Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: 01-ai/Yi-1.5-6B-Chat
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: yi-1-5-6b_eqa_lora_sft
+  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. -->
+
+# yi-1-5-6b_eqa_lora_sft
+
+This model is a fine-tuned version of [01-ai/Yi-1.5-6B-Chat](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) on the energy_qa_alpaca 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-1.5-6B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678efbe85f017444878c2e2036eb0ccda34793e470ad042b357672945094aeb5
+size 72673016

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 8.068623002055475e+16,
+    "train_loss": 1.7541659650032235,
+    "train_runtime": 6424.1022,
+    "train_samples_per_second": 2.234,
+    "train_steps_per_second": 0.279
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: 01-ai/Yi-1.5-6B-Chat
+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 0.15.2

checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-1.5-6B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f771737798d801dc4a456a1eb924d1077130501b7c1e591f34fa19a9ff84c5d
+size 72673016

checkpoint-1000/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e252123c79885e8f8f5a05431581b0092d3e116567b251a6f177601f0f08b9
+size 145605155

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7742f57d6748a994796e54556d7aa815c4953a13a94d3bf47d4e1c767c576e9
+size 1465

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.557374764857521,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.5925259590148926,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 2.5484,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.7384228706359863,
+      "learning_rate": 5e-06,
+      "loss": 2.5036,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.7028982639312744,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 2.5177,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.1780974864959717,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 2.4746,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 2.8278558254241943,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.5083,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 2.5323452949523926,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.4383,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 1.2514830827713013,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.1978,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 1.1612293720245361,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.0549,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 0.9937079548835754,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.1649,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.056492567062378,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0852,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.9864413142204285,
+      "learning_rate": 3e-05,
+      "loss": 1.934,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.9184162616729736,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 2.0746,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 1.044710397720337,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.9812,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.9160545468330383,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.8794,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.9865038990974426,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.9266,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.9860550165176392,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.8417,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.9826656579971313,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.9756,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.9479106664657593,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.8803,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 1.005937933921814,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.8677,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 1.1173028945922852,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8416,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 1.0000165700912476,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.8607,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 1.3015921115875244,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.9752,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 1.0431042909622192,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.8514,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 1.0463422536849976,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.8656,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 1.0947015285491943,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.9479,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.9953688979148865,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.8627,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 1.0779668092727661,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.8262,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 1.2166972160339355,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.8461,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 1.055553674697876,
+      "learning_rate": 8e-05,
+      "loss": 1.9684,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 1.0838943719863892,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8891,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.9238198399543762,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.8507,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 1.186009168624878,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.8269,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 1.122663140296936,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.7877,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 1.176620364189148,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.8373,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 1.0495474338531494,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.838,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 1.0859992504119873,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.845,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 1.1708000898361206,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.8148,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 1.0338629484176636,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7982,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 1.2173702716827393,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.792,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 1.1683762073516846,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.8381,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 1.0897382497787476,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.8142,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.9195744395256042,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.8362,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 1.039374589920044,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7565,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 1.0218507051467896,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.8728,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 1.0597004890441895,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7938,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 1.1160184144973755,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.8156,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.99184250831604,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.7255,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 1.0527223348617554,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8942,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 1.0618565082550049,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.7666,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 1.1174343824386597,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.7274,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 1.045905351638794,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.9156,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 1.1782068014144897,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.8142,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 1.0786527395248413,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.8206,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 1.0150487422943115,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.7779,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 1.0553853511810303,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.8223,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 1.0968186855316162,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.7834,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.9188632369041443,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.8808,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.9829431772232056,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.8455,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 1.034116268157959,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.8042,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 1.0451691150665283,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.7696,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 1.064620852470398,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.8668,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 1.0409430265426636,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.8274,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 1.0153954029083252,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.8084,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.9218955039978027,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.8457,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.9664631485939026,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.772,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 1.0060662031173706,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.727,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 1.0184046030044556,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.7638,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.9374409317970276,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.7323,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.9715288877487183,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.7169,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 1.088680624961853,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.8065,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.9513164758682251,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.6545,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.9501610398292542,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.8605,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.9788233041763306,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.7838,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 1.0686471462249756,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.7832,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.9658113121986389,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.7721,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 1.0429141521453857,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.7741,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.9593327641487122,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.7534,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.9077600240707397,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.8398,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 1.048581600189209,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.8134,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.9498254060745239,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.7497,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 1.0249079465866089,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.6412,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.9723719358444214,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.7741,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.954607367515564,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.7865,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.9485211372375488,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.813,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.9606624841690063,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.7426,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.9899424910545349,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.7802,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 1.0416887998580933,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.7418,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.958951473236084,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.7791,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.993934154510498,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.739,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.9372468590736389,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.7406,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.9601876735687256,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.7357,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9922548532485962,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.7677,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.9353616833686829,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.8202,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8890717625617981,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.7473,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 1.0059962272644043,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7978,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.9888349771499634,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.7481,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.9407850503921509,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.7667,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 1.0001949071884155,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.7742,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.9057056307792664,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.816,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 1.0183491706848145,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.8137,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.9340478777885437,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.7735,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.9671086668968201,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.7204,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.9643672704696655,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.748,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.9929302334785461,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.7682,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 1.0192108154296875,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6811,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.9536918997764587,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.7562,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9654401540756226,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.7098,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.9755784869194031,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5997,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.920735776424408,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.8432,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.9787949323654175,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.7575,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9688432812690735,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6978,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.9125113487243652,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.7075,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.954394519329071,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.7341,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.9641663432121277,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.84,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.974785327911377,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.717,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 1.0628243684768677,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.7745,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9969517588615417,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.7366,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.9360251426696777,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.7395,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.9315335154533386,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.7478,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 1.008952260017395,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.6532,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.9224027395248413,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6901,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 1.0089499950408936,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7778,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 1.0609345436096191,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.7429,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.9656564593315125,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.7799,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.9876144528388977,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.7204,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.9239578247070312,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.7871,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9991699457168579,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.7259,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.9193426370620728,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.7508,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9434049129486084,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.8071,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9454895257949829,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.7493,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9811017513275146,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.7469,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9470755457878113,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.7392,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 1.0244383811950684,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7735,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 1.1164230108261108,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.7982,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 1.0754444599151611,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.7041,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.9588093757629395,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.8321,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.9360554218292236,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.7865,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.9670904278755188,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.7208,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.9358083605766296,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6911,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 1.0316359996795654,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.6729,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.9509869813919067,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.7395,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9687904119491577,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.7688,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8772656917572021,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.7311,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.9465420842170715,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7634,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.9126701354980469,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6924,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.070681095123291,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6977,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.9621564149856567,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.7579,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 1.0299642086029053,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.6608,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 1.0028384923934937,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.8124,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9672207832336426,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7581,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 1.0683056116104126,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7852,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 1.023703694343567,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.6159,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 1.0113016366958618,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.7385,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 1.0289918184280396,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.8094,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9700524806976318,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6953,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.9488673806190491,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.6345,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.99649977684021,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.7524,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.9158934354782104,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.7326,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.9467411637306213,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.7519,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.8946711421012878,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.6291,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.9915565848350525,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.757,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9836114645004272,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.8026,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 0.9982685446739197,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.7819,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 1.0257214307785034,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.719,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.9735772013664246,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.7153,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.9777944684028625,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.7256,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9858867526054382,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.7,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.9058387875556946,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.7095,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 1.0151069164276123,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.7606,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9841256141662598,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.7015,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.9631791710853577,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.7847,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 1.1236021518707275,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.7388,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 1.0226027965545654,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6993,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 1.0021902322769165,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.753,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9932888746261597,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6798,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 1.007003664970398,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.8083,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.9325096011161804,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.7057,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.9602507948875427,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.7063,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.814627468585968,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6748,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 1.0444878339767456,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.7389,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8829376101493835,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.7323,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9832122325897217,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.7698,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8969665169715881,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.7473,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9865416884422302,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6655,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.9947900176048279,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7719,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.9595984816551208,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.6078,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 1.0105018615722656,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.7251,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 1.039826512336731,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7688,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.9929054379463196,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.7562,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.084277629852295,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6752,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 1.0061899423599243,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.7075,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.9747031927108765,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.6154,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 1.0520727634429932,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6982,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.9064339995384216,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.7331,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.9782255291938782,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.6223,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9979589581489563,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.7069,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.9500666260719299,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6931,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 1.0122525691986084,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.745,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0289945602416992,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.729,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 1.014304280281067,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.7108,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.492061751902208e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87eaa3512a157f5d0c7785d61d4dd86da22136cc4779d09d5833877f1f1a7a
+size 6161

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: 01-ai/Yi-1.5-6B-Chat
+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 0.15.2

checkpoint-1500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-1.5-6B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddbca025aa7d46dca4716c5e76c89a06a3f9fc64a16011d72f9c3c35aa982e5
+size 72673016

checkpoint-1500/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aee3a5960b891b2f9d5ea45f35ffc78c665a444fdb6930faf3ade090cd97ac7
+size 145605155

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ecf9f08b8ece20f8e38217288ba9577a3fcfff91bb28828bd121972f45e8e0
+size 1465

