Upload folder using huggingface_hub

README.md

@@ -1,21 +1,105 @@
 ---
 license: apache-2.0
-base_model: ai21labs/Jamba-v0.1
+library_name: peft
 tags:
-- trl
-- sft
 - generated_from_trainer
+base_model: ai21labs/Jamba-v0.1
 model-index:
-- name: Jambatypus
+- name: out
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Jambatypus
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
 
-This model is a fine-tuned version of [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) on an unknown dataset.
+axolotl version: `0.4.0`
+```yaml
+
+base_model: ai21labs/Jamba-v0.1
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: chargoddard/Open-Platypus-Chat
+    type: sharegpt
+chat_template: chatml
+dataset_prepared_path:
+val_set_size: 0.01
+output_dir: ./out
+hub_strategy: every_save
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+eval_sample_packing: false
+
+use_wandb: true
+wandb_project: axolotl
+wandb_entity:
+wandb_watch:
+wandb_name: Jambatypus-v0.1
+wandb_log_model:
+
+adapter: qlora
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+
+low_cpu_mem_usage: true
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 4
+save_total_limit: 2
+debug:
+deepspeed:
+weight_decay: 0.0
+special_tokens:
+
+```
+
+</details><br>
+
+# out
+
+This model is a fine-tuned version of [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9573
 
 ## Model description
 
@@ -34,24 +118,32 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-07
-- train_batch_size: 2
-- eval_batch_size: 8
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
 - num_epochs: 1
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5915        | 0.0   | 1    | 1.0279          |
+| 0.4249        | 0.25  | 84   | 0.9711          |
+| 0.3911        | 0.5   | 168  | 0.9590          |
+| 0.4655        | 0.75  | 252  | 0.9628          |
+| 0.4569        | 1.0   | 336  | 0.9573          |
 
 
 ### Framework versions
 
+- PEFT 0.10.0
 - Transformers 4.40.0.dev0
-- Pytorch 2.2.0+cu121
+- Pytorch 2.1.2+cu118
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.0

adapter_config.json

@@ -3,26 +3,34 @@
   "auto_mapping": null,
   "base_model_name_or_path": "ai21labs/Jamba-v0.1",
   "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": false,
-  "init_lora_weights": false,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
-  "lora_dropout": 0.001,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "embed_tokens",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
     "in_proj",
     "out_proj",
+    "dt_proj",
+    "down_proj",
+    "router",
+    "up_proj",
+    "o_proj",
+    "v_proj",
     "x_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b546e88fba6a21cb58cb344345b20a7fe1c09f4e948ca61b90164deb1efdd3
+size 1063383458

checkpoint-252/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ai21labs/Jamba-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-252/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai21labs/Jamba-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "in_proj",
+    "out_proj",
+    "dt_proj",
+    "down_proj",
+    "router",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "x_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-252/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9148e8f4de6c2968f94c17c863730d0f78ae529d8f9b137af890de19f18ec7d
+size 1062947520

checkpoint-252/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3740beddd3bdf7ae9002977ecc09273be04bf96313d16ca50b7dfe2a0ae849d
+size 534637428

checkpoint-252/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3c1076d830420e4dca05297f74c03c74429fe2e2837a7c7aff89654669a17d
+size 14244

checkpoint-252/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dc8b5f86dd96656dfc1be4982fb4e764b1326aadaf793a1f6099b3f4e81510
+size 1064

checkpoint-252/special_tokens_map.json

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

checkpoint-252/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
+size 1124742

