Upload folder using huggingface_hub

README.md

@@ -0,0 +1,134 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+tags:
+- generated_from_trainer
+datasets:
+- pp-beta/whalebrainprompt
+model-index:
+- name: outputs/mymodel
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+adapter: lora
+base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+bf16: auto
+dataset_processes: 32
+datasets:
+- message_property_mappings:
+    content: content
+    role: role
+  path: pp-beta/whalebrainprompt
+  type: chat_template
+  trust_remote_code: false
+chat_template: chatml
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+learning_rate: 0.0002
+lisa_layers_attribute: model.layers
+load_best_model_at_end: false
+load_in_4bit: false
+load_in_8bit: true
+lora_alpha: 16
+lora_dropout: 0.05
+lora_r: 8
+lora_target_modules:
+- q_proj
+- v_proj
+- k_proj
+- o_proj
+- gate_proj
+- down_proj
+- up_proj
+loraplus_lr_embedding: 1.0e-06
+lr_scheduler: cosine
+max_prompt_len: 1024
+mean_resizing_embeddings: false
+micro_batch_size: 8
+num_epochs: 1.0
+optimizer: adamw_bnb_8bit
+output_dir: ./outputs/mymodel
+pretrain_multipack_attn: true
+pretrain_multipack_buffer_size: 10000
+qlora_sharded_model_loading: false
+ray_num_workers: 1
+resources_per_worker:
+  GPU: 1
+sample_packing_bin_size: 200
+sample_packing_group_size: 100000
+save_only_model: false
+save_safetensors: true
+sequence_len: 2048
+shuffle_merged_datasets: true
+skip_prepare_dataset: false
+strict: false
+train_on_inputs: false
+trl:
+  log_completions: false
+  ref_model_mixup_alpha: 0.9
+  ref_model_sync_steps: 64
+  sync_ref_model: false
+  use_vllm: false
+  vllm_device: auto
+  vllm_dtype: auto
+  vllm_gpu_memory_utilization: 0.9
+use_ray: false
+val_set_size: 0.0
+weight_decay: 0.0
+
+```
+
+</details><br>
+
+# outputs/mymodel
+
+This model is a fine-tuned version of [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO) on the pp-beta/whalebrainprompt dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 24
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "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:e5070b2495c909238960a53d255bde14c865699979243aee066fc68f54945bc1
+size 83945296

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-804/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+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 0.14.0

checkpoint-804/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-804/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5070b2495c909238960a53d255bde14c865699979243aee066fc68f54945bc1
+size 83945296

checkpoint-804/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cd0035bd605b5552438ab226c70f9ee028e551a0cecd7e90ef35060961f3ad
+size 43123028

checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de24f16a2dabcb71e110da15b1860e0d6ee8d7e9574a13096dfe85c3133e026
+size 14244

checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbbfc073b960457a703d50bcf643869fc15027249c9f25d7d90f8e901d9204e
+size 1064

checkpoint-804/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-804/tokenizer.model

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

checkpoint-804/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

checkpoint-804/trainer_state.json

@@ -0,0 +1,1440 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993784959602238,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004972032318210068,
+      "grad_norm": 2.5709357261657715,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.307,
+      "step": 4
+    },
+    {
+      "epoch": 0.009944064636420136,
+      "grad_norm": 1.4358521699905396,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.1509,
+      "step": 8
+    },
+    {
+      "epoch": 0.014916096954630205,
+      "grad_norm": 1.1599832773208618,
+      "learning_rate": 0.0001,
+      "loss": 0.9128,
+      "step": 12
+    },
+    {
+      "epoch": 0.019888129272840272,
+      "grad_norm": 0.9250568747520447,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.7575,
+      "step": 16
+    },
+    {
+      "epoch": 0.024860161591050343,
+      "grad_norm": 0.6691205501556396,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6885,
+      "step": 20
+    },
+    {
+      "epoch": 0.02983219390926041,
+      "grad_norm": 0.6702026128768921,
+      "learning_rate": 0.0002,
+      "loss": 0.6703,
+      "step": 24
+    },
+    {
+      "epoch": 0.03480422622747048,
+      "grad_norm": 0.6191584467887878,
+      "learning_rate": 0.00019998702249713748,
+      "loss": 0.6191,
+      "step": 28
+    },
+    {
+      "epoch": 0.039776258545680544,
+      "grad_norm": 0.585008978843689,
+      "learning_rate": 0.0001999480933568615,
+      "loss": 0.6302,
+      "step": 32
+    },
+    {
+      "epoch": 0.044748290863890615,
+      "grad_norm": 0.5618470907211304,
+      "learning_rate": 0.00019988322268323268,
+      "loss": 0.6047,
+      "step": 36
+    },
+    {
