Upload folder using huggingface_hub

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Navid-AI/Yehia-7B-preview
+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

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Navid-AI/Yehia-7B-preview",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040b0c46086d5de5d700de069e1c794492e4cb923a9e4d58602ef0948f72dd1e
+size 639691872

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfef32a52ae29e03f1575a3a80001ea318020b974ed80cb26af8e2d0076995c
+size 325356005

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6e019b42245a715c34362e58a5c13bf6ad36e7fd7bd7394dca498a4332db9d
+size 14645

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d0c717e37076f80c8ef7c63477b9e91d848076cbc196766bdea83f45036c76
+size 1465

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/special_tokens_map.json

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

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feff3deb3537c4a47b77585053ad2aa00484da7907b188e0111cbed1f4592e67
+size 1228714

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/tokenizer_config.json

@@ -0,0 +1,205 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "3": {
+      "content": "0",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "1",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "2",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "3",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "4",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "5",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "6",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "7",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "8",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "9",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "٠",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "١",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "٢",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "٣",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "٤",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "٥",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "٦",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "٧",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "٨",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "٩",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/trainer_state.json

@@ -0,0 +1,1679 @@
+{
+  "best_metric": 2.220811367034912,
+  "best_model_checkpoint": "/root/workspace/Shaer/sft/outputs/train/train_20260407_231929/checkpoint-2200",
+  "epoch": 1.0386544703452345,
+  "eval_steps": 200,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00047211566833874297,
+      "grad_norm": 30.142330169677734,
+      "learning_rate": 6.25e-07,
+      "loss": 3.0146,
+      "step": 1
+    },
+    {
+      "epoch": 0.00472115668338743,
+      "grad_norm": 8.47068977355957,
+      "learning_rate": 6.25e-06,
+      "loss": 2.8822,
+      "step": 10
+    },
+    {
+      "epoch": 0.00944231336677486,
+      "grad_norm": 6.628307342529297,
+      "learning_rate": 1.25e-05,
+      "loss": 2.637,
+      "step": 20
+    },
+    {
+      "epoch": 0.01416347005016229,
+      "grad_norm": 6.049447536468506,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 2.5786,
+      "step": 30
+    },
+    {
+      "epoch": 0.01888462673354972,
+      "grad_norm": 5.447391510009766,
+      "learning_rate": 2.5e-05,
+      "loss": 2.5111,
+      "step": 40
+    },
+    {
+      "epoch": 0.02360578341693715,
+      "grad_norm": 5.204133033752441,
+      "learning_rate": 3.125e-05,
+      "loss": 2.4953,
+      "step": 50
+    },
+    {
+      "epoch": 0.02832694010032458,
+      "grad_norm": 4.883266925811768,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.3978,
+      "step": 60
+    },
+    {
+      "epoch": 0.03304809678371201,
+      "grad_norm": 4.5991668701171875,
+      "learning_rate": 4.3750000000000006e-05,
+      "loss": 2.5324,
+      "step": 70
+    },
+    {
+      "epoch": 0.03776925346709944,
+      "grad_norm": 4.424217224121094,
+      "learning_rate": 5e-05,
+      "loss": 2.4601,
+      "step": 80
+    },
+    {
+      "epoch": 0.04249041015048687,
+      "grad_norm": 4.650262832641602,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 2.3872,
+      "step": 90
+    },
+    {
+      "epoch": 0.0472115668338743,
+      "grad_norm": 4.841930866241455,
+      "learning_rate": 6.25e-05,
+      "loss": 2.5049,
+      "step": 100
+    },
+    {
+      "epoch": 0.05193272351726173,
+      "grad_norm": 4.097159385681152,
+      "learning_rate": 6.875e-05,
+      "loss": 2.4224,
+      "step": 110
+    },
+    {
+      "epoch": 0.05665388020064916,
+      "grad_norm": 4.343025207519531,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.46,
+      "step": 120
+    },
+    {
+      "epoch": 0.06137503688403659,
+      "grad_norm": 4.271331787109375,
+      "learning_rate": 7.999995321261445e-05,
+      "loss": 2.4338,
+      "step": 130
+    },
+    {
+      "epoch": 0.06609619356742402,
+      "grad_norm": 3.785423994064331,
+      "learning_rate": 7.999831566561234e-05,
+      "loss": 2.4077,
+      "step": 140
+    },
+    {
+      "epoch": 0.07081735025081144,
+      "grad_norm": 3.9054527282714844,
+      "learning_rate": 7.999433885878404e-05,
+      "loss": 2.3977,
+      "step": 150
+    },
+    {
+      "epoch": 0.07553850693419888,
+      "grad_norm": 4.048571586608887,
+      "learning_rate": 7.998802302470891e-05,
+      "loss": 2.4109,
+      "step": 160
+    },
+    {
+      "epoch": 0.08025966361758631,
+      "grad_norm": 3.7052175998687744,
+      "learning_rate": 7.997936853276194e-05,
