Initial model upload

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,141 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: ibm-granite/granite-3.1-8b-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.1-8b-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.2`
+```yaml
+base_model: ibm-granite/granite-3.1-8b-instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+resize_token_embeddings_to_32x: true
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+- path: /home/ec2-user/SageMaker/task_decomposition/data/task_decomposition_training_data_code.jsonl
+  type: chat_template
+  chat_template: tokenizer_default
+  field_messages: conversations
+  message_field_role: role
+  message_field_content: value
+dataset_prepared_path: last_run_prepared_sft
+
+val_set_size: 0
+sequence_len: 8192
+sample_packing: false
+pad_to_sequence_len: true
+eval_sample_packing: false
+output_dir: /home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.1-8b-lora
+
+wandb_project: null
+wandb_entity: null
+wandb_watch: null
+wandb_name: null
+wandb_log_model: null
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+eval_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 1e-05
+
+max_grad_norm: 1.0
+logging_steps: 10
+
+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:
+xformers_attention:
+flash_attention: true
+warmup_ratio: 0.05
+eval_steps:
+save_strategy: epoch
+eval_table_size:
+num_processes: 8
+deepspeed:
+weight_decay: 0.0
+```
+
+</details><br>
+
+# home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.0-8b-lora
+
+This model is a fine-tuned version of [ibm-granite/granite-3.1-8b-instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct) on the /home/ec2-user/SageMaker/task_decomposition/data/task_decomposition_training_data_code.jsonl dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 131
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.3
+- Pytorch 2.3.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

README.md

@@ -0,0 +1,141 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: ibm-granite/granite-3.1-8b-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.1-8b-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.2`
+```yaml
+base_model: ibm-granite/granite-3.1-8b-instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+resize_token_embeddings_to_32x: true
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+- path: /home/ec2-user/SageMaker/task_decomposition/data/task_decomposition_training_data_code.jsonl
+  type: chat_template
+  chat_template: tokenizer_default
+  field_messages: conversations
+  message_field_role: role
+  message_field_content: value
+dataset_prepared_path: last_run_prepared_sft
+
+val_set_size: 0
+sequence_len: 8192
+sample_packing: false
+pad_to_sequence_len: true
+eval_sample_packing: false
+output_dir: /home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.1-8b-lora
+
+wandb_project: null
+wandb_entity: null
+wandb_watch: null
+wandb_name: null
+wandb_log_model: null
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+eval_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 1e-05
+
+max_grad_norm: 1.0
+logging_steps: 10
+
+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:
+xformers_attention:
+flash_attention: true
+warmup_ratio: 0.05
+eval_steps:
+save_strategy: epoch
+eval_table_size:
+num_processes: 8
+deepspeed:
+weight_decay: 0.0
+```
+
+</details><br>
+
+# home/ec2-user/SageMaker/task_decomposition/trained_models/granite-code-plans-3.0-8b-lora
+
+This model is a fine-tuned version of [ibm-granite/granite-3.1-8b-instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct) on the /home/ec2-user/SageMaker/task_decomposition/data/task_decomposition_training_data_code.jsonl dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 131
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.3
+- Pytorch 2.3.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.1-8b-instruct",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c3edb99c6fc94c240b9835eb699c595319870dd0c7d63e62ccead0ebe33cfb
+size 798955662

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end_of_role|>": 49153,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

checkpoint-2634/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.1-8b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

checkpoint-2634/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.1-8b-instruct",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2634/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ebaf12130f5535a2f0f5535926bf7abfcd5fb36a79ed786d165ab5999d812b
+size 1201743872

checkpoint-2634/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end_of_role|>": 49153,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

checkpoint-2634/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89902f0ada51006c8f38e151736085e7a3f0f9ff7f5e322283cde55b9482a7a5
+size 201669716

checkpoint-2634/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbb3e9320cd68bfe8c2bf072af8314d8ce5efd24e4384ff04b193579c3e7200
+size 15984

checkpoint-2634/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab1f7aef383750eace0f5192955176857f85e40b72609de632e8e6991478fc5
+size 15984

checkpoint-2634/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753bffddc284b0654ce16c1507fa2788baad2d52808943365d875916e088cafb
+size 15984

checkpoint-2634/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed518fa1cf576370463fb2c80cc41ea79ab84f310b30a6b9a6ab8ac5c80a9e7
+size 15984

checkpoint-2634/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dba4fac68ce5da86e140d8e7c676ab9e7e3c1e7a80583bdcf190b5552f59a1
+size 15984