+      "epoch": 0.049720323182100686,
+      "grad_norm": 0.5016953945159912,
+      "learning_rate": 0.00019979242731343804,
+      "loss": 0.6009,
+      "step": 40
+    },
+    {
+      "epoch": 0.05469235550031075,
+      "grad_norm": 0.4973951578140259,
+      "learning_rate": 0.00019967573081342103,
+      "loss": 0.5741,
+      "step": 44
+    },
+    {
+      "epoch": 0.05966438781852082,
+      "grad_norm": 0.5195545554161072,
+      "learning_rate": 0.00019953316347176488,
+      "loss": 0.5883,
+      "step": 48
+    },
+    {
+      "epoch": 0.06463642013673089,
+      "grad_norm": 0.4920307993888855,
+      "learning_rate": 0.00019936476229183133,
+      "loss": 0.557,
+      "step": 52
+    },
+    {
+      "epoch": 0.06960845245494096,
+      "grad_norm": 0.4726178050041199,
+      "learning_rate": 0.0001991705709821562,
+      "loss": 0.534,
+      "step": 56
+    },
+    {
+      "epoch": 0.07458048477315103,
+      "grad_norm": 0.5112979412078857,
+      "learning_rate": 0.0001989506399451051,
+      "loss": 0.5725,
+      "step": 60
+    },
+    {
+      "epoch": 0.07955251709136109,
+      "grad_norm": 0.4693872034549713,
+      "learning_rate": 0.00019870502626379127,
+      "loss": 0.5515,
+      "step": 64
+    },
+    {
+      "epoch": 0.08452454940957116,
+      "grad_norm": 0.5028090476989746,
+      "learning_rate": 0.00019843379368725977,
+      "loss": 0.5525,
+      "step": 68
+    },
+    {
+      "epoch": 0.08949658172778123,
+      "grad_norm": 0.4817284345626831,
+      "learning_rate": 0.00019813701261394136,
+      "loss": 0.5563,
+      "step": 72
+    },
+    {
+      "epoch": 0.0944686140459913,
+      "grad_norm": 0.4770365357398987,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.551,
+      "step": 76
+    },
+    {
+      "epoch": 0.09944064636420137,
+      "grad_norm": 0.4698512554168701,
+      "learning_rate": 0.0001974671197062428,
+      "loss": 0.55,
+      "step": 80
+    },
+    {
+      "epoch": 0.10441267868241144,
+      "grad_norm": 0.4815049469470978,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.5324,
+      "step": 84
+    },
+    {
+      "epoch": 0.1093847110006215,
+      "grad_norm": 0.47757378220558167,
+      "learning_rate": 0.00019669604297853764,
+      "loss": 0.5403,
+      "step": 88
+    },
+    {
+      "epoch": 0.11435674331883157,
+      "grad_norm": 0.5221468806266785,
+      "learning_rate": 0.00019627280675097908,
+      "loss": 0.5585,
+      "step": 92
+    },
+    {
+      "epoch": 0.11932877563704164,
+      "grad_norm": 0.5312801599502563,
+      "learning_rate": 0.00019582458291091663,
+      "loss": 0.5434,
+      "step": 96
+    },
+    {
+      "epoch": 0.12430080795525171,
+      "grad_norm": 0.4535232186317444,
+      "learning_rate": 0.00019535148779487363,
+      "loss": 0.566,
+      "step": 100
+    },
+    {
+      "epoch": 0.12927284027346178,
+      "grad_norm": 0.45621493458747864,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 0.5339,
+      "step": 104
+    },
+    {
+      "epoch": 0.13424487259167184,
+      "grad_norm": 0.4411988854408264,
+      "learning_rate": 0.0001943311813257743,
+      "loss": 0.5377,
+      "step": 108
+    },
+    {
+      "epoch": 0.13921690490988192,
+      "grad_norm": 0.4519474506378174,
+      "learning_rate": 0.00019378423479332046,
+      "loss": 0.5392,
+      "step": 112
+    },
+    {
+      "epoch": 0.14418893722809198,
+      "grad_norm": 0.4649061858654022,
+      "learning_rate": 0.0001932129465573568,
+      "loss": 0.5258,
+      "step": 116
+    },
+    {
+      "epoch": 0.14916096954630206,
+      "grad_norm": 0.44414597749710083,
+      "learning_rate": 0.00019261746489577765,
+      "loss": 0.5237,
+      "step": 120
+    },
+    {
+      "epoch": 0.15413300186451212,
+      "grad_norm": 0.4718000590801239,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 0.5323,
+      "step": 124
+    },
+    {
+      "epoch": 0.15910503418272218,
+      "grad_norm": 0.43624797463417053,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.5179,
+      "step": 128
+    },
+    {
+      "epoch": 0.16407706650093226,
+      "grad_norm": 0.47694411873817444,
+      "learning_rate": 0.00019068743608505455,
+      "loss": 0.54,
+      "step": 132
+    },
+    {
+      "epoch": 0.16904909881914232,
+      "grad_norm": 0.4488740861415863,
+      "learning_rate": 0.0001899967884766212,
+      "loss": 0.5071,
+      "step": 136
+    },
+    {
+      "epoch": 0.1740211311373524,
+      "grad_norm": 0.4883563220500946,
+      "learning_rate": 0.00018928278219658643,
+      "loss": 0.5273,
+      "step": 140
+    },
+    {
+      "epoch": 0.17899316345556246,
+      "grad_norm": 0.4428342878818512,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.5205,
+      "step": 144
+    },
+    {
+      "epoch": 0.18396519577377252,
+      "grad_norm": 0.4439612925052643,
+      "learning_rate": 0.00018778544091784048,