+      "loss": 2.3596,
+      "step": 170
+    },
+    {
+      "epoch": 0.08498082030097374,
+      "grad_norm": 4.4373626708984375,
+      "learning_rate": 7.996837588909207e-05,
+      "loss": 2.3011,
+      "step": 180
+    },
+    {
+      "epoch": 0.08970197698436116,
+      "grad_norm": 3.7303075790405273,
+      "learning_rate": 7.995504573659266e-05,
+      "loss": 2.3416,
+      "step": 190
+    },
+    {
+      "epoch": 0.0944231336677486,
+      "grad_norm": 3.744011640548706,
+      "learning_rate": 7.993937885486372e-05,
+      "loss": 2.3189,
+      "step": 200
+    },
+    {
+      "epoch": 0.0944231336677486,
+      "eval_loss": 2.3407740592956543,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 350.1688,
+      "eval_samples_per_second": 9.941,
+      "eval_steps_per_second": 9.941,
+      "step": 200
+    },
+    {
+      "epoch": 0.09914429035113603,
+      "grad_norm": 3.7035298347473145,
+      "learning_rate": 7.992137616016654e-05,
+      "loss": 2.365,
+      "step": 210
+    },
+    {
+      "epoch": 0.10386544703452345,
+      "grad_norm": 3.529247283935547,
+      "learning_rate": 7.990103870537e-05,
+      "loss": 2.3329,
+      "step": 220
+    },
+    {
+      "epoch": 0.10858660371791089,
+      "grad_norm": 3.8830602169036865,
+      "learning_rate": 7.98783676798889e-05,
+      "loss": 2.3873,
+      "step": 230
+    },
+    {
+      "epoch": 0.11330776040129832,
+      "grad_norm": 3.476334571838379,
+      "learning_rate": 7.985336440961461e-05,
+      "loss": 2.2371,
+      "step": 240
+    },
+    {
+      "epoch": 0.11802891708468574,
+      "grad_norm": 4.167378902435303,
+      "learning_rate": 7.982603035683727e-05,
+      "loss": 2.3619,
+      "step": 250
+    },
+    {
+      "epoch": 0.12275007376807318,
+      "grad_norm": 3.4892165660858154,
+      "learning_rate": 7.979636712016057e-05,
+      "loss": 2.2421,
+      "step": 260
+    },
+    {
+      "epoch": 0.1274712304514606,
+      "grad_norm": 3.373124599456787,
+      "learning_rate": 7.976437643440794e-05,
+      "loss": 2.3554,
+      "step": 270
+    },
+    {
+      "epoch": 0.13219238713484804,
+      "grad_norm": 3.5341732501983643,
+      "learning_rate": 7.973006017052134e-05,
+      "loss": 2.286,
+      "step": 280
+    },
+    {
+      "epoch": 0.13691354381823548,
+      "grad_norm": 4.150211334228516,
+      "learning_rate": 7.969342033545173e-05,
+      "loss": 2.2679,
+      "step": 290
+    },
+    {
+      "epoch": 0.14163470050162288,
+      "grad_norm": 3.900872230529785,
+      "learning_rate": 7.965445907204167e-05,
+      "loss": 2.2735,
+      "step": 300
+    },
+    {
+      "epoch": 0.14635585718501032,
+      "grad_norm": 3.468568801879883,
+      "learning_rate": 7.961317865890009e-05,
+      "loss": 2.2891,
+      "step": 310
+    },
+    {
+      "epoch": 0.15107701386839775,
+      "grad_norm": 4.023585796356201,
+      "learning_rate": 7.956958151026892e-05,
+      "loss": 2.296,
+      "step": 320
+    },
+    {
+      "epoch": 0.1557981705517852,
+      "grad_norm": 3.8859283924102783,
+      "learning_rate": 7.952367017588201e-05,
+      "loss": 2.2715,
+      "step": 330
+    },
+    {
+      "epoch": 0.16051932723517262,
+      "grad_norm": 3.8064515590667725,
+      "learning_rate": 7.947544734081591e-05,
+      "loss": 2.2985,
+      "step": 340
+    },
+    {
+      "epoch": 0.16524048391856005,
+      "grad_norm": 3.9534919261932373,
+      "learning_rate": 7.942491582533292e-05,
+      "loss": 2.1724,
+      "step": 350
+    },
+    {
+      "epoch": 0.1699616406019475,
+      "grad_norm": 3.795976400375366,
+      "learning_rate": 7.937207858471606e-05,
+      "loss": 2.2274,
+      "step": 360
+    },
+    {
+      "epoch": 0.1746827972853349,
+      "grad_norm": 3.661334991455078,
+      "learning_rate": 7.931693870909632e-05,
+      "loss": 2.1867,
+      "step": 370
+    },
+    {
+      "epoch": 0.17940395396872233,
+      "grad_norm": 3.495767116546631,
+      "learning_rate": 7.925949942327188e-05,
+      "loss": 2.3057,
+      "step": 380
+    },
+    {
+      "epoch": 0.18412511065210976,
+      "grad_norm": 4.623363494873047,
+      "learning_rate": 7.919976408651955e-05,
+      "loss": 2.1401,
+      "step": 390
+    },
+    {
+      "epoch": 0.1888462673354972,
+      "grad_norm": 3.796987295150757,
+      "learning_rate": 7.913773619239826e-05,
+      "loss": 2.3061,
+      "step": 400
+    },
+    {
+      "epoch": 0.1888462673354972,
+      "eval_loss": 2.299203872680664,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 353.4444,
+      "eval_samples_per_second": 9.849,
+      "eval_steps_per_second": 9.849,
+      "step": 400
+    },
+    {
+      "epoch": 0.19356742401888463,
+      "grad_norm": 4.216252326965332,
+      "learning_rate": 7.90734193685448e-05,
+      "loss": 2.1973,
+      "step": 410
+    },
+    {
+      "epoch": 0.19828858070227207,
+      "grad_norm": 3.813667058944702,
+      "learning_rate": 7.900681737646161e-05,
+      "loss": 2.1532,
+      "step": 420
+    },
+    {
+      "epoch": 0.2030097373856595,
+      "grad_norm": 4.209104061126709,
+      "learning_rate": 7.89379341112968e-05,
+      "loss": 2.22,
+      "step": 430
+    },
+    {
+      "epoch": 0.2077308940690469,
+      "grad_norm": 3.4763920307159424,
+      "learning_rate": 7.88667736016164e-05,
+      "loss": 2.0545,
+      "step": 440
+    },
+    {
+      "epoch": 0.21245205075243434,
+      "grad_norm": 3.641535520553589,
+      "learning_rate": 7.87933400091687e-05,
+      "loss": 2.0677,
+      "step": 450
+    },
+    {
+      "epoch": 0.21717320743582177,
