Upload folder using huggingface_hub

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

README.md

@@ -0,0 +1,68 @@
+---
+license: other
+base_model: microsoft/Orca-2-13b
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5966
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.645         | 0.23  | 100  | 1.6467          |
+| 1.6459        | 0.45  | 200  | 1.6197          |
+| 1.5916        | 0.68  | 300  | 1.6115          |
+| 1.3587        | 0.9   | 400  | 1.6088          |
+| 1.5232        | 1.12  | 500  | 1.6029          |
+| 1.7568        | 1.34  | 600  | 1.6010          |
+| 1.6536        | 1.57  | 700  | 1.5978          |
+| 1.7821        | 1.8   | 800  | 1.5966          |
+
+
+### Framework versions
+
+- Transformers 4.35.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.7
+- Tokenizers 0.14.1

Untitled.ipynb

@@ -0,0 +1,168 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2416e8ad-7826-4bb6-8164-74b25e985cc3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token will not been saved to git credential helper. Pass `add_to_git_credential=True` if you want to set the git credential as well.\n",
+      "Token is valid (permission: write).\n",
+      "Your token has been saved to /root/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "83545320358d42d281a156c7218a6d7d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.safetensors:   0%|          | 0.00/501M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "721787676a094649b2628451be2d4dbe",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bb346063ffcb4bb79c6fd2de19e9c3e5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "training_args.bin:   0%|          | 0.00/4.54k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9b32558fcff04f8ebe7406dc211e2020",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b8ae21de7cdd4fc0a9b2f2c0d6831d91",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.bin:   0%|          | 0.00/501M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8e88e53f527f4d909bac26964562a544",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Upload 6 LFS files:   0%|          | 0/6 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "69f9a82abb7c4d9fa60d92a7452194c0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "!huggingface-cli login --token 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\n",
+    "from huggingface_hub import HfApi\n",
+    "\n",
+    "api = HfApi()\n",
+    "\n",
+    "# Upload all the content from the local folder to your remote Space.\n",
+    "# By default, files are uploaded at the root of the repo\n",
+    "\n",
+    "api.upload_folder(\n",
+    "\n",
+    "    folder_path=\"/workspace/axolotl/qlora-out\",\n",
+    "\n",
+    "    repo_id=\"nRuaif/Testing_orca\",\n",
+    "\n",
+    "    repo_type=\"model\",\n",
+    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c6a284d-3e1c-46e5-b77d-1ad91f4bbf49",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Orca-2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b989b079724b489fd14c33183c4f2070261ddd08f263cfbde80d0b5d55cd42f7
+size 500897101

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|im_end|>": 32002,
+  "<|im_start|>": 32001,
+  "[PAD]": 32000
+}

checkpoint-400/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: microsoft/Orca-2-13b
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Orca-2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c62787a70f77635cce674888be2fc769ffa4907090f5ced1e428c786d0a084
+size 500770656

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd2b592221a94f23bd082ad23d49447f02ec8cb19c1c8c6163603b8ac24b417
+size 14575

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e63f97842231a81ecd895cbbc697f62a7ab3d723944666deb2a60aec887006e
+size 627

checkpoint-400/trainer_state.json

@@ -0,0 +1,2451 @@
+{
+  "best_metric": 1.6087621450424194,
+  "best_model_checkpoint": "./qlora-out/checkpoint-400",
+  "epoch": 0.9034443817052513,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.6126,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4954,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6e-06,
+      "loss": 2.4127,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.5176,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 2.2497,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4175,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 2.6525,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.1653,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8e-05,
+      "loss": 2.1483,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 2.3218,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 2.2764,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4e-05,
+      "loss": 2.2225,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.1253,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.1824,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 2.5585,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.1777,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 2.3706,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.6e-05,
+      "loss": 1.7773,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.8e-05,
+      "loss": 1.9601,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4e-05,
+      "loss": 1.7374,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.2e-05,
+      "loss": 2.0932,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.6992,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.7488,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8932,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5e-05,
+      "loss": 1.9512,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.8087,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.7846,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.8874,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.8e-05,
+      "loss": 1.919,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6e-05,
+      "loss": 1.7985,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.2e-05,
+      "loss": 1.8528,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.8325,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.6e-05,