checkpoint-252/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}

checkpoint-252/trainer_state.json

@@ -0,0 +1,1817 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7486075009283327,
+  "eval_steps": 84,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.297607958316803,
+      "learning_rate": 2e-05,
+      "loss": 0.5915,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.027875304222107,
+      "eval_runtime": 319.0994,
+      "eval_samples_per_second": 0.78,
+      "eval_steps_per_second": 0.78,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3444654643535614,
+      "learning_rate": 4e-05,
+      "loss": 0.5941,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.31323298811912537,
+      "learning_rate": 6e-05,
+      "loss": 0.5986,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3083553612232208,
+      "learning_rate": 8e-05,
+      "loss": 0.589,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3427445590496063,
+      "learning_rate": 0.0001,
+      "loss": 0.6559,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.26026275753974915,
+      "learning_rate": 0.00012,
+      "loss": 0.6444,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.22449900209903717,
+      "learning_rate": 0.00014,
+      "loss": 0.5621,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.18667733669281006,
+      "learning_rate": 0.00016,
+      "loss": 0.574,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.1876465231180191,
+      "learning_rate": 0.00018,
+      "loss": 0.6105,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.2330338954925537,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.18704406917095184,
+      "learning_rate": 0.00019999535665248002,
+      "loss": 0.5431,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.20125611126422882,
+      "learning_rate": 0.0001999814270411335,
+      "loss": 0.5219,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.17054004967212677,
+      "learning_rate": 0.000199958212459561,
+      "loss": 0.5022,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.20665132999420166,
+      "learning_rate": 0.00019992571506363,
+      "loss": 0.5907,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.21675613522529602,
+      "learning_rate": 0.00019988393787127441,
+      "loss": 0.4667,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.20350293815135956,
+      "learning_rate": 0.0001998328847622148,
+      "loss": 0.5533,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.18382889032363892,
+      "learning_rate": 0.00019977256047759765,
+      "loss": 0.5022,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.1696760207414627,
+      "learning_rate": 0.00019970297061955533,
+      "loss": 0.5381,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.19592055678367615,
+      "learning_rate": 0.00019962412165068573,
+      "loss": 0.5733,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.17972029745578766,
+      "learning_rate": 0.00019953602089345217,
+      "loss": 0.5891,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.19014880061149597,
+      "learning_rate": 0.0001994386765295032,
+      "loss": 0.5629,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.15824897587299347,
+      "learning_rate": 0.00019933209759891317,
+      "loss": 0.5627,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.17133353650569916,
+      "learning_rate": 0.00019921629399934223,
+      "loss": 0.5542,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.13738161325454712,
+      "learning_rate": 0.00019909127648511755,
+      "loss": 0.4443,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.16617180407047272,
+      "learning_rate": 0.0001989570566662345,
+      "loss": 0.5469,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.13969440758228302,
+      "learning_rate": 0.00019881364700727823,
+      "loss": 0.5141,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1598738580942154,
+      "learning_rate": 0.0001986610608262665,
+      "loss": 0.5598,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.14080321788787842,
+      "learning_rate": 0.00019849931229341258,
+      "loss": 0.4978,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16124503314495087,
+      "learning_rate": 0.00019832841642980945,
+      "loss": 0.613,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.1537931114435196,
+      "learning_rate": 0.00019814838910603481,
+      "loss": 0.4913,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16199100017547607,
+      "learning_rate": 0.00019795924704067721,
+      "loss": 0.4872,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.13554096221923828,
+      "learning_rate": 0.00019776100779878345,
+      "loss": 0.4609,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.18090932071208954,
+      "learning_rate": 0.00019755368979022732,
+      "loss": 0.4582,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.14535771310329437,
+      "learning_rate": 0.00019733731226800015,
+      "loss": 0.5359,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1427253782749176,
+      "learning_rate": 0.00019711189532642243,
+      "loss": 0.5324,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13935472071170807,
+      "learning_rate": 0.00019687745989927823,
+      "loss": 0.5106,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.1388338804244995,
+      "learning_rate": 0.00019663402775787066,
+      "loss": 0.5634,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13948731124401093,
+      "learning_rate": 0.00019638162150900027,
+      "loss": 0.5058,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.13687050342559814,
+      "learning_rate": 0.00019612026459286578,
+      "loss": 0.5806,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.1311887949705124,
+      "learning_rate": 0.00019584998128088684,
+      "loss": 0.4552,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.15644784271717072,
+      "learning_rate": 0.0001955707966734505,
+      "loss": 0.4424,
+      "step": 41
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.14039994776248932,
+      "learning_rate": 0.00019528273669757972,
+      "loss": 0.4905,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.14709696173667908,
+      "learning_rate": 0.0001949858281045261,
+      "loss": 0.5655,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.1661250740289688,
+      "learning_rate": 0.00019468009846728513,
+      "loss": 0.5141,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3046470582485199,
+      "learning_rate": 0.00019436557617803595,
+      "loss": 0.4792,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.15159915387630463,
+      "learning_rate": 0.00019404229044550433,
+      "loss": 0.5077,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.15115606784820557,
+      "learning_rate": 0.00019371027129225042,
+      "loss": 0.4915,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.14040274918079376,
+      "learning_rate": 0.0001933695495518804,
+      "loss": 0.5048,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.14947518706321716,
+      "learning_rate": 0.00019302015686618326,
+      "loss": 0.5124,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.13805006444454193,
+      "learning_rate": 0.0001926621256821922,
+      "loss": 0.4455,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.14188264310359955,
+      "learning_rate": 0.00019229548924917146,
+      "loss": 0.5244,
+      "step": 51
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1314387321472168,
+      "learning_rate": 0.00019192028161552847,
+      "loss": 0.5251,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1659722477197647,
+      "learning_rate": 0.0001915365376256519,
+      "loss": 0.4851,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1405472755432129,
+      "learning_rate": 0.00019114429291667583,
+      "loss": 0.463,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.14347247779369354,
+      "learning_rate": 0.00019074358391517023,
+      "loss": 0.4491,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.14897900819778442,
+      "learning_rate": 0.00019033444783375804,
+      "loss": 0.4942,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.13556955754756927,
+      "learning_rate": 0.00018991692266765947,
+      "loss": 0.4755,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.16432009637355804,
+      "learning_rate": 0.00018949104719116332,
+      "loss": 0.5747,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15541689097881317,
+      "learning_rate": 0.00018905686095402647,
+      "loss": 0.533,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1607791632413864,
+      "learning_rate": 0.0001886144042778006,
+      "loss": 0.556,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15379983186721802,
+      "learning_rate": 0.00018816371825208789,
+      "loss": 0.4549,
+      "step": 61
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15419824421405792,
+      "learning_rate": 0.0001877048447307252,
+      "loss": 0.4933,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1353635936975479,
+      "learning_rate": 0.00018723782632789701,
+      "loss": 0.393,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.15725383162498474,
+      "learning_rate": 0.00018676270641417822,
+      "loss": 0.4671,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.12909093499183655,
+      "learning_rate": 0.0001862795291125063,
+      "loss": 0.484,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.14394541084766388,
+      "learning_rate": 0.0001857883392940837,
+      "loss": 0.5232,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1671515554189682,
+      "learning_rate": 0.000185289182574211,
+      "loss": 0.4683,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1658957600593567,
+      "learning_rate": 0.0001847821053080505,
+      "loss": 0.5072,
+      "step": 68
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.15142019093036652,
+      "learning_rate": 0.00018426715458632153,
+      "loss": 0.5328,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.141921728849411,
+      "learning_rate": 0.00018374437823092724,
+      "loss": 0.4387,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.1730872541666031,
+      "learning_rate": 0.00018321382479051347,
+      "loss": 0.5323,
+      "step": 71
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.13589338958263397,
+      "learning_rate": 0.00018267554353596025,
+      "loss": 0.4217,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16519547998905182,
+      "learning_rate": 0.0001821295844558062,
+      "loss": 0.4498,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16089589893817902,
+      "learning_rate": 0.0001815759982516061,
+      "loss": 0.5204,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16409483551979065,
+      "learning_rate": 0.00018101483633322255,
+      "loss": 0.4511,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.16179721057415009,
+      "learning_rate": 0.00018044615081405153,
+      "loss": 0.5866,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.15137337148189545,
+      "learning_rate": 0.00017986999450618295,
+      "loss": 0.4728,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.14265336096286774,
+      "learning_rate": 0.00017928642091549613,
+      "loss": 0.4491,
+      "step": 78
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.14860045909881592,
+      "learning_rate": 0.00017869548423669077,
+      "loss": 0.4734,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.14790605008602142,
+      "learning_rate": 0.00017809723934825405,
+      "loss": 0.533,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1581815779209137,
+      "learning_rate": 0.00017749174180736442,
+      "loss": 0.4661,
+      "step": 81
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1520436853170395,
+      "learning_rate": 0.00017687904784473188,
+      "loss": 0.5292,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15341107547283173,
+      "learning_rate": 0.00017625921435937637,
+      "loss": 0.5062,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.14248648285865784,
+      "learning_rate": 0.00017563229891334338,
+      "loss": 0.4249,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.9711415767669678,
+      "eval_runtime": 320.5008,
+      "eval_samples_per_second": 0.777,
+      "eval_steps_per_second": 0.777,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.16506022214889526,
+      "learning_rate": 0.00017499835972635856,
+      "loss": 0.4873,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14895877242088318,
+      "learning_rate": 0.00017435745567042095,
+      "loss": 0.4774,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.25245463848114014,