+      "grad_norm": 3.803286075592041,
+      "learning_rate": 7.871763762864084e-05,
+      "loss": 2.1762,
+      "step": 460
+    },
+    {
+      "epoch": 0.2218943641192092,
+      "grad_norm": 3.9546217918395996,
+      "learning_rate": 7.86396708874077e-05,
+      "loss": 2.1684,
+      "step": 470
+    },
+    {
+      "epoch": 0.22661552080259664,
+      "grad_norm": 4.3554606437683105,
+      "learning_rate": 7.855944434527292e-05,
+      "loss": 2.1964,
+      "step": 480
+    },
+    {
+      "epoch": 0.23133667748598408,
+      "grad_norm": 3.782496929168701,
+      "learning_rate": 7.847696269420224e-05,
+      "loss": 2.1335,
+      "step": 490
+    },
+    {
+      "epoch": 0.23605783416937148,
+      "grad_norm": 3.415630340576172,
+      "learning_rate": 7.839223075804911e-05,
+      "loss": 2.2143,
+      "step": 500
+    },
+    {
+      "epoch": 0.24077899085275892,
+      "grad_norm": 3.917701005935669,
+      "learning_rate": 7.830525349227256e-05,
+      "loss": 2.0401,
+      "step": 510
+    },
+    {
+      "epoch": 0.24550014753614635,
+      "grad_norm": 4.105495929718018,
+      "learning_rate": 7.821603598364735e-05,
+      "loss": 2.103,
+      "step": 520
+    },
+    {
+      "epoch": 0.2502213042195338,
+      "grad_norm": 3.6898550987243652,
+      "learning_rate": 7.812458344996656e-05,
+      "loss": 2.1612,
+      "step": 530
+    },
+    {
+      "epoch": 0.2549424609029212,
+      "grad_norm": 4.940375328063965,
+      "learning_rate": 7.803090123973636e-05,
+      "loss": 2.0302,
+      "step": 540
+    },
+    {
+      "epoch": 0.2596636175863086,
+      "grad_norm": 4.549220561981201,
+      "learning_rate": 7.793499483186321e-05,
+      "loss": 2.0838,
+      "step": 550
+    },
+    {
+      "epoch": 0.2643847742696961,
+      "grad_norm": 4.168620586395264,
+      "learning_rate": 7.783686983533349e-05,
+      "loss": 2.1059,
+      "step": 560
+    },
+    {
+      "epoch": 0.2691059309530835,
+      "grad_norm": 4.045541286468506,
+      "learning_rate": 7.773653198888539e-05,
+      "loss": 1.9832,
+      "step": 570
+    },
+    {
+      "epoch": 0.27382708763647096,
+      "grad_norm": 3.6355466842651367,
+      "learning_rate": 7.763398716067335e-05,
+      "loss": 2.1549,
+      "step": 580
+    },
+    {
+      "epoch": 0.27854824431985836,
+      "grad_norm": 4.54807710647583,
+      "learning_rate": 7.752924134792482e-05,
+      "loss": 2.0566,
+      "step": 590
+    },
+    {
+      "epoch": 0.28326940100324577,
+      "grad_norm": 3.9295012950897217,
+      "learning_rate": 7.742230067658956e-05,
+      "loss": 2.1123,
+      "step": 600
+    },
+    {
+      "epoch": 0.28326940100324577,
+      "eval_loss": 2.270296096801758,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 358.1373,
+      "eval_samples_per_second": 9.72,
+      "eval_steps_per_second": 9.72,
+      "step": 600
+    },
+    {
+      "epoch": 0.28799055768663323,
+      "grad_norm": 4.00673770904541,
+      "learning_rate": 7.731317140098132e-05,
+      "loss": 2.0683,
+      "step": 610
+    },
+    {
+      "epoch": 0.29271171437002064,
+      "grad_norm": 3.957310199737549,
+      "learning_rate": 7.720185990341213e-05,
+      "loss": 2.0445,
+      "step": 620
+    },
+    {
+      "epoch": 0.2974328710534081,
+      "grad_norm": 3.8637807369232178,
+      "learning_rate": 7.708837269381894e-05,
+      "loss": 2.0444,
+      "step": 630
+    },
+    {
+      "epoch": 0.3021540277367955,
+      "grad_norm": 3.878016471862793,
+      "learning_rate": 7.697271640938301e-05,
+      "loss": 2.162,
+      "step": 640
+    },
+    {
+      "epoch": 0.30687518442018297,
+      "grad_norm": 3.7371389865875244,
+      "learning_rate": 7.685489781414167e-05,
+      "loss": 2.1384,
+      "step": 650
+    },
+    {
+      "epoch": 0.3115963411035704,
+      "grad_norm": 3.849411725997925,
+      "learning_rate": 7.673492379859269e-05,
+      "loss": 2.1002,
+      "step": 660
+    },
+    {
+      "epoch": 0.3163174977869578,
+      "grad_norm": 4.087588310241699,
+      "learning_rate": 7.661280137929142e-05,
+      "loss": 2.043,
+      "step": 670
+    },
+    {
+      "epoch": 0.32103865447034524,
+      "grad_norm": 4.038987636566162,
+      "learning_rate": 7.648853769844036e-05,
+      "loss": 2.0346,
+      "step": 680
+    },
+    {
+      "epoch": 0.32575981115373265,
+      "grad_norm": 4.1521806716918945,
+      "learning_rate": 7.636214002347141e-05,
+      "loss": 2.0754,
+      "step": 690
+    },
+    {
+      "epoch": 0.3304809678371201,
+      "grad_norm": 3.7634150981903076,
+      "learning_rate": 7.623361574662094e-05,
+      "loss": 2.0254,
+      "step": 700
+    },
+    {
+      "epoch": 0.3352021245205075,
+      "grad_norm": 3.9338746070861816,
+      "learning_rate": 7.610297238449738e-05,
+      "loss": 2.1953,
+      "step": 710
+    },
+    {
+      "epoch": 0.339923281203895,
+      "grad_norm": 4.635639667510986,
+      "learning_rate": 7.597021757764171e-05,
+      "loss": 2.1131,
+      "step": 720
+    },
+    {
+      "epoch": 0.3446444378872824,
+      "grad_norm": 3.961137533187866,
+      "learning_rate": 7.58353590900805e-05,
+      "loss": 2.0124,
+      "step": 730
+    },
+    {
+      "epoch": 0.3493655945706698,
+      "grad_norm": 4.165374755859375,
+      "learning_rate": 7.569840480887191e-05,
+      "loss": 1.9259,
+      "step": 740
+    },
+    {
+      "epoch": 0.35408675125405725,
+      "grad_norm": 3.9706571102142334,
+      "learning_rate": 7.555936274364443e-05,
+      "loss": 2.0454,
+      "step": 750
+    },
+    {
+      "epoch": 0.35880790793744466,
