Upload folder using huggingface_hub

phi-sft-out/README.md

@@ -0,0 +1,156 @@
+---
+base_model: microsoft/phi-1_5
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/phi-sft-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)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: microsoft/phi-1_5
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: ptoro/honkers-phi
+    type: alpaca
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/phi-sft-out
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: qlora
+lora_model_dir:
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_torch
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+lr_scheduler: cosine
+learning_rate: 0.000003
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: True
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+resize_token_embeddings_to_32x: true
+special_tokens:
+  pad_token: "<|endoftext|>"
+
+```
+
+</details><br>
+
+# outputs/phi-sft-out
+
+This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5482
+
+## 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: 3e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2333        | 0.0106 | 1    | 1.5896          |
+| 1.7286        | 0.2553 | 24   | 1.5891          |
+| 1.2823        | 0.5106 | 48   | 1.5875          |
+| 1.3856        | 0.7660 | 72   | 1.5844          |
+| 1.244         | 1.0213 | 96   | 1.5804          |
+| 1.2499        | 1.2447 | 120  | 1.5753          |
+| 1.1656        | 1.5    | 144  | 1.5706          |
+| 1.1928        | 1.7553 | 168  | 1.5656          |
+| 1.1623        | 2.0106 | 192  | 1.5608          |
+| 1.2679        | 2.2340 | 216  | 1.5571          |
+| 1.2845        | 2.4894 | 240  | 1.5537          |
+| 1.1226        | 2.7447 | 264  | 1.5516          |
+| 1.2575        | 3.0    | 288  | 1.5497          |
+| 1.2465        | 3.2234 | 312  | 1.5486          |
+| 1.1699        | 3.4787 | 336  | 1.5483          |
+| 1.2021        | 3.7340 | 360  | 1.5482          |
+
+
+### Framework versions
+
+- PEFT 0.11.2.dev0
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

phi-sft-out/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "dense",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi-sft-out/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80368d659341cb7b3f65869a330e5c6e6b75044f4e5d77ebe3db3f76ca690793
+size 226596042

phi-sft-out/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

phi-sft-out/checkpoint-188/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-1_5
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

phi-sft-out/checkpoint-188/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "dense",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi-sft-out/checkpoint-188/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b5b892feeb14c6625382251e26758b57036baa24f73e771fa848be3c7825ca
+size 226530600

phi-sft-out/checkpoint-188/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

phi-sft-out/checkpoint-188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25804b9697d1ed444578fee052dac516cf011d9291f2277fd863b351366b002a
+size 453227642

phi-sft-out/checkpoint-188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5f3aa316bb7d0ffb35ed58a795009860ed39f571b413f9a91ac45e187d4e37
+size 14244

phi-sft-out/checkpoint-188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9b4e2304d4c84e1e8eaed6a1c791737dfbbd60f197668e8b439f2c5e51d0e3
+size 1064

phi-sft-out/checkpoint-188/special_tokens_map.json

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

phi-sft-out/checkpoint-188/tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

phi-sft-out/checkpoint-188/trainer_state.json

@@ -0,0 +1,1413 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9680851063829787,
+  "eval_steps": 24,
+  "global_step": 188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010638297872340425,
+      "grad_norm": 0.10508890450000763,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 1.2333,
+      "step": 1
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "eval_loss": 1.5895557403564453,
+      "eval_runtime": 2.9603,
+      "eval_samples_per_second": 35.469,
+      "eval_steps_per_second": 17.903,
+      "step": 1
+    },
+    {
+      "epoch": 0.02127659574468085,
+      "grad_norm": 0.12071573734283447,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 1.3986,
+      "step": 2
+    },
+    {
+      "epoch": 0.031914893617021274,
+      "grad_norm": 0.10401547700166702,
+      "learning_rate": 9e-08,
+      "loss": 1.2058,
+      "step": 3
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.12298297882080078,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.3298,
+      "step": 4
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 0.1327030211687088,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 1.4031,
+      "step": 5
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 0.12036772817373276,
+      "learning_rate": 1.8e-07,
+      "loss": 1.5335,
+      "step": 6
+    },
+    {
+      "epoch": 0.07446808510638298,
+      "grad_norm": 0.14979703724384308,
+      "learning_rate": 2.1000000000000003e-07,
+      "loss": 1.3224,
+      "step": 7
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.13082227110862732,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.4035,
+      "step": 8
+    },
+    {
+      "epoch": 0.09574468085106383,
+      "grad_norm": 0.09265327453613281,
+      "learning_rate": 2.7e-07,
+      "loss": 1.1546,
+      "step": 9
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 0.10080434381961823,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.2652,
+      "step": 10
+    },
+    {
+      "epoch": 0.11702127659574468,
+      "grad_norm": 0.10915568470954895,
+      "learning_rate": 3.3e-07,
+      "loss": 1.1438,
+      "step": 11
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.1307348906993866,
+      "learning_rate": 3.6e-07,
+      "loss": 1.2821,
+      "step": 12
+    },
+    {
+      "epoch": 0.13829787234042554,
+      "grad_norm": 0.09814529865980148,
+      "learning_rate": 3.9e-07,
+      "loss": 1.3905,
+      "step": 13
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 0.11842218786478043,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 1.3085,
+      "step": 14
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 0.10207124054431915,
+      "learning_rate": 4.5e-07,
+      "loss": 1.19,
+      "step": 15
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.1150127425789833,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.386,
+      "step": 16
+    },
+    {
+      "epoch": 0.18085106382978725,
+      "grad_norm": 0.11641352623701096,
+      "learning_rate": 5.100000000000001e-07,
+      "loss": 1.4357,
+      "step": 17
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 0.15035435557365417,
+      "learning_rate": 5.4e-07,
+      "loss": 1.2549,
+      "step": 18
+    },
+    {
+      "epoch": 0.20212765957446807,
+      "grad_norm": 0.0984087809920311,
+      "learning_rate": 5.7e-07,
+      "loss": 0.9723,
+      "step": 19
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.11582670360803604,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.1402,
+      "step": 20
+    },
+    {
+      "epoch": 0.22340425531914893,
+      "grad_norm": 0.10151291638612747,
+      "learning_rate": 6.3e-07,
+      "loss": 1.1533,
+      "step": 21
+    },
+    {
+      "epoch": 0.23404255319148937,
+      "grad_norm": 0.09040653705596924,
+      "learning_rate": 6.6e-07,
+      "loss": 1.0438,
+      "step": 22
+    },
+    {
+      "epoch": 0.24468085106382978,
+      "grad_norm": 0.10666865110397339,
+      "learning_rate": 6.900000000000001e-07,
+      "loss": 1.3195,
+      "step": 23
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.12293969094753265,
+      "learning_rate": 7.2e-07,
+      "loss": 1.7286,
+      "step": 24
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "eval_loss": 1.5890721082687378,
+      "eval_runtime": 2.9908,
+      "eval_samples_per_second": 35.108,
+      "eval_steps_per_second": 17.721,
+      "step": 24
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 0.11052387952804565,
+      "learning_rate": 7.5e-07,
+      "loss": 1.1413,
+      "step": 25
+    },
+    {
+      "epoch": 0.2765957446808511,
+      "grad_norm": 0.09323304146528244,
+      "learning_rate": 7.8e-07,
+      "loss": 1.2906,
+      "step": 26
+    },
+    {
+      "epoch": 0.2872340425531915,
+      "grad_norm": 0.12542971968650818,
+      "learning_rate": 8.100000000000001e-07,
+      "loss": 1.2809,
+      "step": 27
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.1080215722322464,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.2735,
+      "step": 28
+    },
+    {
+      "epoch": 0.30851063829787234,
+      "grad_norm": 0.11304887384176254,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": 1.3767,
+      "step": 29
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 0.15650290250778198,
+      "learning_rate": 9e-07,
+      "loss": 1.4713,
+      "step": 30
+    },
+    {
+      "epoch": 0.32978723404255317,
+      "grad_norm": 0.12139321118593216,
+      "learning_rate": 9.3e-07,
+      "loss": 1.3479,
+      "step": 31
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.10141867399215698,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.1512,
+      "step": 32
+    },
+    {
+      "epoch": 0.35106382978723405,
+      "grad_norm": 0.15045498311519623,
+      "learning_rate": 9.9e-07,
+      "loss": 1.5059,
+      "step": 33
+    },
+    {
+      "epoch": 0.3617021276595745,
+      "grad_norm": 0.12956956028938293,
+      "learning_rate": 1.0200000000000002e-06,
+      "loss": 1.2849,
+      "step": 34
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 0.12963886559009552,
+      "learning_rate": 1.05e-06,
+      "loss": 1.5025,
+      "step": 35
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.11268144845962524,
+      "learning_rate": 1.08e-06,
+      "loss": 1.2987,
+      "step": 36
+    },
+    {
+      "epoch": 0.39361702127659576,
+      "grad_norm": 0.12941108644008636,
+      "learning_rate": 1.11e-06,
+      "loss": 1.3432,
+      "step": 37
+    },
+    {
+      "epoch": 0.40425531914893614,
+      "grad_norm": 0.11319927126169205,
+      "learning_rate": 1.14e-06,
+      "loss": 1.1665,
+      "step": 38
+    },
+    {
+      "epoch": 0.4148936170212766,
+      "grad_norm": 0.11748912930488586,
+      "learning_rate": 1.17e-06,
+      "loss": 1.423,
+      "step": 39
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.11666171997785568,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4391,
+      "step": 40
+    },
+    {
+      "epoch": 0.43617021276595747,
+      "grad_norm": 0.12274409830570221,
+      "learning_rate": 1.2299999999999999e-06,
+      "loss": 1.4865,
+      "step": 41
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 0.09922561049461365,
+      "learning_rate": 1.26e-06,
+      "loss": 1.2193,
+      "step": 42
+    },
+    {
+      "epoch": 0.4574468085106383,
+      "grad_norm": 0.12003930658102036,
+      "learning_rate": 1.29e-06,
+      "loss": 1.3024,
+      "step": 43
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.12094161659479141,
+      "learning_rate": 1.32e-06,
+      "loss": 1.4654,
+      "step": 44
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 0.12934774160385132,
+      "learning_rate": 1.35e-06,
+      "loss": 1.3713,
+      "step": 45
+    },
+    {
+      "epoch": 0.48936170212765956,
+      "grad_norm": 0.09754550457000732,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 1.1991,
+      "step": 46
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.11549004167318344,
+      "learning_rate": 1.41e-06,
+      "loss": 1.4859,
+      "step": 47
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.12035688012838364,
+      "learning_rate": 1.44e-06,
+      "loss": 1.2823,
+      "step": 48
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "eval_loss": 1.5874611139297485,
+      "eval_runtime": 2.9787,
+      "eval_samples_per_second": 35.251,
+      "eval_steps_per_second": 17.793,
+      "step": 48
+    },
+    {
+      "epoch": 0.5212765957446809,
+      "grad_norm": 0.12258938699960709,
+      "learning_rate": 1.4700000000000001e-06,
+      "loss": 1.2966,
+      "step": 49
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.12217017263174057,
+      "learning_rate": 1.5e-06,
+      "loss": 1.2988,
+      "step": 50
+    },
+    {
+      "epoch": 0.5425531914893617,
+      "grad_norm": 0.12793436646461487,
+      "learning_rate": 1.53e-06,
+      "loss": 1.4233,
+      "step": 51
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.11145548522472382,
+      "learning_rate": 1.56e-06,
+      "loss": 1.2792,
+      "step": 52
+    },
+    {
+      "epoch": 0.5638297872340425,
+      "grad_norm": 0.13195408880710602,
+      "learning_rate": 1.59e-06,
+      "loss": 1.4481,
+      "step": 53
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 0.10663347691297531,
+      "learning_rate": 1.6200000000000002e-06,
+      "loss": 1.2331,
+      "step": 54
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 0.10975392907857895,
+      "learning_rate": 1.65e-06,
+      "loss": 1.1839,
+      "step": 55
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.13139477372169495,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 1.436,
+      "step": 56
+    },
+    {
+      "epoch": 0.6063829787234043,
+      "grad_norm": 0.0924743041396141,
+      "learning_rate": 1.71e-06,
+      "loss": 1.1291,
+      "step": 57
+    },
+    {
+      "epoch": 0.6170212765957447,
+      "grad_norm": 0.12475109100341797,
+      "learning_rate": 1.7399999999999999e-06,
+      "loss": 1.3444,
+      "step": 58
+    },
+    {
+      "epoch": 0.6276595744680851,
+      "grad_norm": 0.08960220962762833,
+      "learning_rate": 1.77e-06,
+      "loss": 1.2511,
+      "step": 59
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.09909304976463318,
+      "learning_rate": 1.8e-06,
+      "loss": 1.1281,
+      "step": 60
+    },
+    {
+      "epoch": 0.648936170212766,
+      "grad_norm": 0.11598234623670578,
+      "learning_rate": 1.83e-06,
+      "loss": 1.486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6595744680851063,
+      "grad_norm": 0.1404409557580948,
+      "learning_rate": 1.86e-06,
+      "loss": 1.4557,
+      "step": 62
+    },
+    {
+      "epoch": 0.6702127659574468,
+      "grad_norm": 0.11349129676818848,
+      "learning_rate": 1.8900000000000001e-06,
+      "loss": 1.3969,
+      "step": 63
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.10858353972434998,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.3515,
+      "step": 64
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 0.11054569482803345,
+      "learning_rate": 1.95e-06,
+      "loss": 1.248,
+      "step": 65
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 0.11826737225055695,
+      "learning_rate": 1.98e-06,
+      "loss": 1.3439,
+      "step": 66
+    },
+    {
+      "epoch": 0.7127659574468085,
+      "grad_norm": 0.12291310727596283,
+      "learning_rate": 2.0100000000000002e-06,
+      "loss": 1.4226,
+      "step": 67
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.1383126825094223,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 1.194,
+      "step": 68
+    },
+    {
+      "epoch": 0.7340425531914894,
+      "grad_norm": 0.10981890559196472,
+      "learning_rate": 2.07e-06,
+      "loss": 1.2502,
+      "step": 69
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.10639657825231552,
+      "learning_rate": 2.1e-06,
+      "loss": 1.2262,
+      "step": 70
+    },
+    {
+      "epoch": 0.7553191489361702,
+      "grad_norm": 0.46177396178245544,
+      "learning_rate": 2.13e-06,
+      "loss": 5.063,
+      "step": 71
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.11061427742242813,
+      "learning_rate": 2.16e-06,
+      "loss": 1.3856,
+      "step": 72
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "eval_loss": 1.5843762159347534,
+      "eval_runtime": 2.9943,
+      "eval_samples_per_second": 35.066,
+      "eval_steps_per_second": 17.7,
+      "step": 72
+    },
+    {
+      "epoch": 0.776595744680851,
+      "grad_norm": 0.13233324885368347,
+      "learning_rate": 2.19e-06,
+      "loss": 1.526,
+      "step": 73
+    },
+    {
+      "epoch": 0.7872340425531915,
+      "grad_norm": 0.14500053226947784,
+      "learning_rate": 2.22e-06,
+      "loss": 1.2554,
+      "step": 74
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 0.10629269480705261,
+      "learning_rate": 2.25e-06,
+      "loss": 1.2917,
+      "step": 75
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.09674028307199478,
+      "learning_rate": 2.28e-06,
+      "loss": 1.2169,
+      "step": 76
+    },
+    {
+      "epoch": 0.8191489361702128,
+      "grad_norm": 0.11965947598218918,
+      "learning_rate": 2.31e-06,
+      "loss": 1.2445,
+      "step": 77
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 0.10441229492425919,
+      "learning_rate": 2.34e-06,
+      "loss": 1.2392,
+      "step": 78
+    },
+    {
+      "epoch": 0.8404255319148937,
+      "grad_norm": 0.13795869052410126,
+      "learning_rate": 2.37e-06,
+      "loss": 1.5335,
+      "step": 79
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.10789927840232849,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.2309,
+      "step": 80
+    },
+    {
+      "epoch": 0.8617021276595744,
+      "grad_norm": 0.10697130113840103,
+      "learning_rate": 2.43e-06,
+      "loss": 1.276,
+      "step": 81
+    },
+    {
+      "epoch": 0.8723404255319149,
+      "grad_norm": 0.11484125256538391,
+      "learning_rate": 2.4599999999999997e-06,
+      "loss": 1.2163,
+      "step": 82
+    },
+    {
+      "epoch": 0.8829787234042553,
+      "grad_norm": 0.09692610800266266,
+      "learning_rate": 2.49e-06,
+      "loss": 1.1554,
+      "step": 83
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.10697747021913528,
+      "learning_rate": 2.52e-06,
+      "loss": 1.211,
+      "step": 84
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 0.10578318685293198,
+      "learning_rate": 2.55e-06,
+      "loss": 1.2634,
+      "step": 85
+    },
+    {
+      "epoch": 0.9148936170212766,
+      "grad_norm": 0.10587752610445023,
+      "learning_rate": 2.58e-06,