+      "learning_rate": 0.00017370964626433567,
+      "loss": 0.5324,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14706483483314514,
+      "learning_rate": 0.0001730549916681868,
+      "loss": 0.4536,
+      "step": 88
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14856815338134766,
+      "learning_rate": 0.00017239355267775018,
+      "loss": 0.4576,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1513276994228363,
+      "learning_rate": 0.0001717253907188477,
+      "loss": 0.4286,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1549597978591919,
+      "learning_rate": 0.00017105056784164294,
+      "loss": 0.4554,
+      "step": 91
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.15850332379341125,
+      "learning_rate": 0.00017036914671487852,
+      "loss": 0.454,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15920379757881165,
+      "learning_rate": 0.00016968119062005642,
+      "loss": 0.5333,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1652740240097046,
+      "learning_rate": 0.00016898676344556118,
+      "loss": 0.5272,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15505805611610413,
+      "learning_rate": 0.00016828592968072678,
+      "loss": 0.5429,
+      "step": 95
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.16118398308753967,
+      "learning_rate": 0.00016757875440984768,
+      "loss": 0.4782,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1549789011478424,
+      "learning_rate": 0.0001668653033061347,
+      "loss": 0.4594,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1643325537443161,
+      "learning_rate": 0.00016614564262561608,
+      "loss": 0.5086,
+      "step": 98
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1949179321527481,
+      "learning_rate": 0.0001654198392009846,
+      "loss": 0.4052,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1303270012140274,
+      "learning_rate": 0.0001646879604353908,
+      "loss": 0.4845,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.13640670478343964,
+      "learning_rate": 0.00016395007429618382,
+      "loss": 0.4459,
+      "step": 101
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.18252772092819214,
+      "learning_rate": 0.00016320624930859904,
+      "loss": 0.523,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.16342373192310333,
+      "learning_rate": 0.00016245655454939474,
+      "loss": 0.4714,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1418078988790512,
+      "learning_rate": 0.00016170105964043695,
+      "loss": 0.4841,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.15758009254932404,
+      "learning_rate": 0.0001609398347422339,
+      "loss": 0.3911,
+      "step": 105
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1476665586233139,
+      "learning_rate": 0.00016017295054742046,
+      "loss": 0.3962,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14230811595916748,
+      "learning_rate": 0.00015940047827419303,
+      "loss": 0.4391,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.15269385278224945,
+      "learning_rate": 0.00015862248965969604,
+      "loss": 0.4992,
+      "step": 108
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14437031745910645,
+      "learning_rate": 0.00015783905695335946,
+      "loss": 0.4768,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1448802649974823,
+      "learning_rate": 0.0001570502529101896,
+      "loss": 0.4469,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1571648269891739,
+      "learning_rate": 0.00015625615078401244,
+      "loss": 0.4048,
+      "step": 111
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1563793420791626,
+      "learning_rate": 0.00015545682432067067,
+      "loss": 0.4518,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1441984921693802,
+      "learning_rate": 0.0001546523477511754,
+      "loss": 0.497,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.13513916730880737,
+      "learning_rate": 0.00015384279578481221,
+      "loss": 0.4923,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1501740962266922,
+      "learning_rate": 0.00015302824360220353,
+      "loss": 0.4701,
+      "step": 115
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2020605355501175,
+      "learning_rate": 0.00015220876684832638,
+      "loss": 0.4122,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.15191146731376648,
+      "learning_rate": 0.0001513844416254879,
+      "loss": 0.4432,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.1627548784017563,
+      "learning_rate": 0.00015055534448625766,
+      "loss": 0.4779,
+      "step": 118
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.14043453335762024,
+      "learning_rate": 0.00014972155242635852,
+      "loss": 0.471,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.16092036664485931,
+      "learning_rate": 0.0001488831428775164,
+      "loss": 0.4543,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1478460729122162,
+      "learning_rate": 0.00014804019370026926,
+      "loss": 0.4521,
+      "step": 121
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15067800879478455,
+      "learning_rate": 0.00014719278317673655,
+      "loss": 0.5665,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.16037791967391968,
+      "learning_rate": 0.0001463409900033493,
+      "loss": 0.5198,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.15850840508937836,
+      "learning_rate": 0.00014548489328354195,
+      "loss": 0.5183,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.13782666623592377,
+      "learning_rate": 0.00014462457252040607,
+      "loss": 0.4415,
+      "step": 125
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.17566777765750885,
+      "learning_rate": 0.00014376010760930728,
+      "loss": 0.5166,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14671465754508972,
+      "learning_rate": 0.00014289157883046568,
+      "loss": 0.454,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14827768504619598,
+      "learning_rate": 0.0001420190668415002,
+      "loss": 0.3743,
+      "step": 128
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.16858412325382233,
+      "learning_rate": 0.00014114265266993846,
+      "loss": 0.5204,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.14838969707489014,
+      "learning_rate": 0.00014026241770569197,
+      "loss": 0.5072,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1676333248615265,
+      "learning_rate": 0.00013937844369349734,
+      "loss": 0.5026,
+      "step": 131
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1548876315355301,
+      "learning_rate": 0.00013849081272532544,
+      "loss": 0.4393,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.16387146711349487,
+      "learning_rate": 0.00013759960723275732,
+      "loss": 0.4899,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15013404190540314,
+      "learning_rate": 0.00013670490997932922,
+      "loss": 0.4398,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1466226577758789,
+      "learning_rate": 0.00013580680405284664,
+      "loss": 0.5087,
+      "step": 135
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15578770637512207,
+      "learning_rate": 0.00013490537285766808,
+      "loss": 0.4662,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.16825653612613678,
+      "learning_rate": 0.00013400070010695966,
+      "loss": 0.4826,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.15624648332595825,
+      "learning_rate": 0.00013309286981492085,
+      "loss": 0.4818,
+      "step": 138
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.16185308992862701,
+      "learning_rate": 0.00013218196628898233,
+      "loss": 0.4848,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.15799778699874878,
+      "learning_rate": 0.00013126807412197665,
+      "loss": 0.4456,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.15358638763427734,
+      "learning_rate": 0.0001303512781842824,
+      "loss": 0.434,
+      "step": 141
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.14526773989200592,
+      "learning_rate": 0.00012943166361594242,
+      "loss": 0.4944,
+      "step": 142
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1717992126941681,
+      "learning_rate": 0.00012850931581875723,
+      "loss": 0.4966,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.14694097638130188,
+      "learning_rate": 0.00012758432044835392,
+      "loss": 0.4055,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.17159771919250488,
+      "learning_rate": 0.0001266567634062317,
+      "loss": 0.4455,
+      "step": 145
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.16740797460079193,
+      "learning_rate": 0.0001257267308317845,
+      "loss": 0.3732,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.14464697241783142,
+      "learning_rate": 0.00012479430909430108,
+      "loss": 0.4976,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.15393030643463135,
+      "learning_rate": 0.00012385958478494487,
+      "loss": 0.3653,
+      "step": 148
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.15888682007789612,
+      "learning_rate": 0.00012292264470871182,
+      "loss": 0.4966,
+      "step": 149
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.14429794251918793,
+      "learning_rate": 0.00012198357587636957,
+      "loss": 0.4821,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15093272924423218,
+      "learning_rate": 0.00012104246549637683,
+      "loss": 0.4431,
+      "step": 151
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.16575871407985687,
+      "learning_rate": 0.00012009940096678452,
+      "loss": 0.4903,
+      "step": 152
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15208427608013153,
+      "learning_rate": 0.00011915446986711953,
+      "loss": 0.4465,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.16902336478233337,
+      "learning_rate": 0.00011820775995025147,
+      "loss": 0.4997,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.1612280309200287,
+      "learning_rate": 0.0001172593591342432,
+      "loss": 0.4258,
+      "step": 155
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.14114782214164734,
+      "learning_rate": 0.00011630935549418627,
+      "loss": 0.5262,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16275247931480408,
+      "learning_rate": 0.00011535783725402163,
+      "loss": 0.4403,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1442529857158661,
+      "learning_rate": 0.00011440489277834645,
+      "loss": 0.479,
+      "step": 158
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.15231800079345703,
+      "learning_rate": 0.0001134506105642081,
+      "loss": 0.4856,
+      "step": 159
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.14390550553798676,
+      "learning_rate": 0.00011249507923288562,
+      "loss": 0.3665,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.19076046347618103,
+      "learning_rate": 0.0001115383875216598,
+      "loss": 0.4423,
+      "step": 161
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.16523972153663635,
+      "learning_rate": 0.00011058062427557229,
+      "loss": 0.5816,
+      "step": 162
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1553642749786377,
+      "learning_rate": 0.00010962187843917497,
+      "loss": 0.4793,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.14419597387313843,
+      "learning_rate": 0.0001086622390482699,
+      "loss": 0.4862,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.14601647853851318,
+      "learning_rate": 0.00010770179522164079,
+      "loss": 0.4589,
+      "step": 165
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.15500588715076447,
+      "learning_rate": 0.0001067406361527768,
+      "loss": 0.4754,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16032655537128448,
+      "learning_rate": 0.00010577885110158958,
+      "loss": 0.4644,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.15342958271503448,
+      "learning_rate": 0.00010481652938612374,
+      "loss": 0.3911,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.9589568972587585,
+      "eval_runtime": 324.8473,
+      "eval_samples_per_second": 0.767,
+      "eval_steps_per_second": 0.767,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.15607774257659912,
+      "learning_rate": 0.00010385376037426226,
+      "loss": 0.492,
+      "step": 169
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.15384891629219055,
+      "learning_rate": 0.00010289063347542726,
+      "loss": 0.487,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.15275317430496216,
+      "learning_rate": 0.00010192723813227672,