+      "grad_norm": 4.537285327911377,
+      "learning_rate": 7.541824102612839e-05,
+      "loss": 2.1438,
+      "step": 760
+    },
+    {
+      "epoch": 0.3635290646208321,
+      "grad_norm": 3.926957607269287,
+      "learning_rate": 7.527504790968045e-05,
+      "loss": 1.9368,
+      "step": 770
+    },
+    {
+      "epoch": 0.3682502213042195,
+      "grad_norm": 4.3333282470703125,
+      "learning_rate": 7.512979176880088e-05,
+      "loss": 2.1462,
+      "step": 780
+    },
+    {
+      "epoch": 0.372971377987607,
+      "grad_norm": 4.292292594909668,
+      "learning_rate": 7.498248109864372e-05,
+      "loss": 1.9981,
+      "step": 790
+    },
+    {
+      "epoch": 0.3776925346709944,
+      "grad_norm": 4.474006652832031,
+      "learning_rate": 7.48331245145201e-05,
+      "loss": 2.0891,
+      "step": 800
+    },
+    {
+      "epoch": 0.3776925346709944,
+      "eval_loss": 2.262274980545044,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 348.9285,
+      "eval_samples_per_second": 9.976,
+      "eval_steps_per_second": 9.976,
+      "step": 800
+    },
+    {
+      "epoch": 0.3824136913543818,
+      "grad_norm": 4.182672023773193,
+      "learning_rate": 7.468173075139425e-05,
+      "loss": 1.9381,
+      "step": 810
+    },
+    {
+      "epoch": 0.38713484803776926,
+      "grad_norm": 3.8186705112457275,
+      "learning_rate": 7.45283086633727e-05,
+      "loss": 1.9693,
+      "step": 820
+    },
+    {
+      "epoch": 0.39185600472115667,
+      "grad_norm": 4.7852888107299805,
+      "learning_rate": 7.437286722318645e-05,
+      "loss": 1.9011,
+      "step": 830
+    },
+    {
+      "epoch": 0.39657716140454413,
+      "grad_norm": 3.930708169937134,
+      "learning_rate": 7.421541552166622e-05,
+      "loss": 1.9544,
+      "step": 840
+    },
+    {
+      "epoch": 0.40129831808793154,
+      "grad_norm": 4.753180980682373,
+      "learning_rate": 7.405596276721074e-05,
+      "loss": 2.0506,
+      "step": 850
+    },
+    {
+      "epoch": 0.406019474771319,
+      "grad_norm": 4.257161617279053,
+      "learning_rate": 7.389451828524829e-05,
+      "loss": 1.9308,
+      "step": 860
+    },
+    {
+      "epoch": 0.4107406314547064,
+      "grad_norm": 5.31283712387085,
+      "learning_rate": 7.373109151769119e-05,
+      "loss": 1.9768,
+      "step": 870
+    },
+    {
+      "epoch": 0.4154617881380938,
+      "grad_norm": 4.300612449645996,
+      "learning_rate": 7.356569202238371e-05,
+      "loss": 2.0375,
+      "step": 880
+    },
+    {
+      "epoch": 0.4201829448214813,
+      "grad_norm": 4.5614094734191895,
+      "learning_rate": 7.339832947254306e-05,
+      "loss": 1.9248,
+      "step": 890
+    },
+    {
+      "epoch": 0.4249041015048687,
+      "grad_norm": 4.338301658630371,
+      "learning_rate": 7.322901365619358e-05,
+      "loss": 1.8801,
+      "step": 900
+    },
+    {
+      "epoch": 0.42962525818825614,
+      "grad_norm": 3.872899293899536,
+      "learning_rate": 7.305775447559447e-05,
+      "loss": 1.9878,
+      "step": 910
+    },
+    {
+      "epoch": 0.43434641487164355,
+      "grad_norm": 4.370180130004883,
+      "learning_rate": 7.28845619466605e-05,
+      "loss": 1.9664,
+      "step": 920
+    },
+    {
+      "epoch": 0.43906757155503096,
+      "grad_norm": 4.291312217712402,
+      "learning_rate": 7.270944619837627e-05,
+      "loss": 1.8474,
+      "step": 930
+    },
+    {
+      "epoch": 0.4437887282384184,
+      "grad_norm": 3.5349154472351074,
+      "learning_rate": 7.253241747220396e-05,
+      "loss": 1.9619,
+      "step": 940
+    },
+    {
+      "epoch": 0.4485098849218058,
+      "grad_norm": 5.893964767456055,
+      "learning_rate": 7.235348612148418e-05,
+      "loss": 1.9513,
+      "step": 950
+    },
+    {
+      "epoch": 0.4532310416051933,
+      "grad_norm": 4.636342525482178,
+      "learning_rate": 7.21726626108306e-05,
+      "loss": 1.8982,
+      "step": 960
+    },
+    {
+      "epoch": 0.4579521982885807,
+      "grad_norm": 4.089775562286377,
+      "learning_rate": 7.198995751551786e-05,
+      "loss": 1.943,
+      "step": 970
+    },
+    {
+      "epoch": 0.46267335497196815,
+      "grad_norm": 4.312414646148682,
+      "learning_rate": 7.180538152086318e-05,
+      "loss": 1.8741,
+      "step": 980
+    },
+    {
+      "epoch": 0.46739451165535556,
+      "grad_norm": 4.798983097076416,
+      "learning_rate": 7.16189454216013e-05,
+      "loss": 1.993,
+      "step": 990
+    },
+    {
+      "epoch": 0.47211566833874297,
+      "grad_norm": 4.957833766937256,
+      "learning_rate": 7.143066012125329e-05,
+      "loss": 1.8977,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47211566833874297,
+      "eval_loss": 2.270979881286621,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 354.6354,
+      "eval_samples_per_second": 9.816,
+      "eval_steps_per_second": 9.816,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47683682502213043,
+      "grad_norm": 5.28878116607666,
+      "learning_rate": 7.12405366314888e-05,
+      "loss": 1.8539,
+      "step": 1010
+    },
+    {
+      "epoch": 0.48155798170551783,
+      "grad_norm": 4.075064659118652,
+      "learning_rate": 7.10485860714821e-05,
+      "loss": 1.9117,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4862791383889053,
+      "grad_norm": 3.6768486499786377,
+      "learning_rate": 7.085481966726173e-05,
+      "loss": 1.8832,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4910002950722927,
+      "grad_norm": 4.2224249839782715,
+      "learning_rate": 7.0659248751054e-05,
+      "loss": 1.95,
+      "step": 1040
+    },
+    {