+      "loss": 1.596,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.9767,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7e-05,
+      "loss": 1.6124,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7.2e-05,
+      "loss": 1.6764,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7.4e-05,
+      "loss": 1.8457,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.6e-05,
+      "loss": 1.6134,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.9267,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8e-05,
+      "loss": 1.8999,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.2e-05,
+      "loss": 1.6804,
+      "step": 41
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.4e-05,
+      "loss": 1.8109,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.6e-05,
+      "loss": 1.7453,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.9238,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9e-05,
+      "loss": 1.5639,
+      "step": 45
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.7264,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.4e-05,
+      "loss": 1.9841,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.6e-05,
+      "loss": 1.5782,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.8e-05,
+      "loss": 1.8506,
+      "step": 49
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001,
+      "loss": 1.5642,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999964526246879e-05,
+      "loss": 1.7945,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999858105490867e-05,
+      "loss": 1.7237,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999680739242022e-05,
+      "loss": 1.7998,
+      "step": 53
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999432430017084e-05,
+      "loss": 1.5217,
+      "step": 54
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.999113181339437e-05,
+      "loss": 1.8277,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.99872299773906e-05,
+      "loss": 1.8734,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.998261884752462e-05,
+      "loss": 1.5751,
+      "step": 57
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.99772984892261e-05,
+      "loss": 1.773,
+      "step": 58
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.997126897798825e-05,
+      "loss": 1.392,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.996453039936682e-05,
+      "loss": 1.7622,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.995708284897889e-05,
+      "loss": 1.7739,
+      "step": 61
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.994892643250147e-05,
+      "loss": 1.9572,
+      "step": 62
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.994006126567006e-05,
+      "loss": 1.6673,
+      "step": 63
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.993048747427696e-05,
+      "loss": 1.6756,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.992020519416948e-05,
+      "loss": 1.6236,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.990921457124805e-05,
+      "loss": 1.6774,
+      "step": 66
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.989751576146413e-05,
+      "loss": 1.7076,
+      "step": 67
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.988510893081799e-05,
+      "loss": 1.8763,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.98719942553564e-05,
+      "loss": 1.6324,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.985817192117001e-05,
+      "loss": 1.7579,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.984364212439088e-05,
+      "loss": 1.6983,
+      "step": 71
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.982840507118958e-05,
+      "loss": 1.6052,
+      "step": 72
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.981246097777231e-05,
+      "loss": 1.7244,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.979581007037776e-05,
+      "loss": 1.7328,
+      "step": 74
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.977845258527403e-05,
+      "loss": 1.5821,
+      "step": 75
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.976038876875518e-05,
+      "loss": 1.6529,
+      "step": 76
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.974161887713775e-05,
+      "loss": 1.6353,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.972214317675713e-05,
+      "loss": 1.5552,
+      "step": 78
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.970196194396381e-05,
+      "loss": 1.5826,
+      "step": 79
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.968107546511942e-05,
+      "loss": 1.9228,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.965948403659267e-05,
+      "loss": 1.7107,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.963718796475515e-05,
+      "loss": 1.7575,
+      "step": 82
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.961418756597702e-05,
+      "loss": 1.5771,
+      "step": 83
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.959048316662246e-05,
+      "loss": 1.8133,
+      "step": 84
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.956607510304508e-05,
+      "loss": 1.5487,
+      "step": 85
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.95409637215831e-05,
+      "loss": 1.6759,
+      "step": 86
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.951514937855454e-05,
+      "loss": 1.8012,
+      "step": 87
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.948863244025203e-05,
+      "loss": 1.5686,
+      "step": 88
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.94614132829377e-05,
+      "loss": 1.8649,
+      "step": 89
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.943349229283781e-05,
+      "loss": 1.7711,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.94048698661373e-05,
+      "loss": 1.6153,
+      "step": 91
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.937554640897413e-05,
+      "loss": 1.5359,
+      "step": 92
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.934552233743352e-05,
+      "loss": 1.2047,
+      "step": 93