+      "loss": 0.4475,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.1687576025724411,
+      "learning_rate": 0.00010096366381239808,
+      "loss": 0.4491,
+      "step": 172
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.17867827415466309,
+      "learning_rate": 0.0001,
+      "loss": 0.4197,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14261119067668915,
+      "learning_rate": 9.903633618760195e-05,
+      "loss": 0.4734,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14787495136260986,
+      "learning_rate": 9.807276186772333e-05,
+      "loss": 0.404,
+      "step": 175
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.15715274214744568,
+      "learning_rate": 9.710936652457276e-05,
+      "loss": 0.4583,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1578068882226944,
+      "learning_rate": 9.614623962573776e-05,
+      "loss": 0.4343,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15597595274448395,
+      "learning_rate": 9.518347061387628e-05,
+      "loss": 0.4454,
+      "step": 178
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.142894446849823,
+      "learning_rate": 9.422114889841044e-05,
+      "loss": 0.4443,
+      "step": 179
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15279816091060638,
+      "learning_rate": 9.325936384722321e-05,
+      "loss": 0.4428,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1651957929134369,
+      "learning_rate": 9.229820477835927e-05,
+      "loss": 0.3857,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.22555674612522125,
+      "learning_rate": 9.133776095173015e-05,
+      "loss": 0.4578,
+      "step": 182
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.14163288474082947,
+      "learning_rate": 9.037812156082504e-05,
+      "loss": 0.4409,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1683199107646942,
+      "learning_rate": 8.941937572442773e-05,
+      "loss": 0.4829,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.17766785621643066,
+      "learning_rate": 8.846161247834024e-05,
+      "loss": 0.4357,
+      "step": 185
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.15518875420093536,
+      "learning_rate": 8.750492076711439e-05,
+      "loss": 0.4681,
+      "step": 186
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.13920673727989197,
+      "learning_rate": 8.654938943579194e-05,
+      "loss": 0.4258,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.17552931606769562,
+      "learning_rate": 8.55951072216536e-05,
+      "loss": 0.3932,
+      "step": 188
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.15486915409564972,
+      "learning_rate": 8.464216274597838e-05,
+      "loss": 0.4679,
+      "step": 189
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1437031477689743,
+      "learning_rate": 8.369064450581373e-05,
+      "loss": 0.3984,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.15499216318130493,
+      "learning_rate": 8.274064086575681e-05,
+      "loss": 0.5216,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.18269003927707672,
+      "learning_rate": 8.179224004974857e-05,
+      "loss": 0.4853,
+      "step": 192
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1596907526254654,
+      "learning_rate": 8.084553013288048e-05,
+      "loss": 0.4784,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.15115347504615784,
+      "learning_rate": 7.990059903321553e-05,
+      "loss": 0.4306,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.19720065593719482,
+      "learning_rate": 7.89575345036232e-05,
+      "loss": 0.4782,
+      "step": 195
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.14170032739639282,
+      "learning_rate": 7.801642412363041e-05,
+      "loss": 0.4318,
+      "step": 196
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16026908159255981,
+      "learning_rate": 7.707735529128819e-05,
+      "loss": 0.4656,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16910114884376526,
+      "learning_rate": 7.614041521505517e-05,
+      "loss": 0.5014,
+      "step": 198
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.18795110285282135,
+      "learning_rate": 7.520569090569893e-05,
+      "loss": 0.4512,
+      "step": 199
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.15903539955615997,
+      "learning_rate": 7.427326916821557e-05,
+      "loss": 0.5036,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15247230231761932,
+      "learning_rate": 7.334323659376829e-05,
+      "loss": 0.4369,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1472063809633255,
+      "learning_rate": 7.24156795516461e-05,
+      "loss": 0.426,
+      "step": 202
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15710321068763733,
+      "learning_rate": 7.149068418124281e-05,
+      "loss": 0.4034,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.15857233107089996,
+      "learning_rate": 7.056833638405762e-05,
+      "loss": 0.4783,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.16299530863761902,
+      "learning_rate": 6.964872181571764e-05,
+      "loss": 0.4719,
+      "step": 205
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.14976787567138672,
+      "learning_rate": 6.87319258780234e-05,
+      "loss": 0.4543,
+      "step": 206
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.14311917126178741,
+      "learning_rate": 6.781803371101774e-05,
+      "loss": 0.4422,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.14494828879833221,
+      "learning_rate": 6.690713018507918e-05,
+      "loss": 0.4078,
+      "step": 208
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1489972174167633,
+      "learning_rate": 6.599929989304035e-05,
+      "loss": 0.3908,
+      "step": 209
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.15475499629974365,
+      "learning_rate": 6.509462714233195e-05,
+      "loss": 0.5416,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1536937654018402,
+      "learning_rate": 6.419319594715339e-05,
+      "loss": 0.4267,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1654786467552185,
+      "learning_rate": 6.32950900206708e-05,
+      "loss": 0.4622,
+      "step": 212
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.14727674424648285,
+      "learning_rate": 6.240039276724272e-05,
+      "loss": 0.441,
+      "step": 213
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1774049550294876,
+      "learning_rate": 6.150918727467455e-05,
+      "loss": 0.4956,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.14867380261421204,
+      "learning_rate": 6.062155630650265e-05,
+      "loss": 0.5788,
+      "step": 215
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16996605694293976,
+      "learning_rate": 5.973758229430806e-05,
+      "loss": 0.588,
+      "step": 216
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.15790195763111115,
+      "learning_rate": 5.885734733006154e-05,
+      "loss": 0.425,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.15656080842018127,
+      "learning_rate": 5.798093315849984e-05,
+      "loss": 0.4193,
+      "step": 218
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.143330916762352,
+      "learning_rate": 5.710842116953438e-05,
+      "loss": 0.4427,
+      "step": 219
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.15389469265937805,
+      "learning_rate": 5.623989239069275e-05,
+      "loss": 0.4265,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.16425251960754395,
+      "learning_rate": 5.537542747959394e-05,
+      "loss": 0.53,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.1583469659090042,
+      "learning_rate": 5.451510671645807e-05,
+      "loss": 0.5009,
+      "step": 222
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.16075047850608826,
+      "learning_rate": 5.36590099966507e-05,
+      "loss": 0.5189,
+      "step": 223
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.14854145050048828,
+      "learning_rate": 5.2807216823263484e-05,
+      "loss": 0.463,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.15285861492156982,
+      "learning_rate": 5.1959806299730774e-05,
+      "loss": 0.4413,
+      "step": 225
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.14538119733333588,
+      "learning_rate": 5.111685712248364e-05,
+      "loss": 0.4736,
+      "step": 226
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.15160393714904785,
+      "learning_rate": 5.0278447573641495e-05,
+      "loss": 0.4298,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14497333765029907,
+      "learning_rate": 4.944465551374238e-05,
+      "loss": 0.3981,
+      "step": 228
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14342719316482544,
+      "learning_rate": 4.861555837451213e-05,
+      "loss": 0.4502,
+      "step": 229
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1621183604001999,
+      "learning_rate": 4.779123315167362e-05,
+      "loss": 0.4322,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.15252463519573212,
+      "learning_rate": 4.6971756397796504e-05,
+      "loss": 0.5072,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.17667719721794128,
+      "learning_rate": 4.61572042151878e-05,
+      "loss": 0.4708,
+      "step": 232
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.15273234248161316,
+      "learning_rate": 4.5347652248824624e-05,
+      "loss": 0.5212,
+      "step": 233
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.16372352838516235,
+      "learning_rate": 4.4543175679329344e-05,
+      "loss": 0.5303,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.14327646791934967,
+      "learning_rate": 4.3743849215987595e-05,
+      "loss": 0.4,
+      "step": 235
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.1604086011648178,
+      "learning_rate": 4.294974708981041e-05,
+      "loss": 0.4508,
+      "step": 236
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.23445452749729156,
+      "learning_rate": 4.216094304664056e-05,
+      "loss": 0.4363,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.15834979712963104,
+      "learning_rate": 4.137751034030399e-05,
+      "loss": 0.5153,
+      "step": 238
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.14937692880630493,
+      "learning_rate": 4.059952172580694e-05,
+      "loss": 0.4423,
+      "step": 239
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.16776776313781738,
+      "learning_rate": 3.982704945257957e-05,
+      "loss": 0.4089,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16948916018009186,
+      "learning_rate": 3.906016525776611e-05,
+      "loss": 0.562,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16811306774616241,
+      "learning_rate": 3.829894035956306e-05,
+      "loss": 0.407,
+      "step": 242
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.13980595767498016,
+      "learning_rate": 3.7543445450605285e-05,
+      "loss": 0.4329,
+      "step": 243
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16961558163166046,
+      "learning_rate": 3.6793750691400994e-05,
+      "loss": 0.4476,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.16474933922290802,
+      "learning_rate": 3.6049925703816214e-05,
+      "loss": 0.4629,
+      "step": 245
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1619129627943039,
+      "learning_rate": 3.53120395646092e-05,
+      "loss": 0.4648,
+      "step": 246
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.20941300690174103,
+      "learning_rate": 3.458016079901544e-05,
+      "loss": 0.4777,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1691591888666153,
+      "learning_rate": 3.38543573743839e-05,
+      "loss": 0.4544,
+      "step": 248
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1482505053281784,
+      "learning_rate": 3.3134696693865316e-05,
+      "loss": 0.4295,
+      "step": 249
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.16560567915439606,
+      "learning_rate": 3.242124559015234e-05,
+      "loss": 0.4568,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15260429680347443,
+      "learning_rate": 3.171407031927325e-05,
+      "loss": 0.4311,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15556661784648895,
+      "learning_rate": 3.101323655443882e-05,
+      "loss": 0.4655,
+      "step": 252
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.9627882838249207,
+      "eval_runtime": 320.8688,
+      "eval_samples_per_second": 0.776,
+      "eval_steps_per_second": 0.776,
+      "step": 252
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 84,
+  "total_flos": 2.5549257243937997e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-252/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92cf4d819bd687a107f49060d4cb816ff788627c8bf6c0b866a032bb83436a5
+size 5816