+      "epoch": 0.49572145175568016,
+      "grad_norm": 3.894782304763794,
+      "learning_rate": 7.046188476062022e-05,
+      "loss": 1.8302,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5004426084390676,
+      "grad_norm": 4.565753936767578,
+      "learning_rate": 7.026273923858778e-05,
+      "loss": 1.8832,
+      "step": 1060
+    },
+    {
+      "epoch": 0.505163765122455,
+      "grad_norm": 3.9510011672973633,
+      "learning_rate": 7.006182383177509e-05,
+      "loss": 1.805,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5098849218058424,
+      "grad_norm": 4.6171135902404785,
+      "learning_rate": 6.985915029051043e-05,
+      "loss": 1.8188,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5146060784892299,
+      "grad_norm": 5.412513256072998,
+      "learning_rate": 6.965473046794474e-05,
+      "loss": 1.8574,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5193272351726173,
+      "grad_norm": 4.663681983947754,
+      "learning_rate": 6.94485763193584e-05,
+      "loss": 1.8357,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5240483918560047,
+      "grad_norm": 4.244945526123047,
+      "learning_rate": 6.924069990146203e-05,
+      "loss": 1.9796,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5287695485393922,
+      "grad_norm": 4.773306369781494,
+      "learning_rate": 6.903111337169141e-05,
+      "loss": 1.8257,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5334907052227795,
+      "grad_norm": 4.239148139953613,
+      "learning_rate": 6.881982898749641e-05,
+      "loss": 1.9188,
+      "step": 1130
+    },
+    {
+      "epoch": 0.538211861906167,
+      "grad_norm": 4.277487754821777,
+      "learning_rate": 6.860685910562414e-05,
+      "loss": 1.9054,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5429330185895545,
+      "grad_norm": 4.414243698120117,
+      "learning_rate": 6.83922161813963e-05,
+      "loss": 1.839,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5476541752729419,
+      "grad_norm": 6.298126697540283,
+      "learning_rate": 6.817591276798071e-05,
+      "loss": 1.8761,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5523753319563293,
+      "grad_norm": 4.1463236808776855,
+      "learning_rate": 6.795796151565721e-05,
+      "loss": 1.7762,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5570964886397167,
+      "grad_norm": 4.317230224609375,
+      "learning_rate": 6.773837517107774e-05,
+      "loss": 1.8916,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5618176453231042,
+      "grad_norm": 4.2871012687683105,
+      "learning_rate": 6.751716657652094e-05,
+      "loss": 1.8083,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5665388020064915,
+      "grad_norm": 3.9133455753326416,
+      "learning_rate": 6.7294348669141e-05,
+      "loss": 1.8111,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5665388020064915,
+      "eval_loss": 2.2480082511901855,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 352.6722,
+      "eval_samples_per_second": 9.87,
+      "eval_steps_per_second": 9.87,
+      "step": 1200
+    },
+    {
+      "epoch": 0.571259958689879,
+      "grad_norm": 4.487409591674805,
+      "learning_rate": 6.706993448021117e-05,
+      "loss": 1.9009,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5759811153732665,
+      "grad_norm": 4.244952201843262,
+      "learning_rate": 6.684393713436148e-05,
+      "loss": 1.9527,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5807022720566539,
+      "grad_norm": 4.0254807472229,
+      "learning_rate": 6.661636984881131e-05,
+      "loss": 1.7961,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5854234287400413,
+      "grad_norm": 4.555695533752441,
+      "learning_rate": 6.638724593259631e-05,
+      "loss": 1.862,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5901445854234287,
+      "grad_norm": 4.84346866607666,
+      "learning_rate": 6.615657878579001e-05,
+      "loss": 1.7753,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5948657421068162,
+      "grad_norm": 4.18584680557251,
+      "learning_rate": 6.592438189872025e-05,
+      "loss": 1.7934,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5995868987902035,
+      "grad_norm": 4.149290561676025,
+      "learning_rate": 6.569066885118008e-05,
+      "loss": 1.8448,
+      "step": 1270
+    },
+    {
+      "epoch": 0.604308055473591,
+      "grad_norm": 4.136205196380615,
+      "learning_rate": 6.545545331163362e-05,
+      "loss": 1.7856,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6090292121569785,
+      "grad_norm": 4.083582401275635,
+      "learning_rate": 6.521874903641668e-05,
+      "loss": 1.7397,
+      "step": 1290
+    },
+    {
+      "epoch": 0.6137503688403659,
+      "grad_norm": 5.102383613586426,
+      "learning_rate": 6.498056986893227e-05,
+      "loss": 1.8024,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6184715255237533,
+      "grad_norm": 4.809868812561035,
+      "learning_rate": 6.474092973884084e-05,
+      "loss": 1.7612,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6231926822071407,
+      "grad_norm": 4.376833915710449,
+      "learning_rate": 6.449984266124579e-05,
+      "loss": 1.8586,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6279138388905282,
+      "grad_norm": 4.385426998138428,
+      "learning_rate": 6.425732273587372e-05,
+      "loss": 1.8276,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6326349955739156,
+      "grad_norm": 4.733769416809082,
+      "learning_rate": 6.401338414624983e-05,
+      "loss": 1.8549,
+      "step": 1340
+    },
+    {
+      "epoch": 0.637356152257303,