+      "loss": 1.369,
+      "step": 86
+    },
+    {
+      "epoch": 0.925531914893617,
+      "grad_norm": 0.11430489271879196,
+      "learning_rate": 2.61e-06,
+      "loss": 1.3048,
+      "step": 87
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.11116154491901398,
+      "learning_rate": 2.64e-06,
+      "loss": 1.1883,
+      "step": 88
+    },
+    {
+      "epoch": 0.9468085106382979,
+      "grad_norm": 0.12686476111412048,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 1.2605,
+      "step": 89
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.10976041853427887,
+      "learning_rate": 2.7e-06,
+      "loss": 1.2345,
+      "step": 90
+    },
+    {
+      "epoch": 0.9680851063829787,
+      "grad_norm": 0.12391550838947296,
+      "learning_rate": 2.73e-06,
+      "loss": 1.2233,
+      "step": 91
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.1277073174715042,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 1.2437,
+      "step": 92
+    },
+    {
+      "epoch": 0.9893617021276596,
+      "grad_norm": 0.10421616584062576,
+      "learning_rate": 2.7900000000000004e-06,
+      "loss": 1.1432,
+      "step": 93
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12696842849254608,
+      "learning_rate": 2.82e-06,
+      "loss": 1.3558,
+      "step": 94
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.10387945920228958,
+      "learning_rate": 2.85e-06,
+      "loss": 1.1902,
+      "step": 95
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.14543002843856812,
+      "learning_rate": 2.88e-06,
+      "loss": 1.244,
+      "step": 96
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "eval_loss": 1.5803985595703125,
+      "eval_runtime": 3.0087,
+      "eval_samples_per_second": 34.899,
+      "eval_steps_per_second": 17.616,
+      "step": 96
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.17504040896892548,
+      "learning_rate": 2.91e-06,
+      "loss": 1.3115,
+      "step": 97
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.14017756283283234,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 1.356,
+      "step": 98
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.11604318767786026,
+      "learning_rate": 2.97e-06,
+      "loss": 1.2806,
+      "step": 99
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.15116065740585327,
+      "learning_rate": 3e-06,
+      "loss": 1.3279,
+      "step": 100
+    },
+    {
+      "epoch": 1.0425531914893618,
+      "grad_norm": 0.10773392021656036,
+      "learning_rate": 2.9999028286680832e-06,
+      "loss": 1.3871,
+      "step": 101
+    },
+    {
+      "epoch": 1.053191489361702,
+      "grad_norm": 0.09363637119531631,
+      "learning_rate": 2.999611327262024e-06,
+      "loss": 1.1334,
+      "step": 102
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.09164439886808395,
+      "learning_rate": 2.999125533549261e-06,
+      "loss": 1.4026,
+      "step": 103
+    },
+    {
+      "epoch": 1.074468085106383,
+      "grad_norm": 0.12113964557647705,
+      "learning_rate": 2.9984455104700915e-06,
+      "loss": 1.2097,
+      "step": 104
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.10569895058870316,
+      "learning_rate": 2.9975713461295125e-06,
+      "loss": 1.3077,
+      "step": 105
+    },
+    {
+      "epoch": 1.0957446808510638,
+      "grad_norm": 0.11219862103462219,
+      "learning_rate": 2.996503153785809e-06,
+      "loss": 1.1923,
+      "step": 106
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.13474853336811066,
+      "learning_rate": 2.9952410718358777e-06,
+      "loss": 1.2729,
+      "step": 107
+    },
+    {
+      "epoch": 1.1170212765957448,
+      "grad_norm": 0.10451857000589371,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.2904,
+      "step": 108
+    },
+    {
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.12593719363212585,
+      "learning_rate": 2.9921359182871422e-06,
+      "loss": 1.4021,
+      "step": 109
+    },
+    {
+      "epoch": 1.1382978723404256,
+      "grad_norm": 0.12547315657138824,
+      "learning_rate": 2.990293248997547e-06,
+      "loss": 1.2093,
+      "step": 110
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.10086555033922195,
+      "learning_rate": 2.988257494668016e-06,
+      "loss": 1.3098,
+      "step": 111
+    },
+    {
+      "epoch": 1.1595744680851063,
+      "grad_norm": 0.10801573097705841,
+      "learning_rate": 2.9860289190544963e-06,
+      "loss": 1.2752,
+      "step": 112
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.11851054430007935,
+      "learning_rate": 2.9836078108952015e-06,
+      "loss": 1.3066,
+      "step": 113
+    },
+    {
+      "epoch": 1.1808510638297873,
+      "grad_norm": 0.1265188604593277,
+      "learning_rate": 2.9809944838732045e-06,
+      "loss": 1.1946,
+      "step": 114
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.10702725499868393,
+      "learning_rate": 2.9781892765757954e-06,
+      "loss": 1.2182,
+      "step": 115
+    },
+    {
+      "epoch": 1.202127659574468,
+      "grad_norm": 0.7757766842842102,
+      "learning_rate": 2.9751925524506135e-06,
+      "loss": 5.6082,
+      "step": 116
+    },
+    {
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.10182739049196243,
+      "learning_rate": 2.9720046997585577e-06,
+      "loss": 1.309,
+      "step": 117
+    },
+    {
+      "epoch": 1.2234042553191489,
+      "grad_norm": 0.14062073826789856,
+      "learning_rate": 2.9686261315234844e-06,
+      "loss": 1.3668,
+      "step": 118
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.1063840240240097,
+      "learning_rate": 2.965057285478694e-06,
+      "loss": 1.2247,
+      "step": 119
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "grad_norm": 0.10701325535774231,
+      "learning_rate": 2.961298624010219e-06,
+      "loss": 1.2499,
+      "step": 120
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "eval_loss": 1.575344204902649,
+      "eval_runtime": 8.2617,
+      "eval_samples_per_second": 12.709,
+      "eval_steps_per_second": 6.415,
+      "step": 120
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.11413375288248062,
+      "learning_rate": 2.957350634096912e-06,
+      "loss": 1.3593,
+      "step": 121
+    },
+    {
+      "epoch": 1.2659574468085106,
+      "grad_norm": 0.10826950520277023,
+      "learning_rate": 2.9532138272473597e-06,
+      "loss": 1.232,
+      "step": 122
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.10749218612909317,
+      "learning_rate": 2.9488887394336023e-06,
+      "loss": 1.401,
+      "step": 123
+    },
+    {
+      "epoch": 1.2872340425531914,
+      "grad_norm": 0.1175396591424942,
+      "learning_rate": 2.944375931021699e-06,
+      "loss": 1.2867,
+      "step": 124
+    },
+    {
+      "epoch": 1.297872340425532,
+      "grad_norm": 0.10688498616218567,
+      "learning_rate": 2.9396759866991214e-06,
+      "loss": 1.3689,
+      "step": 125
+    },
+    {
+      "epoch": 1.3085106382978724,
+      "grad_norm": 0.11630786955356598,
+      "learning_rate": 2.934789515399002e-06,
+      "loss": 1.2328,
+      "step": 126
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.11495409905910492,
+      "learning_rate": 2.9297171502212414e-06,
+      "loss": 1.1738,
+      "step": 127
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.10823408514261246,
+      "learning_rate": 2.924459548350479e-06,
+      "loss": 1.2318,
+      "step": 128
+    },
+    {
+      "epoch": 1.3404255319148937,
+      "grad_norm": 0.10759969800710678,
+      "learning_rate": 2.9190173909709506e-06,
+      "loss": 1.319,
+      "step": 129
+    },
+    {
+      "epoch": 1.351063829787234,
+      "grad_norm": 0.12790299952030182,
+      "learning_rate": 2.9133913831782307e-06,
+      "loss": 1.4282,
+      "step": 130
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.10899878293275833,
+      "learning_rate": 2.9075822538878805e-06,
+      "loss": 1.2455,
+      "step": 131
+    },
+    {
+      "epoch": 1.372340425531915,
+      "grad_norm": 0.12732432782649994,
+      "learning_rate": 2.9015907557410068e-06,
+      "loss": 1.2227,
+      "step": 132
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.10140018165111542,
+      "learning_rate": 2.8954176650067494e-06,
+      "loss": 1.0596,
+      "step": 133
+    },
+    {
+      "epoch": 1.3936170212765957,
+      "grad_norm": 0.12063546478748322,
+      "learning_rate": 2.889063781481708e-06,
+      "loss": 1.3321,
+      "step": 134
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.11323118209838867,
+      "learning_rate": 2.8825299283863144e-06,
+      "loss": 1.3366,
+      "step": 135
+    },
+    {
+      "epoch": 1.4148936170212765,
+      "grad_norm": 0.12391477078199387,
+      "learning_rate": 2.8758169522581796e-06,
+      "loss": 1.2917,
+      "step": 136
+    },
+    {
+      "epoch": 1.425531914893617,
+      "grad_norm": 0.12329094856977463,
+      "learning_rate": 2.8689257228424125e-06,
+      "loss": 1.1365,
+      "step": 137
+    },
+    {
+      "epoch": 1.4361702127659575,
+      "grad_norm": 0.11298198997974396,
+      "learning_rate": 2.8618571329789333e-06,
+      "loss": 1.4996,
+      "step": 138
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.10263165086507797,
+      "learning_rate": 2.8546120984867994e-06,
+      "loss": 1.199,
+      "step": 139
+    },
+    {
+      "epoch": 1.4574468085106382,
+      "grad_norm": 0.13330323994159698,
+      "learning_rate": 2.8471915580455442e-06,
+      "loss": 1.3746,
+      "step": 140
+    },
+    {
+      "epoch": 1.4680851063829787,
+      "grad_norm": 0.10694881528615952,
+      "learning_rate": 2.8395964730735666e-06,
+      "loss": 1.3798,
+      "step": 141
+    },
+    {
+      "epoch": 1.4787234042553192,
+      "grad_norm": 0.10929003357887268,
+      "learning_rate": 2.8318278276035626e-06,
+      "loss": 1.2918,
+      "step": 142
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.10969982296228409,
+      "learning_rate": 2.8238866281550366e-06,
+      "loss": 1.0444,
+      "step": 143
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10668367147445679,
+      "learning_rate": 2.815773903603892e-06,
+      "loss": 1.1656,
+      "step": 144
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5705612897872925,
+      "eval_runtime": 5.6853,
+      "eval_samples_per_second": 18.469,
+      "eval_steps_per_second": 9.322,
+      "step": 144
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.12057002633810043,
+      "learning_rate": 2.807490705049127e-06,
+      "loss": 1.2475,
+      "step": 145
+    },
+    {
+      "epoch": 1.521276595744681,
+      "grad_norm": 0.10394139587879181,
+      "learning_rate": 2.7990381056766585e-06,
+      "loss": 1.3376,
+      "step": 146
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.12907464802265167,
+      "learning_rate": 2.7904172006202705e-06,
+      "loss": 1.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.5425531914893615,
+      "grad_norm": 0.1252606213092804,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.1744,
+      "step": 148
+    },
+    {
+      "epoch": 1.5531914893617023,
+      "grad_norm": 0.1514441967010498,
+      "learning_rate": 2.772674962876085e-06,
+      "loss": 1.9324,
+      "step": 149
+    },
+    {
+      "epoch": 1.5638297872340425,
+      "grad_norm": 0.12377320230007172,
+      "learning_rate": 2.7635559289041174e-06,
+      "loss": 1.4511,
+      "step": 150
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.10629550367593765,
+      "learning_rate": 2.7542731863820665e-06,
+      "loss": 1.257,
+      "step": 151
+    },
+    {
+      "epoch": 1.5851063829787235,
+      "grad_norm": 0.10322704166173935,
+      "learning_rate": 2.744827937998538e-06,
+      "loss": 1.1796,
+      "step": 152
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.12690168619155884,
+      "learning_rate": 2.735221407496686e-06,
+      "loss": 1.3325,
+      "step": 153
+    },
+    {
+      "epoch": 1.6063829787234043,
+      "grad_norm": 0.0982392430305481,
+      "learning_rate": 2.725454839515663e-06,
+      "loss": 1.2169,
+      "step": 154
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.11184275150299072,
+      "learning_rate": 2.7155294994293606e-06,
+      "loss": 1.295,
+      "step": 155
+    },
+    {
+      "epoch": 1.627659574468085,
+      "grad_norm": 0.10721098631620407,
+      "learning_rate": 2.7054466731824676e-06,
+      "loss": 1.1945,
+      "step": 156
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.1254221498966217,
+      "learning_rate": 2.695207667123857e-06,
+      "loss": 1.2693,
+      "step": 157
+    },
+    {
+      "epoch": 1.648936170212766,
+      "grad_norm": 0.1157686784863472,
+      "learning_rate": 2.684813807837338e-06,
+      "loss": 1.1992,
+      "step": 158
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.10201229155063629,
+      "learning_rate": 2.674266441969778e-06,
+      "loss": 1.2401,
+      "step": 159
+    },
+    {
+      "epoch": 1.6702127659574468,
+      "grad_norm": 0.10953360050916672,
+      "learning_rate": 2.6635669360566298e-06,
+      "loss": 1.1627,
+      "step": 160
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.1248813271522522,
+      "learning_rate": 2.652716676344881e-06,
+      "loss": 1.3179,
+      "step": 161
+    },
+    {
+      "epoch": 1.6914893617021276,
+      "grad_norm": 0.09584470838308334,
+      "learning_rate": 2.6417170686134472e-06,
+      "loss": 1.2128,
+      "step": 162
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.12864486873149872,
+      "learning_rate": 2.630569537991042e-06,
+      "loss": 1.1889,
+      "step": 163
+    },
+    {
+      "epoch": 1.7127659574468086,
+      "grad_norm": 0.11820186674594879,
+      "learning_rate": 2.6192755287715282e-06,
+      "loss": 1.2848,
+      "step": 164
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.13811764121055603,
+      "learning_rate": 2.6078365042267987e-06,
+      "loss": 1.2091,
+      "step": 165
+    },
+    {
+      "epoch": 1.7340425531914894,
+      "grad_norm": 0.12099539488554001,
+      "learning_rate": 2.5962539464171862e-06,
+      "loss": 1.2853,
+      "step": 166
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.14544783532619476,
+      "learning_rate": 2.5845293559994513e-06,
+      "loss": 1.1574,
+      "step": 167
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "grad_norm": 0.11159494519233704,
+      "learning_rate": 2.5726642520323493e-06,
+      "loss": 1.1928,
+      "step": 168
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "eval_loss": 1.5656005144119263,
+      "eval_runtime": 3.0568,
+      "eval_samples_per_second": 34.349,
+      "eval_steps_per_second": 17.338,
+      "step": 168
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.1385321319103241,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 1.365,
+      "step": 169
+    },
+    {
+      "epoch": 1.7765957446808511,
+      "grad_norm": 0.12905962765216827,
+      "learning_rate": 2.548518670511823e-06,
+      "loss": 1.3664,
+      "step": 170
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.09589093923568726,
+      "learning_rate": 2.536241321302821e-06,
+      "loss": 1.1508,
+      "step": 171
+    },
+    {
+      "epoch": 1.797872340425532,
+      "grad_norm": 0.12533985078334808,
+      "learning_rate": 2.5238297148279814e-06,
+      "loss": 1.2892,
+      "step": 172
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.11337278038263321,
+      "learning_rate": 2.5112854591570804e-06,
+      "loss": 1.2772,
+      "step": 173
+    },
+    {
+      "epoch": 1.8191489361702127,
+      "grad_norm": 0.1345362514257431,
+      "learning_rate": 2.4986101795461608e-06,
+      "loss": 1.3583,
+      "step": 174
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.121876560151577,
+      "learning_rate": 2.485805518226959e-06,
+      "loss": 1.2065,
+      "step": 175
+    },
+    {
+      "epoch": 1.8404255319148937,
+      "grad_norm": 0.10669907927513123,
+      "learning_rate": 2.4728731341941343e-06,
+      "loss": 1.2339,
+      "step": 176
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.12710174918174744,
+      "learning_rate": 2.4598147029903284e-06,
+      "loss": 1.4597,
+      "step": 177
+    },
+    {
+      "epoch": 1.8617021276595744,
+      "grad_norm": 0.11735282093286514,
+      "learning_rate": 2.4466319164890795e-06,
+      "loss": 1.2273,
+      "step": 178
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.12083889544010162,
+      "learning_rate": 2.4333264826756165e-06,
+      "loss": 1.3051,
+      "step": 179
+    },
+    {
+      "epoch": 1.8829787234042552,
+      "grad_norm": 0.10338792204856873,
+      "learning_rate": 2.4199001254255746e-06,
+      "loss": 1.3827,
+      "step": 180
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.10191334784030914,
+      "learning_rate": 2.406354584281642e-06,
+      "loss": 1.4067,
+      "step": 181
+    },
+    {
+      "epoch": 1.9042553191489362,
+      "grad_norm": 0.10776273161172867,
+      "learning_rate": 2.3926916142281846e-06,
+      "loss": 1.2344,
+      "step": 182
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.1253603845834732,
+      "learning_rate": 2.378912985463867e-06,
+      "loss": 1.2179,
+      "step": 183
+    },
+    {
+      "epoch": 1.925531914893617,
+      "grad_norm": 0.09942696243524551,
+      "learning_rate": 2.365020483172301e-06,
+      "loss": 1.0613,
+      "step": 184
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.10441701859235764,
+      "learning_rate": 2.351015907290755e-06,
+      "loss": 1.3886,
+      "step": 185
+    },
+    {
+      "epoch": 1.9468085106382977,
+      "grad_norm": 0.10571073740720749,
+      "learning_rate": 2.3369010722769502e-06,
+      "loss": 1.2023,
+      "step": 186
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.12477201223373413,
+      "learning_rate": 2.3226778068739783e-06,
+      "loss": 1.361,
+      "step": 187
+    },
+    {
+      "epoch": 1.9680851063829787,
+      "grad_norm": 0.12106247246265411,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.4153,
+      "step": 188
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 94,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6313126920192000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