checkpoint-336/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ai21labs/Jamba-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-336/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai21labs/Jamba-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "in_proj",
+    "out_proj",
+    "dt_proj",
+    "down_proj",
+    "router",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "x_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-336/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946caaf56c399fa340ba39252e63fa2030e38c5f287093d6f070fba98de065dd
+size 1062947520

checkpoint-336/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1139c488391aded478ce1712957f2e1c1ec48bb1a1266c0a445bf30c76e6db9
+size 534639348

checkpoint-336/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090813dfaba36bbb1fd2dc6ca37a71ba0688884c2e93563f97ea7b2566dd62ab
+size 14244

checkpoint-336/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924d302abf5f685356e66110270e1f4d44c1c6f59465d461e888926b2dade607
+size 1064

checkpoint-336/special_tokens_map.json

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

checkpoint-336/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
+size 1124742

checkpoint-336/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}

checkpoint-336/trainer_state.json

@@ -0,0 +1,2413 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9981433345711103,
+  "eval_steps": 84,
+  "global_step": 336,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.297607958316803,
+      "learning_rate": 2e-05,
+      "loss": 0.5915,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.027875304222107,
+      "eval_runtime": 319.0994,
+      "eval_samples_per_second": 0.78,
+      "eval_steps_per_second": 0.78,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3444654643535614,
+      "learning_rate": 4e-05,
+      "loss": 0.5941,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.31323298811912537,
+      "learning_rate": 6e-05,
+      "loss": 0.5986,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3083553612232208,
+      "learning_rate": 8e-05,
+      "loss": 0.589,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.3427445590496063,
+      "learning_rate": 0.0001,
+      "loss": 0.6559,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.26026275753974915,
+      "learning_rate": 0.00012,
+      "loss": 0.6444,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.22449900209903717,
+      "learning_rate": 0.00014,
+      "loss": 0.5621,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.18667733669281006,
+      "learning_rate": 0.00016,
+      "loss": 0.574,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.1876465231180191,
+      "learning_rate": 0.00018,
+      "loss": 0.6105,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.2330338954925537,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.18704406917095184,
+      "learning_rate": 0.00019999535665248002,
+      "loss": 0.5431,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.20125611126422882,
+      "learning_rate": 0.0001999814270411335,
+      "loss": 0.5219,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.17054004967212677,
+      "learning_rate": 0.000199958212459561,
+      "loss": 0.5022,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.20665132999420166,
+      "learning_rate": 0.00019992571506363,
+      "loss": 0.5907,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.21675613522529602,
+      "learning_rate": 0.00019988393787127441,
+      "loss": 0.4667,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.20350293815135956,
+      "learning_rate": 0.0001998328847622148,
+      "loss": 0.5533,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.18382889032363892,
+      "learning_rate": 0.00019977256047759765,
+      "loss": 0.5022,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.1696760207414627,
+      "learning_rate": 0.00019970297061955533,
+      "loss": 0.5381,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.19592055678367615,
+      "learning_rate": 0.00019962412165068573,
+      "loss": 0.5733,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.17972029745578766,
+      "learning_rate": 0.00019953602089345217,
+      "loss": 0.5891,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.19014880061149597,
+      "learning_rate": 0.0001994386765295032,
+      "loss": 0.5629,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.15824897587299347,
+      "learning_rate": 0.00019933209759891317,
+      "loss": 0.5627,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.17133353650569916,
+      "learning_rate": 0.00019921629399934223,
+      "loss": 0.5542,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.13738161325454712,
+      "learning_rate": 0.00019909127648511755,
+      "loss": 0.4443,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.16617180407047272,
+      "learning_rate": 0.0001989570566662345,
+      "loss": 0.5469,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.13969440758228302,
+      "learning_rate": 0.00019881364700727823,
+      "loss": 0.5141,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1598738580942154,
+      "learning_rate": 0.0001986610608262665,
+      "loss": 0.5598,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.14080321788787842,
+      "learning_rate": 0.00019849931229341258,
+      "loss": 0.4978,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16124503314495087,
+      "learning_rate": 0.00019832841642980945,
+      "loss": 0.613,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.1537931114435196,
+      "learning_rate": 0.00019814838910603481,
+      "loss": 0.4913,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16199100017547607,
+      "learning_rate": 0.00019795924704067721,
+      "loss": 0.4872,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.13554096221923828,
+      "learning_rate": 0.00019776100779878345,
+      "loss": 0.4609,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.18090932071208954,
+      "learning_rate": 0.00019755368979022732,
+      "loss": 0.4582,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.14535771310329437,
+      "learning_rate": 0.00019733731226800015,
+      "loss": 0.5359,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1427253782749176,
+      "learning_rate": 0.00019711189532642243,
+      "loss": 0.5324,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13935472071170807,
+      "learning_rate": 0.00019687745989927823,
+      "loss": 0.5106,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.1388338804244995,
+      "learning_rate": 0.00019663402775787066,
+      "loss": 0.5634,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13948731124401093,
+      "learning_rate": 0.00019638162150900027,
+      "loss": 0.5058,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.13687050342559814,
+      "learning_rate": 0.00019612026459286578,
+      "loss": 0.5806,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.1311887949705124,
+      "learning_rate": 0.00019584998128088684,
+      "loss": 0.4552,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.15644784271717072,
+      "learning_rate": 0.0001955707966734505,
+      "loss": 0.4424,
+      "step": 41
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.14039994776248932,
+      "learning_rate": 0.00019528273669757972,
+      "loss": 0.4905,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.14709696173667908,
+      "learning_rate": 0.0001949858281045261,
+      "loss": 0.5655,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.1661250740289688,
+      "learning_rate": 0.00019468009846728513,
+      "loss": 0.5141,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3046470582485199,
+      "learning_rate": 0.00019436557617803595,
+      "loss": 0.4792,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.15159915387630463,
+      "learning_rate": 0.00019404229044550433,
+      "loss": 0.5077,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.15115606784820557,
+      "learning_rate": 0.00019371027129225042,
+      "loss": 0.4915,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.14040274918079376,
+      "learning_rate": 0.0001933695495518804,
+      "loss": 0.5048,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.14947518706321716,
+      "learning_rate": 0.00019302015686618326,
+      "loss": 0.5124,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.13805006444454193,
+      "learning_rate": 0.0001926621256821922,
+      "loss": 0.4455,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.14188264310359955,
+      "learning_rate": 0.00019229548924917146,
+      "loss": 0.5244,
+      "step": 51
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1314387321472168,
+      "learning_rate": 0.00019192028161552847,
+      "loss": 0.5251,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1659722477197647,
+      "learning_rate": 0.0001915365376256519,
+      "loss": 0.4851,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1405472755432129,
+      "learning_rate": 0.00019114429291667583,
+      "loss": 0.463,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.14347247779369354,
+      "learning_rate": 0.00019074358391517023,
+      "loss": 0.4491,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.14897900819778442,
+      "learning_rate": 0.00019033444783375804,
+      "loss": 0.4942,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.13556955754756927,
+      "learning_rate": 0.00018991692266765947,
+      "loss": 0.4755,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.16432009637355804,
+      "learning_rate": 0.00018949104719116332,
+      "loss": 0.5747,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15541689097881317,
+      "learning_rate": 0.00018905686095402647,
+      "loss": 0.533,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1607791632413864,
+      "learning_rate": 0.0001886144042778006,
+      "loss": 0.556,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15379983186721802,
+      "learning_rate": 0.00018816371825208789,
+      "loss": 0.4549,
+      "step": 61
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15419824421405792,
+      "learning_rate": 0.0001877048447307252,
+      "loss": 0.4933,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1353635936975479,
+      "learning_rate": 0.00018723782632789701,
+      "loss": 0.393,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.15725383162498474,
+      "learning_rate": 0.00018676270641417822,
+      "loss": 0.4671,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.12909093499183655,
+      "learning_rate": 0.0001862795291125063,
+      "loss": 0.484,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.14394541084766388,
+      "learning_rate": 0.0001857883392940837,
+      "loss": 0.5232,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1671515554189682,
+      "learning_rate": 0.000185289182574211,
+      "loss": 0.4683,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1658957600593567,
+      "learning_rate": 0.0001847821053080505,
+      "loss": 0.5072,
+      "step": 68
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.15142019093036652,
+      "learning_rate": 0.00018426715458632153,
+      "loss": 0.5328,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.141921728849411,
+      "learning_rate": 0.00018374437823092724,
+      "loss": 0.4387,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.1730872541666031,
+      "learning_rate": 0.00018321382479051347,
+      "loss": 0.5323,
+      "step": 71
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.13589338958263397,
+      "learning_rate": 0.00018267554353596025,
+      "loss": 0.4217,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16519547998905182,
+      "learning_rate": 0.0001821295844558062,
+      "loss": 0.4498,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16089589893817902,
+      "learning_rate": 0.0001815759982516061,
+      "loss": 0.5204,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.16409483551979065,
+      "learning_rate": 0.00018101483633322255,
+      "loss": 0.4511,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.16179721057415009,
+      "learning_rate": 0.00018044615081405153,
+      "loss": 0.5866,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.15137337148189545,
+      "learning_rate": 0.00017986999450618295,
+      "loss": 0.4728,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.14265336096286774,
+      "learning_rate": 0.00017928642091549613,
+      "loss": 0.4491,
+      "step": 78
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.14860045909881592,
+      "learning_rate": 0.00017869548423669077,
+      "loss": 0.4734,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.14790605008602142,
+      "learning_rate": 0.00017809723934825405,
+      "loss": 0.533,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1581815779209137,
+      "learning_rate": 0.00017749174180736442,
+      "loss": 0.4661,
+      "step": 81
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1520436853170395,
+      "learning_rate": 0.00017687904784473188,
+      "loss": 0.5292,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15341107547283173,
+      "learning_rate": 0.00017625921435937637,
+      "loss": 0.5062,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.14248648285865784,
+      "learning_rate": 0.00017563229891334338,