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8360621472862816,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.5925259590148926,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 2.5484,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.7384228706359863,
+      "learning_rate": 5e-06,
+      "loss": 2.5036,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.7028982639312744,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 2.5177,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.1780974864959717,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 2.4746,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 2.8278558254241943,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.5083,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 2.5323452949523926,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.4383,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 1.2514830827713013,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.1978,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 1.1612293720245361,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.0549,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 0.9937079548835754,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.1649,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.056492567062378,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0852,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.9864413142204285,
+      "learning_rate": 3e-05,
+      "loss": 1.934,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.9184162616729736,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 2.0746,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 1.044710397720337,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.9812,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.9160545468330383,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.8794,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.9865038990974426,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.9266,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.9860550165176392,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.8417,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.9826656579971313,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.9756,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.9479106664657593,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.8803,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 1.005937933921814,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.8677,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 1.1173028945922852,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8416,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 1.0000165700912476,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.8607,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 1.3015921115875244,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.9752,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 1.0431042909622192,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.8514,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 1.0463422536849976,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.8656,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 1.0947015285491943,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.9479,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.9953688979148865,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.8627,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 1.0779668092727661,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.8262,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 1.2166972160339355,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.8461,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 1.055553674697876,
+      "learning_rate": 8e-05,
+      "loss": 1.9684,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 1.0838943719863892,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8891,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.9238198399543762,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.8507,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 1.186009168624878,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.8269,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 1.122663140296936,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.7877,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 1.176620364189148,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.8373,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 1.0495474338531494,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.838,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 1.0859992504119873,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.845,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 1.1708000898361206,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.8148,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 1.0338629484176636,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7982,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 1.2173702716827393,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.792,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 1.1683762073516846,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.8381,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 1.0897382497787476,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.8142,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.9195744395256042,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.8362,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 1.039374589920044,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7565,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 1.0218507051467896,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.8728,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 1.0597004890441895,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7938,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 1.1160184144973755,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.8156,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.99184250831604,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.7255,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 1.0527223348617554,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8942,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 1.0618565082550049,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.7666,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 1.1174343824386597,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.7274,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 1.045905351638794,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.9156,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 1.1782068014144897,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.8142,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 1.0786527395248413,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.8206,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 1.0150487422943115,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.7779,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 1.0553853511810303,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.8223,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 1.0968186855316162,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.7834,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.9188632369041443,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.8808,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.9829431772232056,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.8455,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 1.034116268157959,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.8042,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 1.0451691150665283,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.7696,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 1.064620852470398,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.8668,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 1.0409430265426636,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.8274,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 1.0153954029083252,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.8084,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.9218955039978027,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.8457,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.9664631485939026,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.772,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 1.0060662031173706,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.727,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 1.0184046030044556,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.7638,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.9374409317970276,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.7323,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.9715288877487183,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.7169,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 1.088680624961853,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.8065,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.9513164758682251,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.6545,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.9501610398292542,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.8605,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.9788233041763306,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.7838,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 1.0686471462249756,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.7832,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.9658113121986389,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.7721,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 1.0429141521453857,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.7741,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.9593327641487122,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.7534,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.9077600240707397,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.8398,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 1.048581600189209,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.8134,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.9498254060745239,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.7497,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 1.0249079465866089,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.6412,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.9723719358444214,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.7741,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.954607367515564,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.7865,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.9485211372375488,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.813,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.9606624841690063,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.7426,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.9899424910545349,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.7802,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 1.0416887998580933,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.7418,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.958951473236084,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.7791,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.993934154510498,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.739,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.9372468590736389,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.7406,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.9601876735687256,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.7357,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9922548532485962,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.7677,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.9353616833686829,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.8202,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8890717625617981,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.7473,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 1.0059962272644043,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7978,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.9888349771499634,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.7481,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.9407850503921509,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.7667,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 1.0001949071884155,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.7742,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.9057056307792664,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.816,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 1.0183491706848145,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.8137,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.9340478777885437,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.7735,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.9671086668968201,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.7204,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.9643672704696655,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.748,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.9929302334785461,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.7682,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 1.0192108154296875,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6811,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.9536918997764587,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.7562,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9654401540756226,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.7098,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.9755784869194031,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5997,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.920735776424408,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.8432,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.9787949323654175,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.7575,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9688432812690735,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6978,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.9125113487243652,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.7075,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.954394519329071,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.7341,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.9641663432121277,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.84,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.974785327911377,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.717,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 