phi-sft-out/checkpoint-188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
+size 6008

phi-sft-out/checkpoint-282/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-1_5
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

phi-sft-out/checkpoint-282/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "dense",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi-sft-out/checkpoint-282/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6bc85608733ba656dcea73ca548f991c037a142239296b421394fab397d592
+size 226530600

phi-sft-out/checkpoint-282/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

phi-sft-out/checkpoint-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc21951633413b444a59ca17c326286efe99637ab2c737f13d5ffe911881396
+size 453227642

phi-sft-out/checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca1cc74a3745d191ce868b3a77914352d382ffa7fe0b75ac3c0939bae1eb286
+size 14244

phi-sft-out/checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3c8b7c4f8c0543a50c7d31d5ea1723a28e5a41b54bf3786034855407ca470e
+size 1064

phi-sft-out/checkpoint-282/special_tokens_map.json

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

phi-sft-out/checkpoint-282/tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

phi-sft-out/checkpoint-282/trainer_state.json

@@ -0,0 +1,2103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9361702127659575,
+  "eval_steps": 24,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010638297872340425,
+      "grad_norm": 0.10508890450000763,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 1.2333,
+      "step": 1
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "eval_loss": 1.5895557403564453,
+      "eval_runtime": 2.9603,
+      "eval_samples_per_second": 35.469,
+      "eval_steps_per_second": 17.903,
+      "step": 1
+    },
+    {
+      "epoch": 0.02127659574468085,
+      "grad_norm": 0.12071573734283447,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 1.3986,
+      "step": 2
+    },
+    {
+      "epoch": 0.031914893617021274,
+      "grad_norm": 0.10401547700166702,
+      "learning_rate": 9e-08,
+      "loss": 1.2058,
+      "step": 3
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.12298297882080078,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.3298,
+      "step": 4
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 0.1327030211687088,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 1.4031,
+      "step": 5
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 0.12036772817373276,
+      "learning_rate": 1.8e-07,
+      "loss": 1.5335,
+      "step": 6
+    },
+    {
+      "epoch": 0.07446808510638298,
+      "grad_norm": 0.14979703724384308,
+      "learning_rate": 2.1000000000000003e-07,
+      "loss": 1.3224,
+      "step": 7
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.13082227110862732,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.4035,
+      "step": 8
+    },
+    {
+      "epoch": 0.09574468085106383,
+      "grad_norm": 0.09265327453613281,
+      "learning_rate": 2.7e-07,
+      "loss": 1.1546,
+      "step": 9
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 0.10080434381961823,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.2652,
+      "step": 10
+    },
+    {
+      "epoch": 0.11702127659574468,
+      "grad_norm": 0.10915568470954895,
+      "learning_rate": 3.3e-07,
+      "loss": 1.1438,
+      "step": 11
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.1307348906993866,
+      "learning_rate": 3.6e-07,
+      "loss": 1.2821,
+      "step": 12
+    },
+    {
+      "epoch": 0.13829787234042554,
+      "grad_norm": 0.09814529865980148,
+      "learning_rate": 3.9e-07,
+      "loss": 1.3905,
+      "step": 13
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 0.11842218786478043,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 1.3085,
+      "step": 14
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 0.10207124054431915,
+      "learning_rate": 4.5e-07,
+      "loss": 1.19,
+      "step": 15
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.1150127425789833,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.386,
+      "step": 16
+    },
+    {
+      "epoch": 0.18085106382978725,
+      "grad_norm": 0.11641352623701096,
+      "learning_rate": 5.100000000000001e-07,
+      "loss": 1.4357,
+      "step": 17
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 0.15035435557365417,
+      "learning_rate": 5.4e-07,
+      "loss": 1.2549,
+      "step": 18
+    },
+    {
+      "epoch": 0.20212765957446807,
+      "grad_norm": 0.0984087809920311,
+      "learning_rate": 5.7e-07,
+      "loss": 0.9723,
+      "step": 19
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.11582670360803604,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.1402,
+      "step": 20
+    },
+    {
+      "epoch": 0.22340425531914893,
+      "grad_norm": 0.10151291638612747,
+      "learning_rate": 6.3e-07,
+      "loss": 1.1533,
+      "step": 21
+    },
+    {
+      "epoch": 0.23404255319148937,
+      "grad_norm": 0.09040653705596924,
+      "learning_rate": 6.6e-07,
+      "loss": 1.0438,
+      "step": 22
+    },
+    {
+      "epoch": 0.24468085106382978,
+      "grad_norm": 0.10666865110397339,
+      "learning_rate": 6.900000000000001e-07,
+      "loss": 1.3195,
+      "step": 23
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.12293969094753265,
+      "learning_rate": 7.2e-07,
+      "loss": 1.7286,
+      "step": 24
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "eval_loss": 1.5890721082687378,
+      "eval_runtime": 2.9908,
+      "eval_samples_per_second": 35.108,
+      "eval_steps_per_second": 17.721,
+      "step": 24
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 0.11052387952804565,
+      "learning_rate": 7.5e-07,
+      "loss": 1.1413,
+      "step": 25
+    },
+    {
+      "epoch": 0.2765957446808511,
+      "grad_norm": 0.09323304146528244,
+      "learning_rate": 7.8e-07,
+      "loss": 1.2906,
+      "step": 26
+    },
+    {
+      "epoch": 0.2872340425531915,
+      "grad_norm": 0.12542971968650818,
+      "learning_rate": 8.100000000000001e-07,
+      "loss": 1.2809,
+      "step": 27
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.1080215722322464,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.2735,
+      "step": 28
+    },
+    {
+      "epoch": 0.30851063829787234,
+      "grad_norm": 0.11304887384176254,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": 1.3767,
+      "step": 29
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 0.15650290250778198,
+      "learning_rate": 9e-07,
+      "loss": 1.4713,
+      "step": 30
+    },
+    {
+      "epoch": 0.32978723404255317,
+      "grad_norm": 0.12139321118593216,
+      "learning_rate": 9.3e-07,
+      "loss": 1.3479,
+      "step": 31
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.10141867399215698,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.1512,
+      "step": 32
+    },
+    {
+      "epoch": 0.35106382978723405,
+      "grad_norm": 0.15045498311519623,
+      "learning_rate": 9.9e-07,
+      "loss": 1.5059,
+      "step": 33
+    },
+    {
+      "epoch": 0.3617021276595745,
+      "grad_norm": 0.12956956028938293,
+      "learning_rate": 1.0200000000000002e-06,
+      "loss": 1.2849,
+      "step": 34
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 0.12963886559009552,
+      "learning_rate": 1.05e-06,
+      "loss": 1.5025,
+      "step": 35
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.11268144845962524,
+      "learning_rate": 1.08e-06,
+      "loss": 1.2987,
+      "step": 36
+    },
+    {
+      "epoch": 0.39361702127659576,
+      "grad_norm": 0.12941108644008636,
+      "learning_rate": 1.11e-06,
+      "loss": 1.3432,
+      "step": 37
+    },
+    {
+      "epoch": 0.40425531914893614,
+      "grad_norm": 0.11319927126169205,
+      "learning_rate": 1.14e-06,
+      "loss": 1.1665,
+      "step": 38
+    },
+    {
+      "epoch": 0.4148936170212766,
+      "grad_norm": 0.11748912930488586,
+      "learning_rate": 1.17e-06,
+      "loss": 1.423,
+      "step": 39
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.11666171997785568,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4391,
+      "step": 40
+    },
+    {
+      "epoch": 0.43617021276595747,
+      "grad_norm": 0.12274409830570221,
+      "learning_rate": 1.2299999999999999e-06,
+      "loss": 1.4865,
+      "step": 41
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 0.09922561049461365,
+      "learning_rate": 1.26e-06,
+      "loss": 1.2193,
+      "step": 42
+    },
+    {
+      "epoch": 0.4574468085106383,
+      "grad_norm": 0.12003930658102036,
+      "learning_rate": 1.29e-06,
+      "loss": 1.3024,
+      "step": 43
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.12094161659479141,
+      "learning_rate": 1.32e-06,
+      "loss": 1.4654,
+      "step": 44
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 0.12934774160385132,
+      "learning_rate": 1.35e-06,
+      "loss": 1.3713,
+      "step": 45
+    },
+    {
+      "epoch": 0.48936170212765956,
+      "grad_norm": 0.09754550457000732,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 1.1991,
+      "step": 46
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.11549004167318344,
+      "learning_rate": 1.41e-06,
+      "loss": 1.4859,
+      "step": 47
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.12035688012838364,
+      "learning_rate": 1.44e-06,
+      "loss": 1.2823,
+      "step": 48
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "eval_loss": 1.5874611139297485,
+      "eval_runtime": 2.9787,
+      "eval_samples_per_second": 35.251,
+      "eval_steps_per_second": 17.793,
+      "step": 48
+    },
+    {
+      "epoch": 0.5212765957446809,
+      "grad_norm": 0.12258938699960709,
+      "learning_rate": 1.4700000000000001e-06,
+      "loss": 1.2966,
+      "step": 49
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.12217017263174057,
+      "learning_rate": 1.5e-06,
+      "loss": 1.2988,
+      "step": 50
+    },
+    {
+      "epoch": 0.5425531914893617,
+      "grad_norm": 0.12793436646461487,
+      "learning_rate": 1.53e-06,
+      "loss": 1.4233,
+      "step": 51
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.11145548522472382,
+      "learning_rate": 1.56e-06,
+      "loss": 1.2792,
+      "step": 52
+    },
+    {
+      "epoch": 0.5638297872340425,
+      "grad_norm": 0.13195408880710602,
+      "learning_rate": 1.59e-06,
+      "loss": 1.4481,
+      "step": 53
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 0.10663347691297531,
+      "learning_rate": 1.6200000000000002e-06,
+      "loss": 1.2331,
+      "step": 54
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 0.10975392907857895,
+      "learning_rate": 1.65e-06,
+      "loss": 1.1839,
+      "step": 55
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.13139477372169495,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 1.436,
+      "step": 56
+    },
+    {
+      "epoch": 0.6063829787234043,
+      "grad_norm": 0.0924743041396141,
+      "learning_rate": 1.71e-06,
+      "loss": 1.1291,
+      "step": 57
+    },
+    {
+      "epoch": 0.6170212765957447,
+      "grad_norm": 0.12475109100341797,
+      "learning_rate": 1.7399999999999999e-06,
+      "loss": 1.3444,
+      "step": 58
+    },
+    {
+      "epoch": 0.6276595744680851,
+      "grad_norm": 0.08960220962762833,
+      "learning_rate": 1.77e-06,
+      "loss": 1.2511,
+      "step": 59
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.09909304976463318,
+      "learning_rate": 1.8e-06,
+      "loss": 1.1281,
+      "step": 60
+    },
+    {
+      "epoch": 0.648936170212766,
+      "grad_norm": 0.11598234623670578,
+      "learning_rate": 1.83e-06,
+      "loss": 1.486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6595744680851063,
+      "grad_norm": 0.1404409557580948,
+      "learning_rate": 1.86e-06,
+      "loss": 1.4557,
+      "step": 62
+    },
+    {
+      "epoch": 0.6702127659574468,
+      "grad_norm": 0.11349129676818848,
+      "learning_rate": 1.8900000000000001e-06,
+      "loss": 1.3969,
+      "step": 63
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.10858353972434998,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.3515,
+      "step": 64
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 0.11054569482803345,
+      "learning_rate": 1.95e-06,
+      "loss": 1.248,
+      "step": 65
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 0.11826737225055695,
+      "learning_rate": 1.98e-06,
+      "loss": 1.3439,
+      "step": 66
+    },
+    {
+      "epoch": 0.7127659574468085,
+      "grad_norm": 0.12291310727596283,
+      "learning_rate": 2.0100000000000002e-06,
+      "loss": 1.4226,
+      "step": 67
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.1383126825094223,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 1.194,
+      "step": 68
+    },
+    {
+      "epoch": 0.7340425531914894,
+      "grad_norm": 0.10981890559196472,
+      "learning_rate": 2.07e-06,
+      "loss": 1.2502,
+      "step": 69
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.10639657825231552,
+      "learning_rate": 2.1e-06,
+      "loss": 1.2262,
+      "step": 70
+    },
+    {
+      "epoch": 0.7553191489361702,
+      "grad_norm": 0.46177396178245544,
+      "learning_rate": 2.13e-06,
+      "loss": 5.063,
+      "step": 71
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.11061427742242813,
+      "learning_rate": 2.16e-06,
+      "loss": 1.3856,
+      "step": 72
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "eval_loss": 1.5843762159347534,
+      "eval_runtime": 2.9943,
+      "eval_samples_per_second": 35.066,
+      "eval_steps_per_second": 17.7,
+      "step": 72
+    },
+    {
+      "epoch": 0.776595744680851,
+      "grad_norm": 0.13233324885368347,
+      "learning_rate": 2.19e-06,
+      "loss": 1.526,
+      "step": 73
+    },
+    {
+      "epoch": 0.7872340425531915,
+      "grad_norm": 0.14500053226947784,
+      "learning_rate": 2.22e-06,
+      "loss": 1.2554,
+      "step": 74
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 0.10629269480705261,
+      "learning_rate": 2.25e-06,
+      "loss": 1.2917,
+      "step": 75
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.09674028307199478,
+      "learning_rate": 2.28e-06,
+      "loss": 1.2169,
+      "step": 76
+    },
+    {
+      "epoch": 0.8191489361702128,
+      "grad_norm": 0.11965947598218918,
+      "learning_rate": 2.31e-06,
+      "loss": 1.2445,
+      "step": 77
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 0.10441229492425919,
+      "learning_rate": 2.34e-06,
+      "loss": 1.2392,
+      "step": 78
+    },
+    {
+      "epoch": 0.8404255319148937,
+      "grad_norm": 0.13795869052410126,
+      "learning_rate": 2.37e-06,
+      "loss": 1.5335,
+      "step": 79
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.10789927840232849,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.2309,
+      "step": 80
+    },
+    {
+      "epoch": 0.8617021276595744,
+      "grad_norm": 0.10697130113840103,
+      "learning_rate": 2.43e-06,
+      "loss": 1.276,
+      "step": 81
+    },
+    {
+      "epoch": 0.8723404255319149,
+      "grad_norm": 0.11484125256538391,
+      "learning_rate": 2.4599999999999997e-06,
+      "loss": 1.2163,
+      "step": 82
+    },
+    {
+      "epoch": 0.8829787234042553,
+      "grad_norm": 0.09692610800266266,
+      "learning_rate": 2.49e-06,
+      "loss": 1.1554,
+      "step": 83
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.10697747021913528,
+      "learning_rate": 2.52e-06,
+      "loss": 1.211,
+      "step": 84
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 0.10578318685293198,
+      "learning_rate": 2.55e-06,
+      "loss": 1.2634,
+      "step": 85
+    },
+    {
+      "epoch": 0.9148936170212766,
+      "grad_norm": 0.10587752610445023,
+      "learning_rate": 2.58e-06,
+      "loss": 1.369,
+      "step": 86
+    },
+    {
+      "epoch": 0.925531914893617,
+      "grad_norm": 0.11430489271879196,
+      "learning_rate": 2.61e-06,
+      "loss": 1.3048,
+      "step": 87
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.11116154491901398,
+      "learning_rate": 2.64e-06,
+      "loss": 1.1883,
+      "step": 88
+    },
+    {
+      "epoch": 0.9468085106382979,
+      "grad_norm": 0.12686476111412048,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 1.2605,
+      "step": 89
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.10976041853427887,
+      "learning_rate": 2.7e-06,
+      "loss": 1.2345,
+      "step": 90
+    },
+    {
+      "epoch": 0.9680851063829787,
+      "grad_norm": 0.12391550838947296,
+      "learning_rate": 2.73e-06,
+      "loss": 1.2233,
+      "step": 91
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.1277073174715042,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 1.2437,
+      "step": 92
+    },
+    {
+      "epoch": 0.9893617021276596,
+      "grad_norm": 0.10421616584062576,
+      "learning_rate": 2.7900000000000004e-06,
+      "loss": 1.1432,
+      "step": 93
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12696842849254608,
+      "learning_rate": 2.82e-06,
+      "loss": 1.3558,
+      "step": 94
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.10387945920228958,
+      "learning_rate": 2.85e-06,
+      "loss": 1.1902,
+      "step": 95
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.14543002843856812,
+      "learning_rate": 2.88e-06,
+      "loss": 1.244,
+      "step": 96
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "eval_loss": 1.5803985595703125,
+      "eval_runtime": 3.0087,
+      "eval_samples_per_second": 34.899,
+      "eval_steps_per_second": 17.616,
+      "step": 96
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.17504040896892548,
+      "learning_rate": 2.91e-06,
+      "loss": 1.3115,
+      "step": 97
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.14017756283283234,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 1.356,
+      "step": 98
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.11604318767786026,
+      "learning_rate": 2.97e-06,
+      "loss": 1.2806,
+      "step": 99
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.15116065740585327,
+      "learning_rate": 3e-06,
+      "loss": 1.3279,
+      "step": 100
+    },
+    {
+      "epoch": 1.0425531914893618,
+      "grad_norm": 0.10773392021656036,
+      "learning_rate": 2.9999028286680832e-06,
+      "loss": 1.3871,
+      "step": 101
+    },
+    {
+      "epoch": 1.053191489361702,
+      "grad_norm": 0.09363637119531631,
+      "learning_rate": 2.999611327262024e-06,
+      "loss": 1.1334,
+      "step": 102
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.09164439886808395,
+      "learning_rate": 2.999125533549261e-06,
+      "loss": 1.4026,
+      "step": 103
+    },
+    {
+      "epoch": 1.074468085106383,
+      "grad_norm": 0.12113964557647705,
+      "learning_rate": 2.9984455104700915e-06,
+      "loss": 1.2097,
+      "step": 104
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.10569895058870316,
+      "learning_rate": 2.9975713461295125e-06,
+      "loss": 1.3077,
+      "step": 105
+    },
+    {
+      "epoch": 1.0957446808510638,
+      "grad_norm": 0.11219862103462219,
+      "learning_rate": 2.996503153785809e-06,
+      "loss": 1.1923,
+      "step": 106
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.13474853336811066,
+      "learning_rate": 2.9952410718358777e-06,
+      "loss": 1.2729,
+      "step": 107
+    },
+    {
+      "epoch": 1.1170212765957448,
+      "grad_norm": 0.10451857000589371,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.2904,
+      "step": 108
+    },
+    {
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.12593719363212585,
+      "learning_rate": 2.9921359182871422e-06,
+      "loss": 1.4021,
+      "step": 109
+    },
+    {
+      "epoch": 1.1382978723404256,
+      "grad_norm": 0.12547315657138824,
+      "learning_rate": 2.990293248997547e-06,
+      "loss": 1.2093,
+      "step": 110
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.10086555033922195,
+      "learning_rate": 2.988257494668016e-06,
+      "loss": 1.3098,
+      "step": 111
+    },
+    {
+      "epoch": 1.1595744680851063,
+      "grad_norm": 0.10801573097705841,
+      "learning_rate": 2.9860289190544963e-06,
+      "loss": 1.2752,
+      "step": 112
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.11851054430007935,
+      "learning_rate": 2.9836078108952015e-06,
+      "loss": 1.3066,
+      "step": 113
+    },
+    {
+      "epoch": 1.1808510638297873,
+      "grad_norm": 0.1265188604593277,
+      "learning_rate": 2.9809944838732045e-06,
+      "loss": 1.1946,
+      "step": 114
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.10702725499868393,
+      "learning_rate": 2.9781892765757954e-06,
+      "loss": 1.2182,
+      "step": 115
+    },
+    {
+      "epoch": 1.202127659574468,
+      "grad_norm": 0.7757766842842102,
+      "learning_rate": 2.9751925524506135e-06,
+      "loss": 5.6082,
+      "step": 116
+    },
+    {
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.10182739049196243,
+      "learning_rate": 2.9720046997585577e-06,
+      "loss": 1.309,
+      "step": 117
+    },
+    {
+      "epoch": 1.2234042553191489,
+      "grad_norm": 0.14062073826789856,
+      "learning_rate": 2.9686261315234844e-06,
+      "loss": 1.3668,
+      "step": 118
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.1063840240240097,
+      "learning_rate": 2.965057285478694e-06,
+      "loss": 1.2247,
+      "step": 119
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "grad_norm": 0.10701325535774231,
+      "learning_rate": 2.961298624010219e-06,
+      "loss": 1.2499,
+      "step": 120
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "eval_loss": 1.575344204902649,
+      "eval_runtime": 8.2617,
+      "eval_samples_per_second": 12.709,
+      "eval_steps_per_second": 6.415,
+      "step": 120
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.11413375288248062,
+      "learning_rate": 2.957350634096912e-06,
+      "loss": 1.3593,
+      "step": 121
+    },
+    {
+      "epoch": 1.2659574468085106,
+      "grad_norm": 0.10826950520277023,
+      "learning_rate": 2.9532138272473597e-06,
+      "loss": 1.232,
+      "step": 122
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.10749218612909317,
+      "learning_rate": 2.9488887394336023e-06,
+      "loss": 1.401,
+      "step": 123
+    },
+    {
+      "epoch": 1.2872340425531914,
+      "grad_norm": 0.1175396591424942,
+      "learning_rate": 2.944375931021699e-06,
+      "loss": 1.2867,
+      "step": 124
+    },
+    {
+      "epoch": 1.297872340425532,
+      "grad_norm": 0.10688498616218567,
+      "learning_rate": 2.9396759866991214e-06,
+      "loss": 1.3689,
+      "step": 125
+    },
+    {
+      "epoch": 1.3085106382978724,
+      "grad_norm": 0.11630786955356598,
+      "learning_rate": 2.934789515399002e-06,
+      "loss": 1.2328,
+      "step": 126
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.11495409905910492,
+      "learning_rate": 2.9297171502212414e-06,
+      "loss": 1.1738,
+      "step": 127
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.10823408514261246,
+      "learning_rate": 2.924459548350479e-06,
+      "loss": 1.2318,
+      "step": 128
+    },
+    {
+      "epoch": 1.3404255319148937,
+      "grad_norm": 0.10759969800710678,
+      "learning_rate": 2.9190173909709506e-06,
+      "loss": 1.319,
+      "step": 129
+    },
+    {
+      "epoch": 1.351063829787234,
+      "grad_norm": 0.12790299952030182,
+      "learning_rate": 2.9133913831782307e-06,
+      "loss": 1.4282,
+      "step": 130
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.10899878293275833,
+      "learning_rate": 2.9075822538878805e-06,
+      "loss": 1.2455,
+      "step": 131
+    },
+    {
+      "epoch": 1.372340425531915,
+      "grad_norm": 0.12732432782649994,
+      "learning_rate": 2.9015907557410068e-06,
+      "loss": 1.2227,
+      "step": 132
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.10140018165111542,
+      "learning_rate": 2.8954176650067494e-06,
+      "loss": 1.0596,
+      "step": 133
+    },
+    {
+      "epoch": 1.3936170212765957,
+      "grad_norm": 0.12063546478748322,
+      "learning_rate": 2.889063781481708e-06,
+      "loss": 1.3321,
+      "step": 134
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.11323118209838867,
+      "learning_rate": 2.8825299283863144e-06,
+      "loss": 1.3366,
+      "step": 135
+    },
+    {
+      "epoch": 1.4148936170212765,
+      "grad_norm": 0.12391477078199387,
+      "learning_rate": 2.8758169522581796e-06,
+      "loss": 1.2917,
+      "step": 136
+    },
+    {
+      "epoch": 1.425531914893617,
+      "grad_norm": 0.12329094856977463,
+      "learning_rate": 2.8689257228424125e-06,
+      "loss": 1.1365,
+      "step": 137
+    },
+    {
+      "epoch": 1.4361702127659575,
+      "grad_norm": 0.11298198997974396,
+      "learning_rate": 2.8618571329789333e-06,
+      "loss": 1.4996,
+      "step": 138
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.10263165086507797,
+      "learning_rate": 2.8546120984867994e-06,
+      "loss": 1.199,
+      "step": 139
+    },
+    {
+      "epoch": 1.4574468085106382,
+      "grad_norm": 0.13330323994159698,
+      "learning_rate": 2.8471915580455442e-06,
+      "loss": 1.3746,
+      "step": 140
+    },
+    {
+      "epoch": 1.4680851063829787,
+      "grad_norm": 0.10694881528615952,
+      "learning_rate": 2.8395964730735666e-06,
+      "loss": 1.3798,
+      "step": 141
+    },
+    {
+      "epoch": 1.4787234042553192,
+      "grad_norm": 0.10929003357887268,
+      "learning_rate": 2.8318278276035626e-06,
