Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+model-index:
+- name: cdb_polyhope_trained
+  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. -->
+
+# cdb_polyhope_trained
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the train_cdb_polyhope dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e945a3ed8fb6a8e001cf93765506fa4f4e8a5f26f7e25358e3647e1e889d3d2
+size 83945296

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9975786924939465,
+    "num_input_tokens_seen": 7706072,
+    "total_flos": 3.298866475009966e+17,
+    "train_loss": 0.08281170262038245,
+    "train_runtime": 2763.8125,
+    "train_samples_per_second": 8.963,
+    "train_steps_per_second": 1.12
+}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22113c08ccf674cc5c04de1ffd8d20cdc39eb799b723881de471618a23755ff3
+size 83945296

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92820e3a359bfbd9c00a7c84c02e9fe730ee77af64ac4949dada1f627457b692
+size 168149074

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f428295c7a74e082df84f05c5059fc45b17341d5982cd437d20453cec60a6d
+size 1064

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-1000/trainer_state.json

@@ -0,0 +1,833 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9685230024213075,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009685230024213076,
+      "grad_norm": 6.778852939605713,
+      "learning_rate": 2.9999227754514262e-05,
+      "loss": 0.8519,
+      "num_input_tokens_seen": 25568,
+      "step": 10
+    },
+    {
+      "epoch": 0.01937046004842615,
+      "grad_norm": 3.0029561519622803,
+      "learning_rate": 2.9996911097572118e-05,
+      "loss": 0.189,
+      "num_input_tokens_seen": 51072,
+      "step": 20
+    },
+    {
+      "epoch": 0.029055690072639227,
+      "grad_norm": 5.477710247039795,
+      "learning_rate": 2.9993050267710624e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 76416,
+      "step": 30
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 4.35634183883667,
+      "learning_rate": 2.9987645662464235e-05,
+      "loss": 0.1905,
+      "num_input_tokens_seen": 101344,
+      "step": 40
+    },
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 4.523565292358398,
+      "learning_rate": 2.9980697838323884e-05,
+      "loss": 0.1794,
+      "num_input_tokens_seen": 126656,
+      "step": 50
+    },
+    {
+      "epoch": 0.05811138014527845,
+      "grad_norm": 1.9348187446594238,
+      "learning_rate": 2.9972207510679677e-05,
+      "loss": 0.1528,
+      "num_input_tokens_seen": 151200,
+      "step": 60
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 2.981433629989624,
+      "learning_rate": 2.996217555374725e-05,
+      "loss": 0.1742,
+      "num_input_tokens_seen": 175968,
+      "step": 70
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 3.6294591426849365,
+      "learning_rate": 2.9950603000477722e-05,
+      "loss": 0.1565,
+      "num_input_tokens_seen": 201280,
+      "step": 80
+    },
+    {
+      "epoch": 0.08716707021791767,
+      "grad_norm": 2.5459301471710205,
+      "learning_rate": 2.993749104245137e-05,
+      "loss": 0.1499,
+      "num_input_tokens_seen": 226432,
+      "step": 90
+    },
+    {
+      "epoch": 0.09685230024213075,
+      "grad_norm": 2.2721059322357178,
+      "learning_rate": 2.992284102975491e-05,
+      "loss": 0.1441,
+      "num_input_tokens_seen": 251744,
+      "step": 100
+    },
+    {
+      "epoch": 0.10653753026634383,
+      "grad_norm": 2.0033624172210693,
+      "learning_rate": 2.9906654470842492e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 276480,
+      "step": 110
+    },
+    {
+      "epoch": 0.1162227602905569,
+      "grad_norm": 8.585118293762207,
+      "learning_rate": 2.9888933032380397e-05,
+      "loss": 0.1333,
+      "num_input_tokens_seen": 301664,
+      "step": 120
+    },
+    {
+      "epoch": 0.12590799031476999,
+      "grad_norm": 1.423967719078064,
+      "learning_rate": 2.9869678539075403e-05,
+      "loss": 0.1728,
+      "num_input_tokens_seen": 326784,
+      "step": 130
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 2.6306211948394775,
+      "learning_rate": 2.9848892973486912e-05,
+      "loss": 0.1281,
+      "num_input_tokens_seen": 351328,
+      "step": 140
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 2.5618090629577637,
+      "learning_rate": 2.9826578475822825e-05,
+      "loss": 0.1136,
+      "num_input_tokens_seen": 376000,
+      "step": 150
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 2.694077730178833,
+      "learning_rate": 2.980273734371914e-05,
+      "loss": 0.1277,
+      "num_input_tokens_seen": 400384,
+      "step": 160
+    },
+    {
+      "epoch": 0.16464891041162227,
+      "grad_norm": 2.632338047027588,
+      "learning_rate": 2.9777372032003423e-05,
+      "loss": 0.1028,
+      "num_input_tokens_seen": 426432,
+      "step": 170
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "grad_norm": 2.3446829319000244,
+      "learning_rate": 2.975048515244199e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 451712,
+      "step": 180
+    },
+    {
+      "epoch": 0.18401937046004843,
+      "grad_norm": 1.8457319736480713,
+      "learning_rate": 2.9722079473471035e-05,
+      "loss": 0.142,
+      "num_input_tokens_seen": 476960,
+      "step": 190
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 1.8676010370254517,
+      "learning_rate": 2.9692157919911536e-05,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 501440,
+      "step": 200
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 4.593673229217529,
+      "learning_rate": 2.966072357266811e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 526656,
+      "step": 210
+    },
+    {
+      "epoch": 0.21307506053268765,
+      "grad_norm": 3.9568676948547363,
+      "learning_rate": 2.9627779668411795e-05,
+      "loss": 0.171,
+      "num_input_tokens_seen": 552544,
+      "step": 220
+    },
+    {
+      "epoch": 0.22276029055690072,
+      "grad_norm": 2.4331846237182617,
+      "learning_rate": 2.9593329599246766e-05,
+      "loss": 0.115,
+      "num_input_tokens_seen": 577472,
+      "step": 230
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 2.525543212890625,
+      "learning_rate": 2.955737691236108e-05,
+      "loss": 0.1158,
+      "num_input_tokens_seen": 601856,
+      "step": 240
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 2.2355105876922607,
+      "learning_rate": 2.9519925309661422e-05,
+      "loss": 0.111,
+      "num_input_tokens_seen": 627904,
+      "step": 250
+    },
+    {
+      "epoch": 0.25181598062953997,
+      "grad_norm": 4.165389537811279,
+      "learning_rate": 2.948097864739194e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 651936,
+      "step": 260
+    },
+    {
+      "epoch": 0.26150121065375304,
+      "grad_norm": 3.1712851524353027,
+      "learning_rate": 2.944054093573719e-05,
+      "loss": 0.143,
+      "num_input_tokens_seen": 676416,
+      "step": 270
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 2.881716728210449,
+      "learning_rate": 2.93986163384092e-05,
+      "loss": 0.1121,
+      "num_input_tokens_seen": 700832,
+      "step": 280
+    },
+    {
+      "epoch": 0.28087167070217917,
+      "grad_norm": 3.060872793197632,
+      "learning_rate": 2.9355209172218777e-05,
+      "loss": 0.1159,
+      "num_input_tokens_seen": 725824,
+      "step": 290
+    },
+    {
+      "epoch": 0.29055690072639223,
+      "grad_norm": 4.449444770812988,
+      "learning_rate": 2.931032390663101e-05,
+      "loss": 0.133,
+      "num_input_tokens_seen": 749408,
+      "step": 300
+    },
+    {
+      "epoch": 0.30024213075060535,
+      "grad_norm": 5.323568344116211,
+      "learning_rate": 2.926396516330506e-05,
+      "loss": 0.1172,
+      "num_input_tokens_seen": 773984,
+      "step": 310
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 3.144500732421875,
+      "learning_rate": 2.921613771561829e-05,
+      "loss": 0.136,
+      "num_input_tokens_seen": 799168,
+      "step": 320
+    },
+    {
+      "epoch": 0.3196125907990315,
+      "grad_norm": 2.433586359024048,
+      "learning_rate": 2.916684648817478e-05,
+      "loss": 0.0973,
+      "num_input_tokens_seen": 824320,
+      "step": 330
+    },
+    {
+      "epoch": 0.32929782082324455,
+      "grad_norm": 3.349472761154175,
+      "learning_rate": 2.9116096556298256e-05,
+      "loss": 0.13,
+      "num_input_tokens_seen": 849632,
+      "step": 340
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 1.8927061557769775,
+      "learning_rate": 2.9063893145509475e-05,
+      "loss": 0.1257,
+      "num_input_tokens_seen": 874400,
+      "step": 350
+    },
+    {
+      "epoch": 0.3486682808716707,
+      "grad_norm": 3.972686529159546,
+      "learning_rate": 2.901024163098822e-05,
+      "loss": 0.1155,
+      "num_input_tokens_seen": 899264,
+      "step": 360
+    },
+    {
+      "epoch": 0.3583535108958838,
+      "grad_norm": 1.177282452583313,
+      "learning_rate": 2.8955147537019815e-05,
+      "loss": 0.1251,
+      "num_input_tokens_seen": 924544,
+      "step": 370
+    },
+    {
+      "epoch": 0.36803874092009686,
+      "grad_norm": 1.9911576509475708,
+      "learning_rate": 2.88986165364263e-05,
+      "loss": 0.1147,
+      "num_input_tokens_seen": 949792,
+      "step": 380
+    },
+    {
+      "epoch": 0.37772397094430993,
+      "grad_norm": 2.402615785598755,
+      "learning_rate": 2.8840654449982344e-05,
+      "loss": 0.1433,
+      "num_input_tokens_seen": 974112,
+      "step": 390
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 1.3184998035430908,
+      "learning_rate": 2.8781267245815898e-05,
+      "loss": 0.1117,
+      "num_input_tokens_seen": 999168,
+      "step": 400
+    },
+    {
+      "epoch": 0.39709443099273606,
+      "grad_norm": 1.9284625053405762,
+      "learning_rate": 2.8720461038793672e-05,
+      "loss": 0.1353,
+      "num_input_tokens_seen": 1024320,
+      "step": 410
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 3.1020259857177734,
+      "learning_rate": 2.8658242089891515e-05,
+      "loss": 0.1165,
+      "num_input_tokens_seen": 1049088,
+      "step": 420
+    },
+    {
+      "epoch": 0.41646489104116224,
+      "grad_norm": 2.203179359436035,
+      "learning_rate": 2.8594616805549752e-05,
+      "loss": 0.1215,
+      "num_input_tokens_seen": 1073632,
+      "step": 430
+    },
+    {
+      "epoch": 0.4261501210653753,
+      "grad_norm": 2.053194522857666,
+      "learning_rate": 2.8529591737013526e-05,
+      "loss": 0.1066,
+      "num_input_tokens_seen": 1098208,
+      "step": 440
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 2.780935049057007,
+      "learning_rate": 2.8463173579658258e-05,
+      "loss": 0.0879,
+      "num_input_tokens_seen": 1122336,
+      "step": 450
+    },
+    {
+      "epoch": 0.44552058111380144,
+      "grad_norm": 1.9929611682891846,
+      "learning_rate": 2.8395369172300235e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 1147392,
+      "step": 460
+    },
+    {
+      "epoch": 0.4552058111380145,
+      "grad_norm": 1.1469779014587402,
+      "learning_rate": 2.8326185496492464e-05,
+      "loss": 0.1052,
+      "num_input_tokens_seen": 1173248,
+      "step": 470
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 2.501117706298828,
+      "learning_rate": 2.825562967580579e-05,
+      "loss": 0.1086,
+      "num_input_tokens_seen": 1197984,
+      "step": 480
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 2.0266308784484863,
+      "learning_rate": 2.8183708975095406e-05,
+      "loss": 0.1201,
+      "num_input_tokens_seen": 1222720,
+      "step": 490
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 1.1120251417160034,
+      "learning_rate": 2.8110430799752845e-05,
+      "loss": 0.1319,
+      "num_input_tokens_seen": 1247232,
+      "step": 500
+    },
+    {
+      "epoch": 0.4939467312348668,
+      "grad_norm": 1.2014496326446533,
+      "learning_rate": 2.8035802694943457e-05,
+      "loss": 0.1071,
+      "num_input_tokens_seen": 1273184,
+      "step": 510
+    },
+    {
+      "epoch": 0.5036319612590799,
+      "grad_norm": 1.1245245933532715,
+      "learning_rate": 2.7959832344829512e-05,
+      "loss": 0.1554,
+      "num_input_tokens_seen": 1298688,
+      "step": 520
+    },
+    {
+      "epoch": 0.513317191283293,
+      "grad_norm": 2.031115770339966,
+      "learning_rate": 2.7882527571779003e-05,
+      "loss": 0.1196,
+      "num_input_tokens_seen": 1324128,
+      "step": 530
+    },
+    {
+      "epoch": 0.5230024213075061,
+      "grad_norm": 1.7691289186477661,
+      "learning_rate": 2.78038963355602e-05,
+      "loss": 0.1334,
+      "num_input_tokens_seen": 1349120,
+      "step": 540
+    },
+    {
+      "epoch": 0.5326876513317191,
+      "grad_norm": 2.9496989250183105,
+      "learning_rate": 2.7723946732522055e-05,
+      "loss": 0.1109,
+      "num_input_tokens_seen": 1374304,
+      "step": 550
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 2.2881715297698975,
+      "learning_rate": 2.764268699476058e-05,
+      "loss": 0.1274,
+      "num_input_tokens_seen": 1399136,
+      "step": 560
+    },
+    {
+      "epoch": 0.5520581113801453,
+      "grad_norm": 1.9754095077514648,
+      "learning_rate": 2.756012548927119e-05,
+      "loss": 0.1397,
+      "num_input_tokens_seen": 1424672,
+      "step": 570
+    },
+    {
+      "epoch": 0.5617433414043583,
+      "grad_norm": 1.9883428812026978,
+      "learning_rate": 2.7476270717087215e-05,
+      "loss": 0.101,
+      "num_input_tokens_seen": 1449024,
+      "step": 580
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.9653130769729614,
+      "learning_rate": 2.7391131312404556e-05,
+      "loss": 0.0941,
+      "num_input_tokens_seen": 1475264,
+      "step": 590
+    },
+    {
+      "epoch": 0.5811138014527845,
+      "grad_norm": 4.576601028442383,
+      "learning_rate": 2.7304716041692663e-05,
+      "loss": 0.0865,
+      "num_input_tokens_seen": 1500064,
+      "step": 600
+    },
+    {
+      "epoch": 0.5907990314769975,
+      "grad_norm": 2.4046311378479004,
+      "learning_rate": 2.7217033802791906e-05,
+      "loss": 0.1596,
+      "num_input_tokens_seen": 1524448,
+      "step": 610
+    },
+    {
+      "epoch": 0.6004842615012107,
+      "grad_norm": 1.7785555124282837,
+      "learning_rate": 2.7128093623997368e-05,
+      "loss": 0.0891,
+      "num_input_tokens_seen": 1549536,
+      "step": 620
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 2.2736170291900635,
+      "learning_rate": 2.7037904663129262e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 1573408,
+      "step": 630
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 1.0862345695495605,
+      "learning_rate": 2.6946476206589972e-05,
+      "loss": 0.1023,
+      "num_input_tokens_seen": 1597888,
+      "step": 640
+    },
+    {
+      "epoch": 0.6295399515738499,
+      "grad_norm": 0.5358290672302246,
+      "learning_rate": 2.6853817668407875e-05,
+      "loss": 0.0669,
+      "num_input_tokens_seen": 1623296,
+      "step": 650
+    },
+    {
+      "epoch": 0.639225181598063,
+      "grad_norm": 2.3138749599456787,
+      "learning_rate": 2.6759938589268023e-05,
+      "loss": 0.1017,
+      "num_input_tokens_seen": 1649216,
+      "step": 660
+    },
+    {
+      "epoch": 0.648910411622276,
+      "grad_norm": 3.2054226398468018,
+      "learning_rate": 2.6664848635529742e-05,
+      "loss": 0.1432,
+      "num_input_tokens_seen": 1673760,
+      "step": 670
+    },
+    {
+      "epoch": 0.6585956416464891,
+      "grad_norm": 1.8352829217910767,
+      "learning_rate": 2.6568557598231385e-05,
+      "loss": 0.1081,
+      "num_input_tokens_seen": 1698592,
+      "step": 680
+    },
+    {
+      "epoch": 0.6682808716707022,
+      "grad_norm": 1.203284740447998,
+      "learning_rate": 2.6471075392082125e-05,
+      "loss": 0.1037,
+      "num_input_tokens_seen": 1723296,
+      "step": 690
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 1.635628581047058,
+      "learning_rate": 2.6372412054441116e-05,
+      "loss": 0.1216,
+      "num_input_tokens_seen": 1748384,
+      "step": 700
+    },
+    {
+      "epoch": 0.6876513317191283,
+      "grad_norm": 0.8993457555770874,
+      "learning_rate": 2.6272577744283965e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 1773600,
+      "step": 710
+    },
+    {
+      "epoch": 0.6973365617433414,
+      "grad_norm": 1.7306419610977173,
+      "learning_rate": 2.617158274115673e-05,
+      "loss": 0.1034,
+      "num_input_tokens_seen": 1798656,
+      "step": 720
+    },
+    {
+      "epoch": 0.7070217917675545,
+      "grad_norm": 2.770066976547241,
+      "learning_rate": 2.6069437444117432e-05,
+      "loss": 0.0872,
+      "num_input_tokens_seen": 1824544,
+      "step": 730
+    },
+    {
+      "epoch": 0.7167070217917676,
+      "grad_norm": 2.3590221405029297,
+      "learning_rate": 2.596615237066535e-05,
+      "loss": 0.1063,
+      "num_input_tokens_seen": 1848896,
+      "step": 740
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 1.0496519804000854,
+      "learning_rate": 2.586173815565805e-05,
+      "loss": 0.1104,
+      "num_input_tokens_seen": 1873248,
+      "step": 750
+    },
+    {
+      "epoch": 0.7360774818401937,
+      "grad_norm": 1.513573408126831,
+      "learning_rate": 2.575620555021634e-05,
+      "loss": 0.1125,
+      "num_input_tokens_seen": 1897184,
+      "step": 760
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 1.5545728206634521,
+      "learning_rate": 2.564956542061732e-05,
+      "loss": 0.0969,
+      "num_input_tokens_seen": 1922368,
+      "step": 770
+    },
+    {
+      "epoch": 0.7554479418886199,
+      "grad_norm": 1.9260263442993164,
+      "learning_rate": 2.5541828747175477e-05,
+      "loss": 0.1142,
+      "num_input_tokens_seen": 1947904,
+      "step": 780
+    },
+    {
+      "epoch": 0.7651331719128329,
+      "grad_norm": 2.396538734436035,
+      "learning_rate": 2.543300662311211e-05,
+      "loss": 0.0926,
+      "num_input_tokens_seen": 1971872,
+      "step": 790
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 1.7069965600967407,
+      "learning_rate": 2.532311025341309e-05,
+      "loss": 0.0802,
+      "num_input_tokens_seen": 1996352,
+      "step": 800
+    },
+    {
+      "epoch": 0.784503631961259,
+      "grad_norm": 5.540910243988037,
+      "learning_rate": 2.5212150953675133e-05,
+      "loss": 0.1248,
+      "num_input_tokens_seen": 2020480,
+      "step": 810
+    },
+    {
+      "epoch": 0.7941888619854721,
+      "grad_norm": 1.7795952558517456,
+      "learning_rate": 2.5100140148940688e-05,
+      "loss": 0.0767,
+      "num_input_tokens_seen": 2044448,
+      "step": 820
+    },
+    {
+      "epoch": 0.8038740920096852,
+      "grad_norm": 2.7387983798980713,
+      "learning_rate": 2.498708937252153e-05,
+      "loss": 0.1239,
+      "num_input_tokens_seen": 2070400,
+      "step": 830
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 2.1243462562561035,
+      "learning_rate": 2.4873010264811222e-05,
+      "loss": 0.108,
+      "num_input_tokens_seen": 2095392,
+      "step": 840
+    },
+    {
+      "epoch": 0.8232445520581114,
+      "grad_norm": 0.9928631782531738,
+      "learning_rate": 2.4757914572086555e-05,
+      "loss": 0.0994,
+      "num_input_tokens_seen": 2120192,
+      "step": 850
+    },
+    {
+      "epoch": 0.8329297820823245,
+      "grad_norm": 6.047460556030273,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.0927,
+      "num_input_tokens_seen": 2144384,
+      "step": 860
+    },
+    {
+      "epoch": 0.8426150121065376,
+      "grad_norm": 2.2197115421295166,
+      "learning_rate": 2.4524720938849883e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2168704,
+      "step": 870
+    },
+    {
+      "epoch": 0.8523002421307506,
+      "grad_norm": 2.0752601623535156,
+      "learning_rate": 2.440664700936861e-05,
+      "loss": 0.1229,
+      "num_input_tokens_seen": 2193248,
+      "step": 880
+    },
+    {
+      "epoch": 0.8619854721549637,
+      "grad_norm": 1.00425386428833,
+      "learning_rate": 2.4287604514462152e-05,
+      "loss": 0.0957,
+      "num_input_tokens_seen": 2217568,
+      "step": 890
+    },
+    {
+      "epoch": 0.8716707021791767,
+      "grad_norm": 1.9153094291687012,
+      "learning_rate": 2.416760571146774e-05,
+      "loss": 0.0975,
+      "num_input_tokens_seen": 2242048,
+      "step": 900
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 2.3558013439178467,
+      "learning_rate": 2.4046662956189898e-05,
+      "loss": 0.1068,
+      "num_input_tokens_seen": 2266112,
+      "step": 910
+    },
+    {
+      "epoch": 0.8910411622276029,
+      "grad_norm": 2.546351909637451,
+      "learning_rate": 2.3924788701628197e-05,
+      "loss": 0.0688,
+      "num_input_tokens_seen": 2290720,
+      "step": 920
+    },
+    {
+      "epoch": 0.9007263922518159,
+      "grad_norm": 1.2526168823242188,
+      "learning_rate": 2.3801995496695028e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 2315488,
+      "step": 930
+    },
+    {
+      "epoch": 0.910411622276029,
+      "grad_norm": 2.134089231491089,
+      "learning_rate": 2.367829598492348e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2340992,
+      "step": 940
+    },
+    {
+      "epoch": 0.9200968523002422,
+      "grad_norm": 1.332915186882019,
+      "learning_rate": 2.3553702903165502e-05,
+      "loss": 0.1,
+      "num_input_tokens_seen": 2366880,
+      "step": 950
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 1.5140970945358276,
+      "learning_rate": 2.3428229080280407e-05,
+      "loss": 0.1089,
+      "num_input_tokens_seen": 2392000,
+      "step": 960
+    },
+    {
+      "epoch": 0.9394673123486683,
+      "grad_norm": 1.531954288482666,
+      "learning_rate": 2.330188743581398e-05,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 2417472,
+      "step": 970
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 1.3347736597061157,
+      "learning_rate": 2.3174690978668155e-05,
+      "loss": 0.1205,
+      "num_input_tokens_seen": 2442496,
+      "step": 980
+    },
+    {
+      "epoch": 0.9588377723970944,
+      "grad_norm": 3.1497702598571777,
+      "learning_rate": 2.3046652805761588e-05,
+      "loss": 0.1004,
+      "num_input_tokens_seen": 2467392,
+      "step": 990
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 1.6756023168563843,
+      "learning_rate": 2.2917786100681078e-05,
+      "loss": 0.1007,
+      "num_input_tokens_seen": 2492768,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3096,
+  "num_input_tokens_seen": 2492768,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0671206790148915e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7a6d9a1a05e78971782a6ee6bb88dfb9617ab9f9e2f35984cd80b0711875f6
+size 5688

checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8c6480a2e32e03f92e2fccc389b6cf9b5355f580066f3c1b39cac5d652930d
+size 83945296

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df64ffde1d99ec422676939a623694193894f5fdea9b1069a5b9c7072a1f107c
+size 168149074

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6729b4eb02aeb2fb6d654b8bca00ebe8fe8c29edfd4ed50961ee70773f756c3b
+size 1064

checkpoint-2000/special_tokens_map.json

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

checkpoint-2000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9365617433414044,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009685230024213076,
+      "grad_norm": 6.778852939605713,
+      "learning_rate": 2.9999227754514262e-05,
+      "loss": 0.8519,
+      "num_input_tokens_seen": 25568,
+      "step": 10
+    },
+    {
+      "epoch": 0.01937046004842615,
+      "grad_norm": 3.0029561519622803,
+      "learning_rate": 2.9996911097572118e-05,
+      "loss": 0.189,
+      "num_input_tokens_seen": 51072,
+      "step": 20
+    },
+    {
+      "epoch": 0.029055690072639227,
+      "grad_norm": 5.477710247039795,
+      "learning_rate": 2.9993050267710624e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 76416,
+      "step": 30
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 4.35634183883667,
+      "learning_rate": 2.9987645662464235e-05,
+      "loss": 0.1905,
+      "num_input_tokens_seen": 101344,
+      "step": 40
+    },
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 4.523565292358398,
+      "learning_rate": 2.9980697838323884e-05,
+      "loss": 0.1794,
+      "num_input_tokens_seen": 126656,
+      "step": 50
+    },
+    {
+      "epoch": 0.05811138014527845,
+      "grad_norm": 1.9348187446594238,
+      "learning_rate": 2.9972207510679677e-05,
+      "loss": 0.1528,
+      "num_input_tokens_seen": 151200,
+      "step": 60
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 2.981433629989624,
+      "learning_rate": 2.996217555374725e-05,
+      "loss": 0.1742,
+      "num_input_tokens_seen": 175968,
+      "step": 70
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 3.6294591426849365,
+      "learning_rate": 2.9950603000477722e-05,
+      "loss": 0.1565,
+      "num_input_tokens_seen": 201280,
+      "step": 80
+    },
+    {
+      "epoch": 0.08716707021791767,
+      "grad_norm": 2.5459301471710205,
+      "learning_rate": 2.993749104245137e-05,
+      "loss": 0.1499,
+      "num_input_tokens_seen": 226432,
+      "step": 90
+    },
+    {
+      "epoch": 0.09685230024213075,
+      "grad_norm": 2.2721059322357178,
+      "learning_rate": 2.992284102975491e-05,
+      "loss": 0.1441,
+      "num_input_tokens_seen": 251744,
+      "step": 100
+    },
+    {
+      "epoch": 0.10653753026634383,
+      "grad_norm": 2.0033624172210693,
+      "learning_rate": 2.9906654470842492e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 276480,
+      "step": 110
+    },
+    {
+      "epoch": 0.1162227602905569,
+      "grad_norm": 8.585118293762207,
+      "learning_rate": 2.9888933032380397e-05,
+      "loss": 0.1333,
+      "num_input_tokens_seen": 301664,
+      "step": 120
+    },
+    {
+      "epoch": 0.12590799031476999,
+      "grad_norm": 1.423967719078064,
+      "learning_rate": 2.9869678539075403e-05,
+      "loss": 0.1728,
+      "num_input_tokens_seen": 326784,
+      "step": 130
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 2.6306211948394775,
+      "learning_rate": 2.9848892973486912e-05,
+      "loss": 0.1281,
+      "num_input_tokens_seen": 351328,
+      "step": 140
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 2.5618090629577637,
+      "learning_rate": 2.9826578475822825e-05,
+      "loss": 0.1136,
+      "num_input_tokens_seen": 376000,
+      "step": 150
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 2.694077730178833,
+      "learning_rate": 2.980273734371914e-05,
+      "loss": 0.1277,
+      "num_input_tokens_seen": 400384,
+      "step": 160
+    },
+    {
+      "epoch": 0.16464891041162227,
+      "grad_norm": 2.632338047027588,
+      "learning_rate": 2.9777372032003423e-05,
+      "loss": 0.1028,
+      "num_input_tokens_seen": 426432,
+      "step": 170
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "grad_norm": 2.3446829319000244,
+      "learning_rate": 2.975048515244199e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 451712,
+      "step": 180
+    },
+    {
+      "epoch": 0.18401937046004843,
+      "grad_norm": 1.8457319736480713,
+      "learning_rate": 2.9722079473471035e-05,
+      "loss": 0.142,
+      "num_input_tokens_seen": 476960,
+      "step": 190
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 1.8676010370254517,
+      "learning_rate": 2.9692157919911536e-05,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 501440,
+      "step": 200
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 4.593673229217529,
+      "learning_rate": 2.966072357266811e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 526656,
+      "step": 210
+    },
+    {
+      "epoch": 0.21307506053268765,
+      "grad_norm": 3.9568676948547363,
+      "learning_rate": 2.9627779668411795e-05,
+      "loss": 0.171,
+      "num_input_tokens_seen": 552544,
+      "step": 220
+    },
+    {
+      "epoch": 0.22276029055690072,
+      "grad_norm": 2.4331846237182617,
+      "learning_rate": 2.9593329599246766e-05,
+      "loss": 0.115,
+      "num_input_tokens_seen": 577472,
+      "step": 230
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 2.525543212890625,
+      "learning_rate": 2.955737691236108e-05,
+      "loss": 0.1158,
+      "num_input_tokens_seen": 601856,
+      "step": 240
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 2.2355105876922607,
+      "learning_rate": 2.9519925309661422e-05,
+      "loss": 0.111,
+      "num_input_tokens_seen": 627904,
+      "step": 250
+    },
+    {
+      "epoch": 0.25181598062953997,
+      "grad_norm": 4.165389537811279,
+      "learning_rate": 2.948097864739194e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 651936,
+      "step": 260
+    },
+    {
+      "epoch": 0.26150121065375304,
+      "grad_norm": 3.1712851524353027,
+      "learning_rate": 2.944054093573719e-05,
+      "loss": 0.143,
+      "num_input_tokens_seen": 676416,
+      "step": 270
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 2.881716728210449,
+      "learning_rate": 2.93986163384092e-05,
+      "loss": 0.1121,
+      "num_input_tokens_seen": 700832,
+      "step": 280
+    },
+    {
+      "epoch": 0.28087167070217917,
+      "grad_norm": 3.060872793197632,
+      "learning_rate": 2.9355209172218777e-05,
+      "loss": 0.1159,
+      "num_input_tokens_seen": 725824,
+      "step": 290
+    },
+    {
+      "epoch": 0.29055690072639223,
+      "grad_norm": 4.449444770812988,
+      "learning_rate": 2.931032390663101e-05,
+      "loss": 0.133,
+      "num_input_tokens_seen": 749408,
+      "step": 300
+    },
+    {
+      "epoch": 0.30024213075060535,
+      "grad_norm": 5.323568344116211,
+      "learning_rate": 2.926396516330506e-05,
+      "loss": 0.1172,
+      "num_input_tokens_seen": 773984,
+      "step": 310
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 3.144500732421875,
+      "learning_rate": 2.921613771561829e-05,
+      "loss": 0.136,
+      "num_input_tokens_seen": 799168,
+      "step": 320
+    },
+    {
+      "epoch": 0.3196125907990315,
+      "grad_norm": 2.433586359024048,
+      "learning_rate": 2.916684648817478e-05,
+      "loss": 0.0973,
+      "num_input_tokens_seen": 824320,
+      "step": 330
+    },
+    {
+      "epoch": 0.32929782082324455,
+      "grad_norm": 3.349472761154175,
+      "learning_rate": 2.9116096556298256e-05,
+      "loss": 0.13,
+      "num_input_tokens_seen": 849632,
+      "step": 340
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 1.8927061557769775,
+      "learning_rate": 2.9063893145509475e-05,
+      "loss": 0.1257,
+      "num_input_tokens_seen": 874400,
+      "step": 350
+    },
+    {
+      "epoch": 0.3486682808716707,
+      "grad_norm": 3.972686529159546,
+      "learning_rate": 2.901024163098822e-05,
+      "loss": 0.1155,
+      "num_input_tokens_seen": 899264,
+      "step": 360
+    },
+    {
+      "epoch": 0.3583535108958838,
+      "grad_norm": 1.177282452583313,
+      "learning_rate": 2.8955147537019815e-05,
+      "loss": 0.1251,
+      "num_input_tokens_seen": 924544,
+      "step": 370
+    },
+    {
+      "epoch": 0.36803874092009686,
+      "grad_norm": 1.9911576509475708,
+      "learning_rate": 2.88986165364263e-05,
+      "loss": 0.1147,
+      "num_input_tokens_seen": 949792,
+      "step": 380
+    },
+    {
+      "epoch": 0.37772397094430993,
+      "grad_norm": 2.402615785598755,
+      "learning_rate": 2.8840654449982344e-05,
+      "loss": 0.1433,
+      "num_input_tokens_seen": 974112,
+      "step": 390
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 1.3184998035430908,
+      "learning_rate": 2.8781267245815898e-05,
+      "loss": 0.1117,
+      "num_input_tokens_seen": 999168,
+      "step": 400
+    },
+    {
+      "epoch": 0.39709443099273606,
+      "grad_norm": 1.9284625053405762,
+      "learning_rate": 2.8720461038793672e-05,
+      "loss": 0.1353,
+      "num_input_tokens_seen": 1024320,
+      "step": 410
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 3.1020259857177734,
+      "learning_rate": 2.8658242089891515e-05,
+      "loss": 0.1165,
+      "num_input_tokens_seen": 1049088,
+      "step": 420
+    },
+    {
+      "epoch": 0.41646489104116224,
+      "grad_norm": 2.203179359436035,
+      "learning_rate": 2.8594616805549752e-05,
+      "loss": 0.1215,
+      "num_input_tokens_seen": 1073632,
+      "step": 430
+    },
+    {
+      "epoch": 0.4261501210653753,
+      "grad_norm": 2.053194522857666,
+      "learning_rate": 2.8529591737013526e-05,
+      "loss": 0.1066,
+      "num_input_tokens_seen": 1098208,
+      "step": 440
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 2.780935049057007,
+      "learning_rate": 2.8463173579658258e-05,
+      "loss": 0.0879,
+      "num_input_tokens_seen": 1122336,
+      "step": 450
+    },
+    {
+      "epoch": 0.44552058111380144,
+      "grad_norm": 1.9929611682891846,
+      "learning_rate": 2.8395369172300235e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 1147392,
+      "step": 460
+    },
+    {
+      "epoch": 0.4552058111380145,
+      "grad_norm": 1.1469779014587402,
+      "learning_rate": 2.8326185496492464e-05,
+      "loss": 0.1052,
+      "num_input_tokens_seen": 1173248,
+      "step": 470
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 2.501117706298828,
+      "learning_rate": 2.825562967580579e-05,
+      "loss": 0.1086,
+      "num_input_tokens_seen": 1197984,
+      "step": 480
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 2.0266308784484863,
+      "learning_rate": 2.8183708975095406e-05,
+      "loss": 0.1201,
+      "num_input_tokens_seen": 1222720,
+      "step": 490
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 1.1120251417160034,
+      "learning_rate": 2.8110430799752845e-05,
+      "loss": 0.1319,
+      "num_input_tokens_seen": 1247232,
+      "step": 500
+    },
+    {
+      "epoch": 0.4939467312348668,
+      "grad_norm": 1.2014496326446533,
+      "learning_rate": 2.8035802694943457e-05,
+      "loss": 0.1071,
+      "num_input_tokens_seen": 1273184,
+      "step": 510
+    },
+    {
+      "epoch": 0.5036319612590799,
+      "grad_norm": 1.1245245933532715,
+      "learning_rate": 2.7959832344829512e-05,
+      "loss": 0.1554,
+      "num_input_tokens_seen": 1298688,
+      "step": 520
+    },
+    {
+      "epoch": 0.513317191283293,
+      "grad_norm": 2.031115770339966,
+      "learning_rate": 2.7882527571779003e-05,
+      "loss": 0.1196,
+      "num_input_tokens_seen": 1324128,
+      "step": 530
+    },
+    {
+      "epoch": 0.5230024213075061,
+      "grad_norm": 1.7691289186477661,
+      "learning_rate": 2.78038963355602e-05,
+      "loss": 0.1334,
+      "num_input_tokens_seen": 1349120,
+      "step": 540
+    },
+    {
+      "epoch": 0.5326876513317191,
+      "grad_norm": 2.9496989250183105,
+      "learning_rate": 2.7723946732522055e-05,
+      "loss": 0.1109,
+      "num_input_tokens_seen": 1374304,
+      "step": 550
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 2.2881715297698975,
+      "learning_rate": 2.764268699476058e-05,
+      "loss": 0.1274,
+      "num_input_tokens_seen": 1399136,
+      "step": 560
+    },
+    {
+      "epoch": 0.5520581113801453,
+      "grad_norm": 1.9754095077514648,
+      "learning_rate": 2.756012548927119e-05,
+      "loss": 0.1397,
+      "num_input_tokens_seen": 1424672,
+      "step": 570
+    },
+    {
+      "epoch": 0.5617433414043583,
+      "grad_norm": 1.9883428812026978,
+      "learning_rate": 2.7476270717087215e-05,
+      "loss": 0.101,
+      "num_input_tokens_seen": 1449024,
+      "step": 580
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.9653130769729614,
+      "learning_rate": 2.7391131312404556e-05,
+      "loss": 0.0941,
+      "num_input_tokens_seen": 1475264,
+      "step": 590
+    },
+    {
+      "epoch": 0.5811138014527845,
+      "grad_norm": 4.576601028442383,
+      "learning_rate": 2.7304716041692663e-05,
+      "loss": 0.0865,
+      "num_input_tokens_seen": 1500064,
+      "step": 600
+    },
+    {
+      "epoch": 0.5907990314769975,
+      "grad_norm": 2.4046311378479004,
+      "learning_rate": 2.7217033802791906e-05,
+      "loss": 0.1596,
+      "num_input_tokens_seen": 1524448,
+      "step": 610
+    },
+    {
+      "epoch": 0.6004842615012107,
+      "grad_norm": 1.7785555124282837,
+      "learning_rate": 2.7128093623997368e-05,
+      "loss": 0.0891,
+      "num_input_tokens_seen": 1549536,
+      "step": 620
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 2.2736170291900635,
+      "learning_rate": 2.7037904663129262e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 1573408,
+      "step": 630
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 1.0862345695495605,
+      "learning_rate": 2.6946476206589972e-05,
+      "loss": 0.1023,
+      "num_input_tokens_seen": 1597888,
+      "step": 640
+    },
+    {
+      "epoch": 0.6295399515738499,
+      "grad_norm": 0.5358290672302246,
+      "learning_rate": 2.6853817668407875e-05,
+      "loss": 0.0669,
+      "num_input_tokens_seen": 1623296,
+      "step": 650
+    },
+    {
+      "epoch": 0.639225181598063,
+      "grad_norm": 2.3138749599456787,
+      "learning_rate": 2.6759938589268023e-05,
+      "loss": 0.1017,
+      "num_input_tokens_seen": 1649216,
+      "step": 660
+    },
+    {
+      "epoch": 0.648910411622276,