1.0628243684768677,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.7745,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9969517588615417,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.7366,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.9360251426696777,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.7395,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.9315335154533386,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.7478,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 1.008952260017395,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.6532,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.9224027395248413,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6901,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 1.0089499950408936,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7778,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 1.0609345436096191,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.7429,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.9656564593315125,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.7799,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.9876144528388977,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.7204,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.9239578247070312,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.7871,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9991699457168579,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.7259,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.9193426370620728,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.7508,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9434049129486084,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.8071,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9454895257949829,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.7493,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9811017513275146,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.7469,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9470755457878113,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.7392,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 1.0244383811950684,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7735,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 1.1164230108261108,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.7982,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 1.0754444599151611,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.7041,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.9588093757629395,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.8321,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.9360554218292236,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.7865,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.9670904278755188,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.7208,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.9358083605766296,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6911,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 1.0316359996795654,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.6729,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.9509869813919067,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.7395,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9687904119491577,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.7688,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8772656917572021,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.7311,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.9465420842170715,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7634,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.9126701354980469,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6924,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.070681095123291,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6977,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.9621564149856567,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.7579,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 1.0299642086029053,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.6608,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 1.0028384923934937,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.8124,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9672207832336426,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7581,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 1.0683056116104126,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7852,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 1.023703694343567,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.6159,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 1.0113016366958618,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.7385,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 1.0289918184280396,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.8094,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9700524806976318,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6953,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.9488673806190491,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.6345,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.99649977684021,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.7524,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.9158934354782104,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.7326,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.9467411637306213,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.7519,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.8946711421012878,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.6291,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.9915565848350525,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.757,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9836114645004272,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.8026,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 0.9982685446739197,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.7819,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 1.0257214307785034,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.719,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.9735772013664246,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.7153,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.9777944684028625,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.7256,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9858867526054382,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.7,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.9058387875556946,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.7095,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 1.0151069164276123,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.7606,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9841256141662598,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.7015,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.9631791710853577,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.7847,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 1.1236021518707275,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.7388,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 1.0226027965545654,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6993,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 1.0021902322769165,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.753,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9932888746261597,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6798,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 1.007003664970398,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.8083,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.9325096011161804,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.7057,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.9602507948875427,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.7063,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.814627468585968,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6748,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 1.0444878339767456,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.7389,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8829376101493835,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.7323,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9832122325897217,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.7698,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8969665169715881,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.7473,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9865416884422302,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6655,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.9947900176048279,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7719,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.9595984816551208,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.6078,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 1.0105018615722656,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.7251,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 1.039826512336731,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7688,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.9929054379463196,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.7562,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.084277629852295,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6752,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 1.0061899423599243,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.7075,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.9747031927108765,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.6154,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 1.0520727634429932,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6982,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.9064339995384216,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.7331,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.9782255291938782,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.6223,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9979589581489563,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.7069,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.9500666260719299,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6931,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 1.0122525691986084,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.745,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0289945602416992,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.729,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 1.014304280281067,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.7108,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5601616386818087,
+      "grad_norm": 1.025936245918274,
+      "learning_rate": 4.839543718475543e-05,
+      "loss": 1.6942,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5629485125060962,
+      "grad_norm": 1.0793489217758179,
+      "learning_rate": 4.790945657175061e-05,
+      "loss": 1.7333,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5657353863303839,
+      "grad_norm": 1.046277642250061,
+      "learning_rate": 4.742367372421811e-05,
+      "loss": 1.749,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5685222601546714,
+      "grad_norm": 1.0622342824935913,
+      "learning_rate": 4.69381345972302e-05,
+      "loss": 1.6864,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5713091339789591,
+      "grad_norm": 0.9354339838027954,
+      "learning_rate": 4.6452885122803205e-05,
+      "loss": 1.6619,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5740960078032467,
+      "grad_norm": 0.9112613797187805,
+      "learning_rate": 4.5967971205552194e-05,
+      "loss": 1.7251,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5768828816275343,
+      "grad_norm": 0.9895853400230408,
+      "learning_rate": 4.548343871834864e-05,
+      "loss": 1.7107,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5796697554518219,
+      "grad_norm": 0.9500023126602173,
+      "learning_rate": 4.499933349798067e-05,
+      "loss": 1.7607,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5824566292761095,
+      "grad_norm": 1.0377269983291626,
+      "learning_rate": 4.451570134081694e-05,
+      "loss": 1.7969,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5852435031003971,
+      "grad_norm": 0.9661582708358765,
+      "learning_rate": 4.403258799847433e-05,
+      "loss": 1.685,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5880303769246847,
+      "grad_norm": 1.0600863695144653,
+      "learning_rate": 4.3550039173489845e-05,
+      "loss": 1.6872,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5908172507489723,
+      "grad_norm": 1.0329686403274536,
+      "learning_rate": 4.306810051499708e-05,
+      "loss": 1.6185,
+      "step": 1060
+    },
+    {
+      "epoch": 0.59360412457326,
+      "grad_norm": 1.0944806337356567,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 1.7209,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5963909983975475,
+      "grad_norm": 0.923368513584137,
+      "learning_rate": 4.210623600109946e-05,
+      "loss": 1.5895,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5991778722218352,
+      "grad_norm": 1.025833249092102,
+      "learning_rate": 4.162640113810706e-05,
+      "loss": 1.7405,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6019647460461227,
+      "grad_norm": 1.026885747909546,
+      "learning_rate": 4.114735841782347e-05,
+      "loss": 1.7871,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6047516198704104,
+      "grad_norm": 0.9980199337005615,
+      "learning_rate": 4.06691531577047e-05,
+      "loss": 1.7028,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6075384936946979,
+      "grad_norm": 0.9639666080474854,
+      "learning_rate": 4.019183059598296e-05,
+      "loss": 1.6743,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6103253675189856,
+      "grad_norm": 0.9345841407775879,
+      "learning_rate": 3.971543588738724e-05,