+      "loss": 1.2918,
+      "step": 142
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.10969982296228409,
+      "learning_rate": 2.8238866281550366e-06,
+      "loss": 1.0444,
+      "step": 143
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10668367147445679,
+      "learning_rate": 2.815773903603892e-06,
+      "loss": 1.1656,
+      "step": 144
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5705612897872925,
+      "eval_runtime": 5.6853,
+      "eval_samples_per_second": 18.469,
+      "eval_steps_per_second": 9.322,
+      "step": 144
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.12057002633810043,
+      "learning_rate": 2.807490705049127e-06,
+      "loss": 1.2475,
+      "step": 145
+    },
+    {
+      "epoch": 1.521276595744681,
+      "grad_norm": 0.10394139587879181,
+      "learning_rate": 2.7990381056766585e-06,
+      "loss": 1.3376,
+      "step": 146
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.12907464802265167,
+      "learning_rate": 2.7904172006202705e-06,
+      "loss": 1.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.5425531914893615,
+      "grad_norm": 0.1252606213092804,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.1744,
+      "step": 148
+    },
+    {
+      "epoch": 1.5531914893617023,
+      "grad_norm": 0.1514441967010498,
+      "learning_rate": 2.772674962876085e-06,
+      "loss": 1.9324,
+      "step": 149
+    },
+    {
+      "epoch": 1.5638297872340425,
+      "grad_norm": 0.12377320230007172,
+      "learning_rate": 2.7635559289041174e-06,
+      "loss": 1.4511,
+      "step": 150
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.10629550367593765,
+      "learning_rate": 2.7542731863820665e-06,
+      "loss": 1.257,
+      "step": 151
+    },
+    {
+      "epoch": 1.5851063829787235,
+      "grad_norm": 0.10322704166173935,
+      "learning_rate": 2.744827937998538e-06,
+      "loss": 1.1796,
+      "step": 152
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.12690168619155884,
+      "learning_rate": 2.735221407496686e-06,
+      "loss": 1.3325,
+      "step": 153
+    },
+    {
+      "epoch": 1.6063829787234043,
+      "grad_norm": 0.0982392430305481,
+      "learning_rate": 2.725454839515663e-06,
+      "loss": 1.2169,
+      "step": 154
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.11184275150299072,
+      "learning_rate": 2.7155294994293606e-06,
+      "loss": 1.295,
+      "step": 155
+    },
+    {
+      "epoch": 1.627659574468085,
+      "grad_norm": 0.10721098631620407,
+      "learning_rate": 2.7054466731824676e-06,
+      "loss": 1.1945,
+      "step": 156
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.1254221498966217,
+      "learning_rate": 2.695207667123857e-06,
+      "loss": 1.2693,
+      "step": 157
+    },
+    {
+      "epoch": 1.648936170212766,
+      "grad_norm": 0.1157686784863472,
+      "learning_rate": 2.684813807837338e-06,
+      "loss": 1.1992,
+      "step": 158
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.10201229155063629,
+      "learning_rate": 2.674266441969778e-06,
+      "loss": 1.2401,
+      "step": 159
+    },
+    {
+      "epoch": 1.6702127659574468,
+      "grad_norm": 0.10953360050916672,
+      "learning_rate": 2.6635669360566298e-06,
+      "loss": 1.1627,
+      "step": 160
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.1248813271522522,
+      "learning_rate": 2.652716676344881e-06,
+      "loss": 1.3179,
+      "step": 161
+    },
+    {
+      "epoch": 1.6914893617021276,
+      "grad_norm": 0.09584470838308334,
+      "learning_rate": 2.6417170686134472e-06,
+      "loss": 1.2128,
+      "step": 162
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.12864486873149872,
+      "learning_rate": 2.630569537991042e-06,
+      "loss": 1.1889,
+      "step": 163
+    },
+    {
+      "epoch": 1.7127659574468086,
+      "grad_norm": 0.11820186674594879,
+      "learning_rate": 2.6192755287715282e-06,
+      "loss": 1.2848,
+      "step": 164
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.13811764121055603,
+      "learning_rate": 2.6078365042267987e-06,
+      "loss": 1.2091,
+      "step": 165
+    },
+    {
+      "epoch": 1.7340425531914894,
+      "grad_norm": 0.12099539488554001,
+      "learning_rate": 2.5962539464171862e-06,
+      "loss": 1.2853,
+      "step": 166
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.14544783532619476,
+      "learning_rate": 2.5845293559994513e-06,
+      "loss": 1.1574,
+      "step": 167
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "grad_norm": 0.11159494519233704,
+      "learning_rate": 2.5726642520323493e-06,
+      "loss": 1.1928,
+      "step": 168
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "eval_loss": 1.5656005144119263,
+      "eval_runtime": 3.0568,
+      "eval_samples_per_second": 34.349,
+      "eval_steps_per_second": 17.338,
+      "step": 168
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.1385321319103241,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 1.365,
+      "step": 169
+    },
+    {
+      "epoch": 1.7765957446808511,
+      "grad_norm": 0.12905962765216827,
+      "learning_rate": 2.548518670511823e-06,
+      "loss": 1.3664,
+      "step": 170
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.09589093923568726,
+      "learning_rate": 2.536241321302821e-06,
+      "loss": 1.1508,
+      "step": 171
+    },
+    {
+      "epoch": 1.797872340425532,
+      "grad_norm": 0.12533985078334808,
+      "learning_rate": 2.5238297148279814e-06,
+      "loss": 1.2892,
+      "step": 172
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.11337278038263321,
+      "learning_rate": 2.5112854591570804e-06,
+      "loss": 1.2772,
+      "step": 173
+    },
+    {
+      "epoch": 1.8191489361702127,
+      "grad_norm": 0.1345362514257431,
+      "learning_rate": 2.4986101795461608e-06,
+      "loss": 1.3583,
+      "step": 174
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.121876560151577,
+      "learning_rate": 2.485805518226959e-06,
+      "loss": 1.2065,
+      "step": 175
+    },
+    {
+      "epoch": 1.8404255319148937,
+      "grad_norm": 0.10669907927513123,
+      "learning_rate": 2.4728731341941343e-06,
+      "loss": 1.2339,
+      "step": 176
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.12710174918174744,
+      "learning_rate": 2.4598147029903284e-06,
+      "loss": 1.4597,
+      "step": 177
+    },
+    {
+      "epoch": 1.8617021276595744,
+      "grad_norm": 0.11735282093286514,
+      "learning_rate": 2.4466319164890795e-06,
+      "loss": 1.2273,
+      "step": 178
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.12083889544010162,
+      "learning_rate": 2.4333264826756165e-06,
+      "loss": 1.3051,
+      "step": 179
+    },
+    {
+      "epoch": 1.8829787234042552,
+      "grad_norm": 0.10338792204856873,
+      "learning_rate": 2.4199001254255746e-06,
+      "loss": 1.3827,
+      "step": 180
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.10191334784030914,
+      "learning_rate": 2.406354584281642e-06,
+      "loss": 1.4067,
+      "step": 181
+    },
+    {
+      "epoch": 1.9042553191489362,
+      "grad_norm": 0.10776273161172867,
+      "learning_rate": 2.3926916142281846e-06,
+      "loss": 1.2344,
+      "step": 182
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.1253603845834732,
+      "learning_rate": 2.378912985463867e-06,
+      "loss": 1.2179,
+      "step": 183
+    },
+    {
+      "epoch": 1.925531914893617,
+      "grad_norm": 0.09942696243524551,
+      "learning_rate": 2.365020483172301e-06,
+      "loss": 1.0613,
+      "step": 184
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.10441701859235764,
+      "learning_rate": 2.351015907290755e-06,
+      "loss": 1.3886,
+      "step": 185
+    },
+    {
+      "epoch": 1.9468085106382977,
+      "grad_norm": 0.10571073740720749,
+      "learning_rate": 2.3369010722769502e-06,
+      "loss": 1.2023,
+      "step": 186
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.12477201223373413,
+      "learning_rate": 2.3226778068739783e-06,
+      "loss": 1.361,
+      "step": 187
+    },
+    {
+      "epoch": 1.9680851063829787,
+      "grad_norm": 0.12106247246265411,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.4153,
+      "step": 188
+    },
+    {
+      "epoch": 1.978723404255319,
+      "grad_norm": 0.17261436581611633,
+      "learning_rate": 2.2939133698763084e-06,
+      "loss": 1.45,
+      "step": 189
+    },
+    {
+      "epoch": 1.9893617021276597,
+      "grad_norm": 0.12172568589448929,
+      "learning_rate": 2.2793759250531504e-06,
+      "loss": 1.1764,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11111535131931305,
+      "learning_rate": 2.2647375029010575e-06,
+      "loss": 1.1347,
+      "step": 191
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "grad_norm": 0.10596352070569992,
+      "learning_rate": 2.25e-06,
+      "loss": 1.1623,
+      "step": 192
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "eval_loss": 1.560809850692749,
+      "eval_runtime": 4.8693,
+      "eval_samples_per_second": 21.564,
+      "eval_steps_per_second": 10.885,
+      "step": 192
+    },
+    {
+      "epoch": 2.0212765957446805,
+      "grad_norm": 0.08630727976560593,
+      "learning_rate": 2.235165325767026e-06,
+      "loss": 1.1733,
+      "step": 193
+    },
+    {
+      "epoch": 2.0319148936170213,
+      "grad_norm": 0.3629175126552582,
+      "learning_rate": 2.2202354022088735e-06,
+      "loss": 1.1114,
+      "step": 194
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "grad_norm": 0.12061420828104019,
+      "learning_rate": 2.2052121636729527e-06,
+      "loss": 1.1813,
+      "step": 195
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.12194402515888214,
+      "learning_rate": 2.1900975565967284e-06,
+      "loss": 1.4466,
+      "step": 196
+    },
+    {
+      "epoch": 2.0319148936170213,
+      "grad_norm": 0.09581239521503448,
+      "learning_rate": 2.1748935392555347e-06,
+      "loss": 1.1863,
+      "step": 197
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.12056192755699158,
+      "learning_rate": 2.1596020815088587e-06,
+      "loss": 1.5781,
+      "step": 198
+    },
+    {
+      "epoch": 2.0531914893617023,
+      "grad_norm": 0.10989479720592499,
+      "learning_rate": 2.1442251645451233e-06,
+      "loss": 1.2638,
+      "step": 199
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 0.1273481398820877,
+      "learning_rate": 2.1287647806249964e-06,
+      "loss": 1.1346,
+      "step": 200
+    },
+    {
+      "epoch": 2.074468085106383,
+      "grad_norm": 0.11547158658504486,
+      "learning_rate": 2.1132229328232755e-06,
+      "loss": 1.124,
+      "step": 201
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.12033279985189438,
+      "learning_rate": 2.0976016347693624e-06,
+      "loss": 1.2695,
+      "step": 202
+    },
+    {
+      "epoch": 2.095744680851064,
+      "grad_norm": 0.11929858475923538,
+      "learning_rate": 2.0819029103863746e-06,
+      "loss": 1.1885,
+      "step": 203
+    },
+    {
+      "epoch": 2.106382978723404,
+      "grad_norm": 0.10733456164598465,
+      "learning_rate": 2.0661287936289213e-06,
+      "loss": 1.3742,
+      "step": 204
+    },
+    {
+      "epoch": 2.117021276595745,
+      "grad_norm": 0.12037491053342819,
+      "learning_rate": 2.050281328219585e-06,
+      "loss": 1.1911,
+      "step": 205
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.12621213495731354,
+      "learning_rate": 2.0343625673841254e-06,
+      "loss": 1.1241,
+      "step": 206
+    },
+    {
+      "epoch": 2.1382978723404253,
+      "grad_norm": 0.15265725553035736,
+      "learning_rate": 2.018374573585467e-06,
+      "loss": 1.4419,
+      "step": 207
+    },
+    {
+      "epoch": 2.148936170212766,
+      "grad_norm": 0.10528834164142609,
+      "learning_rate": 2.0023194182564793e-06,
+      "loss": 1.2211,
+      "step": 208
+    },
+    {
+      "epoch": 2.1595744680851063,
+      "grad_norm": 0.11791864037513733,
+      "learning_rate": 1.986199181531599e-06,
+      "loss": 1.2159,
+      "step": 209
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "grad_norm": 0.1230137050151825,
+      "learning_rate": 1.9700159519773233e-06,
+      "loss": 1.2687,
+      "step": 210
+    },
+    {
+      "epoch": 2.1808510638297873,
+      "grad_norm": 0.11243241280317307,
+      "learning_rate": 1.9537718263216137e-06,
+      "loss": 1.2008,
+      "step": 211
+    },
+    {
+      "epoch": 2.1914893617021276,
+      "grad_norm": 0.13040384650230408,
+      "learning_rate": 1.9374689091822377e-06,
+      "loss": 1.2937,
+      "step": 212
+    },
+    {
+      "epoch": 2.202127659574468,
+      "grad_norm": 0.096621572971344,
+      "learning_rate": 1.9211093127940917e-06,
+      "loss": 1.1315,
+      "step": 213
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 0.10366329550743103,
+      "learning_rate": 1.9046951567355363e-06,
+      "loss": 1.1998,
+      "step": 214
+    },
+    {
+      "epoch": 2.223404255319149,
+      "grad_norm": 0.13266436755657196,
+      "learning_rate": 1.888228567653781e-06,
+      "loss": 1.2169,
+      "step": 215
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "grad_norm": 0.12041480094194412,
+      "learning_rate": 1.87171167898935e-06,
+      "loss": 1.2679,
+      "step": 216
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "eval_loss": 1.557094931602478,
+      "eval_runtime": 3.8276,
+      "eval_samples_per_second": 27.432,
+      "eval_steps_per_second": 13.847,
+      "step": 216
+    },
+    {
+      "epoch": 2.24468085106383,
+      "grad_norm": 0.11926256865262985,
+      "learning_rate": 1.8551466306996702e-06,
+      "loss": 1.2496,
+      "step": 217
+    },
+    {
+      "epoch": 2.25531914893617,
+      "grad_norm": 0.11768142879009247,
+      "learning_rate": 1.838535568981816e-06,
+      "loss": 1.2793,
+      "step": 218
+    },
+    {
+      "epoch": 2.2659574468085104,
+      "grad_norm": 0.09850093722343445,
+      "learning_rate": 1.821880645994443e-06,
+      "loss": 1.1712,
+      "step": 219
+    },
+    {
+      "epoch": 2.276595744680851,
+      "grad_norm": 0.11399635672569275,
+      "learning_rate": 1.8051840195789509e-06,
+      "loss": 1.3151,
+      "step": 220
+    },
+    {
+      "epoch": 2.2872340425531914,
+      "grad_norm": 0.10654745250940323,
+      "learning_rate": 1.788447852979909e-06,
+      "loss": 1.1726,
+      "step": 221
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 0.12983720004558563,
+      "learning_rate": 1.7716743145647837e-06,
+      "loss": 1.2158,
+      "step": 222
+    },
+    {
+      "epoch": 2.3085106382978724,
+      "grad_norm": 0.08331640809774399,
+      "learning_rate": 1.754865577543e-06,
+      "loss": 0.8472,
+      "step": 223
+    },
+    {
+      "epoch": 2.3191489361702127,
+      "grad_norm": 0.11662207543849945,
+      "learning_rate": 1.738023819684377e-06,
+      "loss": 1.2938,
+      "step": 224
+    },
+    {
+      "epoch": 2.329787234042553,
+      "grad_norm": 0.13265132904052734,
+      "learning_rate": 1.7211512230369716e-06,
+      "loss": 1.3288,
+      "step": 225
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.10342156141996384,
+      "learning_rate": 1.7042499736443702e-06,
+      "loss": 1.2352,
+      "step": 226
+    },
+    {
+      "epoch": 2.351063829787234,
+      "grad_norm": 0.10495639592409134,
+      "learning_rate": 1.6873222612624575e-06,
+      "loss": 1.1748,
+      "step": 227
+    },
+    {
+      "epoch": 2.3617021276595747,
+      "grad_norm": 0.1564377248287201,
+      "learning_rate": 1.6703702790757123e-06,
+      "loss": 1.4071,
+      "step": 228
+    },
+    {
+      "epoch": 2.372340425531915,
+      "grad_norm": 0.11000990867614746,
+      "learning_rate": 1.6533962234130513e-06,
+      "loss": 1.2102,
+      "step": 229
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.12565018236637115,
+      "learning_rate": 1.6364022934632706e-06,
+      "loss": 1.4047,
+      "step": 230
+    },
+    {
+      "epoch": 2.393617021276596,
+      "grad_norm": 0.11519981920719147,
+      "learning_rate": 1.6193906909901133e-06,
+      "loss": 1.3905,
+      "step": 231
+    },
+    {
+      "epoch": 2.404255319148936,
+      "grad_norm": 0.12704767286777496,
+      "learning_rate": 1.6023636200470066e-06,
+      "loss": 1.0632,
+      "step": 232
+    },
+    {
+      "epoch": 2.4148936170212765,
+      "grad_norm": 0.11226076632738113,
+      "learning_rate": 1.5853232866915004e-06,
+      "loss": 1.2448,
+      "step": 233
+    },
+    {
+      "epoch": 2.425531914893617,
+      "grad_norm": 0.11282170563936234,
+      "learning_rate": 1.5682718986994457e-06,
+      "loss": 1.5068,
+      "step": 234
+    },
+    {
+      "epoch": 2.4361702127659575,
+      "grad_norm": 0.09763903170824051,
+      "learning_rate": 1.5512116652789518e-06,
+      "loss": 1.2398,
+      "step": 235
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 0.11640322953462601,
+      "learning_rate": 1.5341447967841585e-06,
+      "loss": 1.3176,
+      "step": 236
+    },
+    {
+      "epoch": 2.4574468085106385,
+      "grad_norm": 0.12292848527431488,
+      "learning_rate": 1.5170735044288565e-06,
+      "loss": 1.8823,
+      "step": 237
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 0.12308197468519211,
+      "learning_rate": 1.5e-06,
+      "loss": 1.14,
+      "step": 238
+    },
+    {
+      "epoch": 2.478723404255319,
+      "grad_norm": 0.11871509999036789,
+      "learning_rate": 1.4829264955711436e-06,
+      "loss": 1.2753,
+      "step": 239
+    },
+    {
+      "epoch": 2.4893617021276597,
+      "grad_norm": 0.14034831523895264,
+      "learning_rate": 1.4658552032158414e-06,
+      "loss": 1.2845,
+      "step": 240
+    },
+    {
+      "epoch": 2.4893617021276597,
+      "eval_loss": 1.5537203550338745,
+      "eval_runtime": 5.1489,
+      "eval_samples_per_second": 20.393,
+      "eval_steps_per_second": 10.294,
+      "step": 240
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12317660450935364,
+      "learning_rate": 1.4487883347210483e-06,
+      "loss": 1.2742,
+      "step": 241
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 0.11180029809474945,
+      "learning_rate": 1.431728101300555e-06,
+      "loss": 1.3743,
+      "step": 242
+    },
+    {
+      "epoch": 2.521276595744681,
+      "grad_norm": 0.12544095516204834,
+      "learning_rate": 1.4146767133085e-06,
+      "loss": 1.2935,
+      "step": 243
+    },
+    {
+      "epoch": 2.5319148936170213,
+      "grad_norm": 0.12283220142126083,
+      "learning_rate": 1.3976363799529937e-06,
+      "loss": 1.2529,
+      "step": 244
+    },
+    {
+      "epoch": 2.5425531914893615,
+      "grad_norm": 0.1375051885843277,
+      "learning_rate": 1.3806093090098872e-06,
+      "loss": 1.2907,
+      "step": 245
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.10762558877468109,
+      "learning_rate": 1.3635977065367295e-06,
+      "loss": 1.1548,
+      "step": 246
+    },
+    {
+      "epoch": 2.5638297872340425,
+      "grad_norm": 0.12075044959783554,
+      "learning_rate": 1.3466037765869486e-06,
+      "loss": 1.2208,
+      "step": 247
+    },
+    {
+      "epoch": 2.574468085106383,
+      "grad_norm": 0.11484728753566742,
+      "learning_rate": 1.3296297209242874e-06,
+      "loss": 1.1182,
+      "step": 248
+    },
+    {
+      "epoch": 2.5851063829787235,
+      "grad_norm": 0.11546777188777924,
+      "learning_rate": 1.312677738737543e-06,
+      "loss": 1.4478,
+      "step": 249
+    },
+    {
+      "epoch": 2.595744680851064,
+      "grad_norm": 0.12128724902868271,
+      "learning_rate": 1.2957500263556303e-06,
+      "loss": 1.3132,
+      "step": 250
+    },
+    {
+      "epoch": 2.6063829787234045,
+      "grad_norm": 0.09233469516038895,
+      "learning_rate": 1.2788487769630284e-06,
+      "loss": 1.0863,
+      "step": 251
+    },
+    {
+      "epoch": 2.617021276595745,
+      "grad_norm": 0.12085112929344177,
+      "learning_rate": 1.261976180315623e-06,
+      "loss": 1.2855,
+      "step": 252
+    },
+    {
+      "epoch": 2.627659574468085,
+      "grad_norm": 0.12655006349086761,
+      "learning_rate": 1.2451344224570002e-06,
+      "loss": 1.2691,
+      "step": 253
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 0.12646865844726562,
+      "learning_rate": 1.2283256854352162e-06,
+      "loss": 1.2194,
+      "step": 254
+    },
+    {
+      "epoch": 2.648936170212766,
+      "grad_norm": 0.1081186905503273,
+      "learning_rate": 1.2115521470200911e-06,
+      "loss": 1.2551,
+      "step": 255
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.12278001755475998,
+      "learning_rate": 1.1948159804210496e-06,
+      "loss": 1.3049,
+      "step": 256
+    },
+    {
+      "epoch": 2.670212765957447,
+      "grad_norm": 0.09346724301576614,
+      "learning_rate": 1.1781193540055573e-06,
+      "loss": 1.1507,
+      "step": 257
+    },
+    {
+      "epoch": 2.6808510638297873,
+      "grad_norm": 0.10679617524147034,
+      "learning_rate": 1.1614644310181842e-06,
+      "loss": 1.2971,
+      "step": 258
+    },
+    {
+      "epoch": 2.6914893617021276,
+      "grad_norm": 0.11394444108009338,
+      "learning_rate": 1.14485336930033e-06,
+      "loss": 1.2133,
+      "step": 259
+    },
+    {
+      "epoch": 2.702127659574468,
+      "grad_norm": 0.1416221708059311,
+      "learning_rate": 1.1282883210106503e-06,
+      "loss": 1.2132,
+      "step": 260
+    },
+    {
+      "epoch": 2.7127659574468086,
+      "grad_norm": 0.09133229404687881,
+      "learning_rate": 1.1117714323462188e-06,
+      "loss": 1.17,
+      "step": 261
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 0.10997346043586731,
+      "learning_rate": 1.0953048432644634e-06,
+      "loss": 1.1443,
+      "step": 262
+    },
+    {
+      "epoch": 2.7340425531914896,
+      "grad_norm": 0.11233331263065338,
+      "learning_rate": 1.0788906872059088e-06,
+      "loss": 1.3383,
+      "step": 263
+    },
+    {
+      "epoch": 2.74468085106383,
+      "grad_norm": 0.11798594146966934,
+      "learning_rate": 1.0625310908177626e-06,
+      "loss": 1.1226,
+      "step": 264
+    },
+    {
+      "epoch": 2.74468085106383,
+      "eval_loss": 1.5516207218170166,
+      "eval_runtime": 4.7557,
+      "eval_samples_per_second": 22.079,
+      "eval_steps_per_second": 11.145,
+      "step": 264
+    },
+    {
+      "epoch": 2.75531914893617,
+      "grad_norm": 0.12637464702129364,
+      "learning_rate": 1.0462281736783864e-06,
+      "loss": 1.4182,
+      "step": 265
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.11374552547931671,
+      "learning_rate": 1.0299840480226768e-06,
+      "loss": 1.2926,
+      "step": 266
+    },
+    {
+      "epoch": 2.776595744680851,
+      "grad_norm": 0.13765357434749603,
+      "learning_rate": 1.0138008184684011e-06,
+      "loss": 1.3036,
+      "step": 267
+    },
+    {
+      "epoch": 2.7872340425531914,
+      "grad_norm": 0.1168639063835144,
+      "learning_rate": 9.976805817435208e-07,
+      "loss": 1.2854,
+      "step": 268
+    },
+    {
+      "epoch": 2.797872340425532,
+      "grad_norm": 0.11609431356191635,
+      "learning_rate": 9.816254264145328e-07,
+      "loss": 1.2832,
+      "step": 269
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 0.11090860515832901,
+      "learning_rate": 9.656374326158753e-07,
+      "loss": 1.4098,
+      "step": 270
+    },
+    {
+      "epoch": 2.8191489361702127,
+      "grad_norm": 0.12376827001571655,
+      "learning_rate": 9.497186717804155e-07,
+      "loss": 1.2335,
+      "step": 271
+    },
+    {
+      "epoch": 2.829787234042553,
+      "grad_norm": 0.11905582994222641,
+      "learning_rate": 9.338712063710786e-07,
+      "loss": 1.1991,
+      "step": 272
+    },
+    {
+      "epoch": 2.8404255319148937,
+      "grad_norm": 0.09383586794137955,
+      "learning_rate": 9.180970896136258e-07,
+      "loss": 1.1715,
+      "step": 273
+    },
+    {
+      "epoch": 2.851063829787234,
+      "grad_norm": 0.14080052077770233,
+      "learning_rate": 9.023983652306379e-07,
+      "loss": 1.3227,
+      "step": 274
+    },
+    {
+      "epoch": 2.8617021276595747,
+      "grad_norm": 0.10943106561899185,
+      "learning_rate": 8.867770671767246e-07,
+      "loss": 0.9774,
+      "step": 275
+    },
+    {
+      "epoch": 2.872340425531915,
+      "grad_norm": 0.093683160841465,
+      "learning_rate": 8.712352193750043e-07,
+      "loss": 1.053,
+      "step": 276
+    },
+    {
+      "epoch": 2.882978723404255,
+      "grad_norm": 0.1352389007806778,
+      "learning_rate": 8.557748354548773e-07,
+      "loss": 1.2713,
+      "step": 277
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 0.09906943887472153,
+      "learning_rate": 8.403979184911411e-07,
+      "loss": 1.3128,
+      "step": 278
+    },
+    {
+      "epoch": 2.904255319148936,
+      "grad_norm": 0.13467717170715332,
+      "learning_rate": 8.251064607444658e-07,
+      "loss": 1.4274,
+      "step": 279
+    },
+    {
+      "epoch": 2.9148936170212765,
+      "grad_norm": 0.11490917205810547,
+      "learning_rate": 8.099024434032718e-07,
+      "loss": 1.307,
+      "step": 280
+    },
+    {
+      "epoch": 2.925531914893617,
+      "grad_norm": 0.10982628166675568,
+      "learning_rate": 7.947878363270472e-07,
+      "loss": 1.0661,
+      "step": 281
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": 0.13426214456558228,
+      "learning_rate": 7.797645977911268e-07,
+      "loss": 1.3296,
+      "step": 282
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 94,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9461272877727744.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