+      "loss": 0.5169,
+      "step": 148
+    },
+    {
+      "epoch": 0.1889372280919826,
+      "grad_norm": 0.5181368589401245,
+      "learning_rate": 0.00018700249455414394,
+      "loss": 0.52,
+      "step": 152
+    },
+    {
+      "epoch": 0.19390926041019266,
+      "grad_norm": 0.4589499831199646,
+      "learning_rate": 0.00018619696668800492,
+      "loss": 0.5212,
+      "step": 156
+    },
+    {
+      "epoch": 0.19888129272840274,
+      "grad_norm": 0.4652368724346161,
+      "learning_rate": 0.00018536906639422725,
+      "loss": 0.5058,
+      "step": 160
+    },
+    {
+      "epoch": 0.2038533250466128,
+      "grad_norm": 0.4471285343170166,
+      "learning_rate": 0.0001845190085543795,
+      "loss": 0.5139,
+      "step": 164
+    },
+    {
+      "epoch": 0.20882535736482288,
+      "grad_norm": 0.4473588466644287,
+      "learning_rate": 0.00018364701380102266,
+      "loss": 0.5011,
+      "step": 168
+    },
+    {
+      "epoch": 0.21379738968303294,
+      "grad_norm": 0.46769270300865173,
+      "learning_rate": 0.000182753308460445,
+      "loss": 0.5095,
+      "step": 172
+    },
+    {
+      "epoch": 0.218769422001243,
+      "grad_norm": 0.4742557108402252,
+      "learning_rate": 0.0001818381244939187,
+      "loss": 0.522,
+      "step": 176
+    },
+    {
+      "epoch": 0.22374145431945308,
+      "grad_norm": 0.4403395354747772,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5067,
+      "step": 180
+    },
+    {
+      "epoch": 0.22871348663766314,
+      "grad_norm": 0.4548196792602539,
+      "learning_rate": 0.00017994427634035015,
+      "loss": 0.5079,
+      "step": 184
+    },
+    {
+      "epoch": 0.23368551895587322,
+      "grad_norm": 0.48214584589004517,
+      "learning_rate": 0.0001789661037017045,
+      "loss": 0.4928,
+      "step": 188
+    },
+    {
+      "epoch": 0.23865755127408328,
+      "grad_norm": 0.4306032061576843,
+      "learning_rate": 0.00017796743540632223,
+      "loss": 0.5083,
+      "step": 192
+    },
+    {
+      "epoch": 0.24362958359229334,
+      "grad_norm": 0.4764976501464844,
+      "learning_rate": 0.00017694853065861662,
+      "loss": 0.4956,
+      "step": 196
+    },
+    {
+      "epoch": 0.24860161591050342,
+      "grad_norm": 0.4228585958480835,
+      "learning_rate": 0.00017590965391537316,
+      "loss": 0.5158,
+      "step": 200
+    },
+    {
+      "epoch": 0.2535736482287135,
+      "grad_norm": 0.4141365587711334,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.4989,
+      "step": 204
+    },
+    {
+      "epoch": 0.25854568054692356,
+      "grad_norm": 0.45275670289993286,
+      "learning_rate": 0.00017377306811809304,
+      "loss": 0.4952,
+      "step": 208
+    },
+    {
+      "epoch": 0.26351771286513365,
+      "grad_norm": 0.4202629327774048,
+      "learning_rate": 0.00017267591361502232,
+      "loss": 0.5082,
+      "step": 212
+    },
+    {
+      "epoch": 0.2684897451833437,
+      "grad_norm": 0.4502929449081421,
+      "learning_rate": 0.00017155989607441213,
+      "loss": 0.4974,
+      "step": 216
+    },
+    {
+      "epoch": 0.27346177750155376,
+      "grad_norm": 0.4718655049800873,
+      "learning_rate": 0.00017042530515867896,
+      "loss": 0.5041,
+      "step": 220
+    },
+    {
+      "epoch": 0.27843380981976384,
+      "grad_norm": 0.43044278025627136,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 0.5007,
+      "step": 224
+    },
+    {
+      "epoch": 0.2834058421379739,
+      "grad_norm": 0.4416678249835968,
+      "learning_rate": 0.00016810158587867973,
+      "loss": 0.5075,
+      "step": 228
+    },
+    {
+      "epoch": 0.28837787445618396,
+      "grad_norm": 0.44607338309288025,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.4979,
+      "step": 232
+    },
+    {
+      "epoch": 0.29334990677439404,
+      "grad_norm": 0.44135963916778564,
+      "learning_rate": 0.0001657071681043731,
+      "loss": 0.5008,
+      "step": 236
+    },
+    {
+      "epoch": 0.2983219390926041,
+      "grad_norm": 0.4461626410484314,
+      "learning_rate": 0.00016448422127361706,
+      "loss": 0.4994,
+      "step": 240
+    },
+    {
+      "epoch": 0.30329397141081416,
+      "grad_norm": 0.4296169877052307,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.508,
+      "step": 244
+    },
+    {
+      "epoch": 0.30826600372902424,
+      "grad_norm": 0.4123411476612091,
+      "learning_rate": 0.00016198843872211404,
+      "loss": 0.491,
+      "step": 248
+    },
+    {
+      "epoch": 0.3132380360472343,
+      "grad_norm": 0.4264468252658844,
+      "learning_rate": 0.00016071625078187114,
+      "loss": 0.5015,
+      "step": 252
+    },
+    {
+      "epoch": 0.31821006836544435,
+      "grad_norm": 0.4258119761943817,
+      "learning_rate": 0.00015942830393526176,
+      "loss": 0.4982,
+      "step": 256
+    },
+    {