+      "loss": 1.6934,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6131122413432731,
+      "grad_norm": 0.9754037261009216,
+      "learning_rate": 3.924001409887158e-05,
+      "loss": 1.6454,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6158991151675608,
+      "grad_norm": 1.0533924102783203,
+      "learning_rate": 3.87656102053517e-05,
+      "loss": 1.7128,
+      "step": 1105
+    },
+    {
+      "epoch": 0.6186859889918483,
+      "grad_norm": 1.022055983543396,
+      "learning_rate": 3.8292269085450474e-05,
+      "loss": 1.6777,
+      "step": 1110
+    },
+    {
+      "epoch": 0.621472862816136,
+      "grad_norm": 0.9270001649856567,
+      "learning_rate": 3.782003551725236e-05,
+      "loss": 1.745,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6242597366404236,
+      "grad_norm": 0.9471579790115356,
+      "learning_rate": 3.734895417406734e-05,
+      "loss": 1.7204,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6270466104647112,
+      "grad_norm": 0.9260222315788269,
+      "learning_rate": 3.687906962020491e-05,
+      "loss": 1.7333,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6298334842889988,
+      "grad_norm": 1.0778995752334595,
+      "learning_rate": 3.641042630675829e-05,
+      "loss": 1.763,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6326203581132864,
+      "grad_norm": 1.0067857503890991,
+      "learning_rate": 3.594306856739924e-05,
+      "loss": 1.6692,
+      "step": 1135
+    },
+    {
+      "epoch": 0.635407231937574,
+      "grad_norm": 0.994063138961792,
+      "learning_rate": 3.547704061418424e-05,
+      "loss": 1.6736,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6381941057618616,
+      "grad_norm": 1.0534288883209229,
+      "learning_rate": 3.501238653337194e-05,
+      "loss": 1.705,
+      "step": 1145
+    },
+    {
+      "epoch": 0.6409809795861492,
+      "grad_norm": 1.098292350769043,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7781,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6437678534104369,
+      "grad_norm": 1.0197910070419312,
+      "learning_rate": 3.408737567998993e-05,
+      "loss": 1.6325,
+      "step": 1155
+    },
+    {
+      "epoch": 0.6465547272347244,
+      "grad_norm": 1.0445324182510376,
+      "learning_rate": 3.362710641347524e-05,
+      "loss": 1.7602,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6493416010590121,
+      "grad_norm": 0.9735073447227478,
+      "learning_rate": 3.316838602319532e-05,
+      "loss": 1.761,
+      "step": 1165
+    },
+    {
+      "epoch": 0.6521284748832996,
+      "grad_norm": 1.056726336479187,
+      "learning_rate": 3.271125790411309e-05,
+      "loss": 1.5925,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6549153487075873,
+      "grad_norm": 1.1253453493118286,
+      "learning_rate": 3.225576530056264e-05,
+      "loss": 1.7672,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6577022225318748,
+      "grad_norm": 0.9200742840766907,
+      "learning_rate": 3.180195130215824e-05,
+      "loss": 1.6926,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6604890963561625,
+      "grad_norm": 1.203482985496521,
+      "learning_rate": 3.1349858839717986e-05,
+      "loss": 1.6457,
+      "step": 1185
+    },
+    {
+      "epoch": 0.66327597018045,
+      "grad_norm": 0.9705748558044434,
+      "learning_rate": 3.089953068120271e-05,
+      "loss": 1.6284,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6660628440047377,
+      "grad_norm": 1.0424647331237793,
+      "learning_rate": 3.0451009427669986e-05,
+      "loss": 1.6443,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6688497178290252,
+      "grad_norm": 1.0199843645095825,
+      "learning_rate": 3.000433750924414e-05,
+      "loss": 1.6971,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6716365916533129,
+      "grad_norm": 0.9686048030853271,
+      "learning_rate": 2.9559557181102315e-05,
+      "loss": 1.7045,
+      "step": 1205
+    },
+    {
+      "epoch": 0.6744234654776005,
+      "grad_norm": 1.1422017812728882,
+      "learning_rate": 2.911671051947722e-05,
+      "loss": 1.6388,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6772103393018881,
+      "grad_norm": 1.0640348196029663,
+      "learning_rate": 2.867583941767657e-05,
+      "loss": 1.6232,
+      "step": 1215
+    },
+    {
+      "epoch": 0.6799972131261757,
+      "grad_norm": 0.9906688332557678,
+      "learning_rate": 2.823698558212009e-05,
+      "loss": 1.7076,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6827840869504633,
+      "grad_norm": 1.047086238861084,
+      "learning_rate": 2.7800190528394122e-05,
+      "loss": 1.6712,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6855709607747509,
+      "grad_norm": 0.9434465169906616,
+      "learning_rate": 2.736549557732405e-05,
+      "loss": 1.6087,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6883578345990385,
+      "grad_norm": 1.0368611812591553,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 1.8661,
+      "step": 1235
+    },
+    {
+      "epoch": 0.6911447084233261,
+      "grad_norm": 1.0463006496429443,
+      "learning_rate": 2.650257026921455e-05,
+      "loss": 1.713,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6939315822476138,
+      "grad_norm": 1.0394631624221802,
+      "learning_rate": 2.607442154493568e-05,
+      "loss": 1.7607,
+      "step": 1245
+    },
+    {
+      "epoch": 0.6967184560719013,
+      "grad_norm": 1.0766334533691406,
+      "learning_rate": 2.5648536181111438e-05,
+      "loss": 1.6821,
+      "step": 1250
+    },
+    {
+      "epoch": 0.699505329896189,
+      "grad_norm": 1.1074429750442505,
+      "learning_rate": 2.5224954466510274e-05,
+      "loss": 1.6959,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7022922037204765,
+      "grad_norm": 0.9983723759651184,
+      "learning_rate": 2.480371647197538e-05,
+      "loss": 1.737,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7050790775447642,
+      "grad_norm": 1.0355981588363647,
+      "learning_rate": 2.438486204663391e-05,
+      "loss": 1.7327,
+      "step": 1265
+    },
+    {
+      "epoch": 0.7078659513690517,
+      "grad_norm": 1.015955924987793,
+      "learning_rate": 2.3968430814127385e-05,
+      "loss": 1.7327,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7106528251933394,
+      "grad_norm": 0.9912840723991394,
+      "learning_rate": 2.3554462168863085e-05,
+      "loss": 1.7214,
+      "step": 1275
+    },
+    {
+      "epoch": 0.7134396990176269,
+      "grad_norm": 1.0331684350967407,
+      "learning_rate": 2.314299527228759e-05,
+      "loss": 1.7073,
+      "step": 1280
+    },
+    {
+      "epoch": 0.7162265728419146,
+      "grad_norm": 0.9723387956619263,
+      "learning_rate": 2.2734069049181882e-05,
+      "loss": 1.6758,
+      "step": 1285
+    },
+    {
+      "epoch": 0.7190134466662021,
+      "grad_norm": 1.0285305976867676,
+      "learning_rate": 2.2327722183979212e-05,
+      "loss": 1.6994,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7218003204904898,
+      "grad_norm": 1.050363302230835,
+      "learning_rate": 2.1923993117105462e-05,
+      "loss": 1.6629,
+      "step": 1295
+    },
+    {
+      "epoch": 0.7245871943147774,
+      "grad_norm": 1.1402173042297363,
+      "learning_rate": 2.1522920041342704e-05,
+      "loss": 1.6634,
+      "step": 1300
+    },
+    {
+      "epoch": 0.727374068139065,
+      "grad_norm": 1.120635986328125,
+      "learning_rate": 2.1124540898216248e-05,
+      "loss": 1.7093,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7301609419633526,
+      "grad_norm": 0.99698805809021,
+      "learning_rate": 2.0728893374405166e-05,
+      "loss": 1.6105,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7329478157876402,
+      "grad_norm": 1.149105429649353,
+      "learning_rate": 2.033601489817738e-05,
+      "loss": 1.8142,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7357346896119278,
+      "grad_norm": 1.1066628694534302,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.7501,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7385215634362154,
+      "grad_norm": 1.021165132522583,
+      "learning_rate": 1.9558713488267238e-05,
+      "loss": 1.7328,
+      "step": 1325
+    },
+    {
+      "epoch": 0.741308437260503,
+      "grad_norm": 1.0248847007751465,
+      "learning_rate": 1.917436408732208e-05,
+      "loss": 1.6973,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7440953110847907,
+      "grad_norm": 1.154515266418457,
+      "learning_rate": 1.8792930792478357e-05,
+      "loss": 1.708,
+      "step": 1335
+    },
+    {
+      "epoch": 0.7468821849090782,
+      "grad_norm": 1.089268684387207,
+      "learning_rate": 1.8414449687337464e-05,
+      "loss": 1.6351,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7496690587333659,
+      "grad_norm": 1.0156011581420898,
+      "learning_rate": 1.8038956576223504e-05,
+      "loss": 1.6265,
+      "step": 1345
+    },
+    {
+      "epoch": 0.7524559325576534,
+      "grad_norm": 0.9937914609909058,
+      "learning_rate": 1.766648698079635e-05,
+      "loss": 1.7038,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7552428063819411,
+      "grad_norm": 1.060723066329956,
+      "learning_rate": 1.7297076136691072e-05,
+      "loss": 1.7939,
+      "step": 1355
+    },
+    {
+      "epoch": 0.7580296802062286,
+      "grad_norm": 1.1211639642715454,
+      "learning_rate": 1.6930758990184875e-05,
+      "loss": 1.7113,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7608165540305163,
+      "grad_norm": 1.1023319959640503,
+      "learning_rate": 1.6567570194891024e-05,
+      "loss": 1.6941,
+      "step": 1365
+    },
+    {
+      "epoch": 0.7636034278548038,
+      "grad_norm": 1.152541160583496,
+      "learning_rate": 1.620754410848069e-05,
+      "loss": 1.6875,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7663903016790915,
+      "grad_norm": 0.987436056137085,
+      "learning_rate": 1.5850714789432663e-05,
+      "loss": 1.7382,
+      "step": 1375
+    },
+    {
+      "epoch": 0.769177175503379,
+      "grad_norm": 1.0982835292816162,
+      "learning_rate": 1.549711599381145e-05,
+      "loss": 1.7245,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7719640493276667,
+      "grad_norm": 0.9890117049217224,
+      "learning_rate": 1.5146781172073959e-05,
+      "loss": 1.7029,
+      "step": 1385
+    },
+    {
+      "epoch": 0.7747509231519543,
+      "grad_norm": 1.0184069871902466,
+      "learning_rate": 1.479974346590503e-05,
+      "loss": 1.6937,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7775377969762419,
+      "grad_norm": 1.0105575323104858,
+      "learning_rate": 1.4456035705082349e-05,
+      "loss": 1.6418,
+      "step": 1395
+    },
+    {
+      "epoch": 0.7803246708005295,
+      "grad_norm": 1.0448589324951172,
+      "learning_rate": 1.4115690404370551e-05,
+      "loss": 1.6564,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7831115446248171,
+      "grad_norm": 1.0229320526123047,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.6874,
+      "step": 1405
+    },
+    {
+      "epoch": 0.7858984184491047,
+      "grad_norm": 0.9846269488334656,
+      "learning_rate": 1.344521564884858e-05,
+      "loss": 1.7533,
+      "step": 1410
+    },
+    {
+      "epoch": 0.7886852922733923,
+      "grad_norm": 1.0062910318374634,
+      "learning_rate": 1.3115149620970795e-05,
+      "loss": 1.7273,
+      "step": 1415
+    },
+    {
+      "epoch": 0.7914721660976799,
+      "grad_norm": 1.0991787910461426,
+      "learning_rate": 1.2788572901068552e-05,
+      "loss": 1.6953,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7942590399219676,
+      "grad_norm": 1.132625937461853,
+      "learning_rate": 1.2465516383309551e-05,
+      "loss": 1.7251,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7970459137462551,
+      "grad_norm": 1.0925284624099731,
+      "learning_rate": 1.2146010628850268e-05,
+      "loss": 1.7683,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7998327875705428,
+      "grad_norm": 1.0317128896713257,
+      "learning_rate": 1.183008586294485e-05,
+      "loss": 1.6232,
+      "step": 1435
+    },
+    {
+      "epoch": 0.8026196613948303,
+      "grad_norm": 1.0753761529922485,
+      "learning_rate": 1.151777197208585e-05,
+      "loss": 1.6474,
+      "step": 1440
+    },
+    {
+      "epoch": 0.805406535219118,
+      "grad_norm": 1.1683920621871948,
+      "learning_rate": 1.1209098501176896e-05,
+      "loss": 1.6708,
+      "step": 1445
+    },
+    {
+      "epoch": 0.8081934090434055,
+      "grad_norm": 1.069035530090332,
+      "learning_rate": 1.0904094650737795e-05,
+      "loss": 1.6566,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8109802828676932,
+      "grad_norm": 1.288718342781067,
+      "learning_rate": 1.0602789274142133e-05,
+      "loss": 1.7592,
+      "step": 1455
+    },
+    {
+      "epoch": 0.8137671566919807,
+      "grad_norm": 1.0440285205841064,
+      "learning_rate": 1.0305210874887766e-05,
+      "loss": 1.6214,
+      "step": 1460
+    },
+    {
+      "epoch": 0.8165540305162684,
+      "grad_norm": 1.0911659002304077,
+      "learning_rate": 1.0011387603900385e-05,
+      "loss": 1.6766,
+      "step": 1465
+    },
+    {
+      "epoch": 0.819340904340556,
+      "grad_norm": 1.0873469114303589,
+      "learning_rate": 9.7213472568704e-06,
+      "loss": 1.7141,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8221277781648436,
+      "grad_norm": 1.0345348119735718,
+      "learning_rate": 9.435117271623566e-06,
+      "loss": 1.5537,
+      "step": 1475
+    },
+    {
+      "epoch": 0.8249146519891312,
+      "grad_norm": 1.103845238685608,
+      "learning_rate": 9.152724725525202e-06,
+      "loss": 1.7075,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8277015258134188,
+      "grad_norm": 0.9956609606742859,
+      "learning_rate": 8.87419633291886e-06,
+      "loss": 1.7054,
+      "step": 1485
+    },
+    {
+      "epoch": 0.8304883996377064,
+      "grad_norm": 1.1183520555496216,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 1.6332,
+      "step": 1490
+    },
+    {
+      "epoch": 0.833275273461994,
+      "grad_norm": 1.100627064704895,
+      "learning_rate": 8.328837035318448e-06,
+      "loss": 1.7479,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8360621472862816,
+      "grad_norm": 1.0140594244003296,
+      "learning_rate": 8.06205772133063e-06,
+      "loss": 1.589,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.740577669473894e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87eaa3512a157f5d0c7785d61d4dd86da22136cc4779d09d5833877f1f1a7a
+size 6161