phi-sft-out/checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
+size 6008

phi-sft-out/checkpoint-376/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-1_5
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

phi-sft-out/checkpoint-376/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "dense",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi-sft-out/checkpoint-376/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241c6c3044862c027dd4a5b884dc64b710af34d4af3be69795a4ff3186febd29
+size 226530600

phi-sft-out/checkpoint-376/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

phi-sft-out/checkpoint-376/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48dcc1cdca3fafb26844cd4b2fce4583f597e3b9ded8785d1613bc12d2bf011
+size 453227642

phi-sft-out/checkpoint-376/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b8dbab6f3f0b4ec0a2aa7cd20a8f0b4e43beeb74cc71cab5d67dec19630101
+size 14244

phi-sft-out/checkpoint-376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fba535709d4b8515923331226da9aae9dad13bc2e531b0585c7d05f01f21f87
+size 1064

phi-sft-out/checkpoint-376/special_tokens_map.json

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

phi-sft-out/checkpoint-376/tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

phi-sft-out/checkpoint-376/trainer_state.json

@@ -0,0 +1,2793 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.904255319148936,
+  "eval_steps": 24,
+  "global_step": 376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010638297872340425,
+      "grad_norm": 0.10508890450000763,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 1.2333,
+      "step": 1
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "eval_loss": 1.5895557403564453,
+      "eval_runtime": 2.9603,
+      "eval_samples_per_second": 35.469,
+      "eval_steps_per_second": 17.903,
+      "step": 1
+    },
+    {
+      "epoch": 0.02127659574468085,
+      "grad_norm": 0.12071573734283447,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 1.3986,
+      "step": 2
+    },
+    {
+      "epoch": 0.031914893617021274,
+      "grad_norm": 0.10401547700166702,
+      "learning_rate": 9e-08,
+      "loss": 1.2058,
+      "step": 3
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.12298297882080078,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.3298,
+      "step": 4
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 0.1327030211687088,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 1.4031,
+      "step": 5
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 0.12036772817373276,
+      "learning_rate": 1.8e-07,
+      "loss": 1.5335,
+      "step": 6
+    },
+    {
+      "epoch": 0.07446808510638298,
+      "grad_norm": 0.14979703724384308,
+      "learning_rate": 2.1000000000000003e-07,
+      "loss": 1.3224,
+      "step": 7
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.13082227110862732,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.4035,
+      "step": 8
+    },
+    {
+      "epoch": 0.09574468085106383,
+      "grad_norm": 0.09265327453613281,
+      "learning_rate": 2.7e-07,
+      "loss": 1.1546,
+      "step": 9
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 0.10080434381961823,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.2652,
+      "step": 10
+    },
+    {
+      "epoch": 0.11702127659574468,
+      "grad_norm": 0.10915568470954895,
+      "learning_rate": 3.3e-07,
+      "loss": 1.1438,
+      "step": 11
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.1307348906993866,
+      "learning_rate": 3.6e-07,
+      "loss": 1.2821,
+      "step": 12
+    },
+    {
+      "epoch": 0.13829787234042554,
+      "grad_norm": 0.09814529865980148,
+      "learning_rate": 3.9e-07,
+      "loss": 1.3905,
+      "step": 13
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 0.11842218786478043,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 1.3085,
+      "step": 14
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 0.10207124054431915,
+      "learning_rate": 4.5e-07,
+      "loss": 1.19,
+      "step": 15
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.1150127425789833,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.386,
+      "step": 16
+    },
+    {
+      "epoch": 0.18085106382978725,
+      "grad_norm": 0.11641352623701096,
+      "learning_rate": 5.100000000000001e-07,
+      "loss": 1.4357,
+      "step": 17
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 0.15035435557365417,
+      "learning_rate": 5.4e-07,
+      "loss": 1.2549,
+      "step": 18
+    },
+    {
+      "epoch": 0.20212765957446807,
+      "grad_norm": 0.0984087809920311,
+      "learning_rate": 5.7e-07,
+      "loss": 0.9723,
+      "step": 19
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.11582670360803604,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.1402,
+      "step": 20
+    },
+    {
+      "epoch": 0.22340425531914893,
+      "grad_norm": 0.10151291638612747,
+      "learning_rate": 6.3e-07,
+      "loss": 1.1533,
+      "step": 21
+    },
+    {
+      "epoch": 0.23404255319148937,
+      "grad_norm": 0.09040653705596924,
+      "learning_rate": 6.6e-07,
+      "loss": 1.0438,
+      "step": 22
+    },
+    {
+      "epoch": 0.24468085106382978,
+      "grad_norm": 0.10666865110397339,
+      "learning_rate": 6.900000000000001e-07,
+      "loss": 1.3195,
+      "step": 23
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.12293969094753265,
+      "learning_rate": 7.2e-07,
+      "loss": 1.7286,
+      "step": 24
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "eval_loss": 1.5890721082687378,
+      "eval_runtime": 2.9908,
+      "eval_samples_per_second": 35.108,
+      "eval_steps_per_second": 17.721,
+      "step": 24
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 0.11052387952804565,
+      "learning_rate": 7.5e-07,
+      "loss": 1.1413,
+      "step": 25
+    },
+    {
+      "epoch": 0.2765957446808511,
+      "grad_norm": 0.09323304146528244,
+      "learning_rate": 7.8e-07,
+      "loss": 1.2906,
+      "step": 26
+    },
+    {
+      "epoch": 0.2872340425531915,
+      "grad_norm": 0.12542971968650818,
+      "learning_rate": 8.100000000000001e-07,
+      "loss": 1.2809,
+      "step": 27
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.1080215722322464,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.2735,
+      "step": 28
+    },
+    {
+      "epoch": 0.30851063829787234,
+      "grad_norm": 0.11304887384176254,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": 1.3767,
+      "step": 29
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 0.15650290250778198,
+      "learning_rate": 9e-07,
+      "loss": 1.4713,
+      "step": 30
+    },
+    {
+      "epoch": 0.32978723404255317,
+      "grad_norm": 0.12139321118593216,
+      "learning_rate": 9.3e-07,
+      "loss": 1.3479,
+      "step": 31
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.10141867399215698,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.1512,
+      "step": 32
+    },
+    {
+      "epoch": 0.35106382978723405,
+      "grad_norm": 0.15045498311519623,
+      "learning_rate": 9.9e-07,
+      "loss": 1.5059,
+      "step": 33
+    },
+    {
+      "epoch": 0.3617021276595745,
+      "grad_norm": 0.12956956028938293,
+      "learning_rate": 1.0200000000000002e-06,
+      "loss": 1.2849,
+      "step": 34
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 0.12963886559009552,
+      "learning_rate": 1.05e-06,
+      "loss": 1.5025,
+      "step": 35
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.11268144845962524,
+      "learning_rate": 1.08e-06,
+      "loss": 1.2987,
+      "step": 36
+    },
+    {
+      "epoch": 0.39361702127659576,
+      "grad_norm": 0.12941108644008636,
+      "learning_rate": 1.11e-06,
+      "loss": 1.3432,
+      "step": 37
+    },
+    {
+      "epoch": 0.40425531914893614,
+      "grad_norm": 0.11319927126169205,
+      "learning_rate": 1.14e-06,
+      "loss": 1.1665,
+      "step": 38
+    },
+    {
+      "epoch": 0.4148936170212766,
+      "grad_norm": 0.11748912930488586,
+      "learning_rate": 1.17e-06,
+      "loss": 1.423,
+      "step": 39
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.11666171997785568,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4391,
+      "step": 40
+    },
+    {
+      "epoch": 0.43617021276595747,
+      "grad_norm": 0.12274409830570221,
+      "learning_rate": 1.2299999999999999e-06,
+      "loss": 1.4865,
+      "step": 41
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 0.09922561049461365,
+      "learning_rate": 1.26e-06,
+      "loss": 1.2193,
+      "step": 42
+    },
+    {
+      "epoch": 0.4574468085106383,
+      "grad_norm": 0.12003930658102036,
+      "learning_rate": 1.29e-06,
+      "loss": 1.3024,
+      "step": 43
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.12094161659479141,
+      "learning_rate": 1.32e-06,
+      "loss": 1.4654,
+      "step": 44
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 0.12934774160385132,
+      "learning_rate": 1.35e-06,
+      "loss": 1.3713,
+      "step": 45
+    },
+    {
+      "epoch": 0.48936170212765956,
+      "grad_norm": 0.09754550457000732,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 1.1991,
+      "step": 46
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.11549004167318344,
+      "learning_rate": 1.41e-06,
+      "loss": 1.4859,
+      "step": 47
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.12035688012838364,
+      "learning_rate": 1.44e-06,
+      "loss": 1.2823,
+      "step": 48
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "eval_loss": 1.5874611139297485,
+      "eval_runtime": 2.9787,
+      "eval_samples_per_second": 35.251,
+      "eval_steps_per_second": 17.793,
+      "step": 48
+    },
+    {
+      "epoch": 0.5212765957446809,
+      "grad_norm": 0.12258938699960709,
+      "learning_rate": 1.4700000000000001e-06,
+      "loss": 1.2966,
+      "step": 49
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.12217017263174057,
+      "learning_rate": 1.5e-06,
+      "loss": 1.2988,
+      "step": 50
+    },
+    {
+      "epoch": 0.5425531914893617,
+      "grad_norm": 0.12793436646461487,
+      "learning_rate": 1.53e-06,
+      "loss": 1.4233,
+      "step": 51
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.11145548522472382,
+      "learning_rate": 1.56e-06,
+      "loss": 1.2792,
+      "step": 52
+    },
+    {
+      "epoch": 0.5638297872340425,
+      "grad_norm": 0.13195408880710602,
+      "learning_rate": 1.59e-06,
+      "loss": 1.4481,
+      "step": 53
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 0.10663347691297531,
+      "learning_rate": 1.6200000000000002e-06,
+      "loss": 1.2331,
+      "step": 54
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 0.10975392907857895,
+      "learning_rate": 1.65e-06,
+      "loss": 1.1839,
+      "step": 55
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.13139477372169495,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 1.436,
+      "step": 56
+    },
+    {
+      "epoch": 0.6063829787234043,
+      "grad_norm": 0.0924743041396141,
+      "learning_rate": 1.71e-06,
+      "loss": 1.1291,
+      "step": 57
+    },
+    {
+      "epoch": 0.6170212765957447,
+      "grad_norm": 0.12475109100341797,
+      "learning_rate": 1.7399999999999999e-06,
+      "loss": 1.3444,
+      "step": 58
+    },
+    {
+      "epoch": 0.6276595744680851,
+      "grad_norm": 0.08960220962762833,
+      "learning_rate": 1.77e-06,
+      "loss": 1.2511,
+      "step": 59
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.09909304976463318,
+      "learning_rate": 1.8e-06,
+      "loss": 1.1281,
+      "step": 60
+    },
+    {
+      "epoch": 0.648936170212766,
+      "grad_norm": 0.11598234623670578,
+      "learning_rate": 1.83e-06,
+      "loss": 1.486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6595744680851063,
+      "grad_norm": 0.1404409557580948,
+      "learning_rate": 1.86e-06,
+      "loss": 1.4557,
+      "step": 62
+    },
+    {
+      "epoch": 0.6702127659574468,
+      "grad_norm": 0.11349129676818848,
+      "learning_rate": 1.8900000000000001e-06,
+      "loss": 1.3969,
+      "step": 63
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.10858353972434998,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.3515,
+      "step": 64
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 0.11054569482803345,
+      "learning_rate": 1.95e-06,
+      "loss": 1.248,
+      "step": 65
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 0.11826737225055695,
+      "learning_rate": 1.98e-06,
+      "loss": 1.3439,
+      "step": 66
+    },
+    {
+      "epoch": 0.7127659574468085,
+      "grad_norm": 0.12291310727596283,
+      "learning_rate": 2.0100000000000002e-06,
+      "loss": 1.4226,
+      "step": 67
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.1383126825094223,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 1.194,
+      "step": 68
+    },
+    {
+      "epoch": 0.7340425531914894,
+      "grad_norm": 0.10981890559196472,
+      "learning_rate": 2.07e-06,
+      "loss": 1.2502,
+      "step": 69
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.10639657825231552,
+      "learning_rate": 2.1e-06,
+      "loss": 1.2262,
+      "step": 70
+    },
+    {
+      "epoch": 0.7553191489361702,
+      "grad_norm": 0.46177396178245544,
+      "learning_rate": 2.13e-06,
+      "loss": 5.063,
+      "step": 71
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.11061427742242813,
+      "learning_rate": 2.16e-06,
+      "loss": 1.3856,
+      "step": 72
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "eval_loss": 1.5843762159347534,
+      "eval_runtime": 2.9943,
+      "eval_samples_per_second": 35.066,
+      "eval_steps_per_second": 17.7,
+      "step": 72
+    },
+    {
+      "epoch": 0.776595744680851,
+      "grad_norm": 0.13233324885368347,
+      "learning_rate": 2.19e-06,
+      "loss": 1.526,
+      "step": 73
+    },
+    {
+      "epoch": 0.7872340425531915,
+      "grad_norm": 0.14500053226947784,
+      "learning_rate": 2.22e-06,
+      "loss": 1.2554,
+      "step": 74
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 0.10629269480705261,
+      "learning_rate": 2.25e-06,
+      "loss": 1.2917,
+      "step": 75
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.09674028307199478,
+      "learning_rate": 2.28e-06,
+      "loss": 1.2169,
+      "step": 76
+    },
+    {
+      "epoch": 0.8191489361702128,
+      "grad_norm": 0.11965947598218918,
+      "learning_rate": 2.31e-06,
+      "loss": 1.2445,
+      "step": 77
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 0.10441229492425919,
+      "learning_rate": 2.34e-06,
+      "loss": 1.2392,
+      "step": 78
+    },
+    {
+      "epoch": 0.8404255319148937,
+      "grad_norm": 0.13795869052410126,
+      "learning_rate": 2.37e-06,
+      "loss": 1.5335,
+      "step": 79
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.10789927840232849,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.2309,
+      "step": 80
+    },
+    {
+      "epoch": 0.8617021276595744,
+      "grad_norm": 0.10697130113840103,
+      "learning_rate": 2.43e-06,
+      "loss": 1.276,
+      "step": 81
+    },
+    {
+      "epoch": 0.8723404255319149,
+      "grad_norm": 0.11484125256538391,
+      "learning_rate": 2.4599999999999997e-06,
+      "loss": 1.2163,
+      "step": 82
+    },
+    {
+      "epoch": 0.8829787234042553,
+      "grad_norm": 0.09692610800266266,
+      "learning_rate": 2.49e-06,
+      "loss": 1.1554,
+      "step": 83
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.10697747021913528,
+      "learning_rate": 2.52e-06,
+      "loss": 1.211,
+      "step": 84
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 0.10578318685293198,
+      "learning_rate": 2.55e-06,
+      "loss": 1.2634,
+      "step": 85
+    },
+    {
+      "epoch": 0.9148936170212766,
+      "grad_norm": 0.10587752610445023,
+      "learning_rate": 2.58e-06,
+      "loss": 1.369,
+      "step": 86
+    },
+    {
+      "epoch": 0.925531914893617,
+      "grad_norm": 0.11430489271879196,
+      "learning_rate": 2.61e-06,
+      "loss": 1.3048,
+      "step": 87
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.11116154491901398,
+      "learning_rate": 2.64e-06,
+      "loss": 1.1883,
+      "step": 88
+    },
+    {
+      "epoch": 0.9468085106382979,
+      "grad_norm": 0.12686476111412048,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 1.2605,
+      "step": 89
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.10976041853427887,
+      "learning_rate": 2.7e-06,
+      "loss": 1.2345,
+      "step": 90
+    },
+    {
+      "epoch": 0.9680851063829787,
+      "grad_norm": 0.12391550838947296,
+      "learning_rate": 2.73e-06,
+      "loss": 1.2233,
+      "step": 91
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.1277073174715042,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 1.2437,
+      "step": 92
+    },
+    {
+      "epoch": 0.9893617021276596,
+      "grad_norm": 0.10421616584062576,
+      "learning_rate": 2.7900000000000004e-06,
+      "loss": 1.1432,
+      "step": 93
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12696842849254608,
+      "learning_rate": 2.82e-06,
+      "loss": 1.3558,
+      "step": 94
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.10387945920228958,
+      "learning_rate": 2.85e-06,
+      "loss": 1.1902,
+      "step": 95
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.14543002843856812,