+      "epoch": 0.32318210068365444,
+      "grad_norm": 0.44614851474761963,
+      "learning_rate": 0.00015812493246896366,
+      "loss": 0.5014,
+      "step": 260
+    },
+    {
+      "epoch": 0.3281541330018645,
+      "grad_norm": 0.4335807263851166,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.4919,
+      "step": 264
+    },
+    {
+      "epoch": 0.3331261653200746,
+      "grad_norm": 0.4183286726474762,
+      "learning_rate": 0.0001554732727535139,
+      "loss": 0.477,
+      "step": 268
+    },
+    {
+      "epoch": 0.33809819763828464,
+      "grad_norm": 0.43014243245124817,
+      "learning_rate": 0.00015412567274279316,
+      "loss": 0.4684,
+      "step": 272
+    },
+    {
+      "epoch": 0.3430702299564947,
+      "grad_norm": 0.4089718163013458,
+      "learning_rate": 0.0001527640244106133,
+      "loss": 0.4927,
+      "step": 276
+    },
+    {
+      "epoch": 0.3480422622747048,
+      "grad_norm": 0.40746763348579407,
+      "learning_rate": 0.0001513886811728769,
+      "loss": 0.4868,
+      "step": 280
+    },
+    {
+      "epoch": 0.35301429459291483,
+      "grad_norm": 0.4374973177909851,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4826,
+      "step": 284
+    },
+    {
+      "epoch": 0.3579863269111249,
+      "grad_norm": 0.4501773715019226,
+      "learning_rate": 0.0001485983413242606,
+      "loss": 0.4952,
+      "step": 288
+    },
+    {
+      "epoch": 0.362958359229335,
+      "grad_norm": 0.4177991449832916,
+      "learning_rate": 0.0001471840689462482,
+      "loss": 0.49,
+      "step": 292
+    },
+    {
+      "epoch": 0.36793039154754503,
+      "grad_norm": 0.4343775510787964,
+      "learning_rate": 0.00014575754994043956,
+      "loss": 0.4872,
+      "step": 296
+    },
+    {
+      "epoch": 0.3729024238657551,
+      "grad_norm": 0.45072102546691895,
+      "learning_rate": 0.00014431915455992414,
+      "loss": 0.4907,
+      "step": 300
+    },
+    {
+      "epoch": 0.3778744561839652,
+      "grad_norm": 0.4326207637786865,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.4885,
+      "step": 304
+    },
+    {
+      "epoch": 0.3828464885021753,
+      "grad_norm": 0.4340527653694153,
+      "learning_rate": 0.0001414082310028012,
+      "loss": 0.4772,
+      "step": 308
+    },
+    {
+      "epoch": 0.3878185208203853,
+      "grad_norm": 0.4523162841796875,
+      "learning_rate": 0.00013993645835656953,
+      "loss": 0.4959,
+      "step": 312
+    },
+    {
+      "epoch": 0.3927905531385954,
+      "grad_norm": 0.4163872003555298,
+      "learning_rate": 0.0001384543202002851,
+      "loss": 0.4889,
+      "step": 316
+    },
+    {
+      "epoch": 0.3977625854568055,
+      "grad_norm": 0.417036771774292,
+      "learning_rate": 0.00013696220122299112,
+      "loss": 0.5005,
+      "step": 320
+    },
+    {
+      "epoch": 0.4027346177750155,
+      "grad_norm": 0.43414178490638733,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.489,
+      "step": 324
+    },
+    {
+      "epoch": 0.4077066500932256,
+      "grad_norm": 0.4082673192024231,
+      "learning_rate": 0.00013394957241364273,
+      "loss": 0.4767,
+      "step": 328
+    },
+    {
+      "epoch": 0.4126786824114357,
+      "grad_norm": 0.4241110682487488,
+      "learning_rate": 0.00013242984450956828,
+      "loss": 0.4757,
+      "step": 332
+    },
+    {
+      "epoch": 0.41765071472964577,
+      "grad_norm": 0.4089127480983734,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.4698,
+      "step": 336
+    },
+    {
+      "epoch": 0.4226227470478558,
+      "grad_norm": 0.4317830502986908,
+      "learning_rate": 0.0001293655338275631,
+      "loss": 0.495,
+      "step": 340
+    },
+    {
+      "epoch": 0.4275947793660659,
+      "grad_norm": 0.4141937792301178,
+      "learning_rate": 0.0001278217463916453,
+      "loss": 0.4813,
+      "step": 344
+    },
+    {
+      "epoch": 0.43256681168427596,
+      "grad_norm": 0.4085291624069214,
+      "learning_rate": 0.0001262707378198587,
+      "loss": 0.4838,
+      "step": 348
+    },
+    {
+      "epoch": 0.437538844002486,
+      "grad_norm": 0.4401163160800934,
+      "learning_rate": 0.00012471291067656697,
+      "loss": 0.4725,
+      "step": 352
+    },
+    {
+      "epoch": 0.4425108763206961,
+      "grad_norm": 0.4499000310897827,
+      "learning_rate": 0.00012314866929589432,
+      "loss": 0.4738,
+      "step": 356
+    },
+    {
+      "epoch": 0.44748290863890616,
+      "grad_norm": 0.4250274896621704,
+      "learning_rate": 0.00012157841967678063,
+      "loss": 0.48,
+      "step": 360
+    },
+    {
+      "epoch": 0.45245494095711625,
+      "grad_norm": 0.4591006934642792,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.4898,
+      "step": 364
+    },
+    {
+      "epoch": 0.4574269732753263,
+      "grad_norm": 0.42636924982070923,
+      "learning_rate": 0.00011842152741040116,
