Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c94d5dc25f7aa372411018ebf84b652f7a47a82cd791ecb630b0870a2b4b1e
+size 167832240

checkpoint-8163/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-8163/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-8163/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c94d5dc25f7aa372411018ebf84b652f7a47a82cd791ecb630b0870a2b4b1e
+size 167832240

checkpoint-8163/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a43a6e2693091bda31318bdf5b02732a7ed14ffb980f944a449a8a8f1336be4
+size 335922386

checkpoint-8163/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-8163/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f0eb2c0fa0fbda1b5866dc373106fc53661a351a69a299530ed4101ec6575e
+size 14244

checkpoint-8163/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711d4ab4746e522a1071d0febf7d76ca7b1edd00051755c64ef6b99ac191feeb
+size 1064

checkpoint-8163/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-8163/tokenizer.model

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

checkpoint-8163/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-8163/trainer_state.json

@@ -0,0 +1,2303 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.999724391364263,
+  "eval_steps": 500,
+  "global_step": 8163,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.019594669342041,
+      "learning_rate": 8.812729498164015e-07,
+      "loss": 2.5969,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.2792530059814453,
+      "learning_rate": 1.799265605875153e-06,
+      "loss": 2.5712,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.6284871101379395,
+      "learning_rate": 2.7172582619339046e-06,
+      "loss": 2.4269,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.638899803161621,
+      "learning_rate": 3.6352509179926564e-06,
+      "loss": 2.3086,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.020103693008423,
+      "learning_rate": 4.553243574051408e-06,
+      "loss": 2.152,
+      "step": 125
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.3148763179779053,
+      "learning_rate": 5.47123623011016e-06,
+      "loss": 2.0393,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.275376558303833,
+      "learning_rate": 6.389228886168911e-06,
+      "loss": 1.954,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.5663716793060303,
+      "learning_rate": 7.307221542227662e-06,
+      "loss": 1.9075,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.4330193996429443,
+      "learning_rate": 8.225214198286414e-06,
+      "loss": 1.8074,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.7704484462738037,
+      "learning_rate": 9.143206854345165e-06,
+      "loss": 1.7968,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.2770776748657227,
+      "learning_rate": 1.0061199510403917e-05,
+      "loss": 1.7784,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.754490613937378,
+      "learning_rate": 1.097919216646267e-05,
+      "loss": 1.6953,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.240971326828003,
+      "learning_rate": 1.189718482252142e-05,
+      "loss": 1.6694,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.4175171852111816,
+      "learning_rate": 1.2815177478580172e-05,
+      "loss": 1.6863,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.8977129459381104,
+      "learning_rate": 1.3733170134638923e-05,
+      "loss": 1.6488,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.4206955432891846,
+      "learning_rate": 1.4651162790697674e-05,
+      "loss": 1.659,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.3763089179992676,
+      "learning_rate": 1.556915544675643e-05,
+      "loss": 1.6077,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.212315320968628,
+      "learning_rate": 1.6487148102815178e-05,
+      "loss": 1.6231,
+      "step": 450
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.6150689125061035,
+      "learning_rate": 1.7405140758873927e-05,
+      "loss": 1.6708,
+      "step": 475
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.622896671295166,
+      "learning_rate": 1.8323133414932683e-05,
+      "loss": 1.5761,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.499622106552124,
+      "learning_rate": 1.9241126070991433e-05,
+      "loss": 1.6017,
+      "step": 525
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.657644748687744,
+      "learning_rate": 2.0159118727050182e-05,
+      "loss": 1.5908,
+      "step": 550
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.4769978523254395,
+      "learning_rate": 2.1077111383108938e-05,
+      "loss": 1.6129,
+      "step": 575
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.1776161193847656,
+      "learning_rate": 2.1995104039167688e-05,
+      "loss": 1.5764,
+      "step": 600
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.463768482208252,
+      "learning_rate": 2.2913096695226437e-05,
+      "loss": 1.579,
+      "step": 625
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.202385902404785,
+      "learning_rate": 2.383108935128519e-05,
+      "loss": 1.5452,
+      "step": 650
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.233647108078003,
+      "learning_rate": 2.4749082007343942e-05,
+      "loss": 1.6323,
+      "step": 675
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.332144021987915,
+      "learning_rate": 2.5667074663402692e-05,
+      "loss": 1.6045,
+      "step": 700
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.251033306121826,
+      "learning_rate": 2.6585067319461444e-05,
+      "loss": 1.5763,
+      "step": 725
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.138462781906128,
+      "learning_rate": 2.7503059975520197e-05,
+      "loss": 1.5706,
+      "step": 750
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.0554285049438477,
+      "learning_rate": 2.8421052631578946e-05,
+      "loss": 1.5216,
+      "step": 775
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.0504651069641113,
+      "learning_rate": 2.93390452876377e-05,
+      "loss": 1.57,
+      "step": 800
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.95691180229187,
+      "learning_rate": 2.997141301388511e-05,
+      "loss": 1.5168,
+      "step": 825
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.863208293914795,
+      "learning_rate": 2.986931663490335e-05,
+      "loss": 1.5552,
+      "step": 850
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.5448153018951416,
+      "learning_rate": 2.9767220255921593e-05,
+      "loss": 1.5648,
+      "step": 875
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.7234387397766113,
+      "learning_rate": 2.9665123876939832e-05,
+      "loss": 1.5216,
+      "step": 900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.56977915763855,
+      "learning_rate": 2.956302749795807e-05,