+      "learning_rate": 2.88e-06,
+      "loss": 1.244,
+      "step": 96
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "eval_loss": 1.5803985595703125,
+      "eval_runtime": 3.0087,
+      "eval_samples_per_second": 34.899,
+      "eval_steps_per_second": 17.616,
+      "step": 96
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.17504040896892548,
+      "learning_rate": 2.91e-06,
+      "loss": 1.3115,
+      "step": 97
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.14017756283283234,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 1.356,
+      "step": 98
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.11604318767786026,
+      "learning_rate": 2.97e-06,
+      "loss": 1.2806,
+      "step": 99
+    },
+    {
+      "epoch": 1.0319148936170213,
+      "grad_norm": 0.15116065740585327,
+      "learning_rate": 3e-06,
+      "loss": 1.3279,
+      "step": 100
+    },
+    {
+      "epoch": 1.0425531914893618,
+      "grad_norm": 0.10773392021656036,
+      "learning_rate": 2.9999028286680832e-06,
+      "loss": 1.3871,
+      "step": 101
+    },
+    {
+      "epoch": 1.053191489361702,
+      "grad_norm": 0.09363637119531631,
+      "learning_rate": 2.999611327262024e-06,
+      "loss": 1.1334,
+      "step": 102
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.09164439886808395,
+      "learning_rate": 2.999125533549261e-06,
+      "loss": 1.4026,
+      "step": 103
+    },
+    {
+      "epoch": 1.074468085106383,
+      "grad_norm": 0.12113964557647705,
+      "learning_rate": 2.9984455104700915e-06,
+      "loss": 1.2097,
+      "step": 104
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.10569895058870316,
+      "learning_rate": 2.9975713461295125e-06,
+      "loss": 1.3077,
+      "step": 105
+    },
+    {
+      "epoch": 1.0957446808510638,
+      "grad_norm": 0.11219862103462219,
+      "learning_rate": 2.996503153785809e-06,
+      "loss": 1.1923,
+      "step": 106
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.13474853336811066,
+      "learning_rate": 2.9952410718358777e-06,
+      "loss": 1.2729,
+      "step": 107
+    },
+    {
+      "epoch": 1.1170212765957448,
+      "grad_norm": 0.10451857000589371,
+      "learning_rate": 2.993785263797297e-06,
+      "loss": 1.2904,
+      "step": 108
+    },
+    {
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.12593719363212585,
+      "learning_rate": 2.9921359182871422e-06,
+      "loss": 1.4021,
+      "step": 109
+    },
+    {
+      "epoch": 1.1382978723404256,
+      "grad_norm": 0.12547315657138824,
+      "learning_rate": 2.990293248997547e-06,
+      "loss": 1.2093,
+      "step": 110
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.10086555033922195,
+      "learning_rate": 2.988257494668016e-06,
+      "loss": 1.3098,
+      "step": 111
+    },
+    {
+      "epoch": 1.1595744680851063,
+      "grad_norm": 0.10801573097705841,
+      "learning_rate": 2.9860289190544963e-06,
+      "loss": 1.2752,
+      "step": 112
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.11851054430007935,
+      "learning_rate": 2.9836078108952015e-06,
+      "loss": 1.3066,
+      "step": 113
+    },
+    {
+      "epoch": 1.1808510638297873,
+      "grad_norm": 0.1265188604593277,
+      "learning_rate": 2.9809944838732045e-06,
+      "loss": 1.1946,
+      "step": 114
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.10702725499868393,
+      "learning_rate": 2.9781892765757954e-06,
+      "loss": 1.2182,
+      "step": 115
+    },
+    {
+      "epoch": 1.202127659574468,
+      "grad_norm": 0.7757766842842102,
+      "learning_rate": 2.9751925524506135e-06,
+      "loss": 5.6082,
+      "step": 116
+    },
+    {
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.10182739049196243,
+      "learning_rate": 2.9720046997585577e-06,
+      "loss": 1.309,
+      "step": 117
+    },
+    {
+      "epoch": 1.2234042553191489,
+      "grad_norm": 0.14062073826789856,
+      "learning_rate": 2.9686261315234844e-06,
+      "loss": 1.3668,
+      "step": 118
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.1063840240240097,
+      "learning_rate": 2.965057285478694e-06,
+      "loss": 1.2247,
+      "step": 119
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "grad_norm": 0.10701325535774231,
+      "learning_rate": 2.961298624010219e-06,
+      "loss": 1.2499,
+      "step": 120
+    },
+    {
+      "epoch": 1.2446808510638299,
+      "eval_loss": 1.575344204902649,
+      "eval_runtime": 8.2617,
+      "eval_samples_per_second": 12.709,
+      "eval_steps_per_second": 6.415,
+      "step": 120
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.11413375288248062,
+      "learning_rate": 2.957350634096912e-06,
+      "loss": 1.3593,
+      "step": 121
+    },
+    {
+      "epoch": 1.2659574468085106,
+      "grad_norm": 0.10826950520277023,
+      "learning_rate": 2.9532138272473597e-06,
+      "loss": 1.232,
+      "step": 122
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.10749218612909317,
+      "learning_rate": 2.9488887394336023e-06,
+      "loss": 1.401,
+      "step": 123
+    },
+    {
+      "epoch": 1.2872340425531914,
+      "grad_norm": 0.1175396591424942,
+      "learning_rate": 2.944375931021699e-06,
+      "loss": 1.2867,
+      "step": 124
+    },
+    {
+      "epoch": 1.297872340425532,
+      "grad_norm": 0.10688498616218567,
+      "learning_rate": 2.9396759866991214e-06,
+      "loss": 1.3689,
+      "step": 125
+    },
+    {
+      "epoch": 1.3085106382978724,
+      "grad_norm": 0.11630786955356598,
+      "learning_rate": 2.934789515399002e-06,
+      "loss": 1.2328,
+      "step": 126
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.11495409905910492,
+      "learning_rate": 2.9297171502212414e-06,
+      "loss": 1.1738,
+      "step": 127
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.10823408514261246,
+      "learning_rate": 2.924459548350479e-06,
+      "loss": 1.2318,
+      "step": 128
+    },
+    {
+      "epoch": 1.3404255319148937,
+      "grad_norm": 0.10759969800710678,
+      "learning_rate": 2.9190173909709506e-06,
+      "loss": 1.319,
+      "step": 129
+    },
+    {
+      "epoch": 1.351063829787234,
+      "grad_norm": 0.12790299952030182,
+      "learning_rate": 2.9133913831782307e-06,
+      "loss": 1.4282,
+      "step": 130
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.10899878293275833,
+      "learning_rate": 2.9075822538878805e-06,
+      "loss": 1.2455,
+      "step": 131
+    },
+    {
+      "epoch": 1.372340425531915,
+      "grad_norm": 0.12732432782649994,
+      "learning_rate": 2.9015907557410068e-06,
+      "loss": 1.2227,
+      "step": 132
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.10140018165111542,
+      "learning_rate": 2.8954176650067494e-06,
+      "loss": 1.0596,
+      "step": 133
+    },
+    {
+      "epoch": 1.3936170212765957,
+      "grad_norm": 0.12063546478748322,
+      "learning_rate": 2.889063781481708e-06,
+      "loss": 1.3321,
+      "step": 134
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.11323118209838867,
+      "learning_rate": 2.8825299283863144e-06,
+      "loss": 1.3366,
+      "step": 135
+    },
+    {
+      "epoch": 1.4148936170212765,
+      "grad_norm": 0.12391477078199387,
+      "learning_rate": 2.8758169522581796e-06,
+      "loss": 1.2917,
+      "step": 136
+    },
+    {
+      "epoch": 1.425531914893617,
+      "grad_norm": 0.12329094856977463,
+      "learning_rate": 2.8689257228424125e-06,
+      "loss": 1.1365,
+      "step": 137
+    },
+    {
+      "epoch": 1.4361702127659575,
+      "grad_norm": 0.11298198997974396,
+      "learning_rate": 2.8618571329789333e-06,
+      "loss": 1.4996,
+      "step": 138
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.10263165086507797,
+      "learning_rate": 2.8546120984867994e-06,
+      "loss": 1.199,
+      "step": 139
+    },
+    {
+      "epoch": 1.4574468085106382,
+      "grad_norm": 0.13330323994159698,
+      "learning_rate": 2.8471915580455442e-06,
+      "loss": 1.3746,
+      "step": 140
+    },
+    {
+      "epoch": 1.4680851063829787,
+      "grad_norm": 0.10694881528615952,
+      "learning_rate": 2.8395964730735666e-06,
+      "loss": 1.3798,
+      "step": 141
+    },
+    {
+      "epoch": 1.4787234042553192,
+      "grad_norm": 0.10929003357887268,
+      "learning_rate": 2.8318278276035626e-06,
+      "loss": 1.2918,
+      "step": 142
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.10969982296228409,
+      "learning_rate": 2.8238866281550366e-06,
+      "loss": 1.0444,
+      "step": 143
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10668367147445679,
+      "learning_rate": 2.815773903603892e-06,
+      "loss": 1.1656,
+      "step": 144
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.5705612897872925,
+      "eval_runtime": 5.6853,
+      "eval_samples_per_second": 18.469,
+      "eval_steps_per_second": 9.322,
+      "step": 144
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.12057002633810043,
+      "learning_rate": 2.807490705049127e-06,
+      "loss": 1.2475,
+      "step": 145
+    },
+    {
+      "epoch": 1.521276595744681,
+      "grad_norm": 0.10394139587879181,
+      "learning_rate": 2.7990381056766585e-06,
+      "loss": 1.3376,
+      "step": 146
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.12907464802265167,
+      "learning_rate": 2.7904172006202705e-06,
+      "loss": 1.3509,
+      "step": 147
+    },
+    {
+      "epoch": 1.5425531914893615,
+      "grad_norm": 0.1252606213092804,
+      "learning_rate": 2.7816291068197328e-06,
+      "loss": 1.1744,
+      "step": 148
+    },
+    {
+      "epoch": 1.5531914893617023,
+      "grad_norm": 0.1514441967010498,
+      "learning_rate": 2.772674962876085e-06,
+      "loss": 1.9324,
+      "step": 149
+    },
+    {
+      "epoch": 1.5638297872340425,
+      "grad_norm": 0.12377320230007172,
+      "learning_rate": 2.7635559289041174e-06,
+      "loss": 1.4511,
+      "step": 150
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.10629550367593765,
+      "learning_rate": 2.7542731863820665e-06,
+      "loss": 1.257,
+      "step": 151
+    },
+    {
+      "epoch": 1.5851063829787235,
+      "grad_norm": 0.10322704166173935,
+      "learning_rate": 2.744827937998538e-06,
+      "loss": 1.1796,
+      "step": 152
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.12690168619155884,
+      "learning_rate": 2.735221407496686e-06,
+      "loss": 1.3325,
+      "step": 153
+    },
+    {
+      "epoch": 1.6063829787234043,
+      "grad_norm": 0.0982392430305481,
+      "learning_rate": 2.725454839515663e-06,
+      "loss": 1.2169,
+      "step": 154
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.11184275150299072,
+      "learning_rate": 2.7155294994293606e-06,
+      "loss": 1.295,
+      "step": 155
+    },
+    {
+      "epoch": 1.627659574468085,
+      "grad_norm": 0.10721098631620407,
+      "learning_rate": 2.7054466731824676e-06,
+      "loss": 1.1945,
+      "step": 156
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.1254221498966217,
+      "learning_rate": 2.695207667123857e-06,
+      "loss": 1.2693,
+      "step": 157
+    },
+    {
+      "epoch": 1.648936170212766,
+      "grad_norm": 0.1157686784863472,
+      "learning_rate": 2.684813807837338e-06,
+      "loss": 1.1992,
+      "step": 158
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.10201229155063629,
+      "learning_rate": 2.674266441969778e-06,
+      "loss": 1.2401,
+      "step": 159
+    },
+    {
+      "epoch": 1.6702127659574468,
+      "grad_norm": 0.10953360050916672,
+      "learning_rate": 2.6635669360566298e-06,
+      "loss": 1.1627,
+      "step": 160
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.1248813271522522,
+      "learning_rate": 2.652716676344881e-06,
+      "loss": 1.3179,
+      "step": 161
+    },
+    {
+      "epoch": 1.6914893617021276,
+      "grad_norm": 0.09584470838308334,
+      "learning_rate": 2.6417170686134472e-06,
+      "loss": 1.2128,
+      "step": 162
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.12864486873149872,
+      "learning_rate": 2.630569537991042e-06,
+      "loss": 1.1889,
+      "step": 163
+    },
+    {
+      "epoch": 1.7127659574468086,
+      "grad_norm": 0.11820186674594879,
+      "learning_rate": 2.6192755287715282e-06,
+      "loss": 1.2848,
+      "step": 164
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.13811764121055603,
+      "learning_rate": 2.6078365042267987e-06,
+      "loss": 1.2091,
+      "step": 165
+    },
+    {
+      "epoch": 1.7340425531914894,
+      "grad_norm": 0.12099539488554001,
+      "learning_rate": 2.5962539464171862e-06,
+      "loss": 1.2853,
+      "step": 166
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.14544783532619476,
+      "learning_rate": 2.5845293559994513e-06,
+      "loss": 1.1574,
+      "step": 167
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "grad_norm": 0.11159494519233704,
+      "learning_rate": 2.5726642520323493e-06,
+      "loss": 1.1928,
+      "step": 168
+    },
+    {
+      "epoch": 1.7553191489361701,
+      "eval_loss": 1.5656005144119263,
+      "eval_runtime": 3.0568,
+      "eval_samples_per_second": 34.349,
+      "eval_steps_per_second": 17.338,
+      "step": 168
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.1385321319103241,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 1.365,
+      "step": 169
+    },
+    {
+      "epoch": 1.7765957446808511,
+      "grad_norm": 0.12905962765216827,
+      "learning_rate": 2.548518670511823e-06,
+      "loss": 1.3664,
+      "step": 170
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.09589093923568726,
+      "learning_rate": 2.536241321302821e-06,
+      "loss": 1.1508,
+      "step": 171
+    },
+    {
+      "epoch": 1.797872340425532,
+      "grad_norm": 0.12533985078334808,
+      "learning_rate": 2.5238297148279814e-06,
+      "loss": 1.2892,
+      "step": 172
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.11337278038263321,
+      "learning_rate": 2.5112854591570804e-06,
+      "loss": 1.2772,
+      "step": 173
+    },
+    {
+      "epoch": 1.8191489361702127,
+      "grad_norm": 0.1345362514257431,
+      "learning_rate": 2.4986101795461608e-06,
+      "loss": 1.3583,
+      "step": 174
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.121876560151577,
+      "learning_rate": 2.485805518226959e-06,
+      "loss": 1.2065,
+      "step": 175
+    },
+    {
+      "epoch": 1.8404255319148937,
+      "grad_norm": 0.10669907927513123,
+      "learning_rate": 2.4728731341941343e-06,
+      "loss": 1.2339,
+      "step": 176
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.12710174918174744,
+      "learning_rate": 2.4598147029903284e-06,
+      "loss": 1.4597,
+      "step": 177
+    },
+    {
+      "epoch": 1.8617021276595744,
+      "grad_norm": 0.11735282093286514,
+      "learning_rate": 2.4466319164890795e-06,
+      "loss": 1.2273,
+      "step": 178
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.12083889544010162,
+      "learning_rate": 2.4333264826756165e-06,
+      "loss": 1.3051,
+      "step": 179
+    },
+    {
+      "epoch": 1.8829787234042552,
+      "grad_norm": 0.10338792204856873,
+      "learning_rate": 2.4199001254255746e-06,
+      "loss": 1.3827,
+      "step": 180
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.10191334784030914,
+      "learning_rate": 2.406354584281642e-06,
+      "loss": 1.4067,
+      "step": 181
+    },
+    {
+      "epoch": 1.9042553191489362,
+      "grad_norm": 0.10776273161172867,
+      "learning_rate": 2.3926916142281846e-06,
+      "loss": 1.2344,
+      "step": 182
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.1253603845834732,
+      "learning_rate": 2.378912985463867e-06,
+      "loss": 1.2179,
+      "step": 183
+    },
+    {
+      "epoch": 1.925531914893617,
+      "grad_norm": 0.09942696243524551,
+      "learning_rate": 2.365020483172301e-06,
+      "loss": 1.0613,
+      "step": 184
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.10441701859235764,
+      "learning_rate": 2.351015907290755e-06,
+      "loss": 1.3886,
+      "step": 185
+    },
+    {
+      "epoch": 1.9468085106382977,
+      "grad_norm": 0.10571073740720749,
+      "learning_rate": 2.3369010722769502e-06,
+      "loss": 1.2023,
+      "step": 186
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.12477201223373413,
+      "learning_rate": 2.3226778068739783e-06,
+      "loss": 1.361,
+      "step": 187
+    },
+    {
+      "epoch": 1.9680851063829787,
+      "grad_norm": 0.12106247246265411,
+      "learning_rate": 2.3083479538733636e-06,
+      "loss": 1.4153,
+      "step": 188
+    },
+    {
+      "epoch": 1.978723404255319,
+      "grad_norm": 0.17261436581611633,
+      "learning_rate": 2.2939133698763084e-06,
+      "loss": 1.45,
+      "step": 189
+    },
+    {
+      "epoch": 1.9893617021276597,
+      "grad_norm": 0.12172568589448929,
+      "learning_rate": 2.2793759250531504e-06,
+      "loss": 1.1764,
+      "step": 190
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11111535131931305,
+      "learning_rate": 2.2647375029010575e-06,
+      "loss": 1.1347,
+      "step": 191
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "grad_norm": 0.10596352070569992,
+      "learning_rate": 2.25e-06,
+      "loss": 1.1623,
+      "step": 192
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "eval_loss": 1.560809850692749,
+      "eval_runtime": 4.8693,
+      "eval_samples_per_second": 21.564,