+      "loss": 0.4736,
+      "step": 368
+    },
+    {
+      "epoch": 0.46239900559353636,
+      "grad_norm": 0.41370445489883423,
+      "learning_rate": 0.00011683570413470383,
+      "loss": 0.479,
+      "step": 372
+    },
+    {
+      "epoch": 0.46737103791174645,
+      "grad_norm": 0.41576653718948364,
+      "learning_rate": 0.00011524551115103454,
+      "loss": 0.4684,
+      "step": 376
+    },
+    {
+      "epoch": 0.4723430702299565,
+      "grad_norm": 0.4330123960971832,
+      "learning_rate": 0.00011365136119407319,
+      "loss": 0.4642,
+      "step": 380
+    },
+    {
+      "epoch": 0.47731510254816656,
+      "grad_norm": 0.43045657873153687,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.483,
+      "step": 384
+    },
+    {
+      "epoch": 0.48228713486637664,
+      "grad_norm": 0.4194320738315582,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.4621,
+      "step": 388
+    },
+    {
+      "epoch": 0.4872591671845867,
+      "grad_norm": 0.40911245346069336,
+      "learning_rate": 0.00010884931159113586,
+      "loss": 0.482,
+      "step": 392
+    },
+    {
+      "epoch": 0.49223119950279676,
+      "grad_norm": 0.4329901337623596,
+      "learning_rate": 0.00010724348001617625,
+      "loss": 0.4743,
+      "step": 396
+    },
+    {
+      "epoch": 0.49720323182100684,
+      "grad_norm": 0.42870208621025085,
+      "learning_rate": 0.00010563576839556374,
+      "loss": 0.4658,
+      "step": 400
+    },
+    {
+      "epoch": 0.5021752641392169,
+      "grad_norm": 0.43135136365890503,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.4651,
+      "step": 404
+    },
+    {
+      "epoch": 0.507147296457427,
+      "grad_norm": 0.41581398248672485,
+      "learning_rate": 0.00010241637452361323,
+      "loss": 0.481,
+      "step": 408
+    },
+    {
+      "epoch": 0.512119328775637,
+      "grad_norm": 0.4430304169654846,
+      "learning_rate": 0.00010080552786613899,
+      "loss": 0.467,
+      "step": 412
+    },
+    {
+      "epoch": 0.5170913610938471,
+      "grad_norm": 0.4333083927631378,
+      "learning_rate": 9.919447213386103e-05,
+      "loss": 0.4659,
+      "step": 416
+    },
+    {
+      "epoch": 0.5220633934120572,
+      "grad_norm": 0.42966219782829285,
+      "learning_rate": 9.75836254763868e-05,
+      "loss": 0.4608,
+      "step": 420
+    },
+    {
+      "epoch": 0.5270354257302673,
+      "grad_norm": 0.44130048155784607,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.451,
+      "step": 424
+    },
+    {
+      "epoch": 0.5320074580484773,
+      "grad_norm": 0.42254915833473206,
+      "learning_rate": 9.436423160443625e-05,
+      "loss": 0.4657,
+      "step": 428
+    },
+    {
+      "epoch": 0.5369794903666874,
+      "grad_norm": 0.4129006266593933,
+      "learning_rate": 9.275651998382377e-05,
+      "loss": 0.4635,
+      "step": 432
+    },
+    {
+      "epoch": 0.5419515226848974,
+      "grad_norm": 0.43645158410072327,
+      "learning_rate": 9.115068840886417e-05,
+      "loss": 0.4568,
+      "step": 436
+    },
+    {
+      "epoch": 0.5469235550031075,
+      "grad_norm": 0.41948822140693665,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4655,
+      "step": 440
+    },
+    {
+      "epoch": 0.5518955873213176,
+      "grad_norm": 0.4248465895652771,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.4694,
+      "step": 444
+    },
+    {
+      "epoch": 0.5568676196395277,
+      "grad_norm": 0.42567265033721924,
+      "learning_rate": 8.634863880592686e-05,
+      "loss": 0.454,
+      "step": 448
+    },
+    {
+      "epoch": 0.5618396519577378,
+      "grad_norm": 0.4329916834831238,
+      "learning_rate": 8.475448884896547e-05,
+      "loss": 0.4609,
+      "step": 452
+    },
+    {
+      "epoch": 0.5668116842759477,
+      "grad_norm": 0.40616366267204285,
+      "learning_rate": 8.316429586529615e-05,
+      "loss": 0.4641,
+      "step": 456
+    },
+    {
+      "epoch": 0.5717837165941578,
+      "grad_norm": 0.4116172790527344,
+      "learning_rate": 8.157847258959885e-05,
+      "loss": 0.4484,
+      "step": 460
+    },
+    {
+      "epoch": 0.5767557489123679,
+      "grad_norm": 0.43640103936195374,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.4582,
+      "step": 464
+    },
+    {
+      "epoch": 0.581727781230578,
+      "grad_norm": 0.41392359137535095,
+      "learning_rate": 7.84215803232194e-05,
+      "loss": 0.4434,
+      "step": 468
+    },
+    {
+      "epoch": 0.5866998135487881,
+      "grad_norm": 0.4084075093269348,
+      "learning_rate": 7.685133070410571e-05,
+      "loss": 0.4722,
+      "step": 472
+    },
+    {
+      "epoch": 0.5916718458669982,
+      "grad_norm": 0.4227941632270813,
+      "learning_rate": 7.528708932343304e-05,
+      "loss": 0.4517,
+      "step": 476
+    },
+    {
+      "epoch": 0.5966438781852083,