+      "grad_norm": 3.2054226398468018,
+      "learning_rate": 2.6664848635529742e-05,
+      "loss": 0.1432,
+      "num_input_tokens_seen": 1673760,
+      "step": 670
+    },
+    {
+      "epoch": 0.6585956416464891,
+      "grad_norm": 1.8352829217910767,
+      "learning_rate": 2.6568557598231385e-05,
+      "loss": 0.1081,
+      "num_input_tokens_seen": 1698592,
+      "step": 680
+    },
+    {
+      "epoch": 0.6682808716707022,
+      "grad_norm": 1.203284740447998,
+      "learning_rate": 2.6471075392082125e-05,
+      "loss": 0.1037,
+      "num_input_tokens_seen": 1723296,
+      "step": 690
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 1.635628581047058,
+      "learning_rate": 2.6372412054441116e-05,
+      "loss": 0.1216,
+      "num_input_tokens_seen": 1748384,
+      "step": 700
+    },
+    {
+      "epoch": 0.6876513317191283,
+      "grad_norm": 0.8993457555770874,
+      "learning_rate": 2.6272577744283965e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 1773600,
+      "step": 710
+    },
+    {
+      "epoch": 0.6973365617433414,
+      "grad_norm": 1.7306419610977173,
+      "learning_rate": 2.617158274115673e-05,
+      "loss": 0.1034,
+      "num_input_tokens_seen": 1798656,
+      "step": 720
+    },
+    {
+      "epoch": 0.7070217917675545,
+      "grad_norm": 2.770066976547241,
+      "learning_rate": 2.6069437444117432e-05,
+      "loss": 0.0872,
+      "num_input_tokens_seen": 1824544,
+      "step": 730
+    },
+    {
+      "epoch": 0.7167070217917676,
+      "grad_norm": 2.3590221405029297,
+      "learning_rate": 2.596615237066535e-05,
+      "loss": 0.1063,
+      "num_input_tokens_seen": 1848896,
+      "step": 740
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 1.0496519804000854,
+      "learning_rate": 2.586173815565805e-05,
+      "loss": 0.1104,
+      "num_input_tokens_seen": 1873248,
+      "step": 750
+    },
+    {
+      "epoch": 0.7360774818401937,
+      "grad_norm": 1.513573408126831,
+      "learning_rate": 2.575620555021634e-05,
+      "loss": 0.1125,
+      "num_input_tokens_seen": 1897184,
+      "step": 760
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 1.5545728206634521,
+      "learning_rate": 2.564956542061732e-05,
+      "loss": 0.0969,
+      "num_input_tokens_seen": 1922368,
+      "step": 770
+    },
+    {
+      "epoch": 0.7554479418886199,
+      "grad_norm": 1.9260263442993164,
+      "learning_rate": 2.5541828747175477e-05,
+      "loss": 0.1142,
+      "num_input_tokens_seen": 1947904,
+      "step": 780
+    },
+    {
+      "epoch": 0.7651331719128329,
+      "grad_norm": 2.396538734436035,
+      "learning_rate": 2.543300662311211e-05,
+      "loss": 0.0926,
+      "num_input_tokens_seen": 1971872,
+      "step": 790
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 1.7069965600967407,
+      "learning_rate": 2.532311025341309e-05,
+      "loss": 0.0802,
+      "num_input_tokens_seen": 1996352,
+      "step": 800
+    },
+    {
+      "epoch": 0.784503631961259,
+      "grad_norm": 5.540910243988037,
+      "learning_rate": 2.5212150953675133e-05,
+      "loss": 0.1248,
+      "num_input_tokens_seen": 2020480,
+      "step": 810
+    },
+    {
+      "epoch": 0.7941888619854721,
+      "grad_norm": 1.7795952558517456,
+      "learning_rate": 2.5100140148940688e-05,
+      "loss": 0.0767,
+      "num_input_tokens_seen": 2044448,
+      "step": 820
+    },
+    {
+      "epoch": 0.8038740920096852,
+      "grad_norm": 2.7387983798980713,
+      "learning_rate": 2.498708937252153e-05,
+      "loss": 0.1239,
+      "num_input_tokens_seen": 2070400,
+      "step": 830
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 2.1243462562561035,
+      "learning_rate": 2.4873010264811222e-05,
+      "loss": 0.108,
+      "num_input_tokens_seen": 2095392,
+      "step": 840
+    },
+    {
+      "epoch": 0.8232445520581114,
+      "grad_norm": 0.9928631782531738,
+      "learning_rate": 2.4757914572086555e-05,
+      "loss": 0.0994,
+      "num_input_tokens_seen": 2120192,
+      "step": 850
+    },
+    {
+      "epoch": 0.8329297820823245,
+      "grad_norm": 6.047460556030273,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.0927,
+      "num_input_tokens_seen": 2144384,
+      "step": 860
+    },
+    {
+      "epoch": 0.8426150121065376,
+      "grad_norm": 2.2197115421295166,
+      "learning_rate": 2.4524720938849883e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2168704,
+      "step": 870
+    },
+    {
+      "epoch": 0.8523002421307506,
+      "grad_norm": 2.0752601623535156,
+      "learning_rate": 2.440664700936861e-05,
+      "loss": 0.1229,
+      "num_input_tokens_seen": 2193248,
+      "step": 880
+    },
+    {
+      "epoch": 0.8619854721549637,
+      "grad_norm": 1.00425386428833,
+      "learning_rate": 2.4287604514462152e-05,
+      "loss": 0.0957,
+      "num_input_tokens_seen": 2217568,
+      "step": 890
+    },
+    {
+      "epoch": 0.8716707021791767,
+      "grad_norm": 1.9153094291687012,
+      "learning_rate": 2.416760571146774e-05,
+      "loss": 0.0975,
+      "num_input_tokens_seen": 2242048,
+      "step": 900
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 2.3558013439178467,
+      "learning_rate": 2.4046662956189898e-05,
+      "loss": 0.1068,
+      "num_input_tokens_seen": 2266112,
+      "step": 910
+    },
+    {
+      "epoch": 0.8910411622276029,
+      "grad_norm": 2.546351909637451,
+      "learning_rate": 2.3924788701628197e-05,
+      "loss": 0.0688,
+      "num_input_tokens_seen": 2290720,
+      "step": 920
+    },
+    {
+      "epoch": 0.9007263922518159,
+      "grad_norm": 1.2526168823242188,
+      "learning_rate": 2.3801995496695028e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 2315488,
+      "step": 930
+    },
+    {
+      "epoch": 0.910411622276029,
+      "grad_norm": 2.134089231491089,
+      "learning_rate": 2.367829598492348e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2340992,
+      "step": 940
+    },
+    {
+      "epoch": 0.9200968523002422,
+      "grad_norm": 1.332915186882019,
+      "learning_rate": 2.3553702903165502e-05,
+      "loss": 0.1,
+      "num_input_tokens_seen": 2366880,
+      "step": 950
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 1.5140970945358276,
+      "learning_rate": 2.3428229080280407e-05,
+      "loss": 0.1089,
+      "num_input_tokens_seen": 2392000,
+      "step": 960
+    },
+    {
+      "epoch": 0.9394673123486683,
+      "grad_norm": 1.531954288482666,
+      "learning_rate": 2.330188743581398e-05,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 2417472,
+      "step": 970
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 1.3347736597061157,
+      "learning_rate": 2.3174690978668155e-05,
+      "loss": 0.1205,
+      "num_input_tokens_seen": 2442496,
+      "step": 980
+    },
+    {
+      "epoch": 0.9588377723970944,
+      "grad_norm": 3.1497702598571777,
+      "learning_rate": 2.3046652805761588e-05,
+      "loss": 0.1004,
+      "num_input_tokens_seen": 2467392,
+      "step": 990
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 1.6756023168563843,
+      "learning_rate": 2.2917786100681078e-05,
+      "loss": 0.1007,
+      "num_input_tokens_seen": 2492768,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9782082324455206,
+      "grad_norm": 2.56594181060791,
+      "learning_rate": 2.2788104132324125e-05,
+      "loss": 0.1179,
+      "num_input_tokens_seen": 2518176,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9878934624697336,
+      "grad_norm": 2.1090595722198486,
+      "learning_rate": 2.2657620253532685e-05,
+      "loss": 0.0971,
+      "num_input_tokens_seen": 2543296,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9975786924939467,
+      "grad_norm": 0.41959595680236816,
+      "learning_rate": 2.252634789971827e-05,
+      "loss": 0.0932,
+      "num_input_tokens_seen": 2567680,
+      "step": 1030
+    },
+    {
+      "epoch": 1.006779661016949,
+      "grad_norm": 1.6389803886413574,
+      "learning_rate": 2.2394300587478566e-05,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 2591016,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0164648910411622,
+      "grad_norm": 1.4045557975769043,
+      "learning_rate": 2.2261491913205684e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 2615752,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0261501210653754,
+      "grad_norm": 2.0734925270080566,
+      "learning_rate": 2.212793555168617e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 2640200,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0358353510895884,
+      "grad_norm": 2.1590147018432617,
+      "learning_rate": 2.1993645254692994e-05,
+      "loss": 0.116,
+      "num_input_tokens_seen": 2665416,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0455205811138015,
+      "grad_norm": 1.739646553993225,
+      "learning_rate": 2.1858634849569578e-05,
+      "loss": 0.0972,
+      "num_input_tokens_seen": 2690376,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0552058111380145,
+      "grad_norm": 0.6458954215049744,
+      "learning_rate": 2.1722918237806042e-05,
+      "loss": 0.0884,
+      "num_input_tokens_seen": 2715080,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0648910411622277,
+      "grad_norm": 2.2830138206481934,
+      "learning_rate": 2.158650939360782e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 2740424,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0745762711864406,
+      "grad_norm": 1.5225194692611694,
+      "learning_rate": 2.1449422362456794e-05,
+      "loss": 0.0813,
+      "num_input_tokens_seen": 2765640,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0842615012106538,
+      "grad_norm": 1.683604121208191,
+      "learning_rate": 2.13116712596651e-05,
+      "loss": 0.0953,
+      "num_input_tokens_seen": 2791176,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0939467312348667,
+      "grad_norm": 1.5679166316986084,
+      "learning_rate": 2.1173270268921703e-05,
+      "loss": 0.0933,
+      "num_input_tokens_seen": 2816072,
+      "step": 1130
+    },
+    {
+      "epoch": 1.10363196125908,
+      "grad_norm": 1.3097947835922241,
+      "learning_rate": 2.1034233640831988e-05,
+      "loss": 0.0819,
+      "num_input_tokens_seen": 2840776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.113317191283293,
+      "grad_norm": 0.5728388428688049,
+      "learning_rate": 2.0894575691450396e-05,
+      "loss": 0.0611,
+      "num_input_tokens_seen": 2865416,
+      "step": 1150
+    },
+    {
+      "epoch": 1.123002421307506,
+      "grad_norm": 2.3043558597564697,
+      "learning_rate": 2.0754310800806395e-05,
+      "loss": 0.0748,
+      "num_input_tokens_seen": 2890248,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1326876513317192,
+      "grad_norm": 1.2087112665176392,
+      "learning_rate": 2.0613453411423797e-05,
+      "loss": 0.0959,
+      "num_input_tokens_seen": 2916392,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1423728813559322,
+      "grad_norm": 1.5639240741729736,
+      "learning_rate": 2.0472018026833684e-05,
+      "loss": 0.0709,
+      "num_input_tokens_seen": 2941160,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1520581113801454,
+      "grad_norm": 0.5889459848403931,
+      "learning_rate": 2.0330019210081022e-05,
+      "loss": 0.0731,
+      "num_input_tokens_seen": 2966120,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1617433414043583,
+      "grad_norm": 1.854230523109436,
+      "learning_rate": 2.0187471582225173e-05,
+      "loss": 0.1005,
+      "num_input_tokens_seen": 2990088,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 2.01247239112854,
+      "learning_rate": 2.004438982083442e-05,
+      "loss": 0.0579,
+      "num_input_tokens_seen": 3015400,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1811138014527844,
+      "grad_norm": 2.292900323867798,
+      "learning_rate": 1.9900788658474677e-05,
+      "loss": 0.0792,
+      "num_input_tokens_seen": 3039464,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1907990314769976,
+      "grad_norm": 1.4194159507751465,
+      "learning_rate": 1.975668288119252e-05,
+      "loss": 0.057,
+      "num_input_tokens_seen": 3063816,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2004842615012106,
+      "grad_norm": 1.0512489080429077,
+      "learning_rate": 1.961208732699275e-05,
+      "loss": 0.102,
+      "num_input_tokens_seen": 3088968,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2101694915254237,
+      "grad_norm": 0.9465106129646301,
+      "learning_rate": 1.9467016884310565e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 3113736,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2198547215496367,
+      "grad_norm": 1.274294376373291,
+      "learning_rate": 1.9321486490478565e-05,
+      "loss": 0.0668,
+      "num_input_tokens_seen": 3138344,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2295399515738499,
+      "grad_norm": 1.9390579462051392,
+      "learning_rate": 1.91755111301887e-05,
+      "loss": 0.0711,
+      "num_input_tokens_seen": 3163496,
+      "step": 1270
+    },
+    {
+      "epoch": 1.239225181598063,
+      "grad_norm": 1.2855744361877441,
+      "learning_rate": 1.902910583394938e-05,
+      "loss": 0.0605,
+      "num_input_tokens_seen": 3188392,
+      "step": 1280
+    },
+    {
+      "epoch": 1.248910411622276,
+      "grad_norm": 2.931248188018799,
+      "learning_rate": 1.888228567653781e-05,
+      "loss": 0.0448,
+      "num_input_tokens_seen": 3213224,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2585956416464892,
+      "grad_norm": 1.9991300106048584,
+      "learning_rate": 1.873506577544784e-05,
+      "loss": 0.0815,
+      "num_input_tokens_seen": 3238568,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2682808716707021,
+      "grad_norm": 1.3530927896499634,
+      "learning_rate": 1.8587461289333327e-05,
+      "loss": 0.1043,
+      "num_input_tokens_seen": 3264264,
+      "step": 1310
+    },
+    {
+      "epoch": 1.2779661016949153,
+      "grad_norm": 2.07991099357605,
+      "learning_rate": 1.8439487416447353e-05,
+      "loss": 0.1037,
+      "num_input_tokens_seen": 3288840,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2876513317191283,
+      "grad_norm": 1.8533947467803955,
+      "learning_rate": 1.8291159393077294e-05,
+      "loss": 0.0928,
+      "num_input_tokens_seen": 3313832,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2973365617433414,
+      "grad_norm": 1.118119716644287,
+      "learning_rate": 1.814249249197602e-05,
+      "loss": 0.0775,
+      "num_input_tokens_seen": 3337736,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3070217917675544,