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.931479807754209e-05,
+      "loss": 1.6326,
+      "step": 94
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.928337406526172e-05,
+      "loss": 1.4582,
+      "step": 95
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.925125074648352e-05,
+      "loss": 1.5503,
+      "step": 96
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.921842857702132e-05,
+      "loss": 1.9591,
+      "step": 97
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.918490802260538e-05,
+      "loss": 1.6741,
+      "step": 98
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.915068955887563e-05,
+      "loss": 1.5237,
+      "step": 99
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.911577367137499e-05,
+      "loss": 1.645,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.6467467546463013,
+      "eval_runtime": 380.1313,
+      "eval_samples_per_second": 1.436,
+      "eval_steps_per_second": 0.718,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.90801608555425e-05,
+      "loss": 1.8182,
+      "step": 101
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.904385161670625e-05,
+      "loss": 1.3908,
+      "step": 102
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.900684647007624e-05,
+      "loss": 1.39,
+      "step": 103
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.896914594073703e-05,
+      "loss": 1.643,
+      "step": 104
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.893075056364034e-05,
+      "loss": 1.6435,
+      "step": 105
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.889166088359741e-05,
+      "loss": 1.6227,
+      "step": 106
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.885187745527133e-05,
+      "loss": 1.5884,
+      "step": 107
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.881140084316907e-05,
+      "loss": 1.5687,
+      "step": 108
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.87702316216336e-05,
+      "loss": 1.7089,
+      "step": 109
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.87283703748356e-05,
+      "loss": 1.6631,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.868581769676533e-05,
+      "loss": 1.6771,
+      "step": 111
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.864257419122405e-05,
+      "loss": 1.5418,
+      "step": 112
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.859864047181552e-05,
+      "loss": 1.2749,
+      "step": 113
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.855401716193732e-05,
+      "loss": 1.5715,
+      "step": 114
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.850870489477197e-05,
+      "loss": 1.6176,
+      "step": 115
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.846270431327793e-05,
+      "loss": 1.8423,
+      "step": 116
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.841601607018052e-05,
+      "loss": 1.5878,
+      "step": 117
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.83686408279626e-05,
+      "loss": 1.661,
+      "step": 118
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.832057925885525e-05,
+      "loss": 1.6109,
+      "step": 119
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.827183204482817e-05,
+      "loss": 1.7273,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.822239987757998e-05,
+      "loss": 1.8402,
+      "step": 121
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.817228345852851e-05,
+      "loss": 1.4303,
+      "step": 122
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.812148349880076e-05,
+      "loss": 1.2896,
+      "step": 123
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.807000071922279e-05,
+      "loss": 1.6951,
+      "step": 124
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.801783585030959e-05,
+      "loss": 1.7379,
+      "step": 125
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.79649896322546e-05,
+      "loss": 1.5715,
+      "step": 126
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.791146281491934e-05,
+      "loss": 1.9257,
+      "step": 127
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.785725615782262e-05,
+      "loss": 1.7964,
+      "step": 128
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.780237043012987e-05,
+      "loss": 1.5906,
+      "step": 129
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.774680641064222e-05,
+      "loss": 1.7997,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.769056488778537e-05,
+      "loss": 1.6863,
+      "step": 131
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.763364665959849e-05,
+      "loss": 1.3936,
+      "step": 132
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.757605253372283e-05,
+      "loss": 1.6815,
+      "step": 133
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.751778332739033e-05,
+      "loss": 1.6042,
+      "step": 134
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.745883986741196e-05,
+      "loss": 1.4678,
+      "step": 135
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.739922299016601e-05,
+      "loss": 1.5455,
+      "step": 136
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.733893354158627e-05,
+      "loss": 1.8297,
+      "step": 137
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.72779723771499e-05,
+      "loss": 1.7075,
+      "step": 138
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.721634036186544e-05,
+      "loss": 1.7954,
+      "step": 139
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.715403837026046e-05,
+      "loss": 1.572,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.709106728636911e-05,
+      "loss": 1.8047,
+      "step": 141
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.702742800371971e-05,
+      "loss": 1.5607,
+      "step": 142
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.696312142532192e-05,
+      "loss": 1.6854,
+      "step": 143
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.689814846365399e-05,
+      "loss": 1.7957,
+      "step": 144
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.683251004064988e-05,
+      "loss": 1.6497,