+      "grad_norm": 0.44045257568359375,
+      "learning_rate": 7.372926218014131e-05,
+      "loss": 0.4625,
+      "step": 480
+    },
+    {
+      "epoch": 0.6016159105034182,
+      "grad_norm": 0.4112107753753662,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.4539,
+      "step": 484
+    },
+    {
+      "epoch": 0.6065879428216283,
+      "grad_norm": 0.4590305685997009,
+      "learning_rate": 7.063446617243694e-05,
+      "loss": 0.4518,
+      "step": 488
+    },
+    {
+      "epoch": 0.6115599751398384,
+      "grad_norm": 0.4143747389316559,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4495,
+      "step": 492
+    },
+    {
+      "epoch": 0.6165320074580485,
+      "grad_norm": 0.4207197427749634,
+      "learning_rate": 6.757015549043175e-05,
+      "loss": 0.4594,
+      "step": 496
+    },
+    {
+      "epoch": 0.6215040397762586,
+      "grad_norm": 0.4427318274974823,
+      "learning_rate": 6.605042758635729e-05,
+      "loss": 0.4483,
+      "step": 500
+    },
+    {
+      "epoch": 0.6264760720944687,
+      "grad_norm": 0.42062947154045105,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.4548,
+      "step": 504
+    },
+    {
+      "epoch": 0.6314481044126787,
+      "grad_norm": 0.40602120757102966,
+      "learning_rate": 6.30377987770089e-05,
+      "loss": 0.4541,
+      "step": 508
+    },
+    {
+      "epoch": 0.6364201367308887,
+      "grad_norm": 0.4235445261001587,
+      "learning_rate": 6.154567979971493e-05,
+      "loss": 0.4547,
+      "step": 512
+    },
+    {
+      "epoch": 0.6413921690490988,
+      "grad_norm": 0.4362446367740631,
+      "learning_rate": 6.006354164343046e-05,
+      "loss": 0.4648,
+      "step": 516
+    },
+    {
+      "epoch": 0.6463642013673089,
+      "grad_norm": 0.4211137890815735,
+      "learning_rate": 5.859176899719883e-05,
+      "loss": 0.4467,
+      "step": 520
+    },
+    {
+      "epoch": 0.651336233685519,
+      "grad_norm": 0.423961341381073,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.4554,
+      "step": 524
+    },
+    {
+      "epoch": 0.656308266003729,
+      "grad_norm": 0.4417620003223419,
+      "learning_rate": 5.568084544007588e-05,
+      "loss": 0.4681,
+      "step": 528
+    },
+    {
+      "epoch": 0.6612802983219391,
+      "grad_norm": 0.4363749921321869,
+      "learning_rate": 5.424245005956048e-05,
+      "loss": 0.4389,
+      "step": 532
+    },
+    {
+      "epoch": 0.6662523306401492,
+      "grad_norm": 0.42354437708854675,
+      "learning_rate": 5.28159310537518e-05,
+      "loss": 0.4524,
+      "step": 536
+    },
+    {
+      "epoch": 0.6712243629583592,
+      "grad_norm": 0.42178061604499817,
+      "learning_rate": 5.14016586757394e-05,
+      "loss": 0.4473,
+      "step": 540
+    },
+    {
+      "epoch": 0.6761963952765693,
+      "grad_norm": 0.4353598356246948,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4473,
+      "step": 544
+    },
+    {
+      "epoch": 0.6811684275947794,
+      "grad_norm": 0.4380674362182617,
+      "learning_rate": 4.861131882712314e-05,
+      "loss": 0.4579,
+      "step": 548
+    },
+    {
+      "epoch": 0.6861404599129894,
+      "grad_norm": 0.4278354048728943,
+      "learning_rate": 4.723597558938672e-05,
+      "loss": 0.4355,
+      "step": 552
+    },
+    {
+      "epoch": 0.6911124922311995,
+      "grad_norm": 0.41823214292526245,
+      "learning_rate": 4.587432725720687e-05,
+      "loss": 0.4394,
+      "step": 556
+    },
+    {
+      "epoch": 0.6960845245494096,
+      "grad_norm": 0.43046334385871887,
+      "learning_rate": 4.452672724648611e-05,
+      "loss": 0.4529,
+      "step": 560
+    },
+    {
+      "epoch": 0.7010565568676196,
+      "grad_norm": 0.430922269821167,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.4462,
+      "step": 564
+    },
+    {
+      "epoch": 0.7060285891858297,
+      "grad_norm": 0.4363158345222473,
+      "learning_rate": 4.1875067531036374e-05,
+      "loss": 0.458,
+      "step": 568
+    },
+    {
+      "epoch": 0.7110006215040398,
+      "grad_norm": 0.41834723949432373,
+      "learning_rate": 4.057169606473827e-05,
+      "loss": 0.4548,
+      "step": 572
+    },
+    {
+      "epoch": 0.7159726538222498,
+      "grad_norm": 0.4106977880001068,
+      "learning_rate": 3.9283749218128885e-05,
+      "loss": 0.463,
+      "step": 576
+    },
+    {
+      "epoch": 0.7209446861404599,
+      "grad_norm": 0.45078086853027344,
+      "learning_rate": 3.8011561277885964e-05,
+      "loss": 0.4459,
+      "step": 580
+    },
+    {
+      "epoch": 0.72591671845867,
+      "grad_norm": 0.4266386330127716,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.438,
+      "step": 584
+    },
+    {
+      "epoch": 0.7308887507768801,
+      "grad_norm": 0.4289485514163971,
+      "learning_rate": 3.5515778726382966e-05,
+      "loss": 0.4522,
+      "step": 588
+    },
+    {