+      "grad_norm": 4.410917282104492,
+      "learning_rate": 6.376804115886843e-05,
+      "loss": 1.8764,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6420773089406905,
+      "grad_norm": 4.764721393585205,
+      "learning_rate": 6.352130812235856e-05,
+      "loss": 1.8351,
+      "step": 1360
+    },
+    {
+      "epoch": 0.646798465624078,
+      "grad_norm": 4.851024150848389,
+      "learning_rate": 6.327319946664486e-05,
+      "loss": 1.7044,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6515196223074653,
+      "grad_norm": 4.550333499908447,
+      "learning_rate": 6.302372970210363e-05,
+      "loss": 1.7638,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6562407789908528,
+      "grad_norm": 4.317182540893555,
+      "learning_rate": 6.277291341871412e-05,
+      "loss": 1.7092,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6609619356742402,
+      "grad_norm": 5.009613513946533,
+      "learning_rate": 6.252076528520544e-05,
+      "loss": 1.7492,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6609619356742402,
+      "eval_loss": 2.263662815093994,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 352.6636,
+      "eval_samples_per_second": 9.871,
+      "eval_steps_per_second": 9.871,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6656830923576276,
+      "grad_norm": 4.208981037139893,
+      "learning_rate": 6.226730004819849e-05,
+      "loss": 1.832,
+      "step": 1410
+    },
+    {
+      "epoch": 0.670404249041015,
+      "grad_norm": 4.324787139892578,
+      "learning_rate": 6.201253253134366e-05,
+      "loss": 1.7723,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6751254057244025,
+      "grad_norm": 7.327449321746826,
+      "learning_rate": 6.175647763445377e-05,
+      "loss": 1.7639,
+      "step": 1430
+    },
+    {
+      "epoch": 0.67984656240779,
+      "grad_norm": 3.9426703453063965,
+      "learning_rate": 6.149915033263275e-05,
+      "loss": 1.7957,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6845677190911773,
+      "grad_norm": 3.9323489665985107,
+      "learning_rate": 6.124056567539975e-05,
+      "loss": 1.8228,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6892888757745648,
+      "grad_norm": 4.784934043884277,
+      "learning_rate": 6.098073878580914e-05,
+      "loss": 1.7085,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6940100324579522,
+      "grad_norm": 3.861611843109131,
+      "learning_rate": 6.0719684859565874e-05,
+      "loss": 1.8695,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6987311891413396,
+      "grad_norm": 4.08355712890625,
+      "learning_rate": 6.04574191641369e-05,
+      "loss": 1.7275,
+      "step": 1480
+    },
+    {
+      "epoch": 0.703452345824727,
+      "grad_norm": 4.46909236907959,
+      "learning_rate": 6.019395703785821e-05,
+      "loss": 1.7672,
+      "step": 1490
+    },
+    {
+      "epoch": 0.7081735025081145,
+      "grad_norm": 4.04533052444458,
+      "learning_rate": 5.992931388903781e-05,
+      "loss": 1.7186,
+      "step": 1500
+    },
+    {
+      "epoch": 0.712894659191502,
+      "grad_norm": 3.886951446533203,
+      "learning_rate": 5.9663505195054614e-05,
+      "loss": 1.6114,
+      "step": 1510
+    },
+    {
+      "epoch": 0.7176158158748893,
+      "grad_norm": 4.191418170928955,
+      "learning_rate": 5.939654650145319e-05,
+      "loss": 1.7433,
+      "step": 1520
+    },
+    {
+      "epoch": 0.7223369725582768,
+      "grad_norm": 4.09813928604126,
+      "learning_rate": 5.9128453421034626e-05,
+      "loss": 1.7873,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7270581292416642,
+      "grad_norm": 4.5093865394592285,
+      "learning_rate": 5.885924163294348e-05,
+      "loss": 1.6315,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7317792859250516,
+      "grad_norm": 4.723282814025879,
+      "learning_rate": 5.858892688175075e-05,
+      "loss": 1.7609,
+      "step": 1550
+    },
+    {
+      "epoch": 0.736500442608439,
+      "grad_norm": 4.511218070983887,
+      "learning_rate": 5.831752497653306e-05,
+      "loss": 1.7207,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7412215992918265,
+      "grad_norm": 4.327647686004639,
+      "learning_rate": 5.804505178994815e-05,
+      "loss": 1.7331,
+      "step": 1570
+    },
+    {
+      "epoch": 0.745942755975214,
+      "grad_norm": 3.9672775268554688,
+      "learning_rate": 5.777152325730648e-05,
+      "loss": 1.766,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7506639126586013,
+      "grad_norm": 4.553341865539551,
+      "learning_rate": 5.749695537563938e-05,
+      "loss": 1.6962,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7553850693419888,
+      "grad_norm": 4.2909016609191895,
+      "learning_rate": 5.722136420276338e-05,
+      "loss": 1.6581,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7553850693419888,
+      "eval_loss": 2.235355854034424,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 356.9133,
+      "eval_samples_per_second": 9.753,
+      "eval_steps_per_second": 9.753,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7601062260253763,
+      "grad_norm": 4.163833141326904,
+      "learning_rate": 5.694476585634114e-05,
+      "loss": 1.694,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7648273827087636,
+      "grad_norm": 4.966216087341309,
+      "learning_rate": 5.666717651293882e-05,
+      "loss": 1.7143,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7695485393921511,
+      "grad_norm": 4.320859432220459,
+      "learning_rate": 5.638861240708003e-05,