+      "loss": 1.4888,
+      "step": 925
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.7813570499420166,
+      "learning_rate": 2.9460931118976314e-05,
+      "loss": 1.55,
+      "step": 950
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.516843318939209,
+      "learning_rate": 2.9358834739994553e-05,
+      "loss": 1.5215,
+      "step": 975
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.7116241455078125,
+      "learning_rate": 2.9256738361012796e-05,
+      "loss": 1.5186,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.504891872406006,
+      "learning_rate": 2.9154641982031038e-05,
+      "loss": 1.4975,
+      "step": 1025
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.4921352863311768,
+      "learning_rate": 2.9052545603049277e-05,
+      "loss": 1.5364,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.4780983924865723,
+      "learning_rate": 2.895044922406752e-05,
+      "loss": 1.5075,
+      "step": 1075
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5795676708221436,
+      "learning_rate": 2.884835284508576e-05,
+      "loss": 1.5197,
+      "step": 1100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.4717788696289062,
+      "learning_rate": 2.8746256466104002e-05,
+      "loss": 1.5436,
+      "step": 1125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.516700029373169,
+      "learning_rate": 2.8644160087122245e-05,
+      "loss": 1.5227,
+      "step": 1150
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.3301610946655273,
+      "learning_rate": 2.8542063708140484e-05,
+      "loss": 1.5403,
+      "step": 1175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.5666234493255615,
+      "learning_rate": 2.8439967329158726e-05,
+      "loss": 1.484,
+      "step": 1200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.273963689804077,
+      "learning_rate": 2.8337870950176966e-05,
+      "loss": 1.4857,
+      "step": 1225
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.419245958328247,
+      "learning_rate": 2.8239858426354477e-05,
+      "loss": 1.4803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.312894821166992,
+      "learning_rate": 2.813776204737272e-05,
+      "loss": 1.497,
+      "step": 1275
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3168880939483643,
+      "learning_rate": 2.8035665668390962e-05,
+      "loss": 1.5124,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.245943546295166,
+      "learning_rate": 2.79335692894092e-05,
+      "loss": 1.4894,
+      "step": 1325
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.4954259395599365,
+      "learning_rate": 2.7831472910427444e-05,
+      "loss": 1.5054,
+      "step": 1350
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.5361862182617188,
+      "learning_rate": 2.7729376531445686e-05,
+      "loss": 1.515,
+      "step": 1375
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.41825795173645,
+      "learning_rate": 2.7627280152463926e-05,
+      "loss": 1.4432,
+      "step": 1400
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.2795910835266113,
+      "learning_rate": 2.7525183773482168e-05,
+      "loss": 1.4956,
+      "step": 1425
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.272019624710083,
+      "learning_rate": 2.7423087394500407e-05,
+      "loss": 1.5067,
+      "step": 1450
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.297214984893799,
+      "learning_rate": 2.732099101551865e-05,
+      "loss": 1.459,
+      "step": 1475
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.2966599464416504,
+      "learning_rate": 2.7218894636536893e-05,
+      "loss": 1.463,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.258310556411743,
+      "learning_rate": 2.7116798257555132e-05,
+      "loss": 1.4855,
+      "step": 1525
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 2.2546372413635254,
+      "learning_rate": 2.7014701878573375e-05,
+      "loss": 1.4389,
+      "step": 1550
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.2848825454711914,
+      "learning_rate": 2.6912605499591614e-05,
+      "loss": 1.4709,
+      "step": 1575
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 2.4607439041137695,
+      "learning_rate": 2.6810509120609856e-05,
+      "loss": 1.4738,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.17085599899292,
+      "learning_rate": 2.67084127416281e-05,
+      "loss": 1.4427,
+      "step": 1625
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.3322973251342773,
+      "learning_rate": 2.6606316362646338e-05,
+      "loss": 1.4576,
+      "step": 1650
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.157118558883667,
+      "learning_rate": 2.650421998366458e-05,
+      "loss": 1.4368,
+      "step": 1675
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.3906755447387695,
+      "learning_rate": 2.640212360468282e-05,
+      "loss": 1.4464,
+      "step": 1700
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 2.19273042678833,
+      "learning_rate": 2.6300027225701063e-05,
+      "loss": 1.4032,
+      "step": 1725
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.0533928871154785,
+      "learning_rate": 2.6197930846719305e-05,
+      "loss": 1.4803,
+      "step": 1750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.090940237045288,
+      "learning_rate": 2.6095834467737544e-05,
+      "loss": 1.4613,
+      "step": 1775
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.2770726680755615,
+      "learning_rate": 2.5993738088755787e-05,
+      "loss": 1.4975,
+      "step": 1800
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.3754994869232178,
+      "learning_rate": 2.589164170977403e-05,
+      "loss": 1.4286,
+      "step": 1825
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.255023717880249,
+      "learning_rate": 2.578954533079227e-05,
+      "loss": 1.4112,
+      "step": 1850
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.0663328170776367,
+      "learning_rate": 2.568744895181051e-05,
+      "loss": 1.4288,
+      "step": 1875
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.1688010692596436,
+      "learning_rate": 2.558535257282875e-05,
+      "loss": 1.4175,
+      "step": 1900
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.078010320663452,
+      "learning_rate": 2.5483256193846993e-05,
+      "loss": 1.44,
+      "step": 1925
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.0523500442504883,
+      "learning_rate": 2.5381159814865236e-05,
+      "loss": 1.402,
+      "step": 1950
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.2531204223632812,
+      "learning_rate": 2.5279063435883475e-05,
+      "loss": 1.442,
+      "step": 1975
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.2075908184051514,
+      "learning_rate": 2.5176967056901718e-05,
+      "loss": 1.4466,