+      "eval_steps_per_second": 10.885,
+      "step": 192
+    },
+    {
+      "epoch": 2.0212765957446805,
+      "grad_norm": 0.08630727976560593,
+      "learning_rate": 2.235165325767026e-06,
+      "loss": 1.1733,
+      "step": 193
+    },
+    {
+      "epoch": 2.0319148936170213,
+      "grad_norm": 0.3629175126552582,
+      "learning_rate": 2.2202354022088735e-06,
+      "loss": 1.1114,
+      "step": 194
+    },
+    {
+      "epoch": 2.0106382978723403,
+      "grad_norm": 0.12061420828104019,
+      "learning_rate": 2.2052121636729527e-06,
+      "loss": 1.1813,
+      "step": 195
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.12194402515888214,
+      "learning_rate": 2.1900975565967284e-06,
+      "loss": 1.4466,
+      "step": 196
+    },
+    {
+      "epoch": 2.0319148936170213,
+      "grad_norm": 0.09581239521503448,
+      "learning_rate": 2.1748935392555347e-06,
+      "loss": 1.1863,
+      "step": 197
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.12056192755699158,
+      "learning_rate": 2.1596020815088587e-06,
+      "loss": 1.5781,
+      "step": 198
+    },
+    {
+      "epoch": 2.0531914893617023,
+      "grad_norm": 0.10989479720592499,
+      "learning_rate": 2.1442251645451233e-06,
+      "loss": 1.2638,
+      "step": 199
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 0.1273481398820877,
+      "learning_rate": 2.1287647806249964e-06,
+      "loss": 1.1346,
+      "step": 200
+    },
+    {
+      "epoch": 2.074468085106383,
+      "grad_norm": 0.11547158658504486,
+      "learning_rate": 2.1132229328232755e-06,
+      "loss": 1.124,
+      "step": 201
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.12033279985189438,
+      "learning_rate": 2.0976016347693624e-06,
+      "loss": 1.2695,
+      "step": 202
+    },
+    {
+      "epoch": 2.095744680851064,
+      "grad_norm": 0.11929858475923538,
+      "learning_rate": 2.0819029103863746e-06,
+      "loss": 1.1885,
+      "step": 203
+    },
+    {
+      "epoch": 2.106382978723404,
+      "grad_norm": 0.10733456164598465,
+      "learning_rate": 2.0661287936289213e-06,
+      "loss": 1.3742,
+      "step": 204
+    },
+    {
+      "epoch": 2.117021276595745,
+      "grad_norm": 0.12037491053342819,
+      "learning_rate": 2.050281328219585e-06,
+      "loss": 1.1911,
+      "step": 205
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.12621213495731354,
+      "learning_rate": 2.0343625673841254e-06,
+      "loss": 1.1241,
+      "step": 206
+    },
+    {
+      "epoch": 2.1382978723404253,
+      "grad_norm": 0.15265725553035736,
+      "learning_rate": 2.018374573585467e-06,
+      "loss": 1.4419,
+      "step": 207
+    },
+    {
+      "epoch": 2.148936170212766,
+      "grad_norm": 0.10528834164142609,
+      "learning_rate": 2.0023194182564793e-06,
+      "loss": 1.2211,
+      "step": 208
+    },
+    {
+      "epoch": 2.1595744680851063,
+      "grad_norm": 0.11791864037513733,
+      "learning_rate": 1.986199181531599e-06,
+      "loss": 1.2159,
+      "step": 209
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "grad_norm": 0.1230137050151825,
+      "learning_rate": 1.9700159519773233e-06,
+      "loss": 1.2687,
+      "step": 210
+    },
+    {
+      "epoch": 2.1808510638297873,
+      "grad_norm": 0.11243241280317307,
+      "learning_rate": 1.9537718263216137e-06,
+      "loss": 1.2008,
+      "step": 211
+    },
+    {
+      "epoch": 2.1914893617021276,
+      "grad_norm": 0.13040384650230408,
+      "learning_rate": 1.9374689091822377e-06,
+      "loss": 1.2937,
+      "step": 212
+    },
+    {
+      "epoch": 2.202127659574468,
+      "grad_norm": 0.096621572971344,
+      "learning_rate": 1.9211093127940917e-06,
+      "loss": 1.1315,
+      "step": 213
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 0.10366329550743103,
+      "learning_rate": 1.9046951567355363e-06,
+      "loss": 1.1998,
+      "step": 214
+    },
+    {
+      "epoch": 2.223404255319149,
+      "grad_norm": 0.13266436755657196,
+      "learning_rate": 1.888228567653781e-06,
+      "loss": 1.2169,
+      "step": 215
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "grad_norm": 0.12041480094194412,
+      "learning_rate": 1.87171167898935e-06,
+      "loss": 1.2679,
+      "step": 216
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "eval_loss": 1.557094931602478,
+      "eval_runtime": 3.8276,
+      "eval_samples_per_second": 27.432,
+      "eval_steps_per_second": 13.847,
+      "step": 216
+    },
+    {
+      "epoch": 2.24468085106383,
+      "grad_norm": 0.11926256865262985,
+      "learning_rate": 1.8551466306996702e-06,
+      "loss": 1.2496,
+      "step": 217
+    },
+    {
+      "epoch": 2.25531914893617,
+      "grad_norm": 0.11768142879009247,
+      "learning_rate": 1.838535568981816e-06,
+      "loss": 1.2793,
+      "step": 218
+    },
+    {
+      "epoch": 2.2659574468085104,
+      "grad_norm": 0.09850093722343445,
+      "learning_rate": 1.821880645994443e-06,
+      "loss": 1.1712,
+      "step": 219
+    },
+    {
+      "epoch": 2.276595744680851,
+      "grad_norm": 0.11399635672569275,
+      "learning_rate": 1.8051840195789509e-06,
+      "loss": 1.3151,
+      "step": 220
+    },
+    {
+      "epoch": 2.2872340425531914,
+      "grad_norm": 0.10654745250940323,
+      "learning_rate": 1.788447852979909e-06,
+      "loss": 1.1726,
+      "step": 221
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 0.12983720004558563,
+      "learning_rate": 1.7716743145647837e-06,
+      "loss": 1.2158,
+      "step": 222
+    },
+    {
+      "epoch": 2.3085106382978724,
+      "grad_norm": 0.08331640809774399,
+      "learning_rate": 1.754865577543e-06,
+      "loss": 0.8472,
+      "step": 223
+    },
+    {
+      "epoch": 2.3191489361702127,
+      "grad_norm": 0.11662207543849945,
+      "learning_rate": 1.738023819684377e-06,
+      "loss": 1.2938,
+      "step": 224
+    },
+    {
+      "epoch": 2.329787234042553,
+      "grad_norm": 0.13265132904052734,
+      "learning_rate": 1.7211512230369716e-06,
+      "loss": 1.3288,
+      "step": 225
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.10342156141996384,
+      "learning_rate": 1.7042499736443702e-06,
+      "loss": 1.2352,
+      "step": 226
+    },
+    {
+      "epoch": 2.351063829787234,
+      "grad_norm": 0.10495639592409134,
+      "learning_rate": 1.6873222612624575e-06,
+      "loss": 1.1748,
+      "step": 227
+    },
+    {
+      "epoch": 2.3617021276595747,
+      "grad_norm": 0.1564377248287201,
+      "learning_rate": 1.6703702790757123e-06,
+      "loss": 1.4071,
+      "step": 228
+    },
+    {
+      "epoch": 2.372340425531915,
+      "grad_norm": 0.11000990867614746,
+      "learning_rate": 1.6533962234130513e-06,
+      "loss": 1.2102,
+      "step": 229
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.12565018236637115,
+      "learning_rate": 1.6364022934632706e-06,
+      "loss": 1.4047,
+      "step": 230
+    },
+    {
+      "epoch": 2.393617021276596,
+      "grad_norm": 0.11519981920719147,
+      "learning_rate": 1.6193906909901133e-06,
+      "loss": 1.3905,
+      "step": 231
+    },
+    {
+      "epoch": 2.404255319148936,
+      "grad_norm": 0.12704767286777496,
+      "learning_rate": 1.6023636200470066e-06,
+      "loss": 1.0632,
+      "step": 232
+    },
+    {
+      "epoch": 2.4148936170212765,
+      "grad_norm": 0.11226076632738113,
+      "learning_rate": 1.5853232866915004e-06,
+      "loss": 1.2448,
+      "step": 233
+    },
+    {
+      "epoch": 2.425531914893617,
+      "grad_norm": 0.11282170563936234,
+      "learning_rate": 1.5682718986994457e-06,
+      "loss": 1.5068,
+      "step": 234
+    },
+    {
+      "epoch": 2.4361702127659575,
+      "grad_norm": 0.09763903170824051,
+      "learning_rate": 1.5512116652789518e-06,
+      "loss": 1.2398,
+      "step": 235
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 0.11640322953462601,
+      "learning_rate": 1.5341447967841585e-06,
+      "loss": 1.3176,
+      "step": 236
+    },
+    {
+      "epoch": 2.4574468085106385,
+      "grad_norm": 0.12292848527431488,
+      "learning_rate": 1.5170735044288565e-06,
+      "loss": 1.8823,
+      "step": 237
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 0.12308197468519211,
+      "learning_rate": 1.5e-06,
+      "loss": 1.14,
+      "step": 238
+    },
+    {
+      "epoch": 2.478723404255319,
+      "grad_norm": 0.11871509999036789,
+      "learning_rate": 1.4829264955711436e-06,
+      "loss": 1.2753,
+      "step": 239
+    },
+    {
+      "epoch": 2.4893617021276597,
+      "grad_norm": 0.14034831523895264,
+      "learning_rate": 1.4658552032158414e-06,
+      "loss": 1.2845,
+      "step": 240
+    },
+    {
+      "epoch": 2.4893617021276597,
+      "eval_loss": 1.5537203550338745,
+      "eval_runtime": 5.1489,
+      "eval_samples_per_second": 20.393,
+      "eval_steps_per_second": 10.294,
+      "step": 240
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12317660450935364,
+      "learning_rate": 1.4487883347210483e-06,
+      "loss": 1.2742,
+      "step": 241
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 0.11180029809474945,
+      "learning_rate": 1.431728101300555e-06,
+      "loss": 1.3743,
+      "step": 242
+    },
+    {
+      "epoch": 2.521276595744681,
+      "grad_norm": 0.12544095516204834,
+      "learning_rate": 1.4146767133085e-06,
+      "loss": 1.2935,
+      "step": 243
+    },
+    {
+      "epoch": 2.5319148936170213,
+      "grad_norm": 0.12283220142126083,
+      "learning_rate": 1.3976363799529937e-06,
+      "loss": 1.2529,
+      "step": 244
+    },
+    {
+      "epoch": 2.5425531914893615,
+      "grad_norm": 0.1375051885843277,
+      "learning_rate": 1.3806093090098872e-06,
+      "loss": 1.2907,
+      "step": 245
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.10762558877468109,
+      "learning_rate": 1.3635977065367295e-06,
+      "loss": 1.1548,
+      "step": 246
+    },
+    {
+      "epoch": 2.5638297872340425,
+      "grad_norm": 0.12075044959783554,
+      "learning_rate": 1.3466037765869486e-06,
+      "loss": 1.2208,
+      "step": 247
+    },
+    {
+      "epoch": 2.574468085106383,
+      "grad_norm": 0.11484728753566742,
+      "learning_rate": 1.3296297209242874e-06,
+      "loss": 1.1182,
+      "step": 248
+    },
+    {
+      "epoch": 2.5851063829787235,
+      "grad_norm": 0.11546777188777924,
+      "learning_rate": 1.312677738737543e-06,
+      "loss": 1.4478,
+      "step": 249
+    },
+    {
+      "epoch": 2.595744680851064,
+      "grad_norm": 0.12128724902868271,
+      "learning_rate": 1.2957500263556303e-06,
+      "loss": 1.3132,
+      "step": 250
+    },
+    {
+      "epoch": 2.6063829787234045,
+      "grad_norm": 0.09233469516038895,
+      "learning_rate": 1.2788487769630284e-06,
+      "loss": 1.0863,
+      "step": 251
+    },
+    {
+      "epoch": 2.617021276595745,
+      "grad_norm": 0.12085112929344177,
+      "learning_rate": 1.261976180315623e-06,
+      "loss": 1.2855,
+      "step": 252
+    },
+    {
+      "epoch": 2.627659574468085,
+      "grad_norm": 0.12655006349086761,
+      "learning_rate": 1.2451344224570002e-06,
+      "loss": 1.2691,
+      "step": 253
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 0.12646865844726562,
+      "learning_rate": 1.2283256854352162e-06,
+      "loss": 1.2194,
+      "step": 254
+    },
+    {
+      "epoch": 2.648936170212766,
+      "grad_norm": 0.1081186905503273,
+      "learning_rate": 1.2115521470200911e-06,
+      "loss": 1.2551,
+      "step": 255
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.12278001755475998,
+      "learning_rate": 1.1948159804210496e-06,
+      "loss": 1.3049,
+      "step": 256
+    },
+    {
+      "epoch": 2.670212765957447,
+      "grad_norm": 0.09346724301576614,
+      "learning_rate": 1.1781193540055573e-06,
+      "loss": 1.1507,
+      "step": 257
+    },
+    {
+      "epoch": 2.6808510638297873,
+      "grad_norm": 0.10679617524147034,
+      "learning_rate": 1.1614644310181842e-06,
+      "loss": 1.2971,
+      "step": 258
+    },
+    {
+      "epoch": 2.6914893617021276,
+      "grad_norm": 0.11394444108009338,
+      "learning_rate": 1.14485336930033e-06,
+      "loss": 1.2133,
+      "step": 259
+    },
+    {
+      "epoch": 2.702127659574468,
+      "grad_norm": 0.1416221708059311,
+      "learning_rate": 1.1282883210106503e-06,
+      "loss": 1.2132,
+      "step": 260
+    },
+    {
+      "epoch": 2.7127659574468086,
+      "grad_norm": 0.09133229404687881,
+      "learning_rate": 1.1117714323462188e-06,
+      "loss": 1.17,
+      "step": 261
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 0.10997346043586731,
+      "learning_rate": 1.0953048432644634e-06,
+      "loss": 1.1443,
+      "step": 262
+    },
+    {
+      "epoch": 2.7340425531914896,
+      "grad_norm": 0.11233331263065338,
+      "learning_rate": 1.0788906872059088e-06,
+      "loss": 1.3383,
+      "step": 263
+    },
+    {
+      "epoch": 2.74468085106383,
+      "grad_norm": 0.11798594146966934,
+      "learning_rate": 1.0625310908177626e-06,
+      "loss": 1.1226,
+      "step": 264
+    },
+    {
+      "epoch": 2.74468085106383,
+      "eval_loss": 1.5516207218170166,
+      "eval_runtime": 4.7557,
+      "eval_samples_per_second": 22.079,
+      "eval_steps_per_second": 11.145,
+      "step": 264
+    },
+    {
+      "epoch": 2.75531914893617,
+      "grad_norm": 0.12637464702129364,
+      "learning_rate": 1.0462281736783864e-06,
+      "loss": 1.4182,
+      "step": 265
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.11374552547931671,
+      "learning_rate": 1.0299840480226768e-06,
+      "loss": 1.2926,
+      "step": 266
+    },
+    {
+      "epoch": 2.776595744680851,
+      "grad_norm": 0.13765357434749603,
+      "learning_rate": 1.0138008184684011e-06,
+      "loss": 1.3036,
+      "step": 267
+    },
+    {
+      "epoch": 2.7872340425531914,
+      "grad_norm": 0.1168639063835144,
+      "learning_rate": 9.976805817435208e-07,
+      "loss": 1.2854,
+      "step": 268
+    },
+    {
+      "epoch": 2.797872340425532,
+      "grad_norm": 0.11609431356191635,
+      "learning_rate": 9.816254264145328e-07,
+      "loss": 1.2832,
+      "step": 269
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 0.11090860515832901,
+      "learning_rate": 9.656374326158753e-07,
+      "loss": 1.4098,
+      "step": 270
+    },
+    {
+      "epoch": 2.8191489361702127,
+      "grad_norm": 0.12376827001571655,
+      "learning_rate": 9.497186717804155e-07,
+      "loss": 1.2335,
+      "step": 271
+    },
+    {
+      "epoch": 2.829787234042553,
+      "grad_norm": 0.11905582994222641,
+      "learning_rate": 9.338712063710786e-07,
+      "loss": 1.1991,
+      "step": 272
+    },
+    {
+      "epoch": 2.8404255319148937,
+      "grad_norm": 0.09383586794137955,
+      "learning_rate": 9.180970896136258e-07,
+      "loss": 1.1715,
+      "step": 273
+    },
+    {
+      "epoch": 2.851063829787234,
+      "grad_norm": 0.14080052077770233,
+      "learning_rate": 9.023983652306379e-07,
+      "loss": 1.3227,
+      "step": 274
+    },
+    {
+      "epoch": 2.8617021276595747,
+      "grad_norm": 0.10943106561899185,
+      "learning_rate": 8.867770671767246e-07,
+      "loss": 0.9774,
+      "step": 275
+    },
+    {
+      "epoch": 2.872340425531915,
+      "grad_norm": 0.093683160841465,
+      "learning_rate": 8.712352193750043e-07,
+      "loss": 1.053,
+      "step": 276
+    },
+    {
+      "epoch": 2.882978723404255,
+      "grad_norm": 0.1352389007806778,
+      "learning_rate": 8.557748354548773e-07,
+      "loss": 1.2713,
+      "step": 277
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 0.09906943887472153,
+      "learning_rate": 8.403979184911411e-07,
+      "loss": 1.3128,
+      "step": 278
+    },
+    {
+      "epoch": 2.904255319148936,
+      "grad_norm": 0.13467717170715332,
+      "learning_rate": 8.251064607444658e-07,
+      "loss": 1.4274,
+      "step": 279
+    },
+    {
+      "epoch": 2.9148936170212765,
+      "grad_norm": 0.11490917205810547,
+      "learning_rate": 8.099024434032718e-07,
+      "loss": 1.307,
+      "step": 280
+    },
+    {
+      "epoch": 2.925531914893617,
+      "grad_norm": 0.10982628166675568,
+      "learning_rate": 7.947878363270472e-07,
+      "loss": 1.0661,
+      "step": 281
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": 0.13426214456558228,
+      "learning_rate": 7.797645977911268e-07,
+      "loss": 1.3296,
+      "step": 282
+    },
+    {
+      "epoch": 2.9468085106382977,
+      "grad_norm": 0.5615570545196533,
+      "learning_rate": 7.648346742329746e-07,
+      "loss": 5.321,
+      "step": 283
+    },
+    {
+      "epoch": 2.9574468085106385,
+      "grad_norm": 0.12761859595775604,
+      "learning_rate": 7.500000000000003e-07,
+      "loss": 1.2247,
+      "step": 284
+    },
+    {
+      "epoch": 2.9680851063829787,
+      "grad_norm": 0.12587665021419525,
+      "learning_rate": 7.352624970989425e-07,
+      "loss": 1.2634,
+      "step": 285
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 0.09242536127567291,
+      "learning_rate": 7.2062407494685e-07,
+      "loss": 1.2181,
+      "step": 286
+    },
+    {
+      "epoch": 2.9893617021276597,
+      "grad_norm": 0.1055845320224762,
+      "learning_rate": 7.06086630123692e-07,
+      "loss": 1.3458,
+      "step": 287
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10968521237373352,
+      "learning_rate": 6.916520461266367e-07,