+      "grad_norm": 2.740079641342163,
+      "learning_rate": 1.7993502020789294e-05,
+      "loss": 0.0521,
+      "num_input_tokens_seen": 3362024,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3167070217917676,
+      "grad_norm": 1.9268351793289185,
+      "learning_rate": 1.7844203320479614e-05,
+      "loss": 0.0687,
+      "num_input_tokens_seen": 3387496,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3263922518159807,
+      "grad_norm": 2.3576388359069824,
+      "learning_rate": 1.7694611763746632e-05,
+      "loss": 0.0704,
+      "num_input_tokens_seen": 3412072,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3360774818401937,
+      "grad_norm": 1.127432942390442,
+      "learning_rate": 1.754474275344427e-05,
+      "loss": 0.0826,
+      "num_input_tokens_seen": 3437096,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3457627118644067,
+      "grad_norm": 4.377537250518799,
+      "learning_rate": 1.7394611720994747e-05,
+      "loss": 0.0445,
+      "num_input_tokens_seen": 3462120,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3554479418886198,
+      "grad_norm": 2.1285200119018555,
+      "learning_rate": 1.724423412479967e-05,
+      "loss": 0.0951,
+      "num_input_tokens_seen": 3486952,
+      "step": 1400
+    },
+    {
+      "epoch": 1.365133171912833,
+      "grad_norm": 0.16216270625591278,
+      "learning_rate": 1.7093625448648348e-05,
+      "loss": 0.0539,
+      "num_input_tokens_seen": 3512264,
+      "step": 1410
+    },
+    {
+      "epoch": 1.374818401937046,
+      "grad_norm": 2.1299915313720703,
+      "learning_rate": 1.694280120012349e-05,
+      "loss": 0.0848,
+      "num_input_tokens_seen": 3537192,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3845036319612591,
+      "grad_norm": 2.476757049560547,
+      "learning_rate": 1.6791776909004434e-05,
+      "loss": 0.0629,
+      "num_input_tokens_seen": 3560872,
+      "step": 1430
+    },
+    {
+      "epoch": 1.394188861985472,
+      "grad_norm": 0.4373377561569214,
+      "learning_rate": 1.664056812566812e-05,
+      "loss": 0.079,
+      "num_input_tokens_seen": 3586216,
+      "step": 1440
+    },
+    {
+      "epoch": 1.4038740920096853,
+      "grad_norm": 1.9471170902252197,
+      "learning_rate": 1.648919041948792e-05,
+      "loss": 0.0798,
+      "num_input_tokens_seen": 3610792,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4135593220338982,
+      "grad_norm": 2.911750316619873,
+      "learning_rate": 1.6337659377230544e-05,
+      "loss": 0.0897,
+      "num_input_tokens_seen": 3634760,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4232445520581114,
+      "grad_norm": 2.9474802017211914,
+      "learning_rate": 1.61859906014511e-05,
+      "loss": 0.0858,
+      "num_input_tokens_seen": 3659560,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4329297820823244,
+      "grad_norm": 0.6501768827438354,
+      "learning_rate": 1.6034199708886573e-05,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 3684840,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4426150121065375,
+      "grad_norm": 1.6708017587661743,
+      "learning_rate": 1.5882302328847847e-05,
+      "loss": 0.0842,
+      "num_input_tokens_seen": 3709096,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4523002421307507,
+      "grad_norm": 1.5014967918395996,
+      "learning_rate": 1.5730314101610376e-05,
+      "loss": 0.0367,
+      "num_input_tokens_seen": 3734728,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4619854721549637,
+      "grad_norm": 3.2587804794311523,
+      "learning_rate": 1.5578250676803824e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 3758984,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4716707021791768,
+      "grad_norm": 6.304242134094238,
+      "learning_rate": 1.5426127711800636e-05,
+      "loss": 0.0712,
+      "num_input_tokens_seen": 3784296,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4813559322033898,
+      "grad_norm": 1.1681016683578491,
+      "learning_rate": 1.5273960870103872e-05,
+      "loss": 0.0705,
+      "num_input_tokens_seen": 3809768,
+      "step": 1530
+    },
+    {
+      "epoch": 1.491041162227603,
+      "grad_norm": 1.111617922782898,
+      "learning_rate": 1.5121765819734418e-05,
+      "loss": 0.071,
+      "num_input_tokens_seen": 3834536,
+      "step": 1540
+    },
+    {
+      "epoch": 1.5007263922518161,
+      "grad_norm": 1.7780523300170898,
+      "learning_rate": 1.4969558231617681e-05,
+      "loss": 0.0648,
+      "num_input_tokens_seen": 3858792,
+      "step": 1550
+    },
+    {
+      "epoch": 1.510411622276029,
+      "grad_norm": 2.2017934322357178,
+      "learning_rate": 1.4817353777970038e-05,
+      "loss": 0.0633,
+      "num_input_tokens_seen": 3883976,
+      "step": 1560
+    },
+    {
+      "epoch": 1.520096852300242,
+      "grad_norm": 1.8567978143692017,
+      "learning_rate": 1.466516813068512e-05,
+      "loss": 0.0726,
+      "num_input_tokens_seen": 3908392,
+      "step": 1570
+    },
+    {
+      "epoch": 1.5297820823244552,
+      "grad_norm": 2.567291021347046,
+      "learning_rate": 1.451301695972015e-05,
+      "loss": 0.0882,
+      "num_input_tokens_seen": 3932552,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5394673123486684,
+      "grad_norm": 1.9968935251235962,
+      "learning_rate": 1.436091593148244e-05,
+      "loss": 0.1149,
+      "num_input_tokens_seen": 3957672,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5491525423728814,
+      "grad_norm": 1.9058917760849,
+      "learning_rate": 1.4208880707216323e-05,
+      "loss": 0.0841,
+      "num_input_tokens_seen": 3982824,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5588377723970943,
+      "grad_norm": 1.9218000173568726,
+      "learning_rate": 1.405692694139054e-05,
+      "loss": 0.0896,
+      "num_input_tokens_seen": 4008072,
+      "step": 1610
+    },
+    {
+      "epoch": 1.5685230024213075,
+      "grad_norm": 1.5786553621292114,
+      "learning_rate": 1.3905070280086387e-05,
+      "loss": 0.0629,
+      "num_input_tokens_seen": 4033096,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5782082324455207,
+      "grad_norm": 2.503990888595581,
+      "learning_rate": 1.3753326359386695e-05,
+      "loss": 0.077,
+      "num_input_tokens_seen": 4058120,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5878934624697336,
+      "grad_norm": 1.5616143941879272,
+      "learning_rate": 1.3601710803765814e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 4082792,
+      "step": 1640
+    },
+    {
+      "epoch": 1.5975786924939466,
+      "grad_norm": 1.2533211708068848,
+      "learning_rate": 1.3450239224480884e-05,
+      "loss": 0.0605,
+      "num_input_tokens_seen": 4107336,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6072639225181597,
+      "grad_norm": 1.1046490669250488,
+      "learning_rate": 1.329892721796433e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 4132456,
+      "step": 1660
+    },
+    {
+      "epoch": 1.616949152542373,
+      "grad_norm": 1.143494725227356,
+      "learning_rate": 1.314779036421802e-05,
+      "loss": 0.0547,
+      "num_input_tokens_seen": 4156584,
+      "step": 1670
+    },
+    {
+      "epoch": 1.626634382566586,
+      "grad_norm": 2.6082706451416016,
+      "learning_rate": 1.2996844225209033e-05,
+      "loss": 0.0919,
+      "num_input_tokens_seen": 4181448,
+      "step": 1680
+    },
+    {
+      "epoch": 1.636319612590799,
+      "grad_norm": 2.4191458225250244,
+      "learning_rate": 1.2846104343267283e-05,
+      "loss": 0.1204,
+      "num_input_tokens_seen": 4207560,
+      "step": 1690
+    },
+    {
+      "epoch": 1.646004842615012,
+      "grad_norm": 2.051799774169922,
+      "learning_rate": 1.2695586239485223e-05,
+      "loss": 0.0664,
+      "num_input_tokens_seen": 4232040,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6556900726392252,
+      "grad_norm": 1.525844931602478,
+      "learning_rate": 1.254530541211968e-05,
+      "loss": 0.0805,
+      "num_input_tokens_seen": 4257576,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6653753026634384,
+      "grad_norm": 0.9474373459815979,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 4282472,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6750605326876513,
+      "grad_norm": 1.8932424783706665,
+      "learning_rate": 1.2245517455915036e-05,
+      "loss": 0.0734,
+      "num_input_tokens_seen": 4306792,
+      "step": 1730
+    },
+    {
+      "epoch": 1.6847457627118643,
+      "grad_norm": 1.9888746738433838,
+      "learning_rate": 1.2096041195062051e-05,
+      "loss": 0.0831,
+      "num_input_tokens_seen": 4333384,
+      "step": 1740
+    },
+    {
+      "epoch": 1.6944309927360774,
+      "grad_norm": 1.8355742692947388,
+      "learning_rate": 1.1946863943419452e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 4358344,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7041162227602906,
+      "grad_norm": 2.8447251319885254,
+      "learning_rate": 1.1798001061181799e-05,
+      "loss": 0.0988,
+      "num_input_tokens_seen": 4381768,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7138014527845038,
+      "grad_norm": 2.670257806777954,
+      "learning_rate": 1.1649467876174252e-05,
+      "loss": 0.0936,
+      "num_input_tokens_seen": 4405192,
+      "step": 1770
+    },
+    {
+      "epoch": 1.7234866828087168,
+      "grad_norm": 1.188839077949524,
+      "learning_rate": 1.1501279682274368e-05,
+      "loss": 0.0901,
+      "num_input_tokens_seen": 4430344,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7331719128329297,
+      "grad_norm": 2.494746685028076,
+      "learning_rate": 1.1353451737837312e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 4455336,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.3223942518234253,
+      "learning_rate": 1.1205999264124788e-05,
+      "loss": 0.0668,
+      "num_input_tokens_seen": 4480648,
+      "step": 1800
+    },
+    {
+      "epoch": 1.752542372881356,
+      "grad_norm": 1.3812003135681152,
+      "learning_rate": 1.105893744373776e-05,
+      "loss": 0.0788,
+      "num_input_tokens_seen": 4506600,
+      "step": 1810
+    },
+    {
+      "epoch": 1.762227602905569,
+      "grad_norm": 0.7805346250534058,
+      "learning_rate": 1.0912281419053139e-05,
+      "loss": 0.0723,
+      "num_input_tokens_seen": 4531368,
+      "step": 1820
+    },
+    {
+      "epoch": 1.771912832929782,
+      "grad_norm": 1.105878472328186,
+      "learning_rate": 1.0766046290664662e-05,
+      "loss": 0.0779,
+      "num_input_tokens_seen": 4555272,
+      "step": 1830
+    },
+    {
+      "epoch": 1.7815980629539951,
+      "grad_norm": 1.8672295808792114,
+      "learning_rate": 1.0620247115828044e-05,
+      "loss": 0.0838,
+      "num_input_tokens_seen": 4580328,
+      "step": 1840
+    },
+    {
+      "epoch": 1.7912832929782083,
+      "grad_norm": 1.844306468963623,
+      "learning_rate": 1.047489890691055e-05,
+      "loss": 0.0594,
+      "num_input_tokens_seen": 4605768,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8009685230024213,
+      "grad_norm": 1.2717005014419556,
+      "learning_rate": 1.0330016629845276e-05,
+      "loss": 0.04,
+      "num_input_tokens_seen": 4631048,
+      "step": 1860
+    },
+    {
+      "epoch": 1.8106537530266342,
+      "grad_norm": 3.5843582153320312,
+      "learning_rate": 1.0185615202590144e-05,
+      "loss": 0.084,
+      "num_input_tokens_seen": 4656456,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8203389830508474,
+      "grad_norm": 4.254288673400879,
+      "learning_rate": 1.004170949359187e-05,
+      "loss": 0.0654,
+      "num_input_tokens_seen": 4681384,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8300242130750606,
+      "grad_norm": 1.351646065711975,
+      "learning_rate": 9.89831432025501e-06,
+      "loss": 0.0712,
+      "num_input_tokens_seen": 4706216,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8397094430992738,
+      "grad_norm": 1.9015384912490845,
+      "learning_rate": 9.755444447416255e-06,
+      "loss": 0.0829,
+      "num_input_tokens_seen": 4730984,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8493946731234867,
+      "grad_norm": 1.3803085088729858,
+      "learning_rate": 9.613114585824196e-06,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 4755112,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8590799031476997,
+      "grad_norm": 6.487275123596191,
+      "learning_rate": 9.471339390624574e-06,
+      "loss": 0.0781,
+      "num_input_tokens_seen": 4780232,
+      "step": 1920
+    },
+    {
+      "epoch": 1.8687651331719128,
+      "grad_norm": 2.182865619659424,
+      "learning_rate": 9.330133459851323e-06,
+      "loss": 0.0908,
+      "num_input_tokens_seen": 4805192,
+      "step": 1930
+    },
+    {
+      "epoch": 1.878450363196126,
+      "grad_norm": 0.42010384798049927,
+      "learning_rate": 9.189511332923463e-06,
+      "loss": 0.0398,
+      "num_input_tokens_seen": 4830856,
+      "step": 1940
+    },
+    {
+      "epoch": 1.888135593220339,
+      "grad_norm": 1.609157919883728,
+      "learning_rate": 9.049487489148008e-06,
+      "loss": 0.0912,
+      "num_input_tokens_seen": 4855656,
+      "step": 1950
+    },
+    {
+      "epoch": 1.897820823244552,
+      "grad_norm": 2.4291250705718994,
+      "learning_rate": 8.910076346229134e-06,
+      "loss": 0.0746,
+      "num_input_tokens_seen": 4880392,
+      "step": 1960
+    },
+    {
+      "epoch": 1.907506053268765,
+      "grad_norm": 2.243717670440674,
+      "learning_rate": 8.77129225878361e-06,
+      "loss": 0.1066,
+      "num_input_tokens_seen": 4905320,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9171912832929783,
+      "grad_norm": 2.145559072494507,
+      "learning_rate": 8.633149516862777e-06,
+      "loss": 0.0839,
+      "num_input_tokens_seen": 4930536,
+      "step": 1980
+    },
+    {
+      "epoch": 1.9268765133171912,
+      "grad_norm": 0.6746326088905334,
+      "learning_rate": 8.495662344481135e-06,
+      "loss": 0.0527,
+      "num_input_tokens_seen": 4956168,
+      "step": 1990
+    },
+    {
+      "epoch": 1.9365617433414044,
+      "grad_norm": 1.293521761894226,
+      "learning_rate": 8.358844898151791e-06,
+      "loss": 0.1033,
+      "num_input_tokens_seen": 4980584,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3096,
+  "num_input_tokens_seen": 4980584,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1321214729853338e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7a6d9a1a05e78971782a6ee6bb88dfb9617ab9f9e2f35984cd80b0711875f6
+size 5688

