm": 1.3418159484863281,
+      "learning_rate": 2.3624996759476285e-07,
+      "logits/chosen": -1.4191877841949463,
+      "logits/rejected": -1.501223087310791,
+      "logps/chosen": -190.763671875,
+      "logps/rejected": -188.54310607910156,
+      "loss": 0.6848,
+      "rewards/accuracies": 0.5510937571525574,
+      "rewards/chosen": -0.7421095967292786,
+      "rewards/margins": 0.05018935725092888,
+      "rewards/rejected": -0.7922989726066589,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5572139303482587,
+      "grad_norm": 1.0886973142623901,
+      "learning_rate": 2.0522015093886614e-07,
+      "logits/chosen": -1.4274046421051025,
+      "logits/rejected": -1.511489748954773,
+      "logps/chosen": -190.62181091308594,
+      "logps/rejected": -189.4832000732422,
+      "loss": 0.6884,
+      "rewards/accuracies": 0.5412499904632568,
+      "rewards/chosen": -0.742114782333374,
+      "rewards/margins": 0.042963698506355286,
+      "rewards/rejected": -0.7850785255432129,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 1.2839570045471191,
+      "learning_rate": 1.7488981696314154e-07,
+      "logits/chosen": -1.4310470819473267,
+      "logits/rejected": -1.504390001296997,
+      "logps/chosen": -190.2706298828125,
+      "logps/rejected": -188.0977020263672,
+      "loss": 0.6868,
+      "rewards/accuracies": 0.547656238079071,
+      "rewards/chosen": -0.7403038144111633,
+      "rewards/margins": 0.04620310664176941,
+      "rewards/rejected": -0.7865069508552551,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6368159203980099,
+      "grad_norm": 1.2762988805770874,
+      "learning_rate": 1.4573274000458839e-07,
+      "logits/chosen": -1.4215110540390015,
+      "logits/rejected": -1.5031652450561523,
+      "logps/chosen": -189.7293701171875,
+      "logps/rejected": -189.09996032714844,
+      "loss": 0.6835,
+      "rewards/accuracies": 0.5501562356948853,
+      "rewards/chosen": -0.7511222958564758,
+      "rewards/margins": 0.05315619334578514,
+      "rewards/rejected": -0.8042784929275513,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6766169154228856,
+      "grad_norm": 1.517782211303711,
+      "learning_rate": 1.1820436756391414e-07,
+      "logits/chosen": -1.385495901107788,
+      "logits/rejected": -1.4789422750473022,
+      "logps/chosen": -193.28277587890625,
+      "logps/rejected": -189.7715606689453,
+      "loss": 0.6848,
+      "rewards/accuracies": 0.5560937523841858,
+      "rewards/chosen": -0.7423578500747681,
+      "rewards/margins": 0.052127428352832794,
+      "rewards/rejected": -0.794485330581665,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 1.2326488494873047,
+      "learning_rate": 9.273470599753375e-08,
+      "logits/chosen": -1.4209693670272827,
+      "logits/rejected": -1.491072654724121,
+      "logps/chosen": -188.58055114746094,
+      "logps/rejected": -188.7568359375,
+      "loss": 0.6834,
+      "rewards/accuracies": 0.5548437237739563,
+      "rewards/chosen": -0.7456573247909546,
+      "rewards/margins": 0.05509215220808983,
+      "rewards/rejected": -0.8007495403289795,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7562189054726368,
+      "grad_norm": 1.1635903120040894,
+      "learning_rate": 6.972160361242119e-08,
+      "logits/chosen": -1.4076248407363892,
+      "logits/rejected": -1.4701765775680542,
+      "logps/chosen": -187.25048828125,
+      "logps/rejected": -188.06027221679688,
+      "loss": 0.6849,
+      "rewards/accuracies": 0.5457812547683716,
+      "rewards/chosen": -0.7482488751411438,
+      "rewards/margins": 0.050881754606962204,
+      "rewards/rejected": -0.7991305589675903,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 1.463752031326294,
+      "learning_rate": 4.952453608509e-08,
+      "logits/chosen": -1.4001586437225342,
+      "logits/rejected": -1.4962129592895508,
+      "logps/chosen": -192.7788848876953,
+      "logps/rejected": -191.05316162109375,
+      "loss": 0.6877,
+      "rewards/accuracies": 0.5378124713897705,
+      "rewards/chosen": -0.7623865008354187,
+      "rewards/margins": 0.047943364828825,
+      "rewards/rejected": -0.8103299736976624,
+      "step": 2000
+    },
+    {
+      "epoch": 0.835820895522388,
+      "grad_norm": 1.200461506843567,
+      "learning_rate": 3.2458991279430717e-08,
+      "logits/chosen": -1.4338061809539795,
+      "logits/rejected": -1.492598295211792,
+      "logps/chosen": -187.86001586914062,
+      "logps/rejected": -190.3682403564453,
+      "loss": 0.6804,
+      "rewards/accuracies": 0.5598437786102295,
+      "rewards/chosen": -0.7565799951553345,
+      "rewards/margins": 0.06183221936225891,
+      "rewards/rejected": -0.818412184715271,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8756218905472637,
+      "grad_norm": 1.30251145362854,
+      "learning_rate": 1.8791541175240787e-08,
+      "logits/chosen": -1.4070285558700562,
+      "logits/rejected": -1.487685203552246,
+      "logps/chosen": -189.3640594482422,
+      "logps/rejected": -188.98089599609375,
+      "loss": 0.6791,
+      "rewards/accuracies": 0.5614062547683716,
+      "rewards/chosen": -0.7591237425804138,
+      "rewards/margins": 0.06378559023141861,
+      "rewards/rejected": -0.822909414768219,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9154228855721394,
+      "grad_norm": 1.1758041381835938,
+      "learning_rate": 8.735677886282183e-09,
+      "logits/chosen": -1.4267709255218506,
+      "logits/rejected": -1.4703466892242432,
+      "logps/chosen": -188.0686492919922,
+      "logps/rejected": -192.47093200683594,
+      "loss": 0.6804,
+      "rewards/accuracies": 0.553906261920929,
+      "rewards/chosen": -0.7582595348358154,
+      "rewards/margins": 0.06273117661476135,
+      "rewards/rejected": -0.8209907412528992,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 1.3671549558639526,
+      "learning_rate": 2.4484788112571488e-09,
+      "logits/chosen": -1.3968582153320312,
+      "logits/rejected": -1.4773013591766357,
+      "logps/chosen": -190.7488250732422,
+      "logps/rejected": -189.8838348388672,
+      "loss": 0.6805,
+      "rewards/accuracies": 0.5579687356948853,
+      "rewards/chosen": -0.756488025188446,
+      "rewards/margins": 0.061892423778772354,
+      "rewards/rejected": -0.8183805346488953,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 1.116024374961853,
+      "learning_rate": 2.8153009641818103e-11,
+      "logits/chosen": -1.4138067960739136,
+      "logits/rejected": -1.4724555015563965,
+      "logps/chosen": -188.42840576171875,
+      "logps/rejected": -188.1235809326172,
+      "loss": 0.6808,
+      "rewards/accuracies": 0.5667187571525574,
+      "rewards/chosen": -0.752957820892334,
+      "rewards/margins": 0.06008431315422058,
+      "rewards/rejected": -0.813042163848877,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66cc57a0e2f8ad90da0d3d8e2cf37c61053a09a6b3b5d9bcbc209f66a8ffee9
+size 6008