checkpoint-1795/README.md

@@ -0,0 +1,202 @@
+---
+base_model: 01-ai/Yi-1.5-6B-Chat
+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 0.15.2

checkpoint-1795/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-1.5-6B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1795/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678efbe85f017444878c2e2036eb0ccda34793e470ad042b357672945094aeb5
+size 72673016

checkpoint-1795/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}

checkpoint-1795/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22dd53ca4bf0f29b9f5c09903e6e6f156453d2cf48363e88e3f4e217ba0bd28e
+size 145605155

checkpoint-1795/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1795/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1eb2e719ba92d61c300d3b21bda51012661191790b1797109a6a81ec3f6ab06
+size 1465

checkpoint-1795/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1795/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

checkpoint-1795/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1795/trainer_state.json

@@ -0,0 +1,2547 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1795,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.5925259590148926,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 2.5484,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.7384228706359863,
+      "learning_rate": 5e-06,
+      "loss": 2.5036,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.7028982639312744,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 2.5177,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.1780974864959717,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 2.4746,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 2.8278558254241943,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.5083,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 2.5323452949523926,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.4383,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 1.2514830827713013,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.1978,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 1.1612293720245361,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.0549,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 0.9937079548835754,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.1649,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.056492567062378,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0852,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.9864413142204285,
+      "learning_rate": 3e-05,
+      "loss": 1.934,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.9184162616729736,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 2.0746,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 1.044710397720337,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.9812,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.9160545468330383,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.8794,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.9865038990974426,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.9266,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.9860550165176392,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.8417,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.9826656579971313,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.9756,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.9479106664657593,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.8803,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 1.005937933921814,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.8677,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 1.1173028945922852,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8416,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 1.0000165700912476,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.8607,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 1.3015921115875244,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.9752,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 1.0431042909622192,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.8514,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 1.0463422536849976,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.8656,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 1.0947015285491943,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.9479,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.9953688979148865,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.8627,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 1.0779668092727661,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.8262,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 1.2166972160339355,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.8461,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 1.055553674697876,
+      "learning_rate": 8e-05,
+      "loss": 1.9684,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 1.0838943719863892,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8891,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.9238198399543762,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.8507,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 1.186009168624878,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.8269,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 1.122663140296936,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.7877,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 1.176620364189148,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.8373,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 1.0495474338531494,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.838,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 1.0859992504119873,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.845,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 1.1708000898361206,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.8148,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 1.0338629484176636,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7982,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 1.2173702716827393,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.792,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 1.1683762073516846,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.8381,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 1.0897382497787476,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.8142,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.9195744395256042,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.8362,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 1.039374589920044,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7565,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 1.0218507051467896,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.8728,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 1.0597004890441895,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7938,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 1.1160184144973755,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.8156,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.99184250831604,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.7255,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 1.0527223348617554,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8942,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 1.0618565082550049,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.7666,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 1.1174343824386597,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.7274,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 1.045905351638794,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.9156,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 1.1782068014144897,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.8142,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 1.0786527395248413,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.8206,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 1.0150487422943115,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.7779,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 1.0553853511810303,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.8223,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 1.0968186855316162,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.7834,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.9188632369041443,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.8808,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.9829431772232056,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.8455,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 1.034116268157959,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.8042,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 1.0451691150665283,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.7696,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 1.064620852470398,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.8668,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 1.0409430265426636,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.8274,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 1.0153954029083252,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.8084,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.9218955039978027,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.8457,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.9664631485939026,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.772,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 1.0060662031173706,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.727,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 1.0184046030044556,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.7638,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.9374409317970276,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.7323,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.9715288877487183,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.7169,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 1.088680624961853,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.8065,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.9513164758682251,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.6545,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.9501610398292542,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.8605,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.9788233041763306,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.7838,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 1.0686471462249756,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.7832,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.9658113121986389,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.7721,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 1.0429141521453857,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.7741,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.9593327641487122,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.7534,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.9077600240707397,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.8398,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 1.048581600189209,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.8134,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.9498254060745239,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.7497,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 1.0249079465866089,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.6412,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.9723719358444214,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.7741,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.954607367515564,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.7865,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.9485211372375488,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.813,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.9606624841690063,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.7426,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.9899424910545349,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.7802,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 1.0416887998580933,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.7418,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.958951473236084,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.7791,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.993934154510498,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.739,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.9372468590736389,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.7406,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.9601876735687256,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.7357,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9922548532485962,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.7677,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.9353616833686829,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.8202,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8890717625617981,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.7473,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 1.0059962272644043,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7978,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.9888349771499634,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.7481,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.9407850503921509,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.7667,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 1.0001949071884155,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.7742,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.9057056307792664,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.816,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 