+      "epoch": 0.7358607830950901,
+      "grad_norm": 0.4158768057823181,
+      "learning_rate": 3.429283189562694e-05,
+      "loss": 0.4424,
+      "step": 592
+    },
+    {
+      "epoch": 0.7408328154133001,
+      "grad_norm": 0.4208343029022217,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.4311,
+      "step": 596
+    },
+    {
+      "epoch": 0.7458048477315102,
+      "grad_norm": 0.44292351603507996,
+      "learning_rate": 3.1898414121320276e-05,
+      "loss": 0.4454,
+      "step": 600
+    },
+    {
+      "epoch": 0.7507768800497203,
+      "grad_norm": 0.4283224940299988,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.4323,
+      "step": 604
+    },
+    {
+      "epoch": 0.7557489123679304,
+      "grad_norm": 0.4522048234939575,
+      "learning_rate": 2.9574694841321082e-05,
+      "loss": 0.4514,
+      "step": 608
+    },
+    {
+      "epoch": 0.7607209446861405,
+      "grad_norm": 0.41480395197868347,
+      "learning_rate": 2.84401039255879e-05,
+      "loss": 0.4422,
+      "step": 612
+    },
+    {
+      "epoch": 0.7656929770043506,
+      "grad_norm": 0.43344831466674805,
+      "learning_rate": 2.7324086384977698e-05,
+      "loss": 0.443,
+      "step": 616
+    },
+    {
+      "epoch": 0.7706650093225605,
+      "grad_norm": 0.4390140175819397,
+      "learning_rate": 2.622693188190699e-05,
+      "loss": 0.4655,
+      "step": 620
+    },
+    {
+      "epoch": 0.7756370416407706,
+      "grad_norm": 0.41029900312423706,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.4196,
+      "step": 624
+    },
+    {
+      "epoch": 0.7806090739589807,
+      "grad_norm": 0.413832426071167,
+      "learning_rate": 2.409034608462686e-05,
+      "loss": 0.4396,
+      "step": 628
+    },
+    {
+      "epoch": 0.7855811062771908,
+      "grad_norm": 0.43535104393959045,
+      "learning_rate": 2.3051469341383402e-05,
+      "loss": 0.4353,
+      "step": 632
+    },
+    {
+      "epoch": 0.7905531385954009,
+      "grad_norm": 0.44554823637008667,
+      "learning_rate": 2.2032564593677774e-05,
+      "loss": 0.4568,
+      "step": 636
+    },
+    {
+      "epoch": 0.795525170913611,
+      "grad_norm": 0.4224577844142914,
+      "learning_rate": 2.1033896298295508e-05,
+      "loss": 0.4414,
+      "step": 640
+    },
+    {
+      "epoch": 0.800497203231821,
+      "grad_norm": 0.4140743017196655,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.4399,
+      "step": 644
+    },
+    {
+      "epoch": 0.805469235550031,
+      "grad_norm": 0.43011415004730225,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4549,
+      "step": 648
+    },
+    {
+      "epoch": 0.8104412678682411,
+      "grad_norm": 0.4245777130126953,
+      "learning_rate": 1.8161875506081293e-05,
+      "loss": 0.4444,
+      "step": 652
+    },
+    {
+      "epoch": 0.8154133001864512,
+      "grad_norm": 0.44440820813179016,
+      "learning_rate": 1.7246691539555028e-05,
+      "loss": 0.46,
+      "step": 656
+    },
+    {
+      "epoch": 0.8203853325046613,
+      "grad_norm": 0.414103627204895,
+      "learning_rate": 1.6352986198977325e-05,
+      "loss": 0.4532,
+      "step": 660
+    },
+    {
+      "epoch": 0.8253573648228714,
+      "grad_norm": 0.41898444294929504,
+      "learning_rate": 1.5480991445620542e-05,
+      "loss": 0.4517,
+      "step": 664
+    },
+    {
+      "epoch": 0.8303293971410814,
+      "grad_norm": 0.4177073836326599,
+      "learning_rate": 1.4630933605772801e-05,
+      "loss": 0.4335,
+      "step": 668
+    },
+    {
+      "epoch": 0.8353014294592915,
+      "grad_norm": 0.4281357228755951,
+      "learning_rate": 1.3803033311995072e-05,
+      "loss": 0.4573,
+      "step": 672
+    },
+    {
+      "epoch": 0.8402734617775015,
+      "grad_norm": 0.4267916977405548,
+      "learning_rate": 1.2997505445856084e-05,
+      "loss": 0.4387,
+      "step": 676
+    },
+    {
+      "epoch": 0.8452454940957116,
+      "grad_norm": 0.42911484837532043,
+      "learning_rate": 1.2214559082159537e-05,
+      "loss": 0.4339,
+      "step": 680
+    },
+    {
+      "epoch": 0.8502175264139217,
+      "grad_norm": 0.4185105264186859,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.4453,
+      "step": 684
+    },
+    {
+      "epoch": 0.8551895587321318,
+      "grad_norm": 0.4304141104221344,
+      "learning_rate": 1.0717217803413604e-05,
+      "loss": 0.4403,
+      "step": 688
+    },
+    {
+      "epoch": 0.8601615910503418,
+      "grad_norm": 0.43691304326057434,
+      "learning_rate": 1.0003211523378796e-05,
+      "loss": 0.4349,
+      "step": 692
+    },
+    {
+      "epoch": 0.8651336233685519,
+      "grad_norm": 0.4254210889339447,
+      "learning_rate": 9.31256391494546e-06,
+      "loss": 0.4312,
+      "step": 696
+    },
+    {
+      "epoch": 0.870105655686762,
+      "grad_norm": 0.4237820506095886,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4435,