+      "step": 2000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.06585431098938,
+      "learning_rate": 2.5074870677919957e-05,
+      "loss": 1.445,
+      "step": 2025
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.291527271270752,
+      "learning_rate": 2.4972774298938196e-05,
+      "loss": 1.4239,
+      "step": 2050
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.077122688293457,
+      "learning_rate": 2.487067791995644e-05,
+      "loss": 1.4512,
+      "step": 2075
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 2.0683939456939697,
+      "learning_rate": 2.4768581540974678e-05,
+      "loss": 1.4313,
+      "step": 2100
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.2548866271972656,
+      "learning_rate": 2.466648516199292e-05,
+      "loss": 1.4499,
+      "step": 2125
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.0333142280578613,
+      "learning_rate": 2.4564388783011163e-05,
+      "loss": 1.489,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.0241236686706543,
+      "learning_rate": 2.4462292404029403e-05,
+      "loss": 1.4531,
+      "step": 2175
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.0434224605560303,
+      "learning_rate": 2.4360196025047645e-05,
+      "loss": 1.4067,
+      "step": 2200
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.0772247314453125,
+      "learning_rate": 2.4258099646065884e-05,
+      "loss": 1.4512,
+      "step": 2225
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 2.219872236251831,
+      "learning_rate": 2.4156003267084127e-05,
+      "loss": 1.4136,
+      "step": 2250
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.0617380142211914,
+      "learning_rate": 2.405390688810237e-05,
+      "loss": 1.4189,
+      "step": 2275
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.143292188644409,
+      "learning_rate": 2.395181050912061e-05,
+      "loss": 1.4343,
+      "step": 2300
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.2767598628997803,
+      "learning_rate": 2.384971413013885e-05,
+      "loss": 1.4309,
+      "step": 2325
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9452316761016846,
+      "learning_rate": 2.374761775115709e-05,
+      "loss": 1.4525,
+      "step": 2350
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.9767943620681763,
+      "learning_rate": 2.3645521372175333e-05,
+      "loss": 1.4146,
+      "step": 2375
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.1205859184265137,
+      "learning_rate": 2.3543424993193576e-05,
+      "loss": 1.3848,
+      "step": 2400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 2.1726503372192383,
+      "learning_rate": 2.3441328614211815e-05,
+      "loss": 1.4229,
+      "step": 2425
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.1361019611358643,
+      "learning_rate": 2.3339232235230058e-05,
+      "loss": 1.3928,
+      "step": 2450
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.9983566999435425,
+      "learning_rate": 2.32371358562483e-05,
+      "loss": 1.4177,
+      "step": 2475
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.072235107421875,
+      "learning_rate": 2.313503947726654e-05,
+      "loss": 1.4299,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.9266953468322754,
+      "learning_rate": 2.3032943098284782e-05,
+      "loss": 1.4124,
+      "step": 2525
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.9758812189102173,
+      "learning_rate": 2.293084671930302e-05,
+      "loss": 1.4642,
+      "step": 2550
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.9793875217437744,
+      "learning_rate": 2.2828750340321264e-05,
+      "loss": 1.4216,
+      "step": 2575
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.8431023359298706,
+      "learning_rate": 2.2726653961339507e-05,
+      "loss": 1.4259,
+      "step": 2600
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.120908260345459,
+      "learning_rate": 2.2624557582357746e-05,
+      "loss": 1.3896,
+      "step": 2625
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.8971043825149536,
+      "learning_rate": 2.252246120337599e-05,
+      "loss": 1.4137,
+      "step": 2650
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.79995858669281,
+      "learning_rate": 2.2420364824394228e-05,
+      "loss": 1.4027,
+      "step": 2675
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.9894652366638184,
+      "learning_rate": 2.231826844541247e-05,
+      "loss": 1.4241,
+      "step": 2700
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8721575736999512,
+      "learning_rate": 2.2216172066430713e-05,
+      "loss": 1.4167,
+      "step": 2725
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.1240813732147217,
+      "learning_rate": 2.2114075687448952e-05,
+      "loss": 1.324,
+      "step": 2750
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.9302886724472046,
+      "learning_rate": 2.2011979308467195e-05,
+      "loss": 1.3041,
+      "step": 2775
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 2.2087652683258057,
+      "learning_rate": 2.1909882929485437e-05,
+      "loss": 1.3632,
+      "step": 2800
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.057499885559082,
+      "learning_rate": 2.1807786550503677e-05,
+      "loss": 1.3536,
+      "step": 2825
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.1920557022094727,
+      "learning_rate": 2.170569017152192e-05,
+      "loss": 1.3375,
+      "step": 2850
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.917410135269165,
+      "learning_rate": 2.160359379254016e-05,
+      "loss": 1.3396,
+      "step": 2875
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.910172462463379,
+      "learning_rate": 2.15014974135584e-05,
+      "loss": 1.2931,
+      "step": 2900
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.9294995069503784,
+      "learning_rate": 2.1399401034576644e-05,
+      "loss": 1.3,
+      "step": 2925
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.2092173099517822,
+      "learning_rate": 2.1297304655594883e-05,
+      "loss": 1.3196,
+      "step": 2950
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 2.212209939956665,
+      "learning_rate": 2.1195208276613126e-05,
+      "loss": 1.3623,
+      "step": 2975
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 2.3022515773773193,
+      "learning_rate": 2.109311189763136e-05,
+      "loss": 1.3402,
+      "step": 3000
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 2.2032854557037354,
+      "learning_rate": 2.0991015518649604e-05,
+      "loss": 1.3677,
+      "step": 3025
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.9251583814620972,
+      "learning_rate": 2.0888919139667847e-05,
+      "loss": 1.2894,
+      "step": 3050
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 2.1988320350646973,