checkpoint-3000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-3000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f40422209b44dcf6949244143f9c3a5028460571a63a7ff281dd5bf6a3becc
+size 83945296

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c72806bedfcea859d7f5efbb8f3bb2d6aca36f701f9c922e30b5589a71b6dc
+size 168149074

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293e3fd50e74dc9b279e0b0769e2c511fe2d3e965dac5dda41bc468401725653
+size 1064

checkpoint-3000/special_tokens_map.json

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

checkpoint-3000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-3000/trainer_state.json

@@ -0,0 +1,2433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9046004842615014,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009685230024213076,
+      "grad_norm": 6.778852939605713,
+      "learning_rate": 2.9999227754514262e-05,
+      "loss": 0.8519,
+      "num_input_tokens_seen": 25568,
+      "step": 10
+    },
+    {
+      "epoch": 0.01937046004842615,
+      "grad_norm": 3.0029561519622803,
+      "learning_rate": 2.9996911097572118e-05,
+      "loss": 0.189,
+      "num_input_tokens_seen": 51072,
+      "step": 20
+    },
+    {
+      "epoch": 0.029055690072639227,
+      "grad_norm": 5.477710247039795,
+      "learning_rate": 2.9993050267710624e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 76416,
+      "step": 30
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 4.35634183883667,
+      "learning_rate": 2.9987645662464235e-05,
+      "loss": 0.1905,
+      "num_input_tokens_seen": 101344,
+      "step": 40
+    },
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 4.523565292358398,
+      "learning_rate": 2.9980697838323884e-05,
+      "loss": 0.1794,
+      "num_input_tokens_seen": 126656,
+      "step": 50
+    },
+    {
+      "epoch": 0.05811138014527845,
+      "grad_norm": 1.9348187446594238,
+      "learning_rate": 2.9972207510679677e-05,
+      "loss": 0.1528,
+      "num_input_tokens_seen": 151200,
+      "step": 60
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 2.981433629989624,
+      "learning_rate": 2.996217555374725e-05,
+      "loss": 0.1742,
+      "num_input_tokens_seen": 175968,
+      "step": 70
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 3.6294591426849365,
+      "learning_rate": 2.9950603000477722e-05,
+      "loss": 0.1565,
+      "num_input_tokens_seen": 201280,
+      "step": 80
+    },
+    {
+      "epoch": 0.08716707021791767,
+      "grad_norm": 2.5459301471710205,
+      "learning_rate": 2.993749104245137e-05,
+      "loss": 0.1499,
+      "num_input_tokens_seen": 226432,
+      "step": 90
+    },
+    {
+      "epoch": 0.09685230024213075,
+      "grad_norm": 2.2721059322357178,
+      "learning_rate": 2.992284102975491e-05,
+      "loss": 0.1441,
+      "num_input_tokens_seen": 251744,
+      "step": 100
+    },
+    {
+      "epoch": 0.10653753026634383,
+      "grad_norm": 2.0033624172210693,
+      "learning_rate": 2.9906654470842492e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 276480,
+      "step": 110
+    },
+    {
+      "epoch": 0.1162227602905569,
+      "grad_norm": 8.585118293762207,
+      "learning_rate": 2.9888933032380397e-05,
+      "loss": 0.1333,
+      "num_input_tokens_seen": 301664,
+      "step": 120
+    },
+    {
+      "epoch": 0.12590799031476999,
+      "grad_norm": 1.423967719078064,
+      "learning_rate": 2.9869678539075403e-05,
+      "loss": 0.1728,
+      "num_input_tokens_seen": 326784,
+      "step": 130
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 2.6306211948394775,
+      "learning_rate": 2.9848892973486912e-05,
+      "loss": 0.1281,
+      "num_input_tokens_seen": 351328,
+      "step": 140
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 2.5618090629577637,
+      "learning_rate": 2.9826578475822825e-05,
+      "loss": 0.1136,
+      "num_input_tokens_seen": 376000,
+      "step": 150
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 2.694077730178833,
+      "learning_rate": 2.980273734371914e-05,
+      "loss": 0.1277,
+      "num_input_tokens_seen": 400384,
+      "step": 160
+    },
+    {
+      "epoch": 0.16464891041162227,
+      "grad_norm": 2.632338047027588,
+      "learning_rate": 2.9777372032003423e-05,
+      "loss": 0.1028,
+      "num_input_tokens_seen": 426432,
+      "step": 170
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "grad_norm": 2.3446829319000244,
+      "learning_rate": 2.975048515244199e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 451712,
+      "step": 180
+    },
+    {
+      "epoch": 0.18401937046004843,
+      "grad_norm": 1.8457319736480713,
+      "learning_rate": 2.9722079473471035e-05,
+      "loss": 0.142,
+      "num_input_tokens_seen": 476960,
+      "step": 190
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 1.8676010370254517,
+      "learning_rate": 2.9692157919911536e-05,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 501440,
+      "step": 200
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 4.593673229217529,
+      "learning_rate": 2.966072357266811e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 526656,
+      "step": 210
+    },
+    {
+      "epoch": 0.21307506053268765,
+      "grad_norm": 3.9568676948547363,
+      "learning_rate": 2.9627779668411795e-05,
+      "loss": 0.171,
+      "num_input_tokens_seen": 552544,
+      "step": 220
+    },
+    {
+      "epoch": 0.22276029055690072,
+      "grad_norm": 2.4331846237182617,
+      "learning_rate": 2.9593329599246766e-05,
+      "loss": 0.115,
+      "num_input_tokens_seen": 577472,
+      "step": 230
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 2.525543212890625,
+      "learning_rate": 2.955737691236108e-05,
+      "loss": 0.1158,
+      "num_input_tokens_seen": 601856,
+      "step": 240
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 2.2355105876922607,
+      "learning_rate": 2.9519925309661422e-05,
+      "loss": 0.111,
+      "num_input_tokens_seen": 627904,
+      "step": 250
+    },
+    {
+      "epoch": 0.25181598062953997,
+      "grad_norm": 4.165389537811279,
+      "learning_rate": 2.948097864739194e-05,
+      "loss": 0.1314,
+      "num_input_tokens_seen": 651936,
+      "step": 260
+    },
+    {
+      "epoch": 0.26150121065375304,
+      "grad_norm": 3.1712851524353027,
+      "learning_rate": 2.944054093573719e-05,
+      "loss": 0.143,
+      "num_input_tokens_seen": 676416,
+      "step": 270
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 2.881716728210449,
+      "learning_rate": 2.93986163384092e-05,
+      "loss": 0.1121,
+      "num_input_tokens_seen": 700832,
+      "step": 280
+    },
+    {
+      "epoch": 0.28087167070217917,
+      "grad_norm": 3.060872793197632,
+      "learning_rate": 2.9355209172218777e-05,
+      "loss": 0.1159,
+      "num_input_tokens_seen": 725824,
+      "step": 290
+    },
+    {
+      "epoch": 0.29055690072639223,
+      "grad_norm": 4.449444770812988,
+      "learning_rate": 2.931032390663101e-05,
+      "loss": 0.133,
+      "num_input_tokens_seen": 749408,
+      "step": 300
+    },
+    {
+      "epoch": 0.30024213075060535,
+      "grad_norm": 5.323568344116211,
+      "learning_rate": 2.926396516330506e-05,
+      "loss": 0.1172,
+      "num_input_tokens_seen": 773984,
+      "step": 310
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 3.144500732421875,
+      "learning_rate": 2.921613771561829e-05,
+      "loss": 0.136,
+      "num_input_tokens_seen": 799168,
+      "step": 320
+    },
+    {
+      "epoch": 0.3196125907990315,
+      "grad_norm": 2.433586359024048,
+      "learning_rate": 2.916684648817478e-05,
+      "loss": 0.0973,
+      "num_input_tokens_seen": 824320,
+      "step": 330
+    },
+    {
+      "epoch": 0.32929782082324455,
+      "grad_norm": 3.349472761154175,
+      "learning_rate": 2.9116096556298256e-05,
+      "loss": 0.13,
+      "num_input_tokens_seen": 849632,
+      "step": 340
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 1.8927061557769775,
+      "learning_rate": 2.9063893145509475e-05,
+      "loss": 0.1257,
+      "num_input_tokens_seen": 874400,
+      "step": 350
+    },
+    {
+      "epoch": 0.3486682808716707,
+      "grad_norm": 3.972686529159546,
+      "learning_rate": 2.901024163098822e-05,
+      "loss": 0.1155,
+      "num_input_tokens_seen": 899264,
+      "step": 360
+    },
+    {
+      "epoch": 0.3583535108958838,
+      "grad_norm": 1.177282452583313,
+      "learning_rate": 2.8955147537019815e-05,
+      "loss": 0.1251,
+      "num_input_tokens_seen": 924544,
+      "step": 370
+    },
+    {
+      "epoch": 0.36803874092009686,
+      "grad_norm": 1.9911576509475708,
+      "learning_rate": 2.88986165364263e-05,
+      "loss": 0.1147,
+      "num_input_tokens_seen": 949792,
+      "step": 380
+    },
+    {
+      "epoch": 0.37772397094430993,
+      "grad_norm": 2.402615785598755,
+      "learning_rate": 2.8840654449982344e-05,
+      "loss": 0.1433,
+      "num_input_tokens_seen": 974112,
+      "step": 390
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 1.3184998035430908,
+      "learning_rate": 2.8781267245815898e-05,
+      "loss": 0.1117,
+      "num_input_tokens_seen": 999168,
+      "step": 400
+    },
+    {
+      "epoch": 0.39709443099273606,
+      "grad_norm": 1.9284625053405762,
+      "learning_rate": 2.8720461038793672e-05,
+      "loss": 0.1353,
+      "num_input_tokens_seen": 1024320,
+      "step": 410
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 3.1020259857177734,
+      "learning_rate": 2.8658242089891515e-05,
+      "loss": 0.1165,
+      "num_input_tokens_seen": 1049088,
+      "step": 420
+    },
+    {
+      "epoch": 0.41646489104116224,
+      "grad_norm": 2.203179359436035,
+      "learning_rate": 2.8594616805549752e-05,
+      "loss": 0.1215,
+      "num_input_tokens_seen": 1073632,
+      "step": 430
+    },
+    {
+      "epoch": 0.4261501210653753,
+      "grad_norm": 2.053194522857666,
+      "learning_rate": 2.8529591737013526e-05,
+      "loss": 0.1066,
+      "num_input_tokens_seen": 1098208,
+      "step": 440
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 2.780935049057007,
+      "learning_rate": 2.8463173579658258e-05,
+      "loss": 0.0879,
+      "num_input_tokens_seen": 1122336,
+      "step": 450
+    },
+    {
+      "epoch": 0.44552058111380144,
+      "grad_norm": 1.9929611682891846,
+      "learning_rate": 2.8395369172300235e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 1147392,
+      "step": 460
+    },
+    {
+      "epoch": 0.4552058111380145,
+      "grad_norm": 1.1469779014587402,
+      "learning_rate": 2.8326185496492464e-05,
+      "loss": 0.1052,
+      "num_input_tokens_seen": 1173248,
+      "step": 470
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 2.501117706298828,
+      "learning_rate": 2.825562967580579e-05,
+      "loss": 0.1086,
+      "num_input_tokens_seen": 1197984,
+      "step": 480
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 2.0266308784484863,
+      "learning_rate": 2.8183708975095406e-05,
+      "loss": 0.1201,
+      "num_input_tokens_seen": 1222720,
+      "step": 490
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 1.1120251417160034,
+      "learning_rate": 2.8110430799752845e-05,
+      "loss": 0.1319,
+      "num_input_tokens_seen": 1247232,
+      "step": 500
+    },
+    {
+      "epoch": 0.4939467312348668,
+      "grad_norm": 1.2014496326446533,
+      "learning_rate": 2.8035802694943457e-05,
+      "loss": 0.1071,
+      "num_input_tokens_seen": 1273184,
+      "step": 510
+    },
+    {
+      "epoch": 0.5036319612590799,
+      "grad_norm": 1.1245245933532715,
+      "learning_rate": 2.7959832344829512e-05,
+      "loss": 0.1554,
+      "num_input_tokens_seen": 1298688,
+      "step": 520
+    },
+    {
+      "epoch": 0.513317191283293,
+      "grad_norm": 2.031115770339966,
+      "learning_rate": 2.7882527571779003e-05,
+      "loss": 0.1196,
+      "num_input_tokens_seen": 1324128,
+      "step": 530
+    },
+    {
+      "epoch": 0.5230024213075061,
+      "grad_norm": 1.7691289186477661,
+      "learning_rate": 2.78038963355602e-05,
+      "loss": 0.1334,
+      "num_input_tokens_seen": 1349120,
+      "step": 540
+    },
+    {
+      "epoch": 0.5326876513317191,
+      "grad_norm": 2.9496989250183105,
+      "learning_rate": 2.7723946732522055e-05,
+      "loss": 0.1109,
+      "num_input_tokens_seen": 1374304,
+      "step": 550
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 2.2881715297698975,
+      "learning_rate": 2.764268699476058e-05,
+      "loss": 0.1274,
+      "num_input_tokens_seen": 1399136,
+      "step": 560
+    },
+    {
+      "epoch": 0.5520581113801453,
+      "grad_norm": 1.9754095077514648,
+      "learning_rate": 2.756012548927119e-05,
+      "loss": 0.1397,
+      "num_input_tokens_seen": 1424672,
+      "step": 570
+    },
+    {
+      "epoch": 0.5617433414043583,
+      "grad_norm": 1.9883428812026978,
+      "learning_rate": 2.7476270717087215e-05,
+      "loss": 0.101,
+      "num_input_tokens_seen": 1449024,
+      "step": 580
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.9653130769729614,
+      "learning_rate": 2.7391131312404556e-05,
+      "loss": 0.0941,
+      "num_input_tokens_seen": 1475264,
+      "step": 590
+    },
+    {
+      "epoch": 0.5811138014527845,
+      "grad_norm": 4.576601028442383,
+      "learning_rate": 2.7304716041692663e-05,
+      "loss": 0.0865,
+      "num_input_tokens_seen": 1500064,
+      "step": 600
+    },
+    {
+      "epoch": 0.5907990314769975,
+      "grad_norm": 2.4046311378479004,
+      "learning_rate": 2.7217033802791906e-05,
+      "loss": 0.1596,
+      "num_input_tokens_seen": 1524448,
+      "step": 610
+    },
+    {
+      "epoch": 0.6004842615012107,
+      "grad_norm": 1.7785555124282837,
+      "learning_rate": 2.7128093623997368e-05,
+      "loss": 0.0891,
+      "num_input_tokens_seen": 1549536,
+      "step": 620
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 2.2736170291900635,
+      "learning_rate": 2.7037904663129262e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 1573408,
+      "step": 630
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 1.0862345695495605,
+      "learning_rate": 2.6946476206589972e-05,
+      "loss": 0.1023,
+      "num_input_tokens_seen": 1597888,
+      "step": 640
+    },
+    {
+      "epoch": 0.6295399515738499,
+      "grad_norm": 0.5358290672302246,
+      "learning_rate": 2.6853817668407875e-05,
+      "loss": 0.0669,
+      "num_input_tokens_seen": 1623296,
+      "step": 650
+    },
+    {
+      "epoch": 0.639225181598063,
+      "grad_norm": 2.3138749599456787,
+      "learning_rate": 2.6759938589268023e-05,
+      "loss": 0.1017,
+      "num_input_tokens_seen": 1649216,
+      "step": 660
+    },
+    {
+      "epoch": 0.648910411622276,
+      "grad_norm": 3.2054226398468018,
+      "learning_rate": 2.6664848635529742e-05,
+      "loss": 0.1432,
+      "num_input_tokens_seen": 1673760,
+      "step": 670
+    },
+    {
+      "epoch": 0.6585956416464891,
+      "grad_norm": 1.8352829217910767,
+      "learning_rate": 2.6568557598231385e-05,
+      "loss": 0.1081,
+      "num_input_tokens_seen": 1698592,
+      "step": 680
+    },
+    {
+      "epoch": 0.6682808716707022,
+      "grad_norm": 1.203284740447998,
+      "learning_rate": 2.6471075392082125e-05,
+      "loss": 0.1037,
+      "num_input_tokens_seen": 1723296,
+      "step": 690
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 1.635628581047058,
+      "learning_rate": 2.6372412054441116e-05,
+      "loss": 0.1216,
+      "num_input_tokens_seen": 1748384,
+      "step": 700
+    },
+    {
+      "epoch": 0.6876513317191283,
+      "grad_norm": 0.8993457555770874,
+      "learning_rate": 2.6272577744283965e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 1773600,
+      "step": 710
+    },
+    {
+      "epoch": 0.6973365617433414,
+      "grad_norm": 1.7306419610977173,
+      "learning_rate": 2.617158274115673e-05,
+      "loss": 0.1034,
+      "num_input_tokens_seen": 1798656,
+      "step": 720
+    },
+    {
+      "epoch": 0.7070217917675545,
+      "grad_norm": 2.770066976547241,
+      "learning_rate": 2.6069437444117432e-05,
+      "loss": 0.0872,
+      "num_input_tokens_seen": 1824544,
+      "step": 730
+    },
+    {
+      "epoch": 0.7167070217917676,
+      "grad_norm": 2.3590221405029297,
+      "learning_rate": 2.596615237066535e-05,
+      "loss": 0.1063,
+      "num_input_tokens_seen": 1848896,
+      "step": 740
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 1.0496519804000854,
+      "learning_rate": 2.586173815565805e-05,
+      "loss": 0.1104,
+      "num_input_tokens_seen": 1873248,
+      "step": 750
+    },