+      "step": 700
+    },
+    {
+      "epoch": 0.875077688004972,
+      "grad_norm": 0.4290446639060974,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.4314,
+      "step": 704
+    },
+    {
+      "epoch": 0.8800497203231821,
+      "grad_norm": 0.41713830828666687,
+      "learning_rate": 7.382535104222366e-06,
+      "loss": 0.4261,
+      "step": 708
+    },
+    {
+      "epoch": 0.8850217526413922,
+      "grad_norm": 0.442330539226532,
+      "learning_rate": 6.787053442643232e-06,
+      "loss": 0.435,
+      "step": 712
+    },
+    {
+      "epoch": 0.8899937849596022,
+      "grad_norm": 0.4291313588619232,
+      "learning_rate": 6.215765206679569e-06,
+      "loss": 0.4309,
+      "step": 716
+    },
+    {
+      "epoch": 0.8949658172778123,
+      "grad_norm": 0.4301079511642456,
+      "learning_rate": 5.668818674225685e-06,
+      "loss": 0.442,
+      "step": 720
+    },
+    {
+      "epoch": 0.8999378495960224,
+      "grad_norm": 0.43183088302612305,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.4403,
+      "step": 724
+    },
+    {
+      "epoch": 0.9049098819142325,
+      "grad_norm": 0.42470988631248474,
+      "learning_rate": 4.648512205126376e-06,
+      "loss": 0.4464,
+      "step": 728
+    },
+    {
+      "epoch": 0.9098819142324425,
+      "grad_norm": 0.4176940619945526,
+      "learning_rate": 4.175417089083378e-06,
+      "loss": 0.4201,
+      "step": 732
+    },
+    {
+      "epoch": 0.9148539465506526,
+      "grad_norm": 0.419644832611084,
+      "learning_rate": 3.7271932490209328e-06,
+      "loss": 0.4389,
+      "step": 736
+    },
+    {
+      "epoch": 0.9198259788688626,
+      "grad_norm": 0.4146890640258789,
+      "learning_rate": 3.3039570214623782e-06,
+      "loss": 0.4538,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247980111870727,
+      "grad_norm": 0.4463767409324646,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.4284,
+      "step": 744
+    },
+    {
+      "epoch": 0.9297700435052828,
+      "grad_norm": 0.4303642511367798,
+      "learning_rate": 2.532880293757223e-06,
+      "loss": 0.4363,
+      "step": 748
+    },
+    {
+      "epoch": 0.9347420758234929,
+      "grad_norm": 0.42455166578292847,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4615,
+      "step": 752
+    },
+    {
+      "epoch": 0.939714108141703,
+      "grad_norm": 0.41838544607162476,
+      "learning_rate": 1.8629873860586566e-06,
+      "loss": 0.4357,
+      "step": 756
+    },
+    {
+      "epoch": 0.944686140459913,
+      "grad_norm": 0.42117899656295776,
+      "learning_rate": 1.566206312740226e-06,
+      "loss": 0.4337,
+      "step": 760
+    },
+    {
+      "epoch": 0.949658172778123,
+      "grad_norm": 0.439235121011734,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.4414,
+      "step": 764
+    },
+    {
+      "epoch": 0.9546302050963331,
+      "grad_norm": 0.45641785860061646,
+      "learning_rate": 1.0493600548948878e-06,
+      "loss": 0.439,
+      "step": 768
+    },
+    {
+      "epoch": 0.9596022374145432,
+      "grad_norm": 0.4211345314979553,
+      "learning_rate": 8.294290178437969e-07,
+      "loss": 0.4444,
+      "step": 772
+    },
+    {
+      "epoch": 0.9645742697327533,
+      "grad_norm": 0.4054080843925476,
+      "learning_rate": 6.352377081687011e-07,
+      "loss": 0.4328,
+      "step": 776
+    },
+    {
+      "epoch": 0.9695463020509634,
+      "grad_norm": 0.39851078391075134,
+      "learning_rate": 4.668365282351372e-07,
+      "loss": 0.4389,
+      "step": 780
+    },
+    {
+      "epoch": 0.9745183343691733,
+      "grad_norm": 0.42228272557258606,
+      "learning_rate": 3.2426918657900704e-07,
+      "loss": 0.43,
+      "step": 784
+    },
+    {
+      "epoch": 0.9794903666873834,
+      "grad_norm": 0.42619001865386963,
+      "learning_rate": 2.0757268656198537e-07,
+      "loss": 0.4424,
+      "step": 788
+    },
+    {
+      "epoch": 0.9844623990055935,
+      "grad_norm": 0.4146987199783325,
+      "learning_rate": 1.1677731676733584e-07,
+      "loss": 0.4475,
+      "step": 792
+    },
+    {
+      "epoch": 0.9894344313238036,
+      "grad_norm": 0.39335352182388306,
+      "learning_rate": 5.190664313851068e-08,
+      "loss": 0.4391,
+      "step": 796
+    },
+    {
+      "epoch": 0.9944064636420137,
+      "grad_norm": 0.418887734413147,
+      "learning_rate": 1.2977502862532297e-08,
+      "loss": 0.4308,
+      "step": 800
+    },
+    {
+      "epoch": 0.9993784959602238,
+      "grad_norm": 0.4512234926223755,
+      "learning_rate": 0.0,
+      "loss": 0.4518,
+      "step": 804
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.314262857038168e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f718fd33a2e6d902c835f6a4079d56fd7c1f1f2b1468872a64c0d3cd5eef86de
+size 6776

config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}