+      "learning_rate": 2.0786822760686086e-05,
+      "loss": 1.3709,
+      "step": 3075
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 2.201289415359497,
+      "learning_rate": 2.068472638170433e-05,
+      "loss": 1.3145,
+      "step": 3100
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.992992877960205,
+      "learning_rate": 2.058263000272257e-05,
+      "loss": 1.3233,
+      "step": 3125
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 2.088419198989868,
+      "learning_rate": 2.048053362374081e-05,
+      "loss": 1.3669,
+      "step": 3150
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.9846084117889404,
+      "learning_rate": 2.0378437244759053e-05,
+      "loss": 1.3646,
+      "step": 3175
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 2.0262553691864014,
+      "learning_rate": 2.0276340865777292e-05,
+      "loss": 1.3577,
+      "step": 3200
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 2.1256277561187744,
+      "learning_rate": 2.0174244486795535e-05,
+      "loss": 1.3292,
+      "step": 3225
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 2.043562889099121,
+      "learning_rate": 2.0072148107813777e-05,
+      "loss": 1.3132,
+      "step": 3250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.0755374431610107,
+      "learning_rate": 1.9970051728832017e-05,
+      "loss": 1.2979,
+      "step": 3275
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 2.0620744228363037,
+      "learning_rate": 1.986795534985026e-05,
+      "loss": 1.3518,
+      "step": 3300
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 2.1864535808563232,
+      "learning_rate": 1.97658589708685e-05,
+      "loss": 1.3529,
+      "step": 3325
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 2.22280216217041,
+      "learning_rate": 1.966376259188674e-05,
+      "loss": 1.3006,
+      "step": 3350
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.9707540273666382,
+      "learning_rate": 1.9561666212904984e-05,
+      "loss": 1.3253,
+      "step": 3375
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.134737730026245,
+      "learning_rate": 1.9459569833923223e-05,
+      "loss": 1.3208,
+      "step": 3400
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.4195773601531982,
+      "learning_rate": 1.9357473454941465e-05,
+      "loss": 1.3174,
+      "step": 3425
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 2.222219944000244,
+      "learning_rate": 1.9255377075959708e-05,
+      "loss": 1.3443,
+      "step": 3450
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.2541654109954834,
+      "learning_rate": 1.9153280696977947e-05,
+      "loss": 1.3312,
+      "step": 3475
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 2.124866008758545,
+      "learning_rate": 1.905118431799619e-05,
+      "loss": 1.3368,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.191096305847168,
+      "learning_rate": 1.894908793901443e-05,
+      "loss": 1.3447,
+      "step": 3525
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.2031023502349854,
+      "learning_rate": 1.8846991560032672e-05,
+      "loss": 1.3101,
+      "step": 3550
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 2.1442978382110596,
+      "learning_rate": 1.8744895181050914e-05,
+      "loss": 1.3408,
+      "step": 3575
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.281747579574585,
+      "learning_rate": 1.8642798802069154e-05,
+      "loss": 1.3028,
+      "step": 3600
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 2.128450870513916,
+      "learning_rate": 1.8540702423087396e-05,
+      "loss": 1.3117,
+      "step": 3625
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.925809383392334,
+      "learning_rate": 1.8438606044105635e-05,
+      "loss": 1.3104,
+      "step": 3650
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 2.0832419395446777,
+      "learning_rate": 1.8336509665123878e-05,
+      "loss": 1.3134,
+      "step": 3675
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.3211681842803955,
+      "learning_rate": 1.823441328614212e-05,
+      "loss": 1.323,
+      "step": 3700
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 2.2126524448394775,
+      "learning_rate": 1.813231690716036e-05,
+      "loss": 1.307,
+      "step": 3725
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 2.2093470096588135,
+      "learning_rate": 1.8030220528178603e-05,
+      "loss": 1.3194,
+      "step": 3750
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.089864730834961,
+      "learning_rate": 1.7928124149196842e-05,
+      "loss": 1.3191,
+      "step": 3775
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.3088159561157227,
+      "learning_rate": 1.7826027770215084e-05,
+      "loss": 1.3545,
+      "step": 3800
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 2.17684006690979,
+      "learning_rate": 1.7723931391233327e-05,
+      "loss": 1.3452,
+      "step": 3825
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 2.3744864463806152,
+      "learning_rate": 1.7621835012251566e-05,
+      "loss": 1.3193,
+      "step": 3850
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 2.2248189449310303,
+      "learning_rate": 1.751973863326981e-05,
+      "loss": 1.3183,
+      "step": 3875
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.2989003658294678,
+      "learning_rate": 1.741764225428805e-05,
+      "loss": 1.3086,
+      "step": 3900
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.115312099456787,
+      "learning_rate": 1.731554587530629e-05,
+      "loss": 1.3372,
+      "step": 3925
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 2.2466862201690674,
+      "learning_rate": 1.721344949632453e-05,
+      "loss": 1.3126,
+      "step": 3950
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 2.152052164077759,
+      "learning_rate": 1.711135311734277e-05,
+      "loss": 1.3127,
+      "step": 3975
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 2.276834487915039,
+      "learning_rate": 1.7009256738361012e-05,
+      "loss": 1.2936,
+      "step": 4000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.3417012691497803,
+      "learning_rate": 1.6907160359379254e-05,
+      "loss": 1.2999,
+      "step": 4025
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 2.0875630378723145,
+      "learning_rate": 1.6805063980397494e-05,
+      "loss": 1.3186,
+      "step": 4050
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.3512613773345947,
+      "learning_rate": 1.6702967601415736e-05,
+      "loss": 1.3242,
+      "step": 4075
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 2.24100399017334,
+      "learning_rate": 1.6600871222433975e-05,
+      "loss": 1.3525,
+      "step": 4100
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.2629716396331787,