+    {
+      "epoch": 0.7360774818401937,
+      "grad_norm": 1.513573408126831,
+      "learning_rate": 2.575620555021634e-05,
+      "loss": 0.1125,
+      "num_input_tokens_seen": 1897184,
+      "step": 760
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 1.5545728206634521,
+      "learning_rate": 2.564956542061732e-05,
+      "loss": 0.0969,
+      "num_input_tokens_seen": 1922368,
+      "step": 770
+    },
+    {
+      "epoch": 0.7554479418886199,
+      "grad_norm": 1.9260263442993164,
+      "learning_rate": 2.5541828747175477e-05,
+      "loss": 0.1142,
+      "num_input_tokens_seen": 1947904,
+      "step": 780
+    },
+    {
+      "epoch": 0.7651331719128329,
+      "grad_norm": 2.396538734436035,
+      "learning_rate": 2.543300662311211e-05,
+      "loss": 0.0926,
+      "num_input_tokens_seen": 1971872,
+      "step": 790
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 1.7069965600967407,
+      "learning_rate": 2.532311025341309e-05,
+      "loss": 0.0802,
+      "num_input_tokens_seen": 1996352,
+      "step": 800
+    },
+    {
+      "epoch": 0.784503631961259,
+      "grad_norm": 5.540910243988037,
+      "learning_rate": 2.5212150953675133e-05,
+      "loss": 0.1248,
+      "num_input_tokens_seen": 2020480,
+      "step": 810
+    },
+    {
+      "epoch": 0.7941888619854721,
+      "grad_norm": 1.7795952558517456,
+      "learning_rate": 2.5100140148940688e-05,
+      "loss": 0.0767,
+      "num_input_tokens_seen": 2044448,
+      "step": 820
+    },
+    {
+      "epoch": 0.8038740920096852,
+      "grad_norm": 2.7387983798980713,
+      "learning_rate": 2.498708937252153e-05,
+      "loss": 0.1239,
+      "num_input_tokens_seen": 2070400,
+      "step": 830
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 2.1243462562561035,
+      "learning_rate": 2.4873010264811222e-05,
+      "loss": 0.108,
+      "num_input_tokens_seen": 2095392,
+      "step": 840
+    },
+    {
+      "epoch": 0.8232445520581114,
+      "grad_norm": 0.9928631782531738,
+      "learning_rate": 2.4757914572086555e-05,
+      "loss": 0.0994,
+      "num_input_tokens_seen": 2120192,
+      "step": 850
+    },
+    {
+      "epoch": 0.8329297820823245,
+      "grad_norm": 6.047460556030273,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.0927,
+      "num_input_tokens_seen": 2144384,
+      "step": 860
+    },
+    {
+      "epoch": 0.8426150121065376,
+      "grad_norm": 2.2197115421295166,
+      "learning_rate": 2.4524720938849883e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2168704,
+      "step": 870
+    },
+    {
+      "epoch": 0.8523002421307506,
+      "grad_norm": 2.0752601623535156,
+      "learning_rate": 2.440664700936861e-05,
+      "loss": 0.1229,
+      "num_input_tokens_seen": 2193248,
+      "step": 880
+    },
+    {
+      "epoch": 0.8619854721549637,
+      "grad_norm": 1.00425386428833,
+      "learning_rate": 2.4287604514462152e-05,
+      "loss": 0.0957,
+      "num_input_tokens_seen": 2217568,
+      "step": 890
+    },
+    {
+      "epoch": 0.8716707021791767,
+      "grad_norm": 1.9153094291687012,
+      "learning_rate": 2.416760571146774e-05,
+      "loss": 0.0975,
+      "num_input_tokens_seen": 2242048,
+      "step": 900
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 2.3558013439178467,
+      "learning_rate": 2.4046662956189898e-05,
+      "loss": 0.1068,
+      "num_input_tokens_seen": 2266112,
+      "step": 910
+    },
+    {
+      "epoch": 0.8910411622276029,
+      "grad_norm": 2.546351909637451,
+      "learning_rate": 2.3924788701628197e-05,
+      "loss": 0.0688,
+      "num_input_tokens_seen": 2290720,
+      "step": 920
+    },
+    {
+      "epoch": 0.9007263922518159,
+      "grad_norm": 1.2526168823242188,
+      "learning_rate": 2.3801995496695028e-05,
+      "loss": 0.1141,
+      "num_input_tokens_seen": 2315488,
+      "step": 930
+    },
+    {
+      "epoch": 0.910411622276029,
+      "grad_norm": 2.134089231491089,
+      "learning_rate": 2.367829598492348e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 2340992,
+      "step": 940
+    },
+    {
+      "epoch": 0.9200968523002422,
+      "grad_norm": 1.332915186882019,
+      "learning_rate": 2.3553702903165502e-05,
+      "loss": 0.1,
+      "num_input_tokens_seen": 2366880,
+      "step": 950
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 1.5140970945358276,
+      "learning_rate": 2.3428229080280407e-05,
+      "loss": 0.1089,
+      "num_input_tokens_seen": 2392000,
+      "step": 960
+    },
+    {
+      "epoch": 0.9394673123486683,
+      "grad_norm": 1.531954288482666,
+      "learning_rate": 2.330188743581398e-05,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 2417472,
+      "step": 970
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 1.3347736597061157,
+      "learning_rate": 2.3174690978668155e-05,
+      "loss": 0.1205,
+      "num_input_tokens_seen": 2442496,
+      "step": 980
+    },
+    {
+      "epoch": 0.9588377723970944,
+      "grad_norm": 3.1497702598571777,
+      "learning_rate": 2.3046652805761588e-05,
+      "loss": 0.1004,
+      "num_input_tokens_seen": 2467392,
+      "step": 990
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 1.6756023168563843,
+      "learning_rate": 2.2917786100681078e-05,
+      "loss": 0.1007,
+      "num_input_tokens_seen": 2492768,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9782082324455206,
+      "grad_norm": 2.56594181060791,
+      "learning_rate": 2.2788104132324125e-05,
+      "loss": 0.1179,
+      "num_input_tokens_seen": 2518176,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9878934624697336,
+      "grad_norm": 2.1090595722198486,
+      "learning_rate": 2.2657620253532685e-05,
+      "loss": 0.0971,
+      "num_input_tokens_seen": 2543296,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9975786924939467,
+      "grad_norm": 0.41959595680236816,
+      "learning_rate": 2.252634789971827e-05,
+      "loss": 0.0932,
+      "num_input_tokens_seen": 2567680,
+      "step": 1030
+    },
+    {
+      "epoch": 1.006779661016949,
+      "grad_norm": 1.6389803886413574,
+      "learning_rate": 2.2394300587478566e-05,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 2591016,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0164648910411622,
+      "grad_norm": 1.4045557975769043,
+      "learning_rate": 2.2261491913205684e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 2615752,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0261501210653754,
+      "grad_norm": 2.0734925270080566,
+      "learning_rate": 2.212793555168617e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 2640200,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0358353510895884,
+      "grad_norm": 2.1590147018432617,
+      "learning_rate": 2.1993645254692994e-05,
+      "loss": 0.116,
+      "num_input_tokens_seen": 2665416,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0455205811138015,
+      "grad_norm": 1.739646553993225,
+      "learning_rate": 2.1858634849569578e-05,
+      "loss": 0.0972,
+      "num_input_tokens_seen": 2690376,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0552058111380145,
+      "grad_norm": 0.6458954215049744,
+      "learning_rate": 2.1722918237806042e-05,
+      "loss": 0.0884,
+      "num_input_tokens_seen": 2715080,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0648910411622277,
+      "grad_norm": 2.2830138206481934,
+      "learning_rate": 2.158650939360782e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 2740424,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0745762711864406,
+      "grad_norm": 1.5225194692611694,
+      "learning_rate": 2.1449422362456794e-05,
+      "loss": 0.0813,
+      "num_input_tokens_seen": 2765640,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0842615012106538,
+      "grad_norm": 1.683604121208191,
+      "learning_rate": 2.13116712596651e-05,
+      "loss": 0.0953,
+      "num_input_tokens_seen": 2791176,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0939467312348667,
+      "grad_norm": 1.5679166316986084,
+      "learning_rate": 2.1173270268921703e-05,
+      "loss": 0.0933,
+      "num_input_tokens_seen": 2816072,
+      "step": 1130
+    },
+    {
+      "epoch": 1.10363196125908,
+      "grad_norm": 1.3097947835922241,
+      "learning_rate": 2.1034233640831988e-05,
+      "loss": 0.0819,
+      "num_input_tokens_seen": 2840776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.113317191283293,
+      "grad_norm": 0.5728388428688049,
+      "learning_rate": 2.0894575691450396e-05,
+      "loss": 0.0611,
+      "num_input_tokens_seen": 2865416,
+      "step": 1150
+    },
+    {
+      "epoch": 1.123002421307506,
+      "grad_norm": 2.3043558597564697,
+      "learning_rate": 2.0754310800806395e-05,
+      "loss": 0.0748,
+      "num_input_tokens_seen": 2890248,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1326876513317192,
+      "grad_norm": 1.2087112665176392,
+      "learning_rate": 2.0613453411423797e-05,
+      "loss": 0.0959,
+      "num_input_tokens_seen": 2916392,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1423728813559322,
+      "grad_norm": 1.5639240741729736,
+      "learning_rate": 2.0472018026833684e-05,
+      "loss": 0.0709,
+      "num_input_tokens_seen": 2941160,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1520581113801454,
+      "grad_norm": 0.5889459848403931,
+      "learning_rate": 2.0330019210081022e-05,
+      "loss": 0.0731,
+      "num_input_tokens_seen": 2966120,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1617433414043583,
+      "grad_norm": 1.854230523109436,
+      "learning_rate": 2.0187471582225173e-05,
+      "loss": 0.1005,
+      "num_input_tokens_seen": 2990088,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 2.01247239112854,
+      "learning_rate": 2.004438982083442e-05,
+      "loss": 0.0579,
+      "num_input_tokens_seen": 3015400,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1811138014527844,
+      "grad_norm": 2.292900323867798,
+      "learning_rate": 1.9900788658474677e-05,
+      "loss": 0.0792,
+      "num_input_tokens_seen": 3039464,
+      "step": 1220
+    },
+    {
+      "epoch": 1.1907990314769976,
+      "grad_norm": 1.4194159507751465,
+      "learning_rate": 1.975668288119252e-05,
+      "loss": 0.057,
+      "num_input_tokens_seen": 3063816,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2004842615012106,
+      "grad_norm": 1.0512489080429077,
+      "learning_rate": 1.961208732699275e-05,
+      "loss": 0.102,
+      "num_input_tokens_seen": 3088968,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2101694915254237,
+      "grad_norm": 0.9465106129646301,
+      "learning_rate": 1.9467016884310565e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 3113736,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2198547215496367,
+      "grad_norm": 1.274294376373291,
+      "learning_rate": 1.9321486490478565e-05,
+      "loss": 0.0668,
+      "num_input_tokens_seen": 3138344,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2295399515738499,
+      "grad_norm": 1.9390579462051392,
+      "learning_rate": 1.91755111301887e-05,
+      "loss": 0.0711,
+      "num_input_tokens_seen": 3163496,
+      "step": 1270
+    },
+    {
+      "epoch": 1.239225181598063,
+      "grad_norm": 1.2855744361877441,
+      "learning_rate": 1.902910583394938e-05,
+      "loss": 0.0605,
+      "num_input_tokens_seen": 3188392,
+      "step": 1280
+    },
+    {
+      "epoch": 1.248910411622276,
+      "grad_norm": 2.931248188018799,
+      "learning_rate": 1.888228567653781e-05,
+      "loss": 0.0448,
+      "num_input_tokens_seen": 3213224,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2585956416464892,
+      "grad_norm": 1.9991300106048584,
+      "learning_rate": 1.873506577544784e-05,
+      "loss": 0.0815,
+      "num_input_tokens_seen": 3238568,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2682808716707021,
+      "grad_norm": 1.3530927896499634,
+      "learning_rate": 1.8587461289333327e-05,
+      "loss": 0.1043,
+      "num_input_tokens_seen": 3264264,
+      "step": 1310
+    },
+    {
+      "epoch": 1.2779661016949153,
+      "grad_norm": 2.07991099357605,
+      "learning_rate": 1.8439487416447353e-05,
+      "loss": 0.1037,
+      "num_input_tokens_seen": 3288840,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2876513317191283,
+      "grad_norm": 1.8533947467803955,
+      "learning_rate": 1.8291159393077294e-05,
+      "loss": 0.0928,
+      "num_input_tokens_seen": 3313832,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2973365617433414,
+      "grad_norm": 1.118119716644287,
+      "learning_rate": 1.814249249197602e-05,
+      "loss": 0.0775,
+      "num_input_tokens_seen": 3337736,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3070217917675544,
+      "grad_norm": 2.740079641342163,
+      "learning_rate": 1.7993502020789294e-05,
+      "loss": 0.0521,
+      "num_input_tokens_seen": 3362024,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3167070217917676,
+      "grad_norm": 1.9268351793289185,
+      "learning_rate": 1.7844203320479614e-05,
+      "loss": 0.0687,
+      "num_input_tokens_seen": 3387496,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3263922518159807,
+      "grad_norm": 2.3576388359069824,
+      "learning_rate": 1.7694611763746632e-05,
+      "loss": 0.0704,
+      "num_input_tokens_seen": 3412072,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3360774818401937,
+      "grad_norm": 1.127432942390442,
+      "learning_rate": 1.754474275344427e-05,
+      "loss": 0.0826,
+      "num_input_tokens_seen": 3437096,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3457627118644067,
+      "grad_norm": 4.377537250518799,
+      "learning_rate": 1.7394611720994747e-05,
+      "loss": 0.0445,
+      "num_input_tokens_seen": 3462120,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3554479418886198,
+      "grad_norm": 2.1285200119018555,
+      "learning_rate": 1.724423412479967e-05,
+      "loss": 0.0951,
+      "num_input_tokens_seen": 3486952,
+      "step": 1400
+    },
+    {
+      "epoch": 1.365133171912833,
+      "grad_norm": 0.16216270625591278,
+      "learning_rate": 1.7093625448648348e-05,
+      "loss": 0.0539,
+      "num_input_tokens_seen": 3512264,
+      "step": 1410
+    },
+    {
+      "epoch": 1.374818401937046,
+      "grad_norm": 2.1299915313720703,
+      "learning_rate": 1.694280120012349e-05,
+      "loss": 0.0848,
+      "num_input_tokens_seen": 3537192,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3845036319612591,
+      "grad_norm": 2.476757049560547,
+      "learning_rate": 1.6791776909004434e-05,
+      "loss": 0.0629,
+      "num_input_tokens_seen": 3560872,
+      "step": 1430
+    },
+    {
+      "epoch": 1.394188861985472,
+      "grad_norm": 0.4373377561569214,
+      "learning_rate": 1.664056812566812e-05,
+      "loss": 0.079,
+      "num_input_tokens_seen": 3586216,
+      "step": 1440
+    },
+    {
+      "epoch": 1.4038740920096853,
+      "grad_norm": 1.9471170902252197,
+      "learning_rate": 1.648919041948792e-05,
+      "loss": 0.0798,
+      "num_input_tokens_seen": 3610792,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4135593220338982,
+      "grad_norm": 2.911750316619873,
+      "learning_rate": 1.6337659377230544e-05,
+      "loss": 0.0897,
+      "num_input_tokens_seen": 3634760,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4232445520581114,
+      "grad_norm": 2.9474802017211914,
+      "learning_rate": 1.61859906014511e-05,
+      "loss": 0.0858,
+      "num_input_tokens_seen": 3659560,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4329297820823244,
+      "grad_norm": 0.6501768827438354,
+      "learning_rate": 1.6034199708886573e-05,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 3684840,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4426150121065375,
+      "grad_norm": 1.6708017587661743,
+      "learning_rate": 1.5882302328847847e-05,
+      "loss": 0.0842,
+      "num_input_tokens_seen": 3709096,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4523002421307507,
+      "grad_norm": 1.5014967918395996,
+      "learning_rate": 1.5730314101610376e-05,
+      "loss": 0.0367,
+      "num_input_tokens_seen": 3734728,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4619854721549637,
+      "grad_norm": 3.2587804794311523,
+      "learning_rate": 1.5578250676803824e-05,
+      "loss": 0.1085,
+      "num_input_tokens_seen": 3758984,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4716707021791768,
+      "grad_norm": 6.304242134094238,
+      "learning_rate": 1.5426127711800636e-05,
+      "loss": 0.0712,
+      "num_input_tokens_seen": 3784296,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4813559322033898,