+      "step": 145
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.676620708768607e-05,
+      "loss": 1.5492,
+      "step": 146
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.669924054556836e-05,
+      "loss": 1.5161,
+      "step": 147
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.663161136451861e-05,
+      "loss": 1.7488,
+      "step": 148
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.656332050416116e-05,
+      "loss": 1.6544,
+      "step": 149
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.649436893350929e-05,
+      "loss": 1.5541,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.642475763095134e-05,
+      "loss": 1.4365,
+      "step": 151
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.635448758423702e-05,
+      "loss": 1.5063,
+      "step": 152
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.628355979046324e-05,
+      "loss": 1.8647,
+      "step": 153
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.621197525606e-05,
+      "loss": 1.6168,
+      "step": 154
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.613973499677614e-05,
+      "loss": 1.6571,
+      "step": 155
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.606684003766493e-05,
+      "loss": 1.4834,
+      "step": 156
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.599329141306946e-05,
+      "loss": 1.3979,
+      "step": 157
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.591909016660807e-05,
+      "loss": 1.6255,
+      "step": 158
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.584423735115938e-05,
+      "loss": 1.4855,
+      "step": 159
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.576873402884756e-05,
+      "loss": 1.7269,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.569258127102707e-05,
+      "loss": 1.7885,
+      "step": 161
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.561578015826758e-05,
+      "loss": 1.6543,
+      "step": 162
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.553833178033855e-05,
+      "loss": 1.6093,
+      "step": 163
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.546023723619386e-05,
+      "loss": 1.5658,
+      "step": 164
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.538149763395612e-05,
+      "loss": 1.5708,
+      "step": 165
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.530211409090104e-05,
+      "loss": 1.6403,
+      "step": 166
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.522208773344147e-05,
+      "loss": 1.2768,
+      "step": 167
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.514141969711154e-05,
+      "loss": 1.4333,
+      "step": 168
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.506011112655044e-05,
+      "loss": 1.5742,
+      "step": 169
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.497816317548625e-05,
+      "loss": 1.4319,
+      "step": 170
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.489557700671948e-05,
+      "loss": 1.7918,
+      "step": 171
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.481235379210671e-05,
+      "loss": 1.7546,
+      "step": 172
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.472849471254386e-05,
+      "loss": 1.6831,
+      "step": 173
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.46440009579494e-05,
+      "loss": 1.5752,
+      "step": 174
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.455887372724761e-05,
+      "loss": 1.5413,
+      "step": 175
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.447311422835142e-05,
+      "loss": 1.6797,
+      "step": 176
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.438672367814532e-05,
+      "loss": 1.7095,
+      "step": 177
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.429970330246817e-05,
+      "loss": 1.4101,
+      "step": 178
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.421205433609568e-05,
+      "loss": 1.7538,
+      "step": 179
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.412377802272297e-05,
+      "loss": 1.7469,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.403487561494691e-05,
+      "loss": 1.6779,
+      "step": 181
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.39453483742483e-05,
+      "loss": 1.5635,
+      "step": 182
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.385519757097405e-05,
+      "loss": 1.6769,
+      "step": 183
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.37644244843191e-05,
+      "loss": 1.7653,
+      "step": 184
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.367303040230828e-05,
+      "loss": 1.6367,
+      "step": 185
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.358101662177803e-05,
+      "loss": 1.8703,
+      "step": 186
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.348838444835798e-05,
+      "loss": 1.6888,
+      "step": 187
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.339513519645249e-05,
+      "loss": 1.7564,
+      "step": 188
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.6898,
+      "step": 189
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.320679075856395e-05,
+      "loss": 1.6917,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.311169824509454e-05,
+      "loss": 1.6607,
+      "step": 191
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.301599399812904e-05,
+      "loss": 1.6159,
+      "step": 192
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.291967937566297e-05,
+      "loss": 1.4132,
+      "step": 193
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.282275574435281e-05,
+      "loss": 1.6247,
+      "step": 194
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.272522447949652e-05,
+      "loss": 1.7138,
+      "step": 195
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.262708696501412e-05,
+      "loss": 1.6365,
+      "step": 196
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.2528344593428e-05,
+      "loss": 1.5955,
+      "step": 197
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.242899876584317e-05,
+      "loss": 1.7734,
+      "step": 198