checkpoint-2634/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ad82c628b592c75294f2afeb315f93392198e2c3e75ebdbc157d6ab68a0dc6
+size 15984

checkpoint-2634/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8254fa21b706860d6a5436375803d5421f86cef2466fa7bdb11f480b806748
+size 15984

checkpoint-2634/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7451f4d374e811fd9af8553a62494efb2128f894b111bc4d501e74ab5b9c5e2
+size 15984

checkpoint-2634/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc409a018e12e79b6a09cca3f51d9317a6dff64227181a981433f442215a27ed
+size 1064

checkpoint-2634/special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2634/tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n    {%- if tools and documents %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\n\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- elif tools %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n    {%- elif documents %}\n        {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- else %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}    \n    {%- endif %}\n    {%- if 'citations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nIn your response, use the symbols <co> and </co> to indicate when a fact comes from a document in the search result, e.g <co>0</co> for a fact from document 0. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n    {%- endif %}\n    {%- if 'hallucinations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nFinally, after the response is written, include a numbered list of sentences from the response that are potentially hallucinated and not based in the documents.' %}\n    {%- endif %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n{%- if tools %}\n    {{- '<|start_of_role|>tools<|end_of_role|>' }}\n    {{- tools | tojson(indent=4) }}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- if documents %}\n    {{- '<|start_of_role|>documents<|end_of_role|>' }}\n    {%- for document in documents %}\n        {{- 'Document ' + loop.index0 | string + '\n' }}\n        {{- document['text'] }}\n        {%- if not loop.last %}\n            {{- '\n\n'}}\n        {%- endif%}\n    {%- endfor %}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in loop_messages %}\n    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n    {%- if loop.last and add_generation_prompt %}\n        {{- '<|start_of_role|>assistant' }}\n            {%- if controls %}\n                {{- ' ' + controls | tojson()}}\n            {%- endif %}\n        {{- '<|end_of_role|>' }}\n    {%- endif %}\n{%- endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