+      "loss": 1.7735,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7742696960755385,
+      "grad_norm": 4.283965587615967,
+      "learning_rate": 5.6109089830296326e-05,
+      "loss": 1.7053,
+      "step": 1640
+    },
+    {
+      "epoch": 0.778990852758926,
+      "grad_norm": 4.564968109130859,
+      "learning_rate": 5.582862513017442e-05,
+      "loss": 1.7928,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7837120094423133,
+      "grad_norm": 4.1493144035339355,
+      "learning_rate": 5.554723470940016e-05,
+      "loss": 1.7643,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7884331661257008,
+      "grad_norm": 4.535817623138428,
+      "learning_rate": 5.526493502479916e-05,
+      "loss": 1.6687,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7931543228090883,
+      "grad_norm": 5.094455242156982,
+      "learning_rate": 5.498174258637445e-05,
+      "loss": 1.7006,
+      "step": 1680
+    },
+    {
+      "epoch": 0.7978754794924756,
+      "grad_norm": 5.213793754577637,
+      "learning_rate": 5.469767395634077e-05,
+      "loss": 1.6883,
+      "step": 1690
+    },
+    {
+      "epoch": 0.8025966361758631,
+      "grad_norm": 4.975552558898926,
+      "learning_rate": 5.441274574815604e-05,
+      "loss": 1.5873,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8073177928592505,
+      "grad_norm": 4.941921234130859,
+      "learning_rate": 5.41269746255497e-05,
+      "loss": 1.7197,
+      "step": 1710
+    },
+    {
+      "epoch": 0.812038949542638,
+      "grad_norm": 4.873169422149658,
+      "learning_rate": 5.38403773015482e-05,
+      "loss": 1.7471,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8167601062260254,
+      "grad_norm": 4.5484161376953125,
+      "learning_rate": 5.355297053749747e-05,
+      "loss": 1.7135,
+      "step": 1730
+    },
+    {
+      "epoch": 0.8214812629094128,
+      "grad_norm": 5.332439422607422,
+      "learning_rate": 5.326477114208272e-05,
+      "loss": 1.5796,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8262024195928003,
+      "grad_norm": 4.353306770324707,
+      "learning_rate": 5.297579597034539e-05,
+      "loss": 1.7093,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8309235762761876,
+      "grad_norm": 4.193436622619629,
+      "learning_rate": 5.268606192269737e-05,
+      "loss": 1.7285,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8356447329595751,
+      "grad_norm": 4.408235549926758,
+      "learning_rate": 5.239558594393264e-05,
+      "loss": 1.6739,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8403658896429625,
+      "grad_norm": 3.962897539138794,
+      "learning_rate": 5.210438502223622e-05,
+      "loss": 1.7057,
+      "step": 1780
+    },
+    {
+      "epoch": 0.84508704632635,
+      "grad_norm": 3.865640163421631,
+      "learning_rate": 5.181247618819068e-05,
+      "loss": 1.6269,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8498082030097374,
+      "grad_norm": 5.170018672943115,
+      "learning_rate": 5.15198765137801e-05,
+      "loss": 1.7186,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8498082030097374,
+      "eval_loss": 2.222907781600952,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 353.2544,
+      "eval_samples_per_second": 9.854,
+      "eval_steps_per_second": 9.854,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8545293596931248,
+      "grad_norm": 4.914104461669922,
+      "learning_rate": 5.122660311139165e-05,
+      "loss": 1.7381,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8592505163765123,
+      "grad_norm": 3.9418787956237793,
+      "learning_rate": 5.093267313281477e-05,
+      "loss": 1.532,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8639716730598996,
+      "grad_norm": 4.703445911407471,
+      "learning_rate": 5.063810376823808e-05,
+      "loss": 1.734,
+      "step": 1830
+    },
+    {
+      "epoch": 0.8686928297432871,
+      "grad_norm": 3.5432028770446777,
+      "learning_rate": 5.034291224524401e-05,
+      "loss": 1.5007,
+      "step": 1840
+    },
+    {
+      "epoch": 0.8734139864266746,
+      "grad_norm": 4.070043563842773,
+      "learning_rate": 5.00471158278013e-05,
+      "loss": 1.5908,
+      "step": 1850
+    },
+    {
+      "epoch": 0.8781351431100619,
+      "grad_norm": 4.701024055480957,
+      "learning_rate": 4.975073181525528e-05,
+      "loss": 1.5333,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8828562997934494,
+      "grad_norm": 4.1728196144104,
+      "learning_rate": 4.9453777541316206e-05,
+      "loss": 1.6249,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8875774564768368,
+      "grad_norm": 4.538570880889893,
+      "learning_rate": 4.915627037304543e-05,
+      "loss": 1.5043,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8922986131602243,
+      "grad_norm": 4.290474891662598,
+      "learning_rate": 4.885822770983982e-05,
+      "loss": 1.5293,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8970197698436116,
+      "grad_norm": 4.274802207946777,
+      "learning_rate": 4.8559666982414036e-05,
+      "loss": 1.611,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9017409265269991,
+      "grad_norm": 3.7836177349090576,
+      "learning_rate": 4.826060565178123e-05,
+      "loss": 1.5847,
+      "step": 1910
+    },
+    {
+      "epoch": 0.9064620832103866,
+      "grad_norm": 4.180873870849609,
+      "learning_rate": 4.796106120823179e-05,
+      "loss": 1.6526,
+      "step": 1920
+    },
+    {
+      "epoch": 0.9111832398937739,
+      "grad_norm": 4.173154830932617,
+      "learning_rate": 4.766105117031048e-05,
+      "loss": 1.6427,
+      "step": 1930
+    },
+    {