+      "grad_norm": 1.1681016683578491,
+      "learning_rate": 1.5273960870103872e-05,
+      "loss": 0.0705,
+      "num_input_tokens_seen": 3809768,
+      "step": 1530
+    },
+    {
+      "epoch": 1.491041162227603,
+      "grad_norm": 1.111617922782898,
+      "learning_rate": 1.5121765819734418e-05,
+      "loss": 0.071,
+      "num_input_tokens_seen": 3834536,
+      "step": 1540
+    },
+    {
+      "epoch": 1.5007263922518161,
+      "grad_norm": 1.7780523300170898,
+      "learning_rate": 1.4969558231617681e-05,
+      "loss": 0.0648,
+      "num_input_tokens_seen": 3858792,
+      "step": 1550
+    },
+    {
+      "epoch": 1.510411622276029,
+      "grad_norm": 2.2017934322357178,
+      "learning_rate": 1.4817353777970038e-05,
+      "loss": 0.0633,
+      "num_input_tokens_seen": 3883976,
+      "step": 1560
+    },
+    {
+      "epoch": 1.520096852300242,
+      "grad_norm": 1.8567978143692017,
+      "learning_rate": 1.466516813068512e-05,
+      "loss": 0.0726,
+      "num_input_tokens_seen": 3908392,
+      "step": 1570
+    },
+    {
+      "epoch": 1.5297820823244552,
+      "grad_norm": 2.567291021347046,
+      "learning_rate": 1.451301695972015e-05,
+      "loss": 0.0882,
+      "num_input_tokens_seen": 3932552,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5394673123486684,
+      "grad_norm": 1.9968935251235962,
+      "learning_rate": 1.436091593148244e-05,
+      "loss": 0.1149,
+      "num_input_tokens_seen": 3957672,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5491525423728814,
+      "grad_norm": 1.9058917760849,
+      "learning_rate": 1.4208880707216323e-05,
+      "loss": 0.0841,
+      "num_input_tokens_seen": 3982824,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5588377723970943,
+      "grad_norm": 1.9218000173568726,
+      "learning_rate": 1.405692694139054e-05,
+      "loss": 0.0896,
+      "num_input_tokens_seen": 4008072,
+      "step": 1610
+    },
+    {
+      "epoch": 1.5685230024213075,
+      "grad_norm": 1.5786553621292114,
+      "learning_rate": 1.3905070280086387e-05,
+      "loss": 0.0629,
+      "num_input_tokens_seen": 4033096,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5782082324455207,
+      "grad_norm": 2.503990888595581,
+      "learning_rate": 1.3753326359386695e-05,
+      "loss": 0.077,
+      "num_input_tokens_seen": 4058120,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5878934624697336,
+      "grad_norm": 1.5616143941879272,
+      "learning_rate": 1.3601710803765814e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 4082792,
+      "step": 1640
+    },
+    {
+      "epoch": 1.5975786924939466,
+      "grad_norm": 1.2533211708068848,
+      "learning_rate": 1.3450239224480884e-05,
+      "loss": 0.0605,
+      "num_input_tokens_seen": 4107336,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6072639225181597,
+      "grad_norm": 1.1046490669250488,
+      "learning_rate": 1.329892721796433e-05,
+      "loss": 0.0985,
+      "num_input_tokens_seen": 4132456,
+      "step": 1660
+    },
+    {
+      "epoch": 1.616949152542373,
+      "grad_norm": 1.143494725227356,
+      "learning_rate": 1.314779036421802e-05,
+      "loss": 0.0547,
+      "num_input_tokens_seen": 4156584,
+      "step": 1670
+    },
+    {
+      "epoch": 1.626634382566586,
+      "grad_norm": 2.6082706451416016,
+      "learning_rate": 1.2996844225209033e-05,
+      "loss": 0.0919,
+      "num_input_tokens_seen": 4181448,
+      "step": 1680
+    },
+    {
+      "epoch": 1.636319612590799,
+      "grad_norm": 2.4191458225250244,
+      "learning_rate": 1.2846104343267283e-05,
+      "loss": 0.1204,
+      "num_input_tokens_seen": 4207560,
+      "step": 1690
+    },
+    {
+      "epoch": 1.646004842615012,
+      "grad_norm": 2.051799774169922,
+      "learning_rate": 1.2695586239485223e-05,
+      "loss": 0.0664,
+      "num_input_tokens_seen": 4232040,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6556900726392252,
+      "grad_norm": 1.525844931602478,
+      "learning_rate": 1.254530541211968e-05,
+      "loss": 0.0805,
+      "num_input_tokens_seen": 4257576,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6653753026634384,
+      "grad_norm": 0.9474373459815979,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.073,
+      "num_input_tokens_seen": 4282472,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6750605326876513,
+      "grad_norm": 1.8932424783706665,
+      "learning_rate": 1.2245517455915036e-05,
+      "loss": 0.0734,
+      "num_input_tokens_seen": 4306792,
+      "step": 1730
+    },
+    {
+      "epoch": 1.6847457627118643,
+      "grad_norm": 1.9888746738433838,
+      "learning_rate": 1.2096041195062051e-05,
+      "loss": 0.0831,
+      "num_input_tokens_seen": 4333384,
+      "step": 1740
+    },
+    {
+      "epoch": 1.6944309927360774,
+      "grad_norm": 1.8355742692947388,
+      "learning_rate": 1.1946863943419452e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 4358344,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7041162227602906,
+      "grad_norm": 2.8447251319885254,
+      "learning_rate": 1.1798001061181799e-05,
+      "loss": 0.0988,
+      "num_input_tokens_seen": 4381768,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7138014527845038,
+      "grad_norm": 2.670257806777954,
+      "learning_rate": 1.1649467876174252e-05,
+      "loss": 0.0936,
+      "num_input_tokens_seen": 4405192,
+      "step": 1770
+    },
+    {
+      "epoch": 1.7234866828087168,
+      "grad_norm": 1.188839077949524,
+      "learning_rate": 1.1501279682274368e-05,
+      "loss": 0.0901,
+      "num_input_tokens_seen": 4430344,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7331719128329297,
+      "grad_norm": 2.494746685028076,
+      "learning_rate": 1.1353451737837312e-05,
+      "loss": 0.0691,
+      "num_input_tokens_seen": 4455336,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.3223942518234253,
+      "learning_rate": 1.1205999264124788e-05,
+      "loss": 0.0668,
+      "num_input_tokens_seen": 4480648,
+      "step": 1800
+    },
+    {
+      "epoch": 1.752542372881356,
+      "grad_norm": 1.3812003135681152,
+      "learning_rate": 1.105893744373776e-05,
+      "loss": 0.0788,
+      "num_input_tokens_seen": 4506600,
+      "step": 1810
+    },
+    {
+      "epoch": 1.762227602905569,
+      "grad_norm": 0.7805346250534058,
+      "learning_rate": 1.0912281419053139e-05,
+      "loss": 0.0723,
+      "num_input_tokens_seen": 4531368,
+      "step": 1820
+    },
+    {
+      "epoch": 1.771912832929782,
+      "grad_norm": 1.105878472328186,
+      "learning_rate": 1.0766046290664662e-05,
+      "loss": 0.0779,
+      "num_input_tokens_seen": 4555272,
+      "step": 1830
+    },
+    {
+      "epoch": 1.7815980629539951,
+      "grad_norm": 1.8672295808792114,
+      "learning_rate": 1.0620247115828044e-05,
+      "loss": 0.0838,
+      "num_input_tokens_seen": 4580328,
+      "step": 1840
+    },
+    {
+      "epoch": 1.7912832929782083,
+      "grad_norm": 1.844306468963623,
+      "learning_rate": 1.047489890691055e-05,
+      "loss": 0.0594,
+      "num_input_tokens_seen": 4605768,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8009685230024213,
+      "grad_norm": 1.2717005014419556,
+      "learning_rate": 1.0330016629845276e-05,
+      "loss": 0.04,
+      "num_input_tokens_seen": 4631048,
+      "step": 1860
+    },
+    {
+      "epoch": 1.8106537530266342,
+      "grad_norm": 3.5843582153320312,
+      "learning_rate": 1.0185615202590144e-05,
+      "loss": 0.084,
+      "num_input_tokens_seen": 4656456,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8203389830508474,
+      "grad_norm": 4.254288673400879,
+      "learning_rate": 1.004170949359187e-05,
+      "loss": 0.0654,
+      "num_input_tokens_seen": 4681384,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8300242130750606,
+      "grad_norm": 1.351646065711975,
+      "learning_rate": 9.89831432025501e-06,
+      "loss": 0.0712,
+      "num_input_tokens_seen": 4706216,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8397094430992738,
+      "grad_norm": 1.9015384912490845,
+      "learning_rate": 9.755444447416255e-06,
+      "loss": 0.0829,
+      "num_input_tokens_seen": 4730984,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8493946731234867,
+      "grad_norm": 1.3803085088729858,
+      "learning_rate": 9.613114585824196e-06,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 4755112,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8590799031476997,
+      "grad_norm": 6.487275123596191,
+      "learning_rate": 9.471339390624574e-06,
+      "loss": 0.0781,
+      "num_input_tokens_seen": 4780232,
+      "step": 1920
+    },
+    {
+      "epoch": 1.8687651331719128,
+      "grad_norm": 2.182865619659424,
+      "learning_rate": 9.330133459851323e-06,
+      "loss": 0.0908,
+      "num_input_tokens_seen": 4805192,
+      "step": 1930
+    },
+    {
+      "epoch": 1.878450363196126,
+      "grad_norm": 0.42010384798049927,
+      "learning_rate": 9.189511332923463e-06,
+      "loss": 0.0398,
+      "num_input_tokens_seen": 4830856,
+      "step": 1940
+    },
+    {
+      "epoch": 1.888135593220339,
+      "grad_norm": 1.609157919883728,
+      "learning_rate": 9.049487489148008e-06,
+      "loss": 0.0912,
+      "num_input_tokens_seen": 4855656,
+      "step": 1950
+    },
+    {
+      "epoch": 1.897820823244552,
+      "grad_norm": 2.4291250705718994,
+      "learning_rate": 8.910076346229134e-06,
+      "loss": 0.0746,
+      "num_input_tokens_seen": 4880392,
+      "step": 1960
+    },
+    {
+      "epoch": 1.907506053268765,
+      "grad_norm": 2.243717670440674,
+      "learning_rate": 8.77129225878361e-06,
+      "loss": 0.1066,
+      "num_input_tokens_seen": 4905320,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9171912832929783,
+      "grad_norm": 2.145559072494507,
+      "learning_rate": 8.633149516862777e-06,
+      "loss": 0.0839,
+      "num_input_tokens_seen": 4930536,
+      "step": 1980
+    },
+    {
+      "epoch": 1.9268765133171912,
+      "grad_norm": 0.6746326088905334,
+      "learning_rate": 8.495662344481135e-06,
+      "loss": 0.0527,
+      "num_input_tokens_seen": 4956168,
+      "step": 1990
+    },
+    {
+      "epoch": 1.9365617433414044,
+      "grad_norm": 1.293521761894226,
+      "learning_rate": 8.358844898151791e-06,
+      "loss": 0.1033,
+      "num_input_tokens_seen": 4980584,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9462469733656174,
+      "grad_norm": 1.7922570705413818,
+      "learning_rate": 8.222711265428779e-06,
+      "loss": 0.079,
+      "num_input_tokens_seen": 5005992,
+      "step": 2010
+    },
+    {
+      "epoch": 1.9559322033898305,
+      "grad_norm": 1.0770626068115234,
+      "learning_rate": 8.087275463456548e-06,
+      "loss": 0.0652,
+      "num_input_tokens_seen": 5032168,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9656174334140437,
+      "grad_norm": 0.7968271374702454,
+      "learning_rate": 7.952551437526648e-06,
+      "loss": 0.0593,
+      "num_input_tokens_seen": 5056296,
+      "step": 2030
+    },
+    {
+      "epoch": 1.9753026634382567,
+      "grad_norm": 2.140667676925659,
+      "learning_rate": 7.818553059641868e-06,
+      "loss": 0.0933,
+      "num_input_tokens_seen": 5080424,
+      "step": 2040
+    },
+    {
+      "epoch": 1.9849878934624696,
+      "grad_norm": 2.905066967010498,
+      "learning_rate": 7.685294127087852e-06,
+      "loss": 0.059,
+      "num_input_tokens_seen": 5104904,
+      "step": 2050
+    },
+    {
+      "epoch": 1.9946731234866828,
+      "grad_norm": 2.5095653533935547,
+      "learning_rate": 7.552788361012486e-06,
+      "loss": 0.0766,
+      "num_input_tokens_seen": 5129064,
+      "step": 2060
+    },
+    {
+      "epoch": 2.0038740920096854,
+      "grad_norm": 1.0241445302963257,
+      "learning_rate": 7.421049405013061e-06,
+      "loss": 0.0637,
+      "num_input_tokens_seen": 5152120,
+      "step": 2070
+    },
+    {
+      "epoch": 2.013559322033898,
+      "grad_norm": 1.7620762586593628,
+      "learning_rate": 7.290090823731452e-06,
+      "loss": 0.0419,
+      "num_input_tokens_seen": 5176728,
+      "step": 2080
+    },
+    {
+      "epoch": 2.0232445520581113,
+      "grad_norm": 1.1471503973007202,
+      "learning_rate": 7.159926101457423e-06,
+      "loss": 0.0586,
+      "num_input_tokens_seen": 5201176,
+      "step": 2090
+    },
+    {
+      "epoch": 2.0329297820823244,
+      "grad_norm": 1.4868978261947632,
+      "learning_rate": 7.030568640740202e-06,
+      "loss": 0.0382,
+      "num_input_tokens_seen": 5225368,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0426150121065376,
+      "grad_norm": 0.8362380266189575,
+      "learning_rate": 6.902031761008456e-06,
+      "loss": 0.0597,
+      "num_input_tokens_seen": 5250136,
+      "step": 2110
+    },
+    {
+      "epoch": 2.052300242130751,
+      "grad_norm": 2.6067404747009277,
+      "learning_rate": 6.774328697198879e-06,
+      "loss": 0.0367,
+      "num_input_tokens_seen": 5274264,
+      "step": 2120
+    },
+    {
+      "epoch": 2.0619854721549635,
+      "grad_norm": 1.6327483654022217,
+      "learning_rate": 6.647472598393399e-06,
+      "loss": 0.04,
+      "num_input_tokens_seen": 5298264,
+      "step": 2130
+    },
+    {
+      "epoch": 2.0716707021791767,
+      "grad_norm": 1.461899995803833,
+      "learning_rate": 6.521476526465309e-06,
+      "loss": 0.0426,
+      "num_input_tokens_seen": 5322872,
+      "step": 2140
+    },
+    {
+      "epoch": 2.08135593220339,
+      "grad_norm": 2.3133087158203125,
+      "learning_rate": 6.3963534547343126e-06,
+      "loss": 0.0706,
+      "num_input_tokens_seen": 5348120,
+      "step": 2150
+    },
+    {
+      "epoch": 2.091041162227603,
+      "grad_norm": 3.1375937461853027,
+      "learning_rate": 6.27211626663071e-06,
+      "loss": 0.0377,
+      "num_input_tokens_seen": 5373240,
+      "step": 2160
+    },
+    {
+      "epoch": 2.100726392251816,
+      "grad_norm": 2.147362470626831,
+      "learning_rate": 6.148777754368862e-06,
+      "loss": 0.0608,
+      "num_input_tokens_seen": 5398296,
+      "step": 2170
+    },
+    {
+      "epoch": 2.110411622276029,
+      "grad_norm": 0.6415455341339111,
+      "learning_rate": 6.026350617630011e-06,
+      "loss": 0.0334,
+      "num_input_tokens_seen": 5424408,
+      "step": 2180
+    },
+    {
+      "epoch": 2.120096852300242,
+      "grad_norm": 3.5363268852233887,
+      "learning_rate": 5.904847462254646e-06,
+      "loss": 0.0445,
+      "num_input_tokens_seen": 5449880,
+      "step": 2190
+    },
+    {
+      "epoch": 2.1297820823244553,
+      "grad_norm": 2.8637278079986572,
+      "learning_rate": 5.784280798944537e-06,
+      "loss": 0.0735,
+      "num_input_tokens_seen": 5474808,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1394673123486685,
+      "grad_norm": 1.1030181646347046,
+      "learning_rate": 5.6646630419745404e-06,
+      "loss": 0.056,
+      "num_input_tokens_seen": 5499672,
+      "step": 2210
+    },
+    {
+      "epoch": 2.1491525423728812,
+      "grad_norm": 1.6034140586853027,
+      "learning_rate": 5.5460065079143694e-06,
+      "loss": 0.0703,
+      "num_input_tokens_seen": 5523672,
+      "step": 2220
+    },
+    {
+      "epoch": 2.1588377723970944,
+      "grad_norm": 4.010861396789551,
+      "learning_rate": 5.428323414360401e-06,
+      "loss": 0.0504,
+      "num_input_tokens_seen": 5548664,
+      "step": 2230
+    },
+    {
+      "epoch": 2.1685230024213076,
+      "grad_norm": 2.1378917694091797,
+      "learning_rate": 5.311625878677658e-06,
+      "loss": 0.0398,
+      "num_input_tokens_seen": 5573944,
+      "step": 2240
+    },
+    {
+      "epoch": 2.1782082324455208,
+      "grad_norm": 1.6304939985275269,
+      "learning_rate": 5.195925916752166e-06,
+      "loss": 0.045,
+      "num_input_tokens_seen": 5599224,
+      "step": 2250
+    },
+    {
+      "epoch": 2.1878934624697335,
+      "grad_norm": 1.6586905717849731,
+      "learning_rate": 5.081235441753685e-06,
+      "loss": 0.0483,
+      "num_input_tokens_seen": 5623864,
+      "step": 2260
+    },
+    {
+      "epoch": 2.1975786924939467,
+      "grad_norm": 2.3342106342315674,
+      "learning_rate": 4.9675662629091055e-06,
+      "loss": 0.0476,
+      "num_input_tokens_seen": 5648760,
+      "step": 2270
+    },
+    {
+      "epoch": 2.20726392251816,
+      "grad_norm": 1.122441291809082,
+      "learning_rate": 4.854930084286458e-06,
+      "loss": 0.0537,
+      "num_input_tokens_seen": 5673720,
+      "step": 2280
+    },
+    {
+      "epoch": 2.216949152542373,
+      "grad_norm": 0.22967131435871124,
+      "learning_rate": 4.743338503589796e-06,