checkpoint-2634/trainer_state.json

@@ -0,0 +1,1874 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997297681695349,
+  "eval_steps": 500,
+  "global_step": 2634,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011378182335371924,
+      "grad_norm": 4.778728008270264,
+      "learning_rate": 7.633587786259543e-07,
+      "loss": 1.0811,
+      "step": 10
+    },
+    {
+      "epoch": 0.022756364670743847,
+      "grad_norm": 4.217845439910889,
+      "learning_rate": 1.5267175572519086e-06,
+      "loss": 1.0744,
+      "step": 20
+    },
+    {
+      "epoch": 0.034134547006115776,
+      "grad_norm": 4.523660182952881,
+      "learning_rate": 2.2900763358778625e-06,
+      "loss": 1.0751,
+      "step": 30
+    },
+    {
+      "epoch": 0.045512729341487694,
+      "grad_norm": 4.545449256896973,
+      "learning_rate": 3.0534351145038173e-06,
+      "loss": 1.0621,
+      "step": 40
+    },
+    {
+      "epoch": 0.05689091167685962,
+      "grad_norm": 4.702221393585205,
+      "learning_rate": 3.816793893129772e-06,
+      "loss": 1.0629,
+      "step": 50
+    },
+    {
+      "epoch": 0.06826909401223155,
+      "grad_norm": 5.066348552703857,
+      "learning_rate": 4.580152671755725e-06,
+      "loss": 1.0345,
+      "step": 60
+    },
+    {
+      "epoch": 0.07964727634760348,
+      "grad_norm": 4.052086353302002,
+      "learning_rate": 5.34351145038168e-06,
+      "loss": 0.9583,
+      "step": 70
+    },
+    {
+      "epoch": 0.09102545868297539,
+      "grad_norm": 3.1136085987091064,
+      "learning_rate": 6.1068702290076346e-06,
+      "loss": 0.8734,
+      "step": 80
+    },
+    {
+      "epoch": 0.10240364101834731,
+      "grad_norm": 2.0436317920684814,
+      "learning_rate": 6.870229007633589e-06,
+      "loss": 0.798,
+      "step": 90
+    },
+    {
+      "epoch": 0.11378182335371924,
+      "grad_norm": 1.6023002862930298,
+      "learning_rate": 7.633587786259543e-06,
+      "loss": 0.7381,
+      "step": 100
+    },
+    {
+      "epoch": 0.12516000568909116,
+      "grad_norm": 1.3594775199890137,
+      "learning_rate": 8.396946564885497e-06,
+      "loss": 0.6903,
+      "step": 110
+    },
+    {
+      "epoch": 0.1365381880244631,
+      "grad_norm": 1.1952372789382935,
+      "learning_rate": 9.16030534351145e-06,
+      "loss": 0.6682,
+      "step": 120
+    },
+    {
+      "epoch": 0.14791637035983501,
+      "grad_norm": 1.0661766529083252,
+      "learning_rate": 9.923664122137405e-06,
+      "loss": 0.6561,
+      "step": 130
+    },
+    {
+      "epoch": 0.15929455269520695,
+      "grad_norm": 1.1098530292510986,
+      "learning_rate": 9.999680994290835e-06,
+      "loss": 0.652,
+      "step": 140
+    },
+    {
+      "epoch": 0.17067273503057886,
+      "grad_norm": 1.070675015449524,
+      "learning_rate": 9.998578310766133e-06,
+      "loss": 0.625,
+      "step": 150
+    },
+    {
+      "epoch": 0.18205091736595078,
+      "grad_norm": 1.066764235496521,
+      "learning_rate": 9.996688184751814e-06,
+      "loss": 0.6181,
+      "step": 160
+    },
+    {
+      "epoch": 0.19342909970132272,
+      "grad_norm": 1.1886961460113525,
+      "learning_rate": 9.994010914005644e-06,
+      "loss": 0.6246,
+      "step": 170
+    },
+    {
+      "epoch": 0.20480728203669463,
+      "grad_norm": 1.1360214948654175,
+      "learning_rate": 9.990546920286894e-06,
+      "loss": 0.6058,
+      "step": 180
+    },
+    {
+      "epoch": 0.21618546437206657,
+      "grad_norm": 1.2674109935760498,
+      "learning_rate": 9.986296749289894e-06,
+      "loss": 0.6091,
+      "step": 190
+    },
+    {
+      "epoch": 0.22756364670743848,
+      "grad_norm": 1.0798505544662476,
+      "learning_rate": 9.981261070558069e-06,
+      "loss": 0.6091,
+      "step": 200
+    },
+    {
+      "epoch": 0.23894182904281042,
+      "grad_norm": 1.795167088508606,
+      "learning_rate": 9.975440677378455e-06,
+      "loss": 0.6095,
+      "step": 210
+    },
+    {
+      "epoch": 0.2503200113781823,
+      "grad_norm": 1.219923496246338,
+      "learning_rate": 9.968836486656746e-06,
+      "loss": 0.6158,
+      "step": 220
+    },
+    {
+      "epoch": 0.26169819371355424,
+      "grad_norm": 1.474357008934021,
+      "learning_rate": 9.961449538772838e-06,
+      "loss": 0.6111,
+      "step": 230
+    },
+    {
+      "epoch": 0.2730763760489262,
+      "grad_norm": 1.2231380939483643,
+      "learning_rate": 9.953280997416937e-06,
+      "loss": 0.6134,
+      "step": 240
+    },
+    {
+      "epoch": 0.2844545583842981,
+      "grad_norm": 1.2513004541397095,
+      "learning_rate": 9.944332149406242e-06,
+      "loss": 0.6106,
+      "step": 250
+    },
+    {