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.232905089192734e-05,
+      "loss": 1.7847,
+      "step": 199
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.222850238989103e-05,
+      "loss": 1.6459,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 1.619735598564148,
+      "eval_runtime": 380.3616,
+      "eval_samples_per_second": 1.435,
+      "eval_steps_per_second": 0.718,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.21273546864673e-05,
+      "loss": 1.7114,
+      "step": 201
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.202560921689166e-05,
+      "loss": 1.591,
+      "step": 202
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.192326742488152e-05,
+      "loss": 1.6804,
+      "step": 203
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.182033076261592e-05,
+      "loss": 1.7938,
+      "step": 204
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.171680069071471e-05,
+      "loss": 1.4387,
+      "step": 205
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.161267867821802e-05,
+      "loss": 1.5711,
+      "step": 206
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.150796620256525e-05,
+      "loss": 1.5225,
+      "step": 207
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.140266474957421e-05,
+      "loss": 1.7374,
+      "step": 208
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.129677581342e-05,
+      "loss": 1.325,
+      "step": 209
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.11903008966138e-05,
+      "loss": 1.6654,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.10832415099816e-05,
+      "loss": 1.7373,
+      "step": 211
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.097559917264267e-05,
+      "loss": 1.7258,
+      "step": 212
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.086737541198811e-05,
+      "loss": 1.6344,
+      "step": 213
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.075857176365911e-05,
+      "loss": 1.5559,
+      "step": 214
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.064918977152516e-05,
+      "loss": 1.7747,
+      "step": 215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.053923098766217e-05,
+      "loss": 1.8065,
+      "step": 216
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.042869697233046e-05,
+      "loss": 1.821,
+      "step": 217
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.031758929395258e-05,
+      "loss": 1.718,
+      "step": 218
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.020590952909105e-05,
+      "loss": 1.6306,
+      "step": 219
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.009365926242603e-05,
+      "loss": 1.8161,
+      "step": 220
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.998084008673285e-05,
+      "loss": 1.2547,
+      "step": 221
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.986745360285932e-05,
+      "loss": 1.5912,
+      "step": 222
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.975350141970311e-05,
+      "loss": 1.5138,
+      "step": 223
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.963898515418884e-05,
+      "loss": 1.72,
+      "step": 224
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.952390643124524e-05,
+      "loss": 1.6342,
+      "step": 225
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.940826688378197e-05,
+      "loss": 1.6454,
+      "step": 226
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.929206815266652e-05,
+      "loss": 1.8337,
+      "step": 227
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.917531188670095e-05,
+      "loss": 1.5335,
+      "step": 228
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.905799974259845e-05,
+      "loss": 1.77,
+      "step": 229
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.894013338495981e-05,
+      "loss": 1.6785,
+      "step": 230
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.882171448624988e-05,
+      "loss": 1.6688,
+      "step": 231
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.870274472677376e-05,
+      "loss": 1.5964,
+      "step": 232
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.8583225794653e-05,
+      "loss": 1.7153,
+      "step": 233
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.846315938580163e-05,
+      "loss": 1.8064,
+      "step": 234
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.834254720390213e-05,
+      "loss": 1.6305,
+      "step": 235
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.82213909603812e-05,
+      "loss": 1.5684,
+      "step": 236
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.809969237438548e-05,
+      "loss": 1.7526,
+      "step": 237
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.797745317275726e-05,
+      "loss": 1.5233,
+      "step": 238
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.78546750900098e-05,
+      "loss": 1.2263,
+      "step": 239
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.773135986830287e-05,
+      "loss": 1.5587,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.760750925741799e-05,
+      "loss": 1.7591,
+      "step": 241
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.74831250147335e-05,
+      "loss": 1.708,
+      "step": 242
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.73582089051998e-05,
+      "loss": 1.5663,
+      "step": 243
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.723276270131422e-05,
+      "loss": 1.2198,
+      "step": 244
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.710678818309576e-05,
+      "loss": 1.5559,
+      "step": 245
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.698028713806004e-05,
+      "loss": 1.5615,
+      "step": 246
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.68532613611938e-05,
+      "loss": 1.8736,
+      "step": 247
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.672571265492943e-05,
+      "loss": 1.802,
+      "step": 248
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.659764282911948e-05,
+      "loss": 1.8928,
+      "step": 249
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.646905370101091e-05,