+      "learning_rate": 1.6498774843452218e-05,
+      "loss": 1.3386,
+      "step": 4125
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 2.21623158454895,
+      "learning_rate": 1.639667846447046e-05,
+      "loss": 1.3263,
+      "step": 4150
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 2.26880145072937,
+      "learning_rate": 1.62945820854887e-05,
+      "loss": 1.3296,
+      "step": 4175
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.2265172004699707,
+      "learning_rate": 1.6192485706506942e-05,
+      "loss": 1.3424,
+      "step": 4200
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 2.2084670066833496,
+      "learning_rate": 1.6090389327525185e-05,
+      "loss": 1.333,
+      "step": 4225
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.146636486053467,
+      "learning_rate": 1.5988292948543424e-05,
+      "loss": 1.324,
+      "step": 4250
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 2.2078332901000977,
+      "learning_rate": 1.5886196569561667e-05,
+      "loss": 1.3032,
+      "step": 4275
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 2.1620240211486816,
+      "learning_rate": 1.5784100190579906e-05,
+      "loss": 1.3679,
+      "step": 4300
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 2.176711082458496,
+      "learning_rate": 1.568200381159815e-05,
+      "loss": 1.3096,
+      "step": 4325
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.3900365829467773,
+      "learning_rate": 1.557990743261639e-05,
+      "loss": 1.3396,
+      "step": 4350
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 2.100839853286743,
+      "learning_rate": 1.547781105363463e-05,
+      "loss": 1.3264,
+      "step": 4375
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 2.218968629837036,
+      "learning_rate": 1.5375714674652873e-05,
+      "loss": 1.3195,
+      "step": 4400
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 2.4888713359832764,
+      "learning_rate": 1.5273618295671112e-05,
+      "loss": 1.295,
+      "step": 4425
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.2046141624450684,
+      "learning_rate": 1.5171521916689355e-05,
+      "loss": 1.3003,
+      "step": 4450
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.1647400856018066,
+      "learning_rate": 1.5069425537707598e-05,
+      "loss": 1.2842,
+      "step": 4475
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 2.187425136566162,
+      "learning_rate": 1.4967329158725839e-05,
+      "loss": 1.3049,
+      "step": 4500
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 2.2171578407287598,
+      "learning_rate": 1.486523277974408e-05,
+      "loss": 1.2987,
+      "step": 4525
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.1128668785095215,
+      "learning_rate": 1.476313640076232e-05,
+      "loss": 1.2926,
+      "step": 4550
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.1411571502685547,
+      "learning_rate": 1.4661040021780561e-05,
+      "loss": 1.3205,
+      "step": 4575
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 2.165693521499634,
+      "learning_rate": 1.4558943642798804e-05,
+      "loss": 1.3014,
+      "step": 4600
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 2.217212200164795,
+      "learning_rate": 1.4456847263817045e-05,
+      "loss": 1.3198,
+      "step": 4625
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 2.3008174896240234,
+      "learning_rate": 1.4354750884835284e-05,
+      "loss": 1.2913,
+      "step": 4650
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.0766916275024414,
+      "learning_rate": 1.4252654505853525e-05,
+      "loss": 1.2867,
+      "step": 4675
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 2.187500476837158,
+      "learning_rate": 1.4150558126871766e-05,
+      "loss": 1.3605,
+      "step": 4700
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 2.143425226211548,
+      "learning_rate": 1.4048461747890009e-05,
+      "loss": 1.3432,
+      "step": 4725
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.3163678646087646,
+      "learning_rate": 1.394636536890825e-05,
+      "loss": 1.3338,
+      "step": 4750
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.1427390575408936,
+      "learning_rate": 1.384426898992649e-05,
+      "loss": 1.3201,
+      "step": 4775
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.3347136974334717,
+      "learning_rate": 1.3742172610944731e-05,
+      "loss": 1.3103,
+      "step": 4800
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 2.1402597427368164,
+      "learning_rate": 1.3640076231962974e-05,
+      "loss": 1.3339,
+      "step": 4825
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 2.13971209526062,
+      "learning_rate": 1.3537979852981215e-05,
+      "loss": 1.3285,
+      "step": 4850
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 2.146343231201172,
+      "learning_rate": 1.3435883473999456e-05,
+      "loss": 1.3313,
+      "step": 4875
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.221480369567871,
+      "learning_rate": 1.3333787095017697e-05,
+      "loss": 1.3038,
+      "step": 4900
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 2.243988275527954,
+      "learning_rate": 1.323169071603594e-05,
+      "loss": 1.3234,
+      "step": 4925
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 2.0634615421295166,
+      "learning_rate": 1.312959433705418e-05,
+      "loss": 1.2806,
+      "step": 4950
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 2.2551660537719727,
+      "learning_rate": 1.3027497958072421e-05,
+      "loss": 1.3113,
+      "step": 4975
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.1955995559692383,
+      "learning_rate": 1.2925401579090662e-05,
+      "loss": 1.3229,
+      "step": 5000
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 2.1404623985290527,
+      "learning_rate": 1.2823305200108903e-05,
+      "loss": 1.2855,
+      "step": 5025
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 2.2120893001556396,
+      "learning_rate": 1.2721208821127146e-05,
+      "loss": 1.3126,
+      "step": 5050
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 2.3724899291992188,
+      "learning_rate": 1.2619112442145386e-05,
+      "loss": 1.307,
+      "step": 5075
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 2.3382725715637207,
+      "learning_rate": 1.2517016063163627e-05,
+      "loss": 1.3255,
+      "step": 5100
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 2.240473508834839,
+      "learning_rate": 1.2414919684181867e-05,
+      "loss": 1.339,
+      "step": 5125
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 2.2863121032714844,
+      "learning_rate": 1.231282330520011e-05,
+      "loss": 1.3023,
+      "step": 5150
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.3358094692230225,