+      "loss": 0.4249,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.9711415767669678,
+      "eval_runtime": 320.5008,
+      "eval_samples_per_second": 0.777,
+      "eval_steps_per_second": 0.777,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.16506022214889526,
+      "learning_rate": 0.00017499835972635856,
+      "loss": 0.4873,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14895877242088318,
+      "learning_rate": 0.00017435745567042095,
+      "loss": 0.4774,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.25245463848114014,
+      "learning_rate": 0.00017370964626433567,
+      "loss": 0.5324,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14706483483314514,
+      "learning_rate": 0.0001730549916681868,
+      "loss": 0.4536,
+      "step": 88
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.14856815338134766,
+      "learning_rate": 0.00017239355267775018,
+      "loss": 0.4576,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1513276994228363,
+      "learning_rate": 0.0001717253907188477,
+      "loss": 0.4286,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1549597978591919,
+      "learning_rate": 0.00017105056784164294,
+      "loss": 0.4554,
+      "step": 91
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.15850332379341125,
+      "learning_rate": 0.00017036914671487852,
+      "loss": 0.454,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15920379757881165,
+      "learning_rate": 0.00016968119062005642,
+      "loss": 0.5333,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1652740240097046,
+      "learning_rate": 0.00016898676344556118,
+      "loss": 0.5272,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15505805611610413,
+      "learning_rate": 0.00016828592968072678,
+      "loss": 0.5429,
+      "step": 95
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.16118398308753967,
+      "learning_rate": 0.00016757875440984768,
+      "loss": 0.4782,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1549789011478424,
+      "learning_rate": 0.0001668653033061347,
+      "loss": 0.4594,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1643325537443161,
+      "learning_rate": 0.00016614564262561608,
+      "loss": 0.5086,
+      "step": 98
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1949179321527481,
+      "learning_rate": 0.0001654198392009846,
+      "loss": 0.4052,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1303270012140274,
+      "learning_rate": 0.0001646879604353908,
+      "loss": 0.4845,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.13640670478343964,
+      "learning_rate": 0.00016395007429618382,
+      "loss": 0.4459,
+      "step": 101
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.18252772092819214,
+      "learning_rate": 0.00016320624930859904,
+      "loss": 0.523,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.16342373192310333,
+      "learning_rate": 0.00016245655454939474,
+      "loss": 0.4714,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1418078988790512,
+      "learning_rate": 0.00016170105964043695,
+      "loss": 0.4841,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.15758009254932404,
+      "learning_rate": 0.0001609398347422339,
+      "loss": 0.3911,
+      "step": 105
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1476665586233139,
+      "learning_rate": 0.00016017295054742046,
+      "loss": 0.3962,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14230811595916748,
+      "learning_rate": 0.00015940047827419303,
+      "loss": 0.4391,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.15269385278224945,
+      "learning_rate": 0.00015862248965969604,
+      "loss": 0.4992,
+      "step": 108
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14437031745910645,
+      "learning_rate": 0.00015783905695335946,
+      "loss": 0.4768,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1448802649974823,
+      "learning_rate": 0.0001570502529101896,
+      "loss": 0.4469,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1571648269891739,
+      "learning_rate": 0.00015625615078401244,
+      "loss": 0.4048,
+      "step": 111
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1563793420791626,
+      "learning_rate": 0.00015545682432067067,
+      "loss": 0.4518,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1441984921693802,
+      "learning_rate": 0.0001546523477511754,
+      "loss": 0.497,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.13513916730880737,
+      "learning_rate": 0.00015384279578481221,
+      "loss": 0.4923,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1501740962266922,
+      "learning_rate": 0.00015302824360220353,
+      "loss": 0.4701,
+      "step": 115
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2020605355501175,
+      "learning_rate": 0.00015220876684832638,
+      "loss": 0.4122,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.15191146731376648,
+      "learning_rate": 0.0001513844416254879,
+      "loss": 0.4432,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.1627548784017563,
+      "learning_rate": 0.00015055534448625766,
+      "loss": 0.4779,
+      "step": 118
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.14043453335762024,
+      "learning_rate": 0.00014972155242635852,
+      "loss": 0.471,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.16092036664485931,
+      "learning_rate": 0.0001488831428775164,
+      "loss": 0.4543,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1478460729122162,
+      "learning_rate": 0.00014804019370026926,
+      "loss": 0.4521,
+      "step": 121
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15067800879478455,
+      "learning_rate": 0.00014719278317673655,
+      "loss": 0.5665,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.16037791967391968,
+      "learning_rate": 0.0001463409900033493,
+      "loss": 0.5198,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.15850840508937836,
+      "learning_rate": 0.00014548489328354195,
+      "loss": 0.5183,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.13782666623592377,
+      "learning_rate": 0.00014462457252040607,
+      "loss": 0.4415,
+      "step": 125
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.17566777765750885,
+      "learning_rate": 0.00014376010760930728,
+      "loss": 0.5166,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14671465754508972,
+      "learning_rate": 0.00014289157883046568,
+      "loss": 0.454,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14827768504619598,
+      "learning_rate": 0.0001420190668415002,
+      "loss": 0.3743,
+      "step": 128
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.16858412325382233,
+      "learning_rate": 0.00014114265266993846,
+      "loss": 0.5204,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.14838969707489014,
+      "learning_rate": 0.00014026241770569197,
+      "loss": 0.5072,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1676333248615265,
+      "learning_rate": 0.00013937844369349734,
+      "loss": 0.5026,
+      "step": 131
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1548876315355301,
+      "learning_rate": 0.00013849081272532544,
+      "loss": 0.4393,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.16387146711349487,
+      "learning_rate": 0.00013759960723275732,
+      "loss": 0.4899,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15013404190540314,
+      "learning_rate": 0.00013670490997932922,
+      "loss": 0.4398,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1466226577758789,
+      "learning_rate": 0.00013580680405284664,
+      "loss": 0.5087,
+      "step": 135
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15578770637512207,
+      "learning_rate": 0.00013490537285766808,
+      "loss": 0.4662,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.16825653612613678,
+      "learning_rate": 0.00013400070010695966,
+      "loss": 0.4826,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.15624648332595825,
+      "learning_rate": 0.00013309286981492085,
+      "loss": 0.4818,
+      "step": 138
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.16185308992862701,
+      "learning_rate": 0.00013218196628898233,
+      "loss": 0.4848,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.15799778699874878,
+      "learning_rate": 0.00013126807412197665,
+      "loss": 0.4456,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.15358638763427734,
+      "learning_rate": 0.0001303512781842824,
+      "loss": 0.434,
+      "step": 141
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.14526773989200592,
+      "learning_rate": 0.00012943166361594242,
+      "loss": 0.4944,
+      "step": 142
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1717992126941681,
+      "learning_rate": 0.00012850931581875723,
+      "loss": 0.4966,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.14694097638130188,
+      "learning_rate": 0.00012758432044835392,
+      "loss": 0.4055,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.17159771919250488,
+      "learning_rate": 0.0001266567634062317,
+      "loss": 0.4455,
+      "step": 145
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.16740797460079193,
+      "learning_rate": 0.0001257267308317845,
+      "loss": 0.3732,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.14464697241783142,
+      "learning_rate": 0.00012479430909430108,
+      "loss": 0.4976,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.15393030643463135,
+      "learning_rate": 0.00012385958478494487,
+      "loss": 0.3653,
+      "step": 148
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.15888682007789612,
+      "learning_rate": 0.00012292264470871182,
+      "loss": 0.4966,
+      "step": 149
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.14429794251918793,
+      "learning_rate": 0.00012198357587636957,
+      "loss": 0.4821,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15093272924423218,
+      "learning_rate": 0.00012104246549637683,
+      "loss": 0.4431,
+      "step": 151
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.16575871407985687,
+      "learning_rate": 0.00012009940096678452,
+      "loss": 0.4903,
+      "step": 152
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15208427608013153,
+      "learning_rate": 0.00011915446986711953,
+      "loss": 0.4465,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.16902336478233337,
+      "learning_rate": 0.00011820775995025147,
+      "loss": 0.4997,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.1612280309200287,
+      "learning_rate": 0.0001172593591342432,
+      "loss": 0.4258,
+      "step": 155
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.14114782214164734,
+      "learning_rate": 0.00011630935549418627,
+      "loss": 0.5262,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16275247931480408,
+      "learning_rate": 0.00011535783725402163,
+      "loss": 0.4403,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1442529857158661,
+      "learning_rate": 0.00011440489277834645,
+      "loss": 0.479,
+      "step": 158
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.15231800079345703,
+      "learning_rate": 0.0001134506105642081,
+      "loss": 0.4856,
+      "step": 159
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.14390550553798676,
+      "learning_rate": 0.00011249507923288562,
+      "loss": 0.3665,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.19076046347618103,
+      "learning_rate": 0.0001115383875216598,
+      "loss": 0.4423,
+      "step": 161
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.16523972153663635,
+      "learning_rate": 0.00011058062427557229,
+      "loss": 0.5816,
+      "step": 162
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1553642749786377,
+      "learning_rate": 0.00010962187843917497,
+      "loss": 0.4793,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.14419597387313843,
+      "learning_rate": 0.0001086622390482699,
+      "loss": 0.4862,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.14601647853851318,
+      "learning_rate": 0.00010770179522164079,
+      "loss": 0.4589,
+      "step": 165
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.15500588715076447,
+      "learning_rate": 0.0001067406361527768,
+      "loss": 0.4754,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16032655537128448,
+      "learning_rate": 0.00010577885110158958,
+      "loss": 0.4644,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.15342958271503448,
+      "learning_rate": 0.00010481652938612374,
+      "loss": 0.3911,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.9589568972587585,
+      "eval_runtime": 324.8473,
+      "eval_samples_per_second": 0.767,
+      "eval_steps_per_second": 0.767,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.15607774257659912,
+      "learning_rate": 0.00010385376037426226,
+      "loss": 0.492,
+      "step": 169
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.15384891629219055,
+      "learning_rate": 0.00010289063347542726,
+      "loss": 0.487,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.15275317430496216,
+      "learning_rate": 0.00010192723813227672,
+      "loss": 0.4475,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.1687576025724411,
+      "learning_rate": 0.00010096366381239808,