+      "loss": 1.7009,
+      "step": 250
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.63399470952193e-05,
+      "loss": 1.4649,
+      "step": 251
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.621032484370299e-05,
+      "loss": 1.5459,
+      "step": 252
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.608018878573709e-05,
+      "loss": 1.7053,
+      "step": 253
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.594954076788736e-05,
+      "loss": 1.6225,
+      "step": 254
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.581838264398401e-05,
+      "loss": 1.6186,
+      "step": 255
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.56867162750954e-05,
+      "loss": 1.5048,
+      "step": 256
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.555454352950161e-05,
+      "loss": 1.6085,
+      "step": 257
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.542186628266802e-05,
+      "loss": 1.6226,
+      "step": 258
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.528868641721857e-05,
+      "loss": 1.8184,
+      "step": 259
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.515500582290914e-05,
+      "loss": 1.4474,
+      "step": 260
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.502082639660067e-05,
+      "loss": 1.8168,
+      "step": 261
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.488615004223233e-05,
+      "loss": 1.5756,
+      "step": 262
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.475097867079436e-05,
+      "loss": 1.6404,
+      "step": 263
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.461531420030117e-05,
+      "loss": 1.6272,
+      "step": 264
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.44791585557639e-05,
+      "loss": 1.6069,
+      "step": 265
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.434251366916322e-05,
+      "loss": 1.7389,
+      "step": 266
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.420538147942197e-05,
+      "loss": 1.4526,
+      "step": 267
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.406776393237747e-05,
+      "loss": 1.395,
+      "step": 268
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.392966298075413e-05,
+      "loss": 1.5559,
+      "step": 269
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.379108058413553e-05,
+      "loss": 1.5938,
+      "step": 270
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.365201870893679e-05,
+      "loss": 1.5633,
+      "step": 271
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.351247932837655e-05,
+      "loss": 1.6534,
+      "step": 272
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.337246442244901e-05,
+      "loss": 1.5687,
+      "step": 273
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.323197597789589e-05,
+      "loss": 1.5531,
+      "step": 274
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.309101598817813e-05,
+      "loss": 1.4546,
+      "step": 275
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.294958645344766e-05,
+      "loss": 1.5684,
+      "step": 276
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.280768938051908e-05,
+      "loss": 1.7263,
+      "step": 277
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.266532678284103e-05,
+      "loss": 1.7123,
+      "step": 278
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.252250068046782e-05,
+      "loss": 1.5563,
+      "step": 279
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.237921310003059e-05,
+      "loss": 1.5035,
+      "step": 280
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.223546607470863e-05,
+      "loss": 1.5747,
+      "step": 281
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.209126164420055e-05,
+      "loss": 1.6334,
+      "step": 282
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.194660185469529e-05,
+      "loss": 1.5158,
+      "step": 283
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.18014887588431e-05,
+      "loss": 1.4902,
+      "step": 284
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.165592441572647e-05,
+      "loss": 1.7115,
+      "step": 285
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.15099108908308e-05,
+      "loss": 1.7038,
+      "step": 286
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.13634502560152e-05,
+      "loss": 1.5703,
+      "step": 287
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.1216544589483e-05,
+      "loss": 1.61,
+      "step": 288
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.106919597575238e-05,
+      "loss": 1.7725,
+      "step": 289
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.092140650562665e-05,
+      "loss": 1.6933,
+      "step": 290
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.07731782761647e-05,
+      "loss": 1.4752,
+      "step": 291
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.062451339065115e-05,
+      "loss": 1.3992,
+      "step": 292
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.047541395856661e-05,
+      "loss": 1.5156,
+      "step": 293
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.032588209555765e-05,
+      "loss": 1.6108,
+      "step": 294
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.01759199234068e-05,
+      "loss": 1.633,
+      "step": 295
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.002552957000254e-05,
+      "loss": 1.6842,
+      "step": 296
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.987471316930893e-05,
+      "loss": 1.5822,
+      "step": 297
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.972347286133548e-05,
+      "loss": 1.5932,
+      "step": 298
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.957181079210675e-05,
+      "loss": 1.7149,
+      "step": 299
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.941972911363186e-05,
+      "loss": 1.5916,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.6114922761917114,
+      "eval_runtime": 379.6975,
+      "eval_samples_per_second": 1.438,
+      "eval_steps_per_second": 0.719,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.926722998387397e-05,