+      "epoch": 0.9159043965771614,
+      "grad_norm": 4.081653594970703,
+      "learning_rate": 4.736059308379185e-05,
+      "loss": 1.6121,
+      "step": 1940
+    },
+    {
+      "epoch": 0.9206255532605488,
+      "grad_norm": 4.480609893798828,
+      "learning_rate": 4.70597045206541e-05,
+      "loss": 1.5421,
+      "step": 1950
+    },
+    {
+      "epoch": 0.9253467099439363,
+      "grad_norm": 4.0933613777160645,
+      "learning_rate": 4.675840307805142e-05,
+      "loss": 1.5211,
+      "step": 1960
+    },
+    {
+      "epoch": 0.9300678666273237,
+      "grad_norm": 4.288510799407959,
+      "learning_rate": 4.645670637728481e-05,
+      "loss": 1.6858,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9347890233107111,
+      "grad_norm": 4.577378273010254,
+      "learning_rate": 4.6154632062771566e-05,
+      "loss": 1.4786,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9395101799940986,
+      "grad_norm": 4.2616143226623535,
+      "learning_rate": 4.585219780101328e-05,
+      "loss": 1.6341,
+      "step": 1990
+    },
+    {
+      "epoch": 0.9442313366774859,
+      "grad_norm": 4.703867435455322,
+      "learning_rate": 4.554942127956274e-05,
+      "loss": 1.5733,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9442313366774859,
+      "eval_loss": 2.2312581539154053,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 358.9867,
+      "eval_samples_per_second": 9.697,
+      "eval_steps_per_second": 9.697,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9489524933608734,
+      "grad_norm": 4.397935390472412,
+      "learning_rate": 4.5246320205989375e-05,
+      "loss": 1.5875,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9536736500442609,
+      "grad_norm": 4.693921089172363,
+      "learning_rate": 4.494291230684376e-05,
+      "loss": 1.6184,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9583948067276483,
+      "grad_norm": 4.748966693878174,
+      "learning_rate": 4.463921532662082e-05,
+      "loss": 1.4966,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9631159634110357,
+      "grad_norm": 4.2403178215026855,
+      "learning_rate": 4.433524702672209e-05,
+      "loss": 1.4156,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9678371200944231,
+      "grad_norm": 4.947932720184326,
+      "learning_rate": 4.403102518441695e-05,
+      "loss": 1.6184,
+      "step": 2050
+    },
+    {
+      "epoch": 0.9725582767778106,
+      "grad_norm": 4.2154717445373535,
+      "learning_rate": 4.372656759180293e-05,
+      "loss": 1.7051,
+      "step": 2060
+    },
+    {
+      "epoch": 0.9772794334611979,
+      "grad_norm": 3.5326645374298096,
+      "learning_rate": 4.34218920547652e-05,
+      "loss": 1.4613,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9820005901445854,
+      "grad_norm": 4.739229202270508,
+      "learning_rate": 4.311701639193515e-05,
+      "loss": 1.5122,
+      "step": 2080
+    },
+    {
+      "epoch": 0.9867217468279729,
+      "grad_norm": 4.80006742477417,
+      "learning_rate": 4.2811958433648385e-05,
+      "loss": 1.4659,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9914429035113603,
+      "grad_norm": 4.20546817779541,
+      "learning_rate": 4.2506736020901774e-05,
+      "loss": 1.6113,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9961640601947477,
+      "grad_norm": 4.925048351287842,
+      "learning_rate": 4.2201367004310214e-05,
+      "loss": 1.4089,
+      "step": 2110
+    },
+    {
+      "epoch": 1.0008852168781353,
+      "grad_norm": 5.191972732543945,
+      "learning_rate": 4.1895869243062516e-05,
+      "loss": 1.5462,
+      "step": 2120
+    },
+    {
+      "epoch": 1.0056063735615226,
+      "grad_norm": 5.342108726501465,
+      "learning_rate": 4.159026060387704e-05,
+      "loss": 1.4714,
+      "step": 2130
+    },
+    {
+      "epoch": 1.01032753024491,
+      "grad_norm": 3.962531328201294,
+      "learning_rate": 4.128455895995667e-05,
+      "loss": 1.6092,
+      "step": 2140
+    },
+    {
+      "epoch": 1.0150486869282975,
+      "grad_norm": 4.554024696350098,
+      "learning_rate": 4.097878218994365e-05,
+      "loss": 1.5228,
+      "step": 2150
+    },
+    {
+      "epoch": 1.0197698436116849,
+      "grad_norm": 4.606506824493408,
+      "learning_rate": 4.067294817687381e-05,
+      "loss": 1.5228,
+      "step": 2160
+    },
+    {
+      "epoch": 1.0244910002950722,
+      "grad_norm": 4.6551313400268555,
+      "learning_rate": 4.0367074807130856e-05,
+      "loss": 1.5002,
+      "step": 2170
+    },
+    {
+      "epoch": 1.0292121569784598,
+      "grad_norm": 3.8967349529266357,
+      "learning_rate": 4.0061179969400176e-05,
+      "loss": 1.5915,
+      "step": 2180
+    },
+    {
+      "epoch": 1.0339333136618472,
+      "grad_norm": 3.576057195663452,
+      "learning_rate": 3.975528155362272e-05,
+      "loss": 1.47,
+      "step": 2190
+    },
+    {
+      "epoch": 1.0386544703452345,
+      "grad_norm": 3.745286464691162,
+      "learning_rate": 3.9449397449948686e-05,
+      "loss": 1.3909,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0386544703452345,
+      "eval_loss": 2.220811367034912,
+      "eval_model_preparation_time": 0.0088,
+      "eval_runtime": 353.6274,
+      "eval_samples_per_second": 9.844,
+      "eval_steps_per_second": 9.844,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4848575842933637e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/fresh_sft/train/train_20260407_231929/checkpoint-2200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca2554451a46c547b0b009cdd6a4e075ed15af7ced0c6efde00df4c8740b2e1
+size 5713