+      "loss": 0.4491,
+      "step": 172
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.17867827415466309,
+      "learning_rate": 0.0001,
+      "loss": 0.4197,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14261119067668915,
+      "learning_rate": 9.903633618760195e-05,
+      "loss": 0.4734,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14787495136260986,
+      "learning_rate": 9.807276186772333e-05,
+      "loss": 0.404,
+      "step": 175
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.15715274214744568,
+      "learning_rate": 9.710936652457276e-05,
+      "loss": 0.4583,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1578068882226944,
+      "learning_rate": 9.614623962573776e-05,
+      "loss": 0.4343,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15597595274448395,
+      "learning_rate": 9.518347061387628e-05,
+      "loss": 0.4454,
+      "step": 178
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.142894446849823,
+      "learning_rate": 9.422114889841044e-05,
+      "loss": 0.4443,
+      "step": 179
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15279816091060638,
+      "learning_rate": 9.325936384722321e-05,
+      "loss": 0.4428,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1651957929134369,
+      "learning_rate": 9.229820477835927e-05,
+      "loss": 0.3857,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.22555674612522125,
+      "learning_rate": 9.133776095173015e-05,
+      "loss": 0.4578,
+      "step": 182
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.14163288474082947,
+      "learning_rate": 9.037812156082504e-05,
+      "loss": 0.4409,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1683199107646942,
+      "learning_rate": 8.941937572442773e-05,
+      "loss": 0.4829,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.17766785621643066,
+      "learning_rate": 8.846161247834024e-05,
+      "loss": 0.4357,
+      "step": 185
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.15518875420093536,
+      "learning_rate": 8.750492076711439e-05,
+      "loss": 0.4681,
+      "step": 186
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.13920673727989197,
+      "learning_rate": 8.654938943579194e-05,
+      "loss": 0.4258,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.17552931606769562,
+      "learning_rate": 8.55951072216536e-05,
+      "loss": 0.3932,
+      "step": 188
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.15486915409564972,
+      "learning_rate": 8.464216274597838e-05,
+      "loss": 0.4679,
+      "step": 189
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1437031477689743,
+      "learning_rate": 8.369064450581373e-05,
+      "loss": 0.3984,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.15499216318130493,
+      "learning_rate": 8.274064086575681e-05,
+      "loss": 0.5216,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.18269003927707672,
+      "learning_rate": 8.179224004974857e-05,
+      "loss": 0.4853,
+      "step": 192
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1596907526254654,
+      "learning_rate": 8.084553013288048e-05,
+      "loss": 0.4784,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.15115347504615784,
+      "learning_rate": 7.990059903321553e-05,
+      "loss": 0.4306,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.19720065593719482,
+      "learning_rate": 7.89575345036232e-05,
+      "loss": 0.4782,
+      "step": 195
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.14170032739639282,
+      "learning_rate": 7.801642412363041e-05,
+      "loss": 0.4318,
+      "step": 196
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16026908159255981,
+      "learning_rate": 7.707735529128819e-05,
+      "loss": 0.4656,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16910114884376526,
+      "learning_rate": 7.614041521505517e-05,
+      "loss": 0.5014,
+      "step": 198
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.18795110285282135,
+      "learning_rate": 7.520569090569893e-05,
+      "loss": 0.4512,
+      "step": 199
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.15903539955615997,
+      "learning_rate": 7.427326916821557e-05,
+      "loss": 0.5036,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15247230231761932,
+      "learning_rate": 7.334323659376829e-05,
+      "loss": 0.4369,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1472063809633255,
+      "learning_rate": 7.24156795516461e-05,
+      "loss": 0.426,
+      "step": 202
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15710321068763733,
+      "learning_rate": 7.149068418124281e-05,
+      "loss": 0.4034,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.15857233107089996,
+      "learning_rate": 7.056833638405762e-05,
+      "loss": 0.4783,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.16299530863761902,
+      "learning_rate": 6.964872181571764e-05,
+      "loss": 0.4719,
+      "step": 205
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.14976787567138672,
+      "learning_rate": 6.87319258780234e-05,
+      "loss": 0.4543,
+      "step": 206
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.14311917126178741,
+      "learning_rate": 6.781803371101774e-05,
+      "loss": 0.4422,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.14494828879833221,
+      "learning_rate": 6.690713018507918e-05,
+      "loss": 0.4078,
+      "step": 208
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1489972174167633,
+      "learning_rate": 6.599929989304035e-05,
+      "loss": 0.3908,
+      "step": 209
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.15475499629974365,
+      "learning_rate": 6.509462714233195e-05,
+      "loss": 0.5416,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1536937654018402,
+      "learning_rate": 6.419319594715339e-05,
+      "loss": 0.4267,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1654786467552185,
+      "learning_rate": 6.32950900206708e-05,
+      "loss": 0.4622,
+      "step": 212
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.14727674424648285,
+      "learning_rate": 6.240039276724272e-05,
+      "loss": 0.441,
+      "step": 213
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1774049550294876,
+      "learning_rate": 6.150918727467455e-05,
+      "loss": 0.4956,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.14867380261421204,
+      "learning_rate": 6.062155630650265e-05,
+      "loss": 0.5788,
+      "step": 215
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16996605694293976,
+      "learning_rate": 5.973758229430806e-05,
+      "loss": 0.588,
+      "step": 216
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.15790195763111115,
+      "learning_rate": 5.885734733006154e-05,
+      "loss": 0.425,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.15656080842018127,
+      "learning_rate": 5.798093315849984e-05,
+      "loss": 0.4193,
+      "step": 218
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.143330916762352,
+      "learning_rate": 5.710842116953438e-05,
+      "loss": 0.4427,
+      "step": 219
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.15389469265937805,
+      "learning_rate": 5.623989239069275e-05,
+      "loss": 0.4265,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.16425251960754395,
+      "learning_rate": 5.537542747959394e-05,
+      "loss": 0.53,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.1583469659090042,
+      "learning_rate": 5.451510671645807e-05,
+      "loss": 0.5009,
+      "step": 222
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.16075047850608826,
+      "learning_rate": 5.36590099966507e-05,
+      "loss": 0.5189,
+      "step": 223
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.14854145050048828,
+      "learning_rate": 5.2807216823263484e-05,
+      "loss": 0.463,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.15285861492156982,
+      "learning_rate": 5.1959806299730774e-05,
+      "loss": 0.4413,
+      "step": 225
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.14538119733333588,
+      "learning_rate": 5.111685712248364e-05,
+      "loss": 0.4736,
+      "step": 226
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.15160393714904785,
+      "learning_rate": 5.0278447573641495e-05,
+      "loss": 0.4298,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14497333765029907,
+      "learning_rate": 4.944465551374238e-05,
+      "loss": 0.3981,
+      "step": 228
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14342719316482544,
+      "learning_rate": 4.861555837451213e-05,
+      "loss": 0.4502,
+      "step": 229
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1621183604001999,
+      "learning_rate": 4.779123315167362e-05,
+      "loss": 0.4322,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.15252463519573212,
+      "learning_rate": 4.6971756397796504e-05,
+      "loss": 0.5072,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.17667719721794128,
+      "learning_rate": 4.61572042151878e-05,
+      "loss": 0.4708,
+      "step": 232
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.15273234248161316,
+      "learning_rate": 4.5347652248824624e-05,
+      "loss": 0.5212,
+      "step": 233
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.16372352838516235,
+      "learning_rate": 4.4543175679329344e-05,
+      "loss": 0.5303,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.14327646791934967,
+      "learning_rate": 4.3743849215987595e-05,
+      "loss": 0.4,
+      "step": 235
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.1604086011648178,
+      "learning_rate": 4.294974708981041e-05,
+      "loss": 0.4508,
+      "step": 236
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.23445452749729156,
+      "learning_rate": 4.216094304664056e-05,
+      "loss": 0.4363,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.15834979712963104,
+      "learning_rate": 4.137751034030399e-05,
+      "loss": 0.5153,
+      "step": 238
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.14937692880630493,
+      "learning_rate": 4.059952172580694e-05,
+      "loss": 0.4423,
+      "step": 239
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.16776776313781738,
+      "learning_rate": 3.982704945257957e-05,
+      "loss": 0.4089,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16948916018009186,
+      "learning_rate": 3.906016525776611e-05,
+      "loss": 0.562,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16811306774616241,
+      "learning_rate": 3.829894035956306e-05,
+      "loss": 0.407,
+      "step": 242
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.13980595767498016,
+      "learning_rate": 3.7543445450605285e-05,
+      "loss": 0.4329,
+      "step": 243
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.16961558163166046,
+      "learning_rate": 3.6793750691400994e-05,
+      "loss": 0.4476,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.16474933922290802,
+      "learning_rate": 3.6049925703816214e-05,
+      "loss": 0.4629,
+      "step": 245
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1619129627943039,
+      "learning_rate": 3.53120395646092e-05,
+      "loss": 0.4648,
+      "step": 246
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.20941300690174103,
+      "learning_rate": 3.458016079901544e-05,
+      "loss": 0.4777,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1691591888666153,
+      "learning_rate": 3.38543573743839e-05,
+      "loss": 0.4544,
+      "step": 248
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1482505053281784,
+      "learning_rate": 3.3134696693865316e-05,
+      "loss": 0.4295,
+      "step": 249
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.16560567915439606,
+      "learning_rate": 3.242124559015234e-05,
+      "loss": 0.4568,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15260429680347443,
+      "learning_rate": 3.171407031927325e-05,
+      "loss": 0.4311,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15556661784648895,
+      "learning_rate": 3.101323655443882e-05,
+      "loss": 0.4655,
+      "step": 252
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.9627882838249207,
+      "eval_runtime": 320.8688,
+      "eval_samples_per_second": 0.776,
+      "eval_steps_per_second": 0.776,
+      "step": 252
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.16530689597129822,
+      "learning_rate": 3.031880937994359e-05,
+      "loss": 0.4532,
+      "step": 253
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1501285582780838,
+      "learning_rate": 2.9630853285121508e-05,
+      "loss": 0.4538,
+      "step": 254
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.16318055987358093,
+      "learning_rate": 2.894943215835708e-05,
+      "loss": 0.4258,
+      "step": 255
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.15718339383602142,
+      "learning_rate": 2.827460928115232e-05,
+      "loss": 0.4724,
+      "step": 256
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.18563856184482574,
+      "learning_rate": 2.7606447322249872e-05,
+      "loss": 0.4064,
+      "step": 257
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.15688276290893555,
+      "learning_rate": 2.6945008331813226e-05,
+      "loss": 0.4399,
+      "step": 258
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.15704520046710968,