+      "learning_rate": 1.221072692621835e-05,
+      "loss": 1.293,
+      "step": 5175
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 2.1806859970092773,
+      "learning_rate": 1.2108630547236591e-05,
+      "loss": 1.2709,
+      "step": 5200
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.169222593307495,
+      "learning_rate": 1.2006534168254832e-05,
+      "loss": 1.2991,
+      "step": 5225
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 2.1876134872436523,
+      "learning_rate": 1.1904437789273075e-05,
+      "loss": 1.2875,
+      "step": 5250
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.261347532272339,
+      "learning_rate": 1.1802341410291316e-05,
+      "loss": 1.3095,
+      "step": 5275
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.2739272117614746,
+      "learning_rate": 1.1700245031309556e-05,
+      "loss": 1.3498,
+      "step": 5300
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 2.3991880416870117,
+      "learning_rate": 1.1598148652327797e-05,
+      "loss": 1.3053,
+      "step": 5325
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 2.3285093307495117,
+      "learning_rate": 1.1496052273346038e-05,
+      "loss": 1.3284,
+      "step": 5350
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 2.225856065750122,
+      "learning_rate": 1.1393955894364281e-05,
+      "loss": 1.2987,
+      "step": 5375
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 2.265589952468872,
+      "learning_rate": 1.1291859515382522e-05,
+      "loss": 1.3131,
+      "step": 5400
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 2.41005802154541,
+      "learning_rate": 1.1189763136400763e-05,
+      "loss": 1.3106,
+      "step": 5425
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9434266090393066,
+      "learning_rate": 1.1087666757419004e-05,
+      "loss": 1.2548,
+      "step": 5450
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.1135506629943848,
+      "learning_rate": 1.0985570378437246e-05,
+      "loss": 1.2141,
+      "step": 5475
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 2.289918899536133,
+      "learning_rate": 1.0883473999455487e-05,
+      "loss": 1.2105,
+      "step": 5500
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 2.446237802505493,
+      "learning_rate": 1.0781377620473728e-05,
+      "loss": 1.2309,
+      "step": 5525
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 2.164933681488037,
+      "learning_rate": 1.0679281241491969e-05,
+      "loss": 1.2119,
+      "step": 5550
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 2.468120813369751,
+      "learning_rate": 1.057718486251021e-05,
+      "loss": 1.222,
+      "step": 5575
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.208359479904175,
+      "learning_rate": 1.0475088483528451e-05,
+      "loss": 1.2341,
+      "step": 5600
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 2.425952196121216,
+      "learning_rate": 1.0372992104546692e-05,
+      "loss": 1.2579,
+      "step": 5625
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.4723472595214844,
+      "learning_rate": 1.0270895725564933e-05,
+      "loss": 1.2541,
+      "step": 5650
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.573694944381714,
+      "learning_rate": 1.0168799346583174e-05,
+      "loss": 1.2233,
+      "step": 5675
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.234358072280884,
+      "learning_rate": 1.0066702967601416e-05,
+      "loss": 1.2408,
+      "step": 5700
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 2.3570847511291504,
+      "learning_rate": 9.964606588619657e-06,
+      "loss": 1.2057,
+      "step": 5725
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 2.402945041656494,
+      "learning_rate": 9.862510209637898e-06,
+      "loss": 1.2441,
+      "step": 5750
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 2.3379828929901123,
+      "learning_rate": 9.760413830656139e-06,
+      "loss": 1.2095,
+      "step": 5775
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 2.4580986499786377,
+      "learning_rate": 9.658317451674382e-06,
+      "loss": 1.2138,
+      "step": 5800
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 2.361599922180176,
+      "learning_rate": 9.556221072692623e-06,
+      "loss": 1.2519,
+      "step": 5825
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 2.320232629776001,
+      "learning_rate": 9.454124693710863e-06,
+      "loss": 1.2443,
+      "step": 5850
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.411405086517334,
+      "learning_rate": 9.352028314729104e-06,
+      "loss": 1.2062,
+      "step": 5875
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 2.377734661102295,
+      "learning_rate": 9.254015790906616e-06,
+      "loss": 1.2335,
+      "step": 5900
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.619082450866699,
+      "learning_rate": 9.151919411924856e-06,
+      "loss": 1.2421,
+      "step": 5925
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 2.4038760662078857,
+      "learning_rate": 9.049823032943099e-06,
+      "loss": 1.2226,
+      "step": 5950
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.423957109451294,
+      "learning_rate": 8.94772665396134e-06,
+      "loss": 1.208,
+      "step": 5975
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.4431958198547363,
+      "learning_rate": 8.845630274979581e-06,
+      "loss": 1.2105,
+      "step": 6000
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 2.4713828563690186,
+      "learning_rate": 8.743533895997822e-06,
+      "loss": 1.2297,
+      "step": 6025
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.3229868412017822,
+      "learning_rate": 8.641437517016064e-06,
+      "loss": 1.2162,
+      "step": 6050
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 2.483553886413574,
+      "learning_rate": 8.539341138034305e-06,
+      "loss": 1.25,
+      "step": 6075
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.567758083343506,
+      "learning_rate": 8.437244759052546e-06,
+      "loss": 1.2351,
+      "step": 6100
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.5052988529205322,
+      "learning_rate": 8.335148380070787e-06,
+      "loss": 1.2068,
+      "step": 6125
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 2.3063817024230957,
+      "learning_rate": 8.233052001089028e-06,
+      "loss": 1.2116,
+      "step": 6150
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 2.531585931777954,
+      "learning_rate": 8.13095562210727e-06,
+      "loss": 1.1786,
+      "step": 6175
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.1010377407073975,
+      "learning_rate": 8.028859243125512e-06,
+      "loss": 1.2529,
+      "step": 6200
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.465160369873047,