1.0183491706848145,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.8137,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.9340478777885437,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.7735,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.9671086668968201,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.7204,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.9643672704696655,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.748,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.9929302334785461,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.7682,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 1.0192108154296875,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6811,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.9536918997764587,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.7562,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9654401540756226,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.7098,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.9755784869194031,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5997,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.920735776424408,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.8432,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.9787949323654175,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.7575,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9688432812690735,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6978,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.9125113487243652,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.7075,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.954394519329071,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.7341,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.9641663432121277,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.84,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.974785327911377,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.717,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 1.0628243684768677,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.7745,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9969517588615417,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.7366,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.9360251426696777,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.7395,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.9315335154533386,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.7478,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 1.008952260017395,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.6532,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.9224027395248413,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6901,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 1.0089499950408936,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7778,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 1.0609345436096191,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.7429,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.9656564593315125,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.7799,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.9876144528388977,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.7204,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.9239578247070312,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.7871,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9991699457168579,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.7259,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.9193426370620728,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.7508,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9434049129486084,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.8071,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9454895257949829,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.7493,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9811017513275146,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.7469,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9470755457878113,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.7392,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 1.0244383811950684,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7735,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 1.1164230108261108,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.7982,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 1.0754444599151611,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.7041,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.9588093757629395,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.8321,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.9360554218292236,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.7865,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.9670904278755188,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.7208,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.9358083605766296,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6911,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 1.0316359996795654,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.6729,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.9509869813919067,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.7395,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9687904119491577,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.7688,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8772656917572021,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.7311,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.9465420842170715,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7634,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.9126701354980469,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6924,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.070681095123291,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6977,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.9621564149856567,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.7579,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 1.0299642086029053,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.6608,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 1.0028384923934937,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.8124,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9672207832336426,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7581,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 1.0683056116104126,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7852,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 1.023703694343567,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.6159,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 1.0113016366958618,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.7385,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 1.0289918184280396,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.8094,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9700524806976318,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6953,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.9488673806190491,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.6345,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.99649977684021,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.7524,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.9158934354782104,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.7326,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.9467411637306213,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.7519,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.8946711421012878,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.6291,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.9915565848350525,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.757,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9836114645004272,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.8026,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 0.9982685446739197,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.7819,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 1.0257214307785034,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.719,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.9735772013664246,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.7153,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.9777944684028625,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.7256,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9858867526054382,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.7,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.9058387875556946,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.7095,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 1.0151069164276123,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.7606,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9841256141662598,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.7015,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.9631791710853577,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.7847,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 1.1236021518707275,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.7388,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 1.0226027965545654,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6993,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 1.0021902322769165,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.753,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9932888746261597,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6798,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 1.007003664970398,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.8083,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.9325096011161804,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.7057,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.9602507948875427,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.7063,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.814627468585968,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6748,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 1.0444878339767456,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.7389,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8829376101493835,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.7323,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9832122325897217,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.7698,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8969665169715881,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.7473,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9865416884422302,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6655,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.9947900176048279,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7719,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.9595984816551208,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.6078,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 1.0105018615722656,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.7251,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 1.039826512336731,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7688,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.9929054379463196,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.7562,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.084277629852295,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6752,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 1.0061899423599243,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.7075,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.9747031927108765,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.6154,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 1.0520727634429932,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6982,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.9064339995384216,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.7331,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.9782255291938782,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.6223,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9979589581489563,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.7069,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.9500666260719299,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6931,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 1.0122525691986084,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.745,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0289945602416992,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.729,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 1.014304280281067,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.7108,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5601616386818087,
+      "grad_norm": 1.025936245918274,
+      "learning_rate": 4.839543718475543e-05,
+      "loss": 1.6942,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5629485125060962,
+      "grad_norm": 1.0793489217758179,
+      "learning_rate": 4.790945657175061e-05,
+      "loss": 1.7333,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5657353863303839,
+      "grad_norm": 1.046277642250061,
+      "learning_rate": 4.742367372421811e-05,
+      "loss": 1.749,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5685222601546714,
+      "grad_norm": 1.0622342824935913,
+      "learning_rate": 4.69381345972302e-05,
+      "loss": 1.6864,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5713091339789591,
+      "grad_norm": 0.9354339838027954,
+      "learning_rate": 4.6452885122803205e-05,
+      "loss": 1.6619,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5740960078032467,
+      "grad_norm": 0.9112613797187805,
+      "learning_rate": 4.5967971205552194e-05,
+      "loss": 1.7251,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5768828816275343,
+      "grad_norm": 0.9895853400230408,