+      "loss": 1.2575,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5497299432754517,
+      "eval_runtime": 3.0359,
+      "eval_samples_per_second": 34.586,
+      "eval_steps_per_second": 17.458,
+      "step": 288
+    },
+    {
+      "epoch": 3.0106382978723403,
+      "grad_norm": 0.12890629470348358,
+      "learning_rate": 6.773221931260217e-07,
+      "loss": 1.2357,
+      "step": 289
+    },
+    {
+      "epoch": 3.0212765957446805,
+      "grad_norm": 0.11267005652189255,
+      "learning_rate": 6.630989277230501e-07,
+      "loss": 1.352,
+      "step": 290
+    },
+    {
+      "epoch": 3.0319148936170213,
+      "grad_norm": 0.16483013331890106,
+      "learning_rate": 6.489840927092458e-07,
+      "loss": 1.121,
+      "step": 291
+    },
+    {
+      "epoch": 3.0106382978723403,
+      "grad_norm": 0.11686303466558456,
+      "learning_rate": 6.349795168276994e-07,
+      "loss": 1.3244,
+      "step": 292
+    },
+    {
+      "epoch": 3.021276595744681,
+      "grad_norm": 0.11969567835330963,
+      "learning_rate": 6.210870145361331e-07,
+      "loss": 1.4993,
+      "step": 293
+    },
+    {
+      "epoch": 3.0319148936170213,
+      "grad_norm": 0.09593074023723602,
+      "learning_rate": 6.073083857718157e-07,
+      "loss": 1.1972,
+      "step": 294
+    },
+    {
+      "epoch": 3.0425531914893615,
+      "grad_norm": 0.1114688366651535,
+      "learning_rate": 5.936454157183583e-07,
+      "loss": 1.3017,
+      "step": 295
+    },
+    {
+      "epoch": 3.0531914893617023,
+      "grad_norm": 0.1574050486087799,
+      "learning_rate": 5.800998745744253e-07,
+      "loss": 1.131,
+      "step": 296
+    },
+    {
+      "epoch": 3.0638297872340425,
+      "grad_norm": 0.09848689287900925,
+      "learning_rate": 5.666735173243836e-07,
+      "loss": 1.2648,
+      "step": 297
+    },
+    {
+      "epoch": 3.074468085106383,
+      "grad_norm": 0.12783421576023102,
+      "learning_rate": 5.533680835109212e-07,
+      "loss": 1.3503,
+      "step": 298
+    },
+    {
+      "epoch": 3.0851063829787235,
+      "grad_norm": 0.16221453249454498,
+      "learning_rate": 5.401852970096719e-07,
+      "loss": 1.3837,
+      "step": 299
+    },
+    {
+      "epoch": 3.095744680851064,
+      "grad_norm": 0.13070747256278992,
+      "learning_rate": 5.27126865805866e-07,
+      "loss": 1.844,
+      "step": 300
+    },
+    {
+      "epoch": 3.106382978723404,
+      "grad_norm": 0.10077214986085892,
+      "learning_rate": 5.141944817730411e-07,
+      "loss": 1.1528,
+      "step": 301
+    },
+    {
+      "epoch": 3.117021276595745,
+      "grad_norm": 0.10629620403051376,
+      "learning_rate": 5.013898204538392e-07,
+      "loss": 1.3626,
+      "step": 302
+    },
+    {
+      "epoch": 3.127659574468085,
+      "grad_norm": 0.11176397651433945,
+      "learning_rate": 4.887145408429194e-07,
+      "loss": 1.401,
+      "step": 303
+    },
+    {
+      "epoch": 3.1382978723404253,
+      "grad_norm": 0.11966844648122787,
+      "learning_rate": 4.7617028517201914e-07,
+      "loss": 1.4937,
+      "step": 304
+    },
+    {
+      "epoch": 3.148936170212766,
+      "grad_norm": 0.09916877746582031,
+      "learning_rate": 4.6375867869717915e-07,
+      "loss": 1.1892,
+      "step": 305
+    },
+    {
+      "epoch": 3.1595744680851063,
+      "grad_norm": 0.14531613886356354,
+      "learning_rate": 4.514813294881772e-07,
+      "loss": 1.4487,
+      "step": 306
+    },
+    {
+      "epoch": 3.1702127659574466,
+      "grad_norm": 0.11752136796712875,
+      "learning_rate": 4.3933982822017883e-07,
+      "loss": 1.1079,
+      "step": 307
+    },
+    {
+      "epoch": 3.1808510638297873,
+      "grad_norm": 0.11633948236703873,
+      "learning_rate": 4.273357479676508e-07,
+      "loss": 1.2957,
+      "step": 308
+    },
+    {
+      "epoch": 3.1914893617021276,
+      "grad_norm": 0.10776685178279877,
+      "learning_rate": 4.154706440005491e-07,
+      "loss": 1.2521,
+      "step": 309
+    },
+    {
+      "epoch": 3.202127659574468,
+      "grad_norm": 0.10373863577842712,
+      "learning_rate": 4.037460535828138e-07,
+      "loss": 1.1982,
+      "step": 310
+    },
+    {
+      "epoch": 3.2127659574468086,
+      "grad_norm": 0.10363980382680893,
+      "learning_rate": 3.921634957732019e-07,
+      "loss": 1.2003,
+      "step": 311
+    },
+    {
+      "epoch": 3.223404255319149,
+      "grad_norm": 0.1123185008764267,
+      "learning_rate": 3.8072447122847184e-07,
+      "loss": 1.2465,
+      "step": 312
+    },
+    {
+      "epoch": 3.223404255319149,
+      "eval_loss": 1.548577070236206,
+      "eval_runtime": 3.0417,
+      "eval_samples_per_second": 34.52,
+      "eval_steps_per_second": 17.425,
+      "step": 312
+    },
+    {
+      "epoch": 3.2340425531914896,
+      "grad_norm": 0.0931960716843605,
+      "learning_rate": 3.694304620089587e-07,
+      "loss": 1.1363,
+      "step": 313
+    },
+    {
+      "epoch": 3.24468085106383,
+      "grad_norm": 0.09377090632915497,
+      "learning_rate": 3.5828293138655306e-07,
+      "loss": 1.2143,
+      "step": 314
+    },
+    {
+      "epoch": 3.25531914893617,
+      "grad_norm": 0.13445159792900085,
+      "learning_rate": 3.4728332365511953e-07,
+      "loss": 1.3706,
+      "step": 315
+    },
+    {
+      "epoch": 3.2659574468085104,
+      "grad_norm": 0.11298293620347977,
+      "learning_rate": 3.3643306394337013e-07,
+      "loss": 1.2664,
+      "step": 316
+    },
+    {
+      "epoch": 3.276595744680851,
+      "grad_norm": 0.10045924782752991,
+      "learning_rate": 3.2573355803022206e-07,
+      "loss": 1.2612,
+      "step": 317
+    },
+    {
+      "epoch": 3.2872340425531914,
+      "grad_norm": 0.13584546744823456,
+      "learning_rate": 3.151861921626624e-07,
+      "loss": 1.2384,
+      "step": 318
+    },
+    {
+      "epoch": 3.297872340425532,
+      "grad_norm": 0.11470676213502884,
+      "learning_rate": 3.0479233287614325e-07,
+      "loss": 1.2728,
+      "step": 319
+    },
+    {
+      "epoch": 3.3085106382978724,
+      "grad_norm": 0.12791061401367188,
+      "learning_rate": 2.9455332681753264e-07,
+      "loss": 1.2408,
+      "step": 320
+    },
+    {
+      "epoch": 3.3191489361702127,
+      "grad_norm": 0.1361236423254013,
+      "learning_rate": 2.844705005706394e-07,
+      "loss": 1.3287,
+      "step": 321
+    },
+    {
+      "epoch": 3.329787234042553,
+      "grad_norm": 0.11060075461864471,
+      "learning_rate": 2.7454516048433704e-07,
+      "loss": 1.4066,
+      "step": 322
+    },
+    {
+      "epoch": 3.3404255319148937,
+      "grad_norm": 0.12533032894134521,
+      "learning_rate": 2.64778592503314e-07,
+      "loss": 1.3182,
+      "step": 323
+    },
+    {
+      "epoch": 3.351063829787234,
+      "grad_norm": 0.10592247545719147,
+      "learning_rate": 2.5517206200146245e-07,
+      "loss": 1.137,
+      "step": 324
+    },
+    {
+      "epoch": 3.3617021276595747,
+      "grad_norm": 0.10802777856588364,
+      "learning_rate": 2.457268136179341e-07,
+      "loss": 1.1359,
+      "step": 325
+    },
+    {
+      "epoch": 3.372340425531915,
+      "grad_norm": 0.12638698518276215,
+      "learning_rate": 2.364440710958828e-07,
+      "loss": 1.1918,
+      "step": 326
+    },
+    {
+      "epoch": 3.382978723404255,
+      "grad_norm": 1.0334383249282837,
+      "learning_rate": 2.2732503712391524e-07,
+      "loss": 6.2297,
+      "step": 327
+    },
+    {
+      "epoch": 3.393617021276596,
+      "grad_norm": 0.13448600471019745,
+      "learning_rate": 2.1837089318026714e-07,
+      "loss": 1.3724,
+      "step": 328
+    },
+    {
+      "epoch": 3.404255319148936,
+      "grad_norm": 0.12653769552707672,
+      "learning_rate": 2.0958279937972978e-07,
+      "loss": 1.2918,
+      "step": 329
+    },
+    {
+      "epoch": 3.4148936170212765,
+      "grad_norm": 0.0998699963092804,
+      "learning_rate": 2.0096189432334195e-07,
+      "loss": 1.2476,
+      "step": 330
+    },
+    {
+      "epoch": 3.425531914893617,
+      "grad_norm": 0.12127155810594559,
+      "learning_rate": 1.9250929495087294e-07,
+      "loss": 1.4288,
+      "step": 331
+    },
+    {
+      "epoch": 3.4361702127659575,
+      "grad_norm": 0.1191040650010109,
+      "learning_rate": 1.842260963961086e-07,
+      "loss": 1.2145,
+      "step": 332
+    },
+    {
+      "epoch": 3.4468085106382977,
+      "grad_norm": 0.13884760439395905,
+      "learning_rate": 1.761133718449634e-07,
+      "loss": 1.2676,
+      "step": 333
+    },
+    {
+      "epoch": 3.4574468085106385,
+      "grad_norm": 0.13023029267787933,
+      "learning_rate": 1.6817217239643717e-07,
+      "loss": 1.326,
+      "step": 334
+    },
+    {
+      "epoch": 3.4680851063829787,
+      "grad_norm": 0.1026253029704094,
+      "learning_rate": 1.6040352692643356e-07,
+      "loss": 1.2225,
+      "step": 335
+    },
+    {
+      "epoch": 3.478723404255319,
+      "grad_norm": 0.11566822230815887,
+      "learning_rate": 1.5280844195445598e-07,
+      "loss": 1.1699,
+      "step": 336
+    },
+    {
+      "epoch": 3.478723404255319,
+      "eval_loss": 1.5482865571975708,
+      "eval_runtime": 8.2306,
+      "eval_samples_per_second": 12.757,
+      "eval_steps_per_second": 6.439,
+      "step": 336
+    },
+    {
+      "epoch": 3.4893617021276597,
+      "grad_norm": 0.11099603772163391,
+      "learning_rate": 1.4538790151320092e-07,
+      "loss": 1.1752,
+      "step": 337
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.10131604224443436,
+      "learning_rate": 1.3814286702106644e-07,
+      "loss": 1.2082,
+      "step": 338
+    },
+    {
+      "epoch": 3.5106382978723403,
+      "grad_norm": 0.1052994355559349,
+      "learning_rate": 1.3107427715758796e-07,
+      "loss": 1.1038,
+      "step": 339
+    },
+    {
+      "epoch": 3.521276595744681,
+      "grad_norm": 0.11623264849185944,
+      "learning_rate": 1.2418304774182077e-07,
+      "loss": 1.1679,
+      "step": 340
+    },
+    {
+      "epoch": 3.5319148936170213,
+      "grad_norm": 0.10955728590488434,
+      "learning_rate": 1.1747007161368584e-07,
+      "loss": 1.198,
+      "step": 341
+    },
+    {
+      "epoch": 3.5425531914893615,
+      "grad_norm": 0.13709692656993866,
+      "learning_rate": 1.1093621851829211e-07,
+      "loss": 1.3202,
+      "step": 342
+    },
+    {
+      "epoch": 3.5531914893617023,
+      "grad_norm": 0.1269705444574356,
+      "learning_rate": 1.0458233499325026e-07,
+      "loss": 1.1253,
+      "step": 343
+    },
+    {
+      "epoch": 3.5638297872340425,
+      "grad_norm": 0.12783360481262207,
+      "learning_rate": 9.840924425899344e-08,
+      "loss": 1.3489,
+      "step": 344
+    },
+    {
+      "epoch": 3.574468085106383,
+      "grad_norm": 0.1359439641237259,
+      "learning_rate": 9.241774611211979e-08,
+      "loss": 1.3248,
+      "step": 345
+    },
+    {
+      "epoch": 3.5851063829787235,
+      "grad_norm": 0.13286209106445312,
+      "learning_rate": 8.660861682176941e-08,
+      "loss": 1.0637,
+      "step": 346
+    },
+    {
+      "epoch": 3.595744680851064,
+      "grad_norm": 0.13463550806045532,
+      "learning_rate": 8.098260902904942e-08,
+      "loss": 1.4834,
+      "step": 347
+    },
+    {
+      "epoch": 3.6063829787234045,
+      "grad_norm": 0.11620105803012848,
+      "learning_rate": 7.554045164952123e-08,
+      "loss": 1.1721,
+      "step": 348
+    },
+    {
+      "epoch": 3.617021276595745,
+      "grad_norm": 0.11728944629430771,
+      "learning_rate": 7.028284977875876e-08,
+      "loss": 1.0798,
+      "step": 349
+    },
+    {
+      "epoch": 3.627659574468085,
+      "grad_norm": 0.10178694874048233,
+      "learning_rate": 6.521048460099788e-08,
+      "loss": 1.1834,
+      "step": 350
+    },
+    {
+      "epoch": 3.6382978723404253,
+      "grad_norm": 0.12597782909870148,
+      "learning_rate": 6.032401330087894e-08,
+      "loss": 1.1844,
+      "step": 351
+    },
+    {
+      "epoch": 3.648936170212766,
+      "grad_norm": 0.12270310521125793,
+      "learning_rate": 5.56240689783013e-08,
+      "loss": 1.2313,
+      "step": 352
+    },
+    {
+      "epoch": 3.6595744680851063,
+      "grad_norm": 0.10874566435813904,
+      "learning_rate": 5.11112605663977e-08,
+      "loss": 1.018,
+      "step": 353
+    },
+    {
+      "epoch": 3.670212765957447,
+      "grad_norm": 0.11302437633275986,
+      "learning_rate": 4.6786172752640576e-08,
+      "loss": 1.304,
+      "step": 354
+    },
+    {
+      "epoch": 3.6808510638297873,
+      "grad_norm": 0.15053825080394745,
+      "learning_rate": 4.264936590308782e-08,
+      "loss": 1.3825,
+      "step": 355
+    },
+    {
+      "epoch": 3.6914893617021276,
+      "grad_norm": 0.12475212663412094,
+      "learning_rate": 3.870137598978152e-08,
+      "loss": 1.1793,
+      "step": 356
+    },
+    {
+      "epoch": 3.702127659574468,
+      "grad_norm": 0.0818130299448967,
+      "learning_rate": 3.494271452130582e-08,
+      "loss": 1.0666,
+      "step": 357
+    },
+    {
+      "epoch": 3.7127659574468086,
+      "grad_norm": 0.0952049046754837,
+      "learning_rate": 3.1373868476515634e-08,
+      "loss": 1.1753,
+      "step": 358
+    },
+    {
+      "epoch": 3.723404255319149,
+      "grad_norm": 0.11639692634344101,
+      "learning_rate": 2.799530024144259e-08,
+      "loss": 1.2072,
+      "step": 359
+    },
+    {
+      "epoch": 3.7340425531914896,
+      "grad_norm": 0.09965858608484268,
+      "learning_rate": 2.4807447549386964e-08,
+      "loss": 1.2021,
+      "step": 360
+    },
+    {
+      "epoch": 3.7340425531914896,
+      "eval_loss": 1.5481599569320679,
+      "eval_runtime": 6.0038,
+      "eval_samples_per_second": 17.489,
+      "eval_steps_per_second": 8.828,
+      "step": 360
+    },
+    {
+      "epoch": 3.74468085106383,
+      "grad_norm": 0.10187926143407822,
+      "learning_rate": 2.1810723424204705e-08,
+      "loss": 1.2199,
+      "step": 361
+    },
+    {
+      "epoch": 3.75531914893617,
+      "grad_norm": 0.1356193870306015,
+      "learning_rate": 1.9005516126795574e-08,
+      "loss": 1.3415,
+      "step": 362
+    },
+    {
+      "epoch": 3.7659574468085104,
+      "grad_norm": 0.10562197864055634,
+      "learning_rate": 1.6392189104798727e-08,
+      "loss": 1.2226,
+      "step": 363
+    },
+    {
+      "epoch": 3.776595744680851,
+      "grad_norm": 0.12549865245819092,
+      "learning_rate": 1.3971080945503866e-08,
+      "loss": 1.2114,
+      "step": 364
+    },
+    {
+      "epoch": 3.7872340425531914,
+      "grad_norm": 0.1090317815542221,
+      "learning_rate": 1.174250533198401e-08,
+      "loss": 1.1658,
+      "step": 365
+    },
+    {
+      "epoch": 3.797872340425532,
+      "grad_norm": 0.11821944266557693,
+      "learning_rate": 9.706751002453329e-09,
+      "loss": 1.1497,
+      "step": 366
+    },
+    {
+      "epoch": 3.8085106382978724,
+      "grad_norm": 0.11243613809347153,
+      "learning_rate": 7.86408171285774e-09,
+      "loss": 1.0885,
+      "step": 367
+    },
+    {
+      "epoch": 3.8191489361702127,
+      "grad_norm": 0.12863968312740326,
+      "learning_rate": 6.214736202703075e-09,
+      "loss": 1.1333,
+      "step": 368
+    },
+    {
+      "epoch": 3.829787234042553,
+      "grad_norm": 0.10371046513319016,
+      "learning_rate": 4.758928164122656e-09,
+      "loss": 1.3754,
+      "step": 369
+    },
+    {
+      "epoch": 3.8404255319148937,
+      "grad_norm": 0.11500074714422226,
+      "learning_rate": 3.4968462141911073e-09,
+      "loss": 1.3089,
+      "step": 370
+    },
+    {
+      "epoch": 3.851063829787234,
+      "grad_norm": 0.10779456794261932,
+      "learning_rate": 2.4286538704875737e-09,
+      "loss": 1.2216,
+      "step": 371
+    },
+    {
+      "epoch": 3.8617021276595747,
+      "grad_norm": 0.11587704718112946,
+      "learning_rate": 1.5544895299086648e-09,
+      "loss": 1.201,
+      "step": 372
+    },
+    {
+      "epoch": 3.872340425531915,
+      "grad_norm": 0.11766841262578964,
+      "learning_rate": 8.744664507389644e-10,
+      "loss": 1.2929,
+      "step": 373
+    },
+    {
+      "epoch": 3.882978723404255,
+      "grad_norm": 0.1037261113524437,
+      "learning_rate": 3.8867273797627003e-10,
+      "loss": 1.0566,
+      "step": 374
+    },
+    {
+      "epoch": 3.8936170212765955,
+      "grad_norm": 0.1192815825343132,
+      "learning_rate": 9.717133191672334e-11,
+      "loss": 1.46,
+      "step": 375
+    },
+    {
+      "epoch": 3.904255319148936,
+      "grad_norm": 0.10904623568058014,
+      "learning_rate": 0.0,
+      "loss": 1.1985,
+      "step": 376
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 94,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2609418835263488e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

phi-sft-out/checkpoint-376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3385717d244ba6cd34f9a94de02b9440c435857ff1e640e8a1c7255c180c1b8
+size 6008

phi-sft-out/checkpoint-94/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-1_5
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

phi-sft-out/checkpoint-94/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "dense",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi-sft-out/checkpoint-94/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998c27a23a6e4a4353f50ca70b9e421e6839ab7c37219765c9ea1bde19655020
+size 226530600

phi-sft-out/checkpoint-94/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}