+      "learning_rate": 7.926762864143753e-06,
+      "loss": 1.221,
+      "step": 6225
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.3965258598327637,
+      "learning_rate": 7.824666485161992e-06,
+      "loss": 1.2492,
+      "step": 6250
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 2.4250175952911377,
+      "learning_rate": 7.722570106180234e-06,
+      "loss": 1.2392,
+      "step": 6275
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.4409801959991455,
+      "learning_rate": 7.620473727198476e-06,
+      "loss": 1.2195,
+      "step": 6300
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.476854085922241,
+      "learning_rate": 7.518377348216717e-06,
+      "loss": 1.2412,
+      "step": 6325
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 2.489551305770874,
+      "learning_rate": 7.416280969234958e-06,
+      "loss": 1.262,
+      "step": 6350
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 2.5215299129486084,
+      "learning_rate": 7.314184590253199e-06,
+      "loss": 1.2228,
+      "step": 6375
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 2.517064332962036,
+      "learning_rate": 7.21208821127144e-06,
+      "loss": 1.2175,
+      "step": 6400
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 2.503761053085327,
+      "learning_rate": 7.109991832289682e-06,
+      "loss": 1.2174,
+      "step": 6425
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 2.4488444328308105,
+      "learning_rate": 7.0078954533079225e-06,
+      "loss": 1.2293,
+      "step": 6450
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.539790391921997,
+      "learning_rate": 6.905799074326164e-06,
+      "loss": 1.2505,
+      "step": 6475
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.5282349586486816,
+      "learning_rate": 6.803702695344405e-06,
+      "loss": 1.2311,
+      "step": 6500
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.55580472946167,
+      "learning_rate": 6.701606316362647e-06,
+      "loss": 1.2493,
+      "step": 6525
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 2.6252071857452393,
+      "learning_rate": 6.599509937380888e-06,
+      "loss": 1.2434,
+      "step": 6550
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.510460138320923,
+      "learning_rate": 6.49741355839913e-06,
+      "loss": 1.2583,
+      "step": 6575
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 2.6028640270233154,
+      "learning_rate": 6.39531717941737e-06,
+      "loss": 1.2593,
+      "step": 6600
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 2.2769548892974854,
+      "learning_rate": 6.2932208004356115e-06,
+      "loss": 1.2259,
+      "step": 6625
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.4939069747924805,
+      "learning_rate": 6.191124421453852e-06,
+      "loss": 1.1955,
+      "step": 6650
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.3038108348846436,
+      "learning_rate": 6.089028042472093e-06,
+      "loss": 1.2067,
+      "step": 6675
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.5069258213043213,
+      "learning_rate": 5.986931663490335e-06,
+      "loss": 1.2033,
+      "step": 6700
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 2.5253121852874756,
+      "learning_rate": 5.884835284508576e-06,
+      "loss": 1.245,
+      "step": 6725
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.492309808731079,
+      "learning_rate": 5.782738905526818e-06,
+      "loss": 1.2218,
+      "step": 6750
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 2.399568796157837,
+      "learning_rate": 5.680642526545059e-06,
+      "loss": 1.2092,
+      "step": 6775
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.5190510749816895,
+      "learning_rate": 5.5785461475633005e-06,
+      "loss": 1.2157,
+      "step": 6800
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 2.393317937850952,
+      "learning_rate": 5.4764497685815405e-06,
+      "loss": 1.2373,
+      "step": 6825
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.5895726680755615,
+      "learning_rate": 5.374353389599782e-06,
+      "loss": 1.2178,
+      "step": 6850
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 2.3802356719970703,
+      "learning_rate": 5.272257010618023e-06,
+      "loss": 1.1854,
+      "step": 6875
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 2.3995566368103027,
+      "learning_rate": 5.170160631636265e-06,
+      "loss": 1.2082,
+      "step": 6900
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 2.3092782497406006,
+      "learning_rate": 5.068064252654506e-06,
+      "loss": 1.2167,
+      "step": 6925
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 2.5264272689819336,
+      "learning_rate": 4.965967873672747e-06,
+      "loss": 1.2114,
+      "step": 6950
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.6355152130126953,
+      "learning_rate": 4.863871494690989e-06,
+      "loss": 1.205,
+      "step": 6975
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.6680080890655518,
+      "learning_rate": 4.7617751157092295e-06,
+      "loss": 1.2288,
+      "step": 7000
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 2.520815134048462,
+      "learning_rate": 4.659678736727471e-06,
+      "loss": 1.2385,
+      "step": 7025
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.6535727977752686,
+      "learning_rate": 4.557582357745712e-06,
+      "loss": 1.2037,
+      "step": 7050
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.6128251552581787,
+      "learning_rate": 4.455485978763953e-06,
+      "loss": 1.2381,
+      "step": 7075
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 2.3994832038879395,
+      "learning_rate": 4.353389599782194e-06,
+      "loss": 1.1994,
+      "step": 7100
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.610602617263794,
+      "learning_rate": 4.251293220800436e-06,
+      "loss": 1.2032,
+      "step": 7125
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 2.55776309967041,
+      "learning_rate": 4.149196841818677e-06,
+      "loss": 1.2614,
+      "step": 7150
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.387730121612549,
+      "learning_rate": 4.0471004628369185e-06,
+      "loss": 1.2142,
+      "step": 7175
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.4818918704986572,
+      "learning_rate": 3.945004083855159e-06,
+      "loss": 1.1894,
+      "step": 7200
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 2.4564781188964844,
+      "learning_rate": 3.842907704873401e-06,
+      "loss": 1.2254,
+      "step": 7225
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 2.775742769241333,
+      "learning_rate": 3.7408113258916417e-06,
+      "loss": 1.2283,
+      "step": 7250
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 2.6153032779693604,