+      "learning_rate": 4.548343871834864e-05,
+      "loss": 1.7107,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5796697554518219,
+      "grad_norm": 0.9500023126602173,
+      "learning_rate": 4.499933349798067e-05,
+      "loss": 1.7607,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5824566292761095,
+      "grad_norm": 1.0377269983291626,
+      "learning_rate": 4.451570134081694e-05,
+      "loss": 1.7969,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5852435031003971,
+      "grad_norm": 0.9661582708358765,
+      "learning_rate": 4.403258799847433e-05,
+      "loss": 1.685,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5880303769246847,
+      "grad_norm": 1.0600863695144653,
+      "learning_rate": 4.3550039173489845e-05,
+      "loss": 1.6872,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5908172507489723,
+      "grad_norm": 1.0329686403274536,
+      "learning_rate": 4.306810051499708e-05,
+      "loss": 1.6185,
+      "step": 1060
+    },
+    {
+      "epoch": 0.59360412457326,
+      "grad_norm": 1.0944806337356567,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 1.7209,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5963909983975475,
+      "grad_norm": 0.923368513584137,
+      "learning_rate": 4.210623600109946e-05,
+      "loss": 1.5895,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5991778722218352,
+      "grad_norm": 1.025833249092102,
+      "learning_rate": 4.162640113810706e-05,
+      "loss": 1.7405,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6019647460461227,
+      "grad_norm": 1.026885747909546,
+      "learning_rate": 4.114735841782347e-05,
+      "loss": 1.7871,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6047516198704104,
+      "grad_norm": 0.9980199337005615,
+      "learning_rate": 4.06691531577047e-05,
+      "loss": 1.7028,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6075384936946979,
+      "grad_norm": 0.9639666080474854,
+      "learning_rate": 4.019183059598296e-05,
+      "loss": 1.6743,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6103253675189856,
+      "grad_norm": 0.9345841407775879,
+      "learning_rate": 3.971543588738724e-05,
+      "loss": 1.6934,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6131122413432731,
+      "grad_norm": 0.9754037261009216,
+      "learning_rate": 3.924001409887158e-05,
+      "loss": 1.6454,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6158991151675608,
+      "grad_norm": 1.0533924102783203,
+      "learning_rate": 3.87656102053517e-05,
+      "loss": 1.7128,
+      "step": 1105
+    },
+    {
+      "epoch": 0.6186859889918483,
+      "grad_norm": 1.022055983543396,
+      "learning_rate": 3.8292269085450474e-05,
+      "loss": 1.6777,
+      "step": 1110
+    },
+    {
+      "epoch": 0.621472862816136,
+      "grad_norm": 0.9270001649856567,
+      "learning_rate": 3.782003551725236e-05,
+      "loss": 1.745,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6242597366404236,
+      "grad_norm": 0.9471579790115356,
+      "learning_rate": 3.734895417406734e-05,
+      "loss": 1.7204,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6270466104647112,
+      "grad_norm": 0.9260222315788269,
+      "learning_rate": 3.687906962020491e-05,
+      "loss": 1.7333,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6298334842889988,
+      "grad_norm": 1.0778995752334595,
+      "learning_rate": 3.641042630675829e-05,
+      "loss": 1.763,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6326203581132864,
+      "grad_norm": 1.0067857503890991,
+      "learning_rate": 3.594306856739924e-05,
+      "loss": 1.6692,
+      "step": 1135
+    },
+    {
+      "epoch": 0.635407231937574,
+      "grad_norm": 0.994063138961792,
+      "learning_rate": 3.547704061418424e-05,
+      "loss": 1.6736,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6381941057618616,
+      "grad_norm": 1.0534288883209229,
+      "learning_rate": 3.501238653337194e-05,
+      "loss": 1.705,
+      "step": 1145
+    },
+    {
+      "epoch": 0.6409809795861492,
+      "grad_norm": 1.098292350769043,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7781,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6437678534104369,
+      "grad_norm": 1.0197910070419312,
+      "learning_rate": 3.408737567998993e-05,
+      "loss": 1.6325,
+      "step": 1155
+    },
+    {
+      "epoch": 0.6465547272347244,
+      "grad_norm": 1.0445324182510376,
+      "learning_rate": 3.362710641347524e-05,
+      "loss": 1.7602,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6493416010590121,
+      "grad_norm": 0.9735073447227478,
+      "learning_rate": 3.316838602319532e-05,
+      "loss": 1.761,
+      "step": 1165
+    },
+    {
+      "epoch": 0.6521284748832996,
+      "grad_norm": 1.056726336479187,
+      "learning_rate": 3.271125790411309e-05,
+      "loss": 1.5925,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6549153487075873,
+      "grad_norm": 1.1253453493118286,
+      "learning_rate": 3.225576530056264e-05,
+      "loss": 1.7672,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6577022225318748,
+      "grad_norm": 0.9200742840766907,
+      "learning_rate": 3.180195130215824e-05,
+      "loss": 1.6926,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6604890963561625,
+      "grad_norm": 1.203482985496521,
+      "learning_rate": 3.1349858839717986e-05,
+      "loss": 1.6457,
+      "step": 1185
+    },
+    {
+      "epoch": 0.66327597018045,
+      "grad_norm": 0.9705748558044434,
+      "learning_rate": 3.089953068120271e-05,
+      "loss": 1.6284,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6660628440047377,
+      "grad_norm": 1.0424647331237793,
+      "learning_rate": 3.0451009427669986e-05,
+      "loss": 1.6443,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6688497178290252,
+      "grad_norm": 1.0199843645095825,
+      "learning_rate": 3.000433750924414e-05,
+      "loss": 1.6971,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6716365916533129,
+      "grad_norm": 0.9686048030853271,
+      "learning_rate": 2.9559557181102315e-05,
+      "loss": 1.7045,
+      "step": 1205
+    },
+    {
+      "epoch": 0.6744234654776005,
+      "grad_norm": 1.1422017812728882,
+      "learning_rate": 2.911671051947722e-05,
+      "loss": 1.6388,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6772103393018881,
+      "grad_norm": 1.0640348196029663,
+      "learning_rate": 2.867583941767657e-05,
+      "loss": 1.6232,
+      "step": 1215
+    },
+    {
+      "epoch": 0.6799972131261757,
+      "grad_norm": 0.9906688332557678,
+      "learning_rate": 2.823698558212009e-05,
+      "loss": 1.7076,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6827840869504633,
+      "grad_norm": 1.047086238861084,
+      "learning_rate": 2.7800190528394122e-05,
+      "loss": 1.6712,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6855709607747509,
+      "grad_norm": 0.9434465169906616,
+      "learning_rate": 2.736549557732405e-05,
+      "loss": 1.6087,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6883578345990385,
+      "grad_norm": 1.0368611812591553,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 1.8661,
+      "step": 1235
+    },
+    {
+      "epoch": 0.6911447084233261,
+      "grad_norm": 1.0463006496429443,
+      "learning_rate": 2.650257026921455e-05,
+      "loss": 1.713,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6939315822476138,
+      "grad_norm": 1.0394631624221802,
+      "learning_rate": 2.607442154493568e-05,
+      "loss": 1.7607,
+      "step": 1245
+    },
+    {
+      "epoch": 0.6967184560719013,
+      "grad_norm": 1.0766334533691406,
+      "learning_rate": 2.5648536181111438e-05,
+      "loss": 1.6821,
+      "step": 1250
+    },
+    {
+      "epoch": 0.699505329896189,
+      "grad_norm": 1.1074429750442505,
+      "learning_rate": 2.5224954466510274e-05,
+      "loss": 1.6959,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7022922037204765,
+      "grad_norm": 0.9983723759651184,
+      "learning_rate": 2.480371647197538e-05,
+      "loss": 1.737,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7050790775447642,
+      "grad_norm": 1.0355981588363647,
+      "learning_rate": 2.438486204663391e-05,
+      "loss": 1.7327,
+      "step": 1265
+    },
+    {
+      "epoch": 0.7078659513690517,
+      "grad_norm": 1.015955924987793,
+      "learning_rate": 2.3968430814127385e-05,
+      "loss": 1.7327,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7106528251933394,
+      "grad_norm": 0.9912840723991394,
+      "learning_rate": 2.3554462168863085e-05,
+      "loss": 1.7214,
+      "step": 1275
+    },
+    {
+      "epoch": 0.7134396990176269,
+      "grad_norm": 1.0331684350967407,
+      "learning_rate": 2.314299527228759e-05,
+      "loss": 1.7073,
+      "step": 1280
+    },
+    {
+      "epoch": 0.7162265728419146,
+      "grad_norm": 0.9723387956619263,
+      "learning_rate": 2.2734069049181882e-05,
+      "loss": 1.6758,
+      "step": 1285
+    },
+    {
+      "epoch": 0.7190134466662021,
+      "grad_norm": 1.0285305976867676,
+      "learning_rate": 2.2327722183979212e-05,
+      "loss": 1.6994,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7218003204904898,
+      "grad_norm": 1.050363302230835,
+      "learning_rate": 2.1923993117105462e-05,
+      "loss": 1.6629,
+      "step": 1295
+    },
+    {
+      "epoch": 0.7245871943147774,
+      "grad_norm": 1.1402173042297363,
+      "learning_rate": 2.1522920041342704e-05,
+      "loss": 1.6634,
+      "step": 1300
+    },
+    {
+      "epoch": 0.727374068139065,
+      "grad_norm": 1.120635986328125,
+      "learning_rate": 2.1124540898216248e-05,
+      "loss": 1.7093,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7301609419633526,
+      "grad_norm": 0.99698805809021,
+      "learning_rate": 2.0728893374405166e-05,
+      "loss": 1.6105,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7329478157876402,
+      "grad_norm": 1.149105429649353,
+      "learning_rate": 2.033601489817738e-05,
+      "loss": 1.8142,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7357346896119278,
+      "grad_norm": 1.1066628694534302,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.7501,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7385215634362154,
+      "grad_norm": 1.021165132522583,
+      "learning_rate": 1.9558713488267238e-05,
+      "loss": 1.7328,
+      "step": 1325
+    },
+    {
+      "epoch": 0.741308437260503,
+      "grad_norm": 1.0248847007751465,
+      "learning_rate": 1.917436408732208e-05,
+      "loss": 1.6973,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7440953110847907,
+      "grad_norm": 1.154515266418457,
+      "learning_rate": 1.8792930792478357e-05,
+      "loss": 1.708,
+      "step": 1335
+    },
+    {
+      "epoch": 0.7468821849090782,
+      "grad_norm": 1.089268684387207,
+      "learning_rate": 1.8414449687337464e-05,
+      "loss": 1.6351,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7496690587333659,
+      "grad_norm": 1.0156011581420898,
+      "learning_rate": 1.8038956576223504e-05,
+      "loss": 1.6265,
+      "step": 1345
+    },
+    {
+      "epoch": 0.7524559325576534,
+      "grad_norm": 0.9937914609909058,
+      "learning_rate": 1.766648698079635e-05,
+      "loss": 1.7038,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7552428063819411,
+      "grad_norm": 1.060723066329956,
+      "learning_rate": 1.7297076136691072e-05,
+      "loss": 1.7939,
+      "step": 1355
+    },
+    {
+      "epoch": 0.7580296802062286,
+      "grad_norm": 1.1211639642715454,
+      "learning_rate": 1.6930758990184875e-05,
+      "loss": 1.7113,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7608165540305163,
+      "grad_norm": 1.1023319959640503,
+      "learning_rate": 1.6567570194891024e-05,
+      "loss": 1.6941,
+      "step": 1365
+    },
+    {
+      "epoch": 0.7636034278548038,
+      "grad_norm": 1.152541160583496,
+      "learning_rate": 1.620754410848069e-05,
+      "loss": 1.6875,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7663903016790915,
+      "grad_norm": 0.987436056137085,
+      "learning_rate": 1.5850714789432663e-05,
+      "loss": 1.7382,
+      "step": 1375
+    },
+    {
+      "epoch": 0.769177175503379,
+      "grad_norm": 1.0982835292816162,
+      "learning_rate": 1.549711599381145e-05,
+      "loss": 1.7245,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7719640493276667,
+      "grad_norm": 0.9890117049217224,
+      "learning_rate": 1.5146781172073959e-05,
+      "loss": 1.7029,
+      "step": 1385
+    },
+    {
+      "epoch": 0.7747509231519543,
+      "grad_norm": 1.0184069871902466,
+      "learning_rate": 1.479974346590503e-05,
+      "loss": 1.6937,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7775377969762419,
+      "grad_norm": 1.0105575323104858,
+      "learning_rate": 1.4456035705082349e-05,
+      "loss": 1.6418,
+      "step": 1395
+    },
+    {
+      "epoch": 0.7803246708005295,
+      "grad_norm": 1.0448589324951172,
+      "learning_rate": 1.4115690404370551e-05,
+      "loss": 1.6564,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7831115446248171,
+      "grad_norm": 1.0229320526123047,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.6874,
+      "step": 1405
+    },
+    {
+      "epoch": 0.7858984184491047,
+      "grad_norm": 0.9846269488334656,
+      "learning_rate": 1.344521564884858e-05,
+      "loss": 1.7533,
+      "step": 1410
+    },
+    {
+      "epoch": 0.7886852922733923,
+      "grad_norm": 1.0062910318374634,
+      "learning_rate": 1.3115149620970795e-05,
+      "loss": 1.7273,
+      "step": 1415
+    },
+    {
+      "epoch": 0.7914721660976799,
+      "grad_norm": 1.0991787910461426,
+      "learning_rate": 1.2788572901068552e-05,
+      "loss": 1.6953,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7942590399219676,
+      "grad_norm": 1.132625937461853,
+      "learning_rate": 1.2465516383309551e-05,
+      "loss": 1.7251,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7970459137462551,
+      "grad_norm": 1.0925284624099731,