+      "loss": 0.0567,
+      "num_input_tokens_seen": 5697784,
+      "step": 2290
+    },
+    {
+      "epoch": 2.226634382566586,
+      "grad_norm": 3.79902720451355,
+      "learning_rate": 4.632803010965056e-06,
+      "loss": 0.0502,
+      "num_input_tokens_seen": 5722040,
+      "step": 2300
+    },
+    {
+      "epoch": 2.236319612590799,
+      "grad_norm": 0.5887905359268188,
+      "learning_rate": 4.523334987816917e-06,
+      "loss": 0.0444,
+      "num_input_tokens_seen": 5747672,
+      "step": 2310
+    },
+    {
+      "epoch": 2.246004842615012,
+      "grad_norm": 1.776781678199768,
+      "learning_rate": 4.414945705636949e-06,
+      "loss": 0.0482,
+      "num_input_tokens_seen": 5772056,
+      "step": 2320
+    },
+    {
+      "epoch": 2.2556900726392253,
+      "grad_norm": 2.457751512527466,
+      "learning_rate": 4.307646324843004e-06,
+      "loss": 0.0398,
+      "num_input_tokens_seen": 5796728,
+      "step": 2330
+    },
+    {
+      "epoch": 2.2653753026634385,
+      "grad_norm": 1.8455132246017456,
+      "learning_rate": 4.201447893630065e-06,
+      "loss": 0.0268,
+      "num_input_tokens_seen": 5822520,
+      "step": 2340
+    },
+    {
+      "epoch": 2.275060532687651,
+      "grad_norm": 3.7571520805358887,
+      "learning_rate": 4.096361346832681e-06,
+      "loss": 0.0427,
+      "num_input_tokens_seen": 5847768,
+      "step": 2350
+    },
+    {
+      "epoch": 2.2847457627118644,
+      "grad_norm": 4.052141189575195,
+      "learning_rate": 3.992397504799039e-06,
+      "loss": 0.0363,
+      "num_input_tokens_seen": 5873208,
+      "step": 2360
+    },
+    {
+      "epoch": 2.2944309927360775,
+      "grad_norm": 2.814667224884033,
+      "learning_rate": 3.889567072276827e-06,
+      "loss": 0.0432,
+      "num_input_tokens_seen": 5897368,
+      "step": 2370
+    },
+    {
+      "epoch": 2.3041162227602907,
+      "grad_norm": 0.680135190486908,
+      "learning_rate": 3.78788063731103e-06,
+      "loss": 0.0662,
+      "num_input_tokens_seen": 5921656,
+      "step": 2380
+    },
+    {
+      "epoch": 2.3138014527845034,
+      "grad_norm": 4.201208591461182,
+      "learning_rate": 3.6873486701536814e-06,
+      "loss": 0.0434,
+      "num_input_tokens_seen": 5946328,
+      "step": 2390
+    },
+    {
+      "epoch": 2.3234866828087166,
+      "grad_norm": 1.828552007675171,
+      "learning_rate": 3.587981522185829e-06,
+      "loss": 0.0425,
+      "num_input_tokens_seen": 5971352,
+      "step": 2400
+    },
+    {
+      "epoch": 2.33317191283293,
+      "grad_norm": 0.6704538464546204,
+      "learning_rate": 3.4897894248516736e-06,
+      "loss": 0.0533,
+      "num_input_tokens_seen": 5995544,
+      "step": 2410
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 2.377774238586426,
+      "learning_rate": 3.3927824886050555e-06,
+      "loss": 0.0499,
+      "num_input_tokens_seen": 6020600,
+      "step": 2420
+    },
+    {
+      "epoch": 2.3525423728813557,
+      "grad_norm": 0.2766050398349762,
+      "learning_rate": 3.2969707018684657e-06,
+      "loss": 0.021,
+      "num_input_tokens_seen": 6045304,
+      "step": 2430
+    },
+    {
+      "epoch": 2.362227602905569,
+      "grad_norm": 1.9754971265792847,
+      "learning_rate": 3.202363930004536e-06,
+      "loss": 0.0216,
+      "num_input_tokens_seen": 6070776,
+      "step": 2440
+    },
+    {
+      "epoch": 2.371912832929782,
+      "grad_norm": 6.165454387664795,
+      "learning_rate": 3.1089719143002615e-06,
+      "loss": 0.0431,
+      "num_input_tokens_seen": 6095256,
+      "step": 2450
+    },
+    {
+      "epoch": 2.3815980629539952,
+      "grad_norm": 2.579355001449585,
+      "learning_rate": 3.016804270963994e-06,
+      "loss": 0.0515,
+      "num_input_tokens_seen": 6120088,
+      "step": 2460
+    },
+    {
+      "epoch": 2.3912832929782084,
+      "grad_norm": 1.1952487230300903,
+      "learning_rate": 2.925870490135255e-06,
+      "loss": 0.0349,
+      "num_input_tokens_seen": 6144792,
+      "step": 2470
+    },
+    {
+      "epoch": 2.400968523002421,
+      "grad_norm": 0.08051615208387375,
+      "learning_rate": 2.8361799349076143e-06,
+      "loss": 0.0251,
+      "num_input_tokens_seen": 6169688,
+      "step": 2480
+    },
+    {
+      "epoch": 2.4106537530266343,
+      "grad_norm": 3.1085357666015625,
+      "learning_rate": 2.747741840364593e-06,
+      "loss": 0.0634,
+      "num_input_tokens_seen": 6194680,
+      "step": 2490
+    },
+    {
+      "epoch": 2.4203389830508475,
+      "grad_norm": 1.2273328304290771,
+      "learning_rate": 2.6605653126287555e-06,
+      "loss": 0.0451,
+      "num_input_tokens_seen": 6218712,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4300242130750607,
+      "grad_norm": 2.9415712356567383,
+      "learning_rate": 2.5746593279241105e-06,
+      "loss": 0.0395,
+      "num_input_tokens_seen": 6243384,
+      "step": 2510
+    },
+    {
+      "epoch": 2.4397094430992734,
+      "grad_norm": 0.24813522398471832,
+      "learning_rate": 2.490032731651833e-06,
+      "loss": 0.0537,
+      "num_input_tokens_seen": 6267416,
+      "step": 2520
+    },
+    {
+      "epoch": 2.4493946731234866,
+      "grad_norm": 1.5883897542953491,
+      "learning_rate": 2.4066942374795205e-06,
+      "loss": 0.0402,
+      "num_input_tokens_seen": 6292696,
+      "step": 2530
+    },
+    {
+      "epoch": 2.4590799031476998,
+      "grad_norm": 0.41333088278770447,
+      "learning_rate": 2.324652426443962e-06,
+      "loss": 0.0295,
+      "num_input_tokens_seen": 6317208,
+      "step": 2540
+    },
+    {
+      "epoch": 2.468765133171913,
+      "grad_norm": 3.1688761711120605,
+      "learning_rate": 2.243915746067587e-06,
+      "loss": 0.0515,
+      "num_input_tokens_seen": 6341688,
+      "step": 2550
+    },
+    {
+      "epoch": 2.478450363196126,
+      "grad_norm": 0.7070954442024231,
+      "learning_rate": 2.164492509488657e-06,
+      "loss": 0.0443,
+      "num_input_tokens_seen": 6366712,
+      "step": 2560
+    },
+    {
+      "epoch": 2.488135593220339,
+      "grad_norm": 0.3987884819507599,
+      "learning_rate": 2.086390894605288e-06,
+      "loss": 0.0555,
+      "num_input_tokens_seen": 6391256,
+      "step": 2570
+    },
+    {
+      "epoch": 2.497820823244552,
+      "grad_norm": 1.7903181314468384,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.054,
+      "num_input_tokens_seen": 6416184,
+      "step": 2580
+    },
+    {
+      "epoch": 2.507506053268765,
+      "grad_norm": 7.973659992218018,
+      "learning_rate": 1.9341845602787733e-06,
+      "loss": 0.075,
+      "num_input_tokens_seen": 6441176,
+      "step": 2590
+    },
+    {
+      "epoch": 2.5171912832929784,
+      "grad_norm": 2.1646482944488525,
+      "learning_rate": 1.8600955129229009e-06,
+      "loss": 0.0384,
+      "num_input_tokens_seen": 6465688,
+      "step": 2600
+    },
+    {
+      "epoch": 2.526876513317191,
+      "grad_norm": 0.9478936791419983,
+      "learning_rate": 1.7873594298234557e-06,
+      "loss": 0.038,
+      "num_input_tokens_seen": 6490456,
+      "step": 2610
+    },
+    {
+      "epoch": 2.5365617433414043,
+      "grad_norm": 0.5018621683120728,
+      "learning_rate": 1.7159838003286848e-06,
+      "loss": 0.0233,
+      "num_input_tokens_seen": 6515704,
+      "step": 2620
+    },
+    {
+      "epoch": 2.5462469733656174,
+      "grad_norm": 4.254843711853027,
+      "learning_rate": 1.645975973706269e-06,
+      "loss": 0.0634,
+      "num_input_tokens_seen": 6540920,
+      "step": 2630
+    },
+    {
+      "epoch": 2.5559322033898306,
+      "grad_norm": 0.3339782655239105,
+      "learning_rate": 1.5773431583866227e-06,
+      "loss": 0.0333,
+      "num_input_tokens_seen": 6565880,
+      "step": 2640
+    },
+    {
+      "epoch": 2.565617433414044,
+      "grad_norm": 2.9373421669006348,
+      "learning_rate": 1.5100924212206534e-06,
+      "loss": 0.0649,
+      "num_input_tokens_seen": 6591000,
+      "step": 2650
+    },
+    {
+      "epoch": 2.5753026634382565,
+      "grad_norm": 1.637086033821106,
+      "learning_rate": 1.44423068675212e-06,
+      "loss": 0.0531,
+      "num_input_tokens_seen": 6615800,
+      "step": 2660
+    },
+    {
+      "epoch": 2.5849878934624697,
+      "grad_norm": 0.06637797504663467,
+      "learning_rate": 1.3797647365046411e-06,
+      "loss": 0.0426,
+      "num_input_tokens_seen": 6639288,
+      "step": 2670
+    },
+    {
+      "epoch": 2.594673123486683,
+      "grad_norm": 0.9268229603767395,
+      "learning_rate": 1.3167012082834212e-06,
+      "loss": 0.0368,
+      "num_input_tokens_seen": 6664632,
+      "step": 2680
+    },
+    {
+      "epoch": 2.6043583535108956,
+      "grad_norm": 4.011239528656006,
+      "learning_rate": 1.2550465954917932e-06,
+      "loss": 0.0165,
+      "num_input_tokens_seen": 6689496,
+      "step": 2690
+    },
+    {
+      "epoch": 2.614043583535109,
+      "grad_norm": 3.382112741470337,
+      "learning_rate": 1.1948072464626102e-06,
+      "loss": 0.0331,
+      "num_input_tokens_seen": 6714552,
+      "step": 2700
+    },
+    {
+      "epoch": 2.623728813559322,
+      "grad_norm": 5.245890140533447,
+      "learning_rate": 1.1359893638045854e-06,
+      "loss": 0.0226,
+      "num_input_tokens_seen": 6739320,
+      "step": 2710
+    },
+    {
+      "epoch": 2.633414043583535,
+      "grad_norm": 2.0806005001068115,
+      "learning_rate": 1.0785990037636335e-06,
+      "loss": 0.0611,
+      "num_input_tokens_seen": 6763352,
+      "step": 2720
+    },
+    {
+      "epoch": 2.6430992736077483,
+      "grad_norm": 2.040339469909668,
+      "learning_rate": 1.022642075599286e-06,
+      "loss": 0.0615,
+      "num_input_tokens_seen": 6787544,
+      "step": 2730
+    },
+    {
+      "epoch": 2.6527845036319615,
+      "grad_norm": 4.939095973968506,
+      "learning_rate": 9.68124340976232e-07,
+      "loss": 0.0393,
+      "num_input_tokens_seen": 6812760,
+      "step": 2740
+    },
+    {
+      "epoch": 2.6624697336561742,
+      "grad_norm": 0.7793028354644775,
+      "learning_rate": 9.150514133710647e-07,
+      "loss": 0.0656,
+      "num_input_tokens_seen": 6838008,
+      "step": 2750
+    },
+    {
+      "epoch": 2.6721549636803874,
+      "grad_norm": 0.568551778793335,
+      "learning_rate": 8.634287574942834e-07,
+      "loss": 0.0452,
+      "num_input_tokens_seen": 6863320,
+      "step": 2760
+    },
+    {
+      "epoch": 2.6818401937046006,
+      "grad_norm": 5.33021354675293,
+      "learning_rate": 8.132616887276212e-07,
+      "loss": 0.0404,
+      "num_input_tokens_seen": 6888824,
+      "step": 2770
+    },
+    {
+      "epoch": 2.6915254237288133,
+      "grad_norm": 4.118853569030762,
+      "learning_rate": 7.645553725767229e-07,
+      "loss": 0.0543,
+      "num_input_tokens_seen": 6913048,
+      "step": 2780
+    },
+    {
+      "epoch": 2.7012106537530265,
+      "grad_norm": 1.218005895614624,
+      "learning_rate": 7.173148241392957e-07,
+      "loss": 0.0459,
+      "num_input_tokens_seen": 6937432,
+      "step": 2790
+    },
+    {
+      "epoch": 2.7108958837772397,
+      "grad_norm": 0.6871452927589417,
+      "learning_rate": 6.71544907588712e-07,
+      "loss": 0.0386,
+      "num_input_tokens_seen": 6962584,
+      "step": 2800
+    },
+    {
+      "epoch": 2.720581113801453,
+      "grad_norm": 2.3115310668945312,
+      "learning_rate": 6.272503356731601e-07,
+      "loss": 0.0714,
+      "num_input_tokens_seen": 6987768,
+      "step": 2810
+    },
+    {
+      "epoch": 2.730266343825666,
+      "grad_norm": 4.2863569259643555,
+      "learning_rate": 5.84435669230401e-07,
+      "loss": 0.0364,
+      "num_input_tokens_seen": 7013336,
+      "step": 2820
+    },
+    {
+      "epoch": 2.739951573849879,
+      "grad_norm": 0.879754900932312,
+      "learning_rate": 5.431053167181515e-07,
+      "loss": 0.0346,
+      "num_input_tokens_seen": 7038648,
+      "step": 2830
+    },
+    {
+      "epoch": 2.749636803874092,
+      "grad_norm": 1.9641544818878174,
+      "learning_rate": 5.032635337601687e-07,
+      "loss": 0.0337,
+      "num_input_tokens_seen": 7064184,
+      "step": 2840
+    },
+    {
+      "epoch": 2.759322033898305,
+      "grad_norm": 0.6523151993751526,
+      "learning_rate": 4.6491442270805596e-07,
+      "loss": 0.0229,
+      "num_input_tokens_seen": 7089336,
+      "step": 2850
+    },
+    {
+      "epoch": 2.7690072639225183,
+      "grad_norm": 0.46984636783599854,
+      "learning_rate": 4.280619322188628e-07,
+      "loss": 0.0472,
+      "num_input_tokens_seen": 7114072,
+      "step": 2860
+    },
+    {
+      "epoch": 2.778692493946731,
+      "grad_norm": 2.178297519683838,
+      "learning_rate": 3.9270985684851545e-07,
+      "loss": 0.0498,
+      "num_input_tokens_seen": 7139576,
+      "step": 2870
+    },
+    {
+      "epoch": 2.788377723970944,
+      "grad_norm": 3.751574993133545,
+      "learning_rate": 3.588618366610941e-07,
+      "loss": 0.0442,
+      "num_input_tokens_seen": 7165432,
+      "step": 2880
+    },
+    {
+      "epoch": 2.7980629539951574,
+      "grad_norm": 1.0459034442901611,
+      "learning_rate": 3.2652135685403593e-07,
+      "loss": 0.0324,
+      "num_input_tokens_seen": 7190808,
+      "step": 2890
+    },
+    {
+      "epoch": 2.8077481840193705,
+      "grad_norm": 3.6684751510620117,
+      "learning_rate": 2.9569174739928096e-07,
+      "loss": 0.0497,
+      "num_input_tokens_seen": 7216440,
+      "step": 2900
+    },
+    {
+      "epoch": 2.8174334140435837,
+      "grad_norm": 4.388014316558838,
+      "learning_rate": 2.663761827003941e-07,
+      "loss": 0.0404,
+      "num_input_tokens_seen": 7243480,
+      "step": 2910
+    },
+    {
+      "epoch": 2.8271186440677964,
+      "grad_norm": 6.251937389373779,
+      "learning_rate": 2.38577681265707e-07,
+      "loss": 0.0479,
+      "num_input_tokens_seen": 7268568,
+      "step": 2920
+    },
+    {
+      "epoch": 2.8368038740920096,
+      "grad_norm": 2.676504611968994,
+      "learning_rate": 2.122991053975215e-07,
+      "loss": 0.0378,
+      "num_input_tokens_seen": 7293784,
+      "step": 2930
+    },
+    {
+      "epoch": 2.846489104116223,
+      "grad_norm": 4.877316474914551,
+      "learning_rate": 1.8754316089737878e-07,
+      "loss": 0.0328,
+      "num_input_tokens_seen": 7318680,
+      "step": 2940
+    },
+    {
+      "epoch": 2.856174334140436,
+      "grad_norm": 1.454691767692566,
+      "learning_rate": 1.6431239678746546e-07,
+      "loss": 0.0411,
+      "num_input_tokens_seen": 7343864,
+      "step": 2950
+    },
+    {
+      "epoch": 2.8658595641646487,
+      "grad_norm": 3.7415764331817627,
+      "learning_rate": 1.4260920504814366e-07,
+      "loss": 0.0649,
+      "num_input_tokens_seen": 7370232,
+      "step": 2960
+    },
+    {
+      "epoch": 2.875544794188862,
+      "grad_norm": 2.577986240386963,
+      "learning_rate": 1.22435820371658e-07,
+      "loss": 0.0462,
+      "num_input_tokens_seen": 7394936,
+      "step": 2970
+    },
+    {
+      "epoch": 2.885230024213075,
+      "grad_norm": 4.861838340759277,
+      "learning_rate": 1.0379431993204458e-07,
+      "loss": 0.0425,
+      "num_input_tokens_seen": 7420088,
+      "step": 2980
+    },
+    {
+      "epoch": 2.8949152542372882,
+      "grad_norm": 3.2706315517425537,
+      "learning_rate": 8.668662317124043e-08,
+      "loss": 0.0418,
+      "num_input_tokens_seen": 7445048,
+      "step": 2990
+    },
+    {
+      "epoch": 2.9046004842615014,
+      "grad_norm": 0.6351612210273743,
+      "learning_rate": 7.111449160146333e-08,
+      "loss": 0.022,
+      "num_input_tokens_seen": 7469144,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3096,
+  "num_input_tokens_seen": 7469144,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.197440763416412e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7a6d9a1a05e78971782a6ee6bb88dfb9617ab9f9e2f35984cd80b0711875f6
+size 5688

checkpoint-3096/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-3096/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3096/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e945a3ed8fb6a8e001cf93765506fa4f4e8a5f26f7e25358e3647e1e889d3d2
+size 83945296

checkpoint-3096/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6e06e3ea474b930e3eb1a1eda05de3340e31330c04a77f3de0619d0b65e354
+size 168149074

checkpoint-3096/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-3096/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c499ee35917a6999d5080692bb0d882ad4d51ced03b11970197ebcff165fb6
+size 1064

checkpoint-3096/special_tokens_map.json

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

checkpoint-3096/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404