+      "learning_rate": 2.629035373566433e-05,
+      "loss": 0.4367,
+      "step": 259
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1557130515575409,
+      "learning_rate": 2.5642544329579088e-05,
+      "loss": 0.4937,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16318149864673615,
+      "learning_rate": 2.500164027364147e-05,
+      "loss": 0.4891,
+      "step": 261
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16402341425418854,
+      "learning_rate": 2.4367701086656624e-05,
+      "loss": 0.5084,
+      "step": 262
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.15349122881889343,
+      "learning_rate": 2.3740785640623643e-05,
+      "loss": 0.465,
+      "step": 263
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16672901809215546,
+      "learning_rate": 2.312095215526814e-05,
+      "loss": 0.4428,
+      "step": 264
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.14176689088344574,
+      "learning_rate": 2.2508258192635612e-05,
+      "loss": 0.4012,
+      "step": 265
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.15022584795951843,
+      "learning_rate": 2.1902760651745958e-05,
+      "loss": 0.413,
+      "step": 266
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.15624596178531647,
+      "learning_rate": 2.1304515763309253e-05,
+      "loss": 0.4438,
+      "step": 267
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15674558281898499,
+      "learning_rate": 2.0713579084503876e-05,
+      "loss": 0.3967,
+      "step": 268
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.16516539454460144,
+      "learning_rate": 2.013000549381706e-05,
+      "loss": 0.5009,
+      "step": 269
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15163196623325348,
+      "learning_rate": 1.9553849185948512e-05,
+      "loss": 0.4626,
+      "step": 270
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.15535032749176025,
+      "learning_rate": 1.8985163666777473e-05,
+      "loss": 0.5294,
+      "step": 271
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1474699229001999,
+      "learning_rate": 1.8424001748393905e-05,
+      "loss": 0.4898,
+      "step": 272
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.14586691558361053,
+      "learning_rate": 1.787041554419381e-05,
+      "loss": 0.3786,
+      "step": 273
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.14684820175170898,
+      "learning_rate": 1.7324456464039752e-05,
+      "loss": 0.3862,
+      "step": 274
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.15825559198856354,
+      "learning_rate": 1.6786175209486566e-05,
+      "loss": 0.4631,
+      "step": 275
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1755644828081131,
+      "learning_rate": 1.6255621769072805e-05,
+      "loss": 0.3825,
+      "step": 276
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.15722620487213135,
+      "learning_rate": 1.5732845413678477e-05,
+      "loss": 0.4219,
+      "step": 277
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.1658666431903839,
+      "learning_rate": 1.521789469194952e-05,
+      "loss": 0.45,
+      "step": 278
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.13978326320648193,
+      "learning_rate": 1.4710817425789014e-05,
+      "loss": 0.4063,
+      "step": 279
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.17951220273971558,
+      "learning_rate": 1.4211660705916285e-05,
+      "loss": 0.4697,
+      "step": 280
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.1507434844970703,
+      "learning_rate": 1.3720470887493719e-05,
+      "loss": 0.4618,
+      "step": 281
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1491430401802063,
+      "learning_rate": 1.3237293585821786e-05,
+      "loss": 0.4294,
+      "step": 282
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.15942510962486267,
+      "learning_rate": 1.2762173672102996e-05,
+      "loss": 0.4503,
+      "step": 283
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.16852998733520508,
+      "learning_rate": 1.2295155269274827e-05,
+      "loss": 0.5253,
+      "step": 284
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.15177421271800995,
+      "learning_rate": 1.1836281747912125e-05,
+      "loss": 0.4395,
+      "step": 285
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.14927661418914795,
+      "learning_rate": 1.1385595722199438e-05,
+      "loss": 0.463,
+      "step": 286
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.186951145529747,
+      "learning_rate": 1.0943139045973549e-05,
+      "loss": 0.4683,
+      "step": 287
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.16321802139282227,
+      "learning_rate": 1.050895280883668e-05,
+      "loss": 0.478,
+      "step": 288
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.15494760870933533,
+      "learning_rate": 1.0083077332340562e-05,
+      "loss": 0.4524,
+      "step": 289
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1643322855234146,
+      "learning_rate": 9.665552166241964e-06,
+      "loss": 0.514,
+      "step": 290
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1540500372648239,
+      "learning_rate": 9.256416084829778e-06,
+      "loss": 0.5143,
+      "step": 291
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.17111855745315552,
+      "learning_rate": 8.855707083324183e-06,
+      "loss": 0.4618,
+      "step": 292
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.1491898000240326,
+      "learning_rate": 8.46346237434813e-06,
+      "loss": 0.413,
+      "step": 293
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.16696412861347198,
+      "learning_rate": 8.079718384471557e-06,
+      "loss": 0.4021,
+      "step": 294
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.16858446598052979,
+      "learning_rate": 7.704510750828542e-06,
+      "loss": 0.4751,
+      "step": 295
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.1504489928483963,
+      "learning_rate": 7.337874317807802e-06,
+      "loss": 0.398,
+      "step": 296
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.183710977435112,
+      "learning_rate": 6.979843133816743e-06,
+      "loss": 0.4214,
+      "step": 297
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.16924622654914856,
+      "learning_rate": 6.630450448119618e-06,
+      "loss": 0.4698,
+      "step": 298
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.16073620319366455,
+      "learning_rate": 6.289728707749609e-06,
+      "loss": 0.509,
+      "step": 299
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1766895204782486,
+      "learning_rate": 5.957709554495683e-06,
+      "loss": 0.4978,
+      "step": 300
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.17092542350292206,
+      "learning_rate": 5.634423821964074e-06,
+      "loss": 0.4194,
+      "step": 301
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1549624800682068,
+      "learning_rate": 5.319901532714877e-06,
+      "loss": 0.4529,
+      "step": 302
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.16290757060050964,
+      "learning_rate": 5.014171895473929e-06,
+      "loss": 0.4134,
+      "step": 303
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1581151932477951,
+      "learning_rate": 4.717263302420283e-06,
+      "loss": 0.4456,
+      "step": 304
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.16641291975975037,
+      "learning_rate": 4.429203326549525e-06,
+      "loss": 0.463,
+      "step": 305
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.1655256152153015,
+      "learning_rate": 4.1500187191131466e-06,
+      "loss": 0.4648,
+      "step": 306
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.16075529158115387,
+      "learning_rate": 3.879735407134244e-06,
+      "loss": 0.4838,
+      "step": 307
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.17388100922107697,
+      "learning_rate": 3.6183784909997187e-06,
+      "loss": 0.4453,
+      "step": 308
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15238863229751587,
+      "learning_rate": 3.3659722421293783e-06,
+      "loss": 0.492,
+      "step": 309
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1615055352449417,
+      "learning_rate": 3.1225401007217936e-06,
+      "loss": 0.4442,
+      "step": 310
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.14086954295635223,
+      "learning_rate": 2.8881046735775742e-06,
+      "loss": 0.3575,
+      "step": 311
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2627798914909363,
+      "learning_rate": 2.66268773199988e-06,
+      "loss": 0.4517,
+      "step": 312
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.16790565848350525,
+      "learning_rate": 2.446310209772684e-06,
+      "loss": 0.4654,
+      "step": 313
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.16735273599624634,
+      "learning_rate": 2.2389922012165944e-06,
+      "loss": 0.4681,
+      "step": 314
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.14851590991020203,
+      "learning_rate": 2.0407529593228116e-06,
+      "loss": 0.4367,
+      "step": 315
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.15848883986473083,
+      "learning_rate": 1.8516108939651945e-06,
+      "loss": 0.4876,
+      "step": 316
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.16141897439956665,
+      "learning_rate": 1.6715835701905603e-06,
+      "loss": 0.4772,
+      "step": 317
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1615990400314331,
+      "learning_rate": 1.5006877065874336e-06,
+      "loss": 0.5161,
+      "step": 318
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.14088964462280273,
+      "learning_rate": 1.3389391737335112e-06,
+      "loss": 0.4474,
+      "step": 319
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.15512192249298096,
+      "learning_rate": 1.1863529927217732e-06,
+      "loss": 0.4444,
+      "step": 320
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.14642339944839478,
+      "learning_rate": 1.0429433337655115e-06,
+      "loss": 0.4234,
+      "step": 321
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16831575334072113,
+      "learning_rate": 9.087235148824368e-07,
+      "loss": 0.4631,
+      "step": 322
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16404962539672852,
+      "learning_rate": 7.837060006577801e-07,
+      "loss": 0.5365,
+      "step": 323
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.15236851572990417,
+      "learning_rate": 6.679024010868618e-07,
+      "loss": 0.4675,
+      "step": 324
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.1572081297636032,
+      "learning_rate": 5.613234704967996e-07,
+      "loss": 0.4364,
+      "step": 325
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.15015996992588043,
+      "learning_rate": 4.639791065478738e-07,
+      "loss": 0.4466,
+      "step": 326
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.1579872965812683,
+      "learning_rate": 3.758783493142737e-07,
+      "loss": 0.5068,
+      "step": 327
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.1496421992778778,
+      "learning_rate": 2.9702938044468e-07,
+      "loss": 0.3996,
+      "step": 328
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.14979000389575958,
+      "learning_rate": 2.2743952240236176e-07,
+      "loss": 0.4681,
+      "step": 329
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1566384732723236,
+      "learning_rate": 1.6711523778520921e-07,
+      "loss": 0.4222,
+      "step": 330
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.15907008945941925,
+      "learning_rate": 1.1606212872559141e-07,
+      "loss": 0.4386,
+      "step": 331
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1623019427061081,
+      "learning_rate": 7.428493637002821e-08,
+      "loss": 0.4347,
+      "step": 332
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1848601996898651,
+      "learning_rate": 4.178754043898669e-08,
+      "loss": 0.4431,
+      "step": 333
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1645398586988449,
+      "learning_rate": 1.8572958866514e-08,
+      "loss": 0.4556,
+      "step": 334
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1536179780960083,
+      "learning_rate": 4.643347520005836e-09,
+      "loss": 0.4282,
+      "step": 335
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15975765883922577,
+      "learning_rate": 0.0,
+      "loss": 0.4569,
+      "step": 336
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9572544097900391,
+      "eval_runtime": 320.7126,
+      "eval_samples_per_second": 0.776,
+      "eval_steps_per_second": 0.776,
+      "step": 336
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 84,
+  "total_flos": 3.406567632525066e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-336/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92cf4d819bd687a107f49060d4cb816ff788627c8bf6c0b866a032bb83436a5
+size 5816

config.json

@@ -40,15 +40,13 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "float32",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": [
-      "mamba"
-    ],
+    "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
@@ -58,9 +56,9 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_mamba_kernels": true,
   "vocab_size": 65536
 }

tokenizer_config.json

@@ -36,6 +36,7 @@
     }
   },
   "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,