+      "learning_rate": 1.2146010628850268e-05,
+      "loss": 1.7683,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7998327875705428,
+      "grad_norm": 1.0317128896713257,
+      "learning_rate": 1.183008586294485e-05,
+      "loss": 1.6232,
+      "step": 1435
+    },
+    {
+      "epoch": 0.8026196613948303,
+      "grad_norm": 1.0753761529922485,
+      "learning_rate": 1.151777197208585e-05,
+      "loss": 1.6474,
+      "step": 1440
+    },
+    {
+      "epoch": 0.805406535219118,
+      "grad_norm": 1.1683920621871948,
+      "learning_rate": 1.1209098501176896e-05,
+      "loss": 1.6708,
+      "step": 1445
+    },
+    {
+      "epoch": 0.8081934090434055,
+      "grad_norm": 1.069035530090332,
+      "learning_rate": 1.0904094650737795e-05,
+      "loss": 1.6566,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8109802828676932,
+      "grad_norm": 1.288718342781067,
+      "learning_rate": 1.0602789274142133e-05,
+      "loss": 1.7592,
+      "step": 1455
+    },
+    {
+      "epoch": 0.8137671566919807,
+      "grad_norm": 1.0440285205841064,
+      "learning_rate": 1.0305210874887766e-05,
+      "loss": 1.6214,
+      "step": 1460
+    },
+    {
+      "epoch": 0.8165540305162684,
+      "grad_norm": 1.0911659002304077,
+      "learning_rate": 1.0011387603900385e-05,
+      "loss": 1.6766,
+      "step": 1465
+    },
+    {
+      "epoch": 0.819340904340556,
+      "grad_norm": 1.0873469114303589,
+      "learning_rate": 9.7213472568704e-06,
+      "loss": 1.7141,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8221277781648436,
+      "grad_norm": 1.0345348119735718,
+      "learning_rate": 9.435117271623566e-06,
+      "loss": 1.5537,
+      "step": 1475
+    },
+    {
+      "epoch": 0.8249146519891312,
+      "grad_norm": 1.103845238685608,
+      "learning_rate": 9.152724725525202e-06,
+      "loss": 1.7075,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8277015258134188,
+      "grad_norm": 0.9956609606742859,
+      "learning_rate": 8.87419633291886e-06,
+      "loss": 1.7054,
+      "step": 1485
+    },
+    {
+      "epoch": 0.8304883996377064,
+      "grad_norm": 1.1183520555496216,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 1.6332,
+      "step": 1490
+    },
+    {
+      "epoch": 0.833275273461994,
+      "grad_norm": 1.100627064704895,
+      "learning_rate": 8.328837035318448e-06,
+      "loss": 1.7479,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8360621472862816,
+      "grad_norm": 1.0140594244003296,
+      "learning_rate": 8.06205772133063e-06,
+      "loss": 1.589,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8388490211105692,
+      "grad_norm": 1.1413642168045044,
+      "learning_rate": 7.799245737966821e-06,
+      "loss": 1.6295,
+      "step": 1505
+    },
+    {
+      "epoch": 0.8416358949348568,
+      "grad_norm": 1.0950514078140259,
+      "learning_rate": 7.540425947248697e-06,
+      "loss": 1.723,
+      "step": 1510
+    },
+    {
+      "epoch": 0.8444227687591445,
+      "grad_norm": 0.9846428036689758,
+      "learning_rate": 7.28562283353637e-06,
+      "loss": 1.6772,
+      "step": 1515
+    },
+    {
+      "epoch": 0.847209642583432,
+      "grad_norm": 1.0106980800628662,
+      "learning_rate": 7.034860501212243e-06,
+      "loss": 1.6939,
+      "step": 1520
+    },
+    {
+      "epoch": 0.8499965164077197,
+      "grad_norm": 1.1142985820770264,
+      "learning_rate": 6.788162672400583e-06,
+      "loss": 1.7637,
+      "step": 1525
+    },
+    {
+      "epoch": 0.8527833902320072,
+      "grad_norm": 0.9894189834594727,
+      "learning_rate": 6.5455526847235825e-06,
+      "loss": 1.7018,
+      "step": 1530
+    },
+    {
+      "epoch": 0.8555702640562949,
+      "grad_norm": 1.1043624877929688,
+      "learning_rate": 6.307053489093506e-06,
+      "loss": 1.6953,
+      "step": 1535
+    },
+    {
+      "epoch": 0.8583571378805824,
+      "grad_norm": 1.0521725416183472,
+      "learning_rate": 6.072687647541553e-06,
+      "loss": 1.7037,
+      "step": 1540
+    },
+    {
+      "epoch": 0.8611440117048701,
+      "grad_norm": 1.0040065050125122,
+      "learning_rate": 5.842477331083518e-06,
+      "loss": 1.7048,
+      "step": 1545
+    },
+    {
+      "epoch": 0.8639308855291576,
+      "grad_norm": 1.0076823234558105,
+      "learning_rate": 5.616444317622388e-06,
+      "loss": 1.6133,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8667177593534453,
+      "grad_norm": 1.0111955404281616,
+      "learning_rate": 5.394609989888161e-06,
+      "loss": 1.7169,
+      "step": 1555
+    },
+    {
+      "epoch": 0.8695046331777329,
+      "grad_norm": 1.2289667129516602,
+      "learning_rate": 5.176995333415019e-06,
+      "loss": 1.7181,
+      "step": 1560
+    },
+    {
+      "epoch": 0.8722915070020205,
+      "grad_norm": 1.096440076828003,
+      "learning_rate": 4.963620934556168e-06,
+      "loss": 1.7217,
+      "step": 1565
+    },
+    {
+      "epoch": 0.8750783808263081,
+      "grad_norm": 1.013545036315918,
+      "learning_rate": 4.754506978536227e-06,
+      "loss": 1.689,
+      "step": 1570
+    },
+    {
+      "epoch": 0.8778652546505957,
+      "grad_norm": 0.9516837000846863,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.7012,
+      "step": 1575
+    },
+    {
+      "epoch": 0.8806521284748833,
+      "grad_norm": 0.8992862105369568,
+      "learning_rate": 4.3491391188503264e-06,
+      "loss": 1.6485,
+      "step": 1580
+    },
+    {
+      "epoch": 0.8834390022991709,
+      "grad_norm": 1.135851263999939,
+      "learning_rate": 4.152923562996297e-06,
+      "loss": 1.6127,
+      "step": 1585
+    },
+    {
+      "epoch": 0.8862258761234585,
+      "grad_norm": 1.005721926689148,
+      "learning_rate": 3.961045141977376e-06,
+      "loss": 1.7072,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8890127499477462,
+      "grad_norm": 1.090638279914856,
+      "learning_rate": 3.773522007498065e-06,
+      "loss": 1.7056,
+      "step": 1595
+    },
+    {
+      "epoch": 0.8917996237720337,
+      "grad_norm": 1.0061423778533936,
+      "learning_rate": 3.590371899252659e-06,
+      "loss": 1.6534,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8945864975963214,
+      "grad_norm": 0.9777345061302185,
+      "learning_rate": 3.4116121432469615e-06,
+      "loss": 1.6287,
+      "step": 1605
+    },
+    {
+      "epoch": 0.8973733714206089,
+      "grad_norm": 0.9867115616798401,
+      "learning_rate": 3.237259650159402e-06,
+      "loss": 1.6605,
+      "step": 1610
+    },
+    {
+      "epoch": 0.9001602452448966,
+      "grad_norm": 1.041188359260559,
+      "learning_rate": 3.0673309137411564e-06,
+      "loss": 1.704,
+      "step": 1615
+    },
+    {
+      "epoch": 0.9029471190691841,
+      "grad_norm": 1.1051174402236938,
+      "learning_rate": 2.9018420092558786e-06,
+      "loss": 1.6372,
+      "step": 1620
+    },
+    {
+      "epoch": 0.9057339928934718,
+      "grad_norm": 1.0812339782714844,
+      "learning_rate": 2.7408085919590264e-06,
+      "loss": 1.7765,
+      "step": 1625
+    },
+    {
+      "epoch": 0.9085208667177593,
+      "grad_norm": 1.0568102598190308,
+      "learning_rate": 2.584245895616788e-06,
+      "loss": 1.7113,
+      "step": 1630
+    },
+    {
+      "epoch": 0.911307740542047,
+      "grad_norm": 1.0920485258102417,
+      "learning_rate": 2.4321687310650487e-06,
+      "loss": 1.7115,
+      "step": 1635
+    },
+    {
+      "epoch": 0.9140946143663345,
+      "grad_norm": 1.0551624298095703,
+      "learning_rate": 2.2845914848082127e-06,
+      "loss": 1.7397,
+      "step": 1640
+    },
+    {
+      "epoch": 0.9168814881906222,
+      "grad_norm": 1.107050895690918,
+      "learning_rate": 2.1415281176583203e-06,
+      "loss": 1.6889,
+      "step": 1645
+    },
+    {
+      "epoch": 0.9196683620149098,
+      "grad_norm": 1.129211664199829,
+      "learning_rate": 2.0029921634142632e-06,
+      "loss": 1.7773,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9224552358391974,
+      "grad_norm": 1.0748560428619385,
+      "learning_rate": 1.8689967275815679e-06,
+      "loss": 1.7075,
+      "step": 1655
+    },
+    {
+      "epoch": 0.925242109663485,
+      "grad_norm": 1.0518732070922852,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 1.7446,
+      "step": 1660
+    },
+    {
+      "epoch": 0.9280289834877726,
+      "grad_norm": 1.0229655504226685,
+      "learning_rate": 1.614677684307264e-06,
+      "loss": 1.6918,
+      "step": 1665
+    },
+    {
+      "epoch": 0.9308158573120602,
+      "grad_norm": 1.0983964204788208,
+      "learning_rate": 1.494378135454938e-06,
+      "loss": 1.7006,
+      "step": 1670
+    },
+    {
+      "epoch": 0.9336027311363478,
+      "grad_norm": 1.015277624130249,
+      "learning_rate": 1.3786672199165962e-06,
+      "loss": 1.6981,
+      "step": 1675
+    },
+    {
+      "epoch": 0.9363896049606354,
+      "grad_norm": 1.041909098625183,
+      "learning_rate": 1.2675558839483848e-06,
+      "loss": 1.6624,
+      "step": 1680
+    },
+    {
+      "epoch": 0.939176478784923,
+      "grad_norm": 1.1352739334106445,
+      "learning_rate": 1.1610546386860988e-06,
+      "loss": 1.6704,
+      "step": 1685
+    },
+    {
+      "epoch": 0.9419633526092106,
+      "grad_norm": 1.1310465335845947,
+      "learning_rate": 1.0591735591507946e-06,
+      "loss": 1.6707,
+      "step": 1690
+    },
+    {
+      "epoch": 0.9447502264334983,
+      "grad_norm": 1.1026233434677124,
+      "learning_rate": 9.619222832957243e-07,
+      "loss": 1.6805,
+      "step": 1695
+    },
+    {
+      "epoch": 0.9475371002577858,
+      "grad_norm": 1.0651291608810425,
+      "learning_rate": 8.693100110945484e-07,
+      "loss": 1.685,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9503239740820735,
+      "grad_norm": 0.9923227429389954,
+      "learning_rate": 7.813455036710715e-07,
+      "loss": 1.6613,
+      "step": 1705
+    },
+    {
+      "epoch": 0.953110847906361,
+      "grad_norm": 1.049928069114685,
+      "learning_rate": 6.980370824703763e-07,
+      "loss": 1.7236,
+      "step": 1710
+    },
+    {
+      "epoch": 0.9558977217306487,
+      "grad_norm": 1.1592174768447876,
+      "learning_rate": 6.193926284716711e-07,
+      "loss": 1.6347,
+      "step": 1715
+    },
+    {
+      "epoch": 0.9586845955549362,
+      "grad_norm": 1.056167483329773,
+      "learning_rate": 5.454195814427021e-07,
+      "loss": 1.7672,
+      "step": 1720
+    },
+    {
+      "epoch": 0.9614714693792239,
+      "grad_norm": 1.0875788927078247,
+      "learning_rate": 4.76124939235989e-07,
+      "loss": 1.6709,
+      "step": 1725
+    },
+    {
+      "epoch": 0.9642583432035114,
+      "grad_norm": 1.0372425317764282,
+      "learning_rate": 4.1151525712680996e-07,
+      "loss": 1.6097,
+      "step": 1730
+    },
+    {
+      "epoch": 0.9670452170277991,
+      "grad_norm": 1.1437121629714966,
+      "learning_rate": 3.515966471930643e-07,
+      "loss": 1.7672,
+      "step": 1735
+    },
+    {
+      "epoch": 0.9698320908520867,
+      "grad_norm": 1.1399418115615845,
+      "learning_rate": 2.963747777370907e-07,
+      "loss": 1.7417,
+      "step": 1740
+    },
+    {
+      "epoch": 0.9726189646763743,
+      "grad_norm": 1.1216853857040405,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 1.5956,
+      "step": 1745
+    },
+    {
+      "epoch": 0.9754058385006619,
+      "grad_norm": 1.017702341079712,
+      "learning_rate": 2.0004171141464467e-07,
+      "loss": 1.7252,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9781927123249495,
+      "grad_norm": 1.0261662006378174,
+      "learning_rate": 1.589396276591937e-07,
+      "loss": 1.6793,
+      "step": 1755
+    },
+    {
+      "epoch": 0.9809795861492371,
+      "grad_norm": 1.1111146211624146,
+      "learning_rate": 1.225525097414637e-07,
+      "loss": 1.6287,
+      "step": 1760
+    },
+    {
+      "epoch": 0.9837664599735247,
+      "grad_norm": 1.1646637916564941,
+      "learning_rate": 9.088379988392848e-08,
+      "loss": 1.6864,
+      "step": 1765
+    },
+    {
+      "epoch": 0.9865533337978123,
+      "grad_norm": 1.091788411140442,
+      "learning_rate": 6.393649394749734e-08,
+      "loss": 1.6652,
+      "step": 1770
+    },
+    {
+      "epoch": 0.9893402076221,
+      "grad_norm": 1.1367450952529907,
+      "learning_rate": 4.171314114815306e-08,
+      "loss": 1.7651,
+      "step": 1775
+    },
+    {
+      "epoch": 0.9921270814463875,
+      "grad_norm": 1.0925397872924805,
+      "learning_rate": 2.4215843815733607e-08,
+      "loss": 1.6174,
+      "step": 1780
+    },
+    {
+      "epoch": 0.9949139552706752,
+      "grad_norm": 0.9592256546020508,
+      "learning_rate": 1.1446257195119048e-08,
+      "loss": 1.708,
+      "step": 1785
+    },
+    {
+      "epoch": 0.9977008290949627,
+      "grad_norm": 1.0410560369491577,
+      "learning_rate": 3.4055892895901167e-09,
+      "loss": 1.7146,
+      "step": 1790
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.932434320449829,
+      "learning_rate": 9.460074656963969e-11,
+      "loss": 1.7885,
+      "step": 1795
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "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": 8.068623002055475e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1795/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87eaa3512a157f5d0c7785d61d4dd86da22136cc4779d09d5833877f1f1a7a
+size 6161

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: 01-ai/Yi-1.5-6B-Chat
+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 0.15.2

checkpoint-500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-1.5-6B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8d6db04c97452b674fbe439db1c14da6a9827700d57039d9fad34d3975c36e
+size 72673016

checkpoint-500/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18043cc675119984440279edae8d1f00b9f046257d79db64cf97f0e9bf7009cd
+size 145605155

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f0c4988d73d67d473e602f2aa816dd296a5c45a1ca3e96c9c11ab32dce2554
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105