+      "loss": 1.5477,
+      "step": 301
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.911431556671968e-05,
+      "loss": 1.4926,
+      "step": 302
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.896098803194828e-05,
+      "loss": 1.7314,
+      "step": 303
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.880724955520104e-05,
+      "loss": 1.7405,
+      "step": 304
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.865310231795026e-05,
+      "loss": 1.7367,
+      "step": 305
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.849854850746833e-05,
+      "loss": 1.7337,
+      "step": 306
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.834359031679679e-05,
+      "loss": 1.7436,
+      "step": 307
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.818822994471505e-05,
+      "loss": 1.8298,
+      "step": 308
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.803246959570928e-05,
+      "loss": 1.8664,
+      "step": 309
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.78763114799412e-05,
+      "loss": 1.7184,
+      "step": 310
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.771975781321655e-05,
+      "loss": 1.2468,
+      "step": 311
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.75628108169538e-05,
+      "loss": 1.6385,
+      "step": 312
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.740547271815253e-05,
+      "loss": 1.4619,
+      "step": 313
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.724774574936188e-05,
+      "loss": 1.5747,
+      "step": 314
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.70896321486489e-05,
+      "loss": 1.5747,
+      "step": 315
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.693113415956674e-05,
+      "loss": 1.6532,
+      "step": 316
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.677225403112276e-05,
+      "loss": 1.7604,
+      "step": 317
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.661299401774678e-05,
+      "loss": 1.7972,
+      "step": 318
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.645335637925896e-05,
+      "loss": 1.3371,
+      "step": 319
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.629334338083773e-05,
+      "loss": 1.7056,
+      "step": 320
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.61329572929878e-05,
+      "loss": 1.7155,
+      "step": 321
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.597220039150768e-05,
+      "loss": 1.6125,
+      "step": 322
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.581107495745769e-05,
+      "loss": 1.5879,
+      "step": 323
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.564958327712734e-05,
+      "loss": 1.639,
+      "step": 324
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.548772764200307e-05,
+      "loss": 1.7122,
+      "step": 325
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.532551034873559e-05,
+      "loss": 1.7528,
+      "step": 326
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.516293369910737e-05,
+      "loss": 1.5804,
+      "step": 327
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.7145,
+      "step": 328
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.483671156336141e-05,
+      "loss": 1.5839,
+      "step": 329
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.467307070617309e-05,
+      "loss": 1.8584,
+      "step": 330
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.450907975041715e-05,
+      "loss": 1.4994,
+      "step": 331
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.43447410230435e-05,
+      "loss": 1.3246,
+      "step": 332
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.418005685593669e-05,
+      "loss": 1.6393,
+      "step": 333
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.401502958588293e-05,
+      "loss": 1.5387,
+      "step": 334
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.384966155453685e-05,
+      "loss": 1.3346,
+      "step": 335
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.368395510838838e-05,
+      "loss": 1.318,
+      "step": 336
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.351791259872929e-05,
+      "loss": 1.7234,
+      "step": 337
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.335153638162005e-05,
+      "loss": 1.5846,
+      "step": 338
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.318482881785613e-05,
+      "loss": 1.4967,
+      "step": 339
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.301779227293475e-05,
+      "loss": 1.6795,
+      "step": 340
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.285042911702115e-05,
+      "loss": 1.466,
+      "step": 341
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.268274172491508e-05,
+      "loss": 1.9118,
+      "step": 342
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.251473247601698e-05,
+      "loss": 1.5324,
+      "step": 343
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.234640375429427e-05,
+      "loss": 1.637,
+      "step": 344
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.217775794824759e-05,
+      "loss": 1.6558,
+      "step": 345
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.200879745087681e-05,
+      "loss": 1.6324,
+      "step": 346
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.183952465964711e-05,
+      "loss": 1.7496,
+      "step": 347
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.166994197645496e-05,
+      "loss": 1.7385,
+      "step": 348
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.15000518075941e-05,
+      "loss": 1.6461,
+      "step": 349
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.132985656372126e-05,
+      "loss": 1.7131,
+      "step": 350
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.115935865982206e-05,
+      "loss": 1.6787,
+      "step": 351
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.098856051517673e-05,
+      "loss": 1.6028,
+      "step": 352
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.081746455332576e-05,
+      "loss": 1.4347,
+      "step": 353