+      "learning_rate": 3.638714946909883e-06,
+      "loss": 1.2595,
+      "step": 7275
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 2.6812705993652344,
+      "learning_rate": 3.5366185679281243e-06,
+      "loss": 1.2156,
+      "step": 7300
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 2.290558338165283,
+      "learning_rate": 3.4345221889463657e-06,
+      "loss": 1.2215,
+      "step": 7325
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.6138980388641357,
+      "learning_rate": 3.332425809964607e-06,
+      "loss": 1.2172,
+      "step": 7350
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 2.496048927307129,
+      "learning_rate": 3.230329430982848e-06,
+      "loss": 1.2826,
+      "step": 7375
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 2.5548458099365234,
+      "learning_rate": 3.128233052001089e-06,
+      "loss": 1.2524,
+      "step": 7400
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 2.4902689456939697,
+      "learning_rate": 3.02613667301933e-06,
+      "loss": 1.2359,
+      "step": 7425
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 2.5479485988616943,
+      "learning_rate": 2.9240402940375716e-06,
+      "loss": 1.2085,
+      "step": 7450
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.4236271381378174,
+      "learning_rate": 2.8219439150558125e-06,
+      "loss": 1.2098,
+      "step": 7475
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 2.533890724182129,
+      "learning_rate": 2.719847536074054e-06,
+      "loss": 1.1894,
+      "step": 7500
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 2.7152767181396484,
+      "learning_rate": 2.617751157092295e-06,
+      "loss": 1.2183,
+      "step": 7525
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 2.515911102294922,
+      "learning_rate": 2.5156547781105365e-06,
+      "loss": 1.2222,
+      "step": 7550
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 2.4286630153656006,
+      "learning_rate": 2.413558399128778e-06,
+      "loss": 1.2213,
+      "step": 7575
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.542311429977417,
+      "learning_rate": 2.3114620201470188e-06,
+      "loss": 1.2121,
+      "step": 7600
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.5168519020080566,
+      "learning_rate": 2.20936564116526e-06,
+      "loss": 1.2178,
+      "step": 7625
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 2.389608383178711,
+      "learning_rate": 2.1072692621835014e-06,
+      "loss": 1.2118,
+      "step": 7650
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 2.4580190181732178,
+      "learning_rate": 2.005172883201743e-06,
+      "loss": 1.2192,
+      "step": 7675
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 2.519462823867798,
+      "learning_rate": 1.9030765042199835e-06,
+      "loss": 1.1993,
+      "step": 7700
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 2.493283748626709,
+      "learning_rate": 1.800980125238225e-06,
+      "loss": 1.2079,
+      "step": 7725
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 2.400961399078369,
+      "learning_rate": 1.6988837462564662e-06,
+      "loss": 1.2182,
+      "step": 7750
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 2.7420430183410645,
+      "learning_rate": 1.5967873672747073e-06,
+      "loss": 1.2169,
+      "step": 7775
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 2.488145351409912,
+      "learning_rate": 1.4946909882929484e-06,
+      "loss": 1.2227,
+      "step": 7800
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.531705856323242,
+      "learning_rate": 1.3925946093111898e-06,
+      "loss": 1.2156,
+      "step": 7825
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.5031278133392334,
+      "learning_rate": 1.2904982303294311e-06,
+      "loss": 1.2055,
+      "step": 7850
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 2.546499729156494,
+      "learning_rate": 1.1884018513476723e-06,
+      "loss": 1.2362,
+      "step": 7875
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 2.5064220428466797,
+      "learning_rate": 1.0863054723659136e-06,
+      "loss": 1.1923,
+      "step": 7900
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 2.7137672901153564,
+      "learning_rate": 9.842090933841545e-07,
+      "loss": 1.2136,
+      "step": 7925
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.4040451049804688,
+      "learning_rate": 8.821127144023959e-07,
+      "loss": 1.1781,
+      "step": 7950
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 2.744879961013794,
+      "learning_rate": 7.800163354206371e-07,
+      "loss": 1.2054,
+      "step": 7975
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 2.4355337619781494,
+      "learning_rate": 6.779199564388783e-07,
+      "loss": 1.221,
+      "step": 8000
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 2.56799054145813,
+      "learning_rate": 5.758235774571195e-07,
+      "loss": 1.1876,
+      "step": 8025
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 2.6261682510375977,
+      "learning_rate": 4.7372719847536076e-07,
+      "loss": 1.1994,
+      "step": 8050
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 2.609344482421875,
+      "learning_rate": 3.7163081949360194e-07,
+      "loss": 1.2013,
+      "step": 8075
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 2.4968795776367188,
+      "learning_rate": 2.695344405118432e-07,
+      "loss": 1.206,
+      "step": 8100
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 2.639547109603882,
+      "learning_rate": 1.674380615300844e-07,
+      "loss": 1.2188,
+      "step": 8125
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 2.6444761753082275,
+      "learning_rate": 6.534168254832563e-08,
+      "loss": 1.2206,
+      "step": 8150
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 8163,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.4349115244339528e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8163/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0098bf4c403c7113d994b6b971eec464999ac2cc8258b74a609b23f91a4762a4
+size 4984

runs/Mar26_16-21-29_r-binarial-tech-ai-9uu5twdo-fb086-rmjvv/events.out.tfevents.1711470113.r-binarial-tech-ai-9uu5twdo-fb086-rmjvv.106.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b1b52c54090cbbede82141bf14749db8830ec95612e5172ecf810ade221dd8
-size 73655
+oid sha256:119a85f2712b0049db20cc71a30518656f925e2e1021be5678f9af87724f27fa
+size 74220

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0098bf4c403c7113d994b6b971eec464999ac2cc8258b74a609b23f91a4762a4
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "mistralai/Mistral-7B-Instruct-v0.2",
+    "project_name": "GALIA",
+    "data_path": "GALIA/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "Rodrigo-Binarial/GALIA",
+    "username": "Rodrigo-Binarial"
+}