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.064607320203551e-05,
+      "loss": 1.5735,
+      "step": 354
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.047438889326376e-05,
+      "loss": 1.2504,
+      "step": 355
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.030241406312528e-05,
+      "loss": 1.9139,
+      "step": 356
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.013015115185706e-05,
+      "loss": 1.5579,
+      "step": 357
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.995760260378395e-05,
+      "loss": 1.6616,
+      "step": 358
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.978477086728374e-05,
+      "loss": 1.7095,
+      "step": 359
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.961165839475263e-05,
+      "loss": 1.8251,
+      "step": 360
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.943826764257021e-05,
+      "loss": 1.5992,
+      "step": 361
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.926460107106482e-05,
+      "loss": 1.712,
+      "step": 362
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.909066114447847e-05,
+      "loss": 1.6707,
+      "step": 363
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.891645033093196e-05,
+      "loss": 1.4995,
+      "step": 364
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.874197110238985e-05,
+      "loss": 1.666,
+      "step": 365
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.856722593462537e-05,
+      "loss": 1.5461,
+      "step": 366
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.839221730718533e-05,
+      "loss": 1.5381,
+      "step": 367
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.821694770335481e-05,
+      "loss": 1.7022,
+      "step": 368
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.804141961012213e-05,
+      "loss": 1.5809,
+      "step": 369
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.786563551814333e-05,
+      "loss": 1.8404,
+      "step": 370
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.768959792170706e-05,
+      "loss": 1.8898,
+      "step": 371
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.751330931869897e-05,
+      "loss": 1.5612,
+      "step": 372
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.733677221056644e-05,
+      "loss": 1.5037,
+      "step": 373
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.715998910228296e-05,
+      "loss": 1.5153,
+      "step": 374
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.69829625023127e-05,
+      "loss": 1.6037,
+      "step": 375
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.68056949225748e-05,
+      "loss": 1.2321,
+      "step": 376
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.66281888784078e-05,
+      "loss": 1.6523,
+      "step": 377
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 6.645044688853395e-05,
+      "loss": 1.443,
+      "step": 378
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.627247147502343e-05,
+      "loss": 1.775,
+      "step": 379
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.60942651632586e-05,
+      "loss": 1.5969,
+      "step": 380
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.591583048189812e-05,
+      "loss": 1.5039,
+      "step": 381
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.573716996284113e-05,
+      "loss": 1.6205,
+      "step": 382
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.555828614119132e-05,
+      "loss": 1.4704,
+      "step": 383
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.537918155522087e-05,
+      "loss": 1.5824,
+      "step": 384
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.519985874633454e-05,
+      "loss": 1.5881,
+      "step": 385
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.502032025903355e-05,
+      "loss": 1.5599,
+      "step": 386
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.484056864087947e-05,
+      "loss": 1.6519,
+      "step": 387
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.466060644245815e-05,
+      "loss": 1.6166,
+      "step": 388
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.448043621734337e-05,
+      "loss": 1.6451,
+      "step": 389
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.430006052206082e-05,
+      "loss": 1.7321,
+      "step": 390
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.411948191605163e-05,
+      "loss": 1.6647,
+      "step": 391
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.393870296163615e-05,
+      "loss": 1.2297,
+      "step": 392
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.375772622397761e-05,
+      "loss": 1.6895,
+      "step": 393
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.357655427104562e-05,
+      "loss": 1.5156,
+      "step": 394
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.339518967357985e-05,
+      "loss": 1.4977,
+      "step": 395
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.321363500505347e-05,
+      "loss": 1.5753,
+      "step": 396
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.303189284163668e-05,
+      "loss": 1.6325,
+      "step": 397
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.284996576216014e-05,
+      "loss": 1.6534,
+      "step": 398
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.266785634807837e-05,
+      "loss": 1.6973,
+      "step": 399
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.248556718343314e-05,
+      "loss": 1.3587,
+      "step": 400
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 1.6087621450424194,
+      "eval_runtime": 379.6023,
+      "eval_samples_per_second": 1.438,
+      "eval_steps_per_second": 0.719,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 884,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.020569592004608e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56fbe111de73ce9d78c5e0425f7afd4ffcc72eb08a33eb2194e62b1a0c9af3f
+size 4539

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "microsoft/Orca-2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 32002,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}