+      "epoch": 0.29583274071967003,
+      "grad_norm": 1.2386839389801025,
+      "learning_rate": 9.93460440448223e-06,
+      "loss": 0.5959,
+      "step": 260
+    },
+    {
+      "epoch": 0.30721092305504194,
+      "grad_norm": 2.128643274307251,
+      "learning_rate": 9.924099295088565e-06,
+      "loss": 0.6016,
+      "step": 270
+    },
+    {
+      "epoch": 0.3185891053904139,
+      "grad_norm": 1.2879629135131836,
+      "learning_rate": 9.9128184761297e-06,
+      "loss": 0.6064,
+      "step": 280
+    },
+    {
+      "epoch": 0.3299672877257858,
+      "grad_norm": 1.2779061794281006,
+      "learning_rate": 9.900763724710169e-06,
+      "loss": 0.5975,
+      "step": 290
+    },
+    {
+      "epoch": 0.34134547006115773,
+      "grad_norm": 2.398998975753784,
+      "learning_rate": 9.887936939854625e-06,
+      "loss": 0.5923,
+      "step": 300
+    },
+    {
+      "epoch": 0.35272365239652964,
+      "grad_norm": 1.3152679204940796,
+      "learning_rate": 9.8743401422087e-06,
+      "loss": 0.5961,
+      "step": 310
+    },
+    {
+      "epoch": 0.36410183473190155,
+      "grad_norm": 1.3303252458572388,
+      "learning_rate": 9.859975473720664e-06,
+      "loss": 0.5988,
+      "step": 320
+    },
+    {
+      "epoch": 0.3754800170672735,
+      "grad_norm": 1.3672901391983032,
+      "learning_rate": 9.844845197304013e-06,
+      "loss": 0.6062,
+      "step": 330
+    },
+    {
+      "epoch": 0.38685819940264543,
+      "grad_norm": 1.2618701457977295,
+      "learning_rate": 9.828951696480982e-06,
+      "loss": 0.5993,
+      "step": 340
+    },
+    {
+      "epoch": 0.39823638173801734,
+      "grad_norm": 5.503425121307373,
+      "learning_rate": 9.81229747500705e-06,
+      "loss": 0.5942,
+      "step": 350
+    },
+    {
+      "epoch": 0.40961456407338925,
+      "grad_norm": 2.4071738719940186,
+      "learning_rate": 9.794885156476532e-06,
+      "loss": 0.5893,
+      "step": 360
+    },
+    {
+      "epoch": 0.4209927464087612,
+      "grad_norm": 1.395342469215393,
+      "learning_rate": 9.776717483909261e-06,
+      "loss": 0.5861,
+      "step": 370
+    },
+    {
+      "epoch": 0.43237092874413313,
+      "grad_norm": 1.5855286121368408,
+      "learning_rate": 9.75779731931848e-06,
+      "loss": 0.6038,
+      "step": 380
+    },
+    {
+      "epoch": 0.44374911107950504,
+      "grad_norm": 1.3623788356781006,
+      "learning_rate": 9.738127643259978e-06,
+      "loss": 0.5767,
+      "step": 390
+    },
+    {
+      "epoch": 0.45512729341487695,
+      "grad_norm": 1.9213502407073975,
+      "learning_rate": 9.717711554362544e-06,
+      "loss": 0.5927,
+      "step": 400
+    },
+    {
+      "epoch": 0.4665054757502489,
+      "grad_norm": 2.3041162490844727,
+      "learning_rate": 9.696552268839846e-06,
+      "loss": 0.5869,
+      "step": 410
+    },
+    {
+      "epoch": 0.47788365808562083,
+      "grad_norm": 1.4046136140823364,
+      "learning_rate": 9.67465311998376e-06,
+      "loss": 0.589,
+      "step": 420
+    },
+    {
+      "epoch": 0.48926184042099274,
+      "grad_norm": 1.43635094165802,
+      "learning_rate": 9.652017557639269e-06,
+      "loss": 0.5869,
+      "step": 430
+    },
+    {
+      "epoch": 0.5006400227563647,
+      "grad_norm": 1.453419804573059,
+      "learning_rate": 9.628649147660989e-06,
+      "loss": 0.5862,
+      "step": 440
+    },
+    {
+      "epoch": 0.5120182050917366,
+      "grad_norm": 1.5567063093185425,
+      "learning_rate": 9.604551571351442e-06,
+      "loss": 0.5821,
+      "step": 450
+    },
+    {
+      "epoch": 0.5233963874271085,
+      "grad_norm": 1.4351816177368164,
+      "learning_rate": 9.579728624881117e-06,
+      "loss": 0.5969,
+      "step": 460
+    },
+    {
+      "epoch": 0.5347745697624804,
+      "grad_norm": 1.4502918720245361,
+      "learning_rate": 9.554184218690458e-06,
+      "loss": 0.5796,
+      "step": 470
+    },
+    {
+      "epoch": 0.5461527520978524,
+      "grad_norm": 1.4197890758514404,
+      "learning_rate": 9.527922376873828e-06,
+      "loss": 0.5882,
+      "step": 480
+    },
+    {
+      "epoch": 0.5575309344332243,
+      "grad_norm": 1.5547962188720703,
+      "learning_rate": 9.500947236545583e-06,
+      "loss": 0.5734,
+      "step": 490
+    },
+    {
+      "epoch": 0.5689091167685962,
+      "grad_norm": 1.4449543952941895,
+      "learning_rate": 9.473263047188344e-06,
+      "loss": 0.5788,
+      "step": 500
+    },
+    {
+      "epoch": 0.5802872991039681,
+      "grad_norm": 1.480697751045227,
+      "learning_rate": 9.444874169983562e-06,
+      "loss": 0.568,
+      "step": 510
+    },
+    {
+      "epoch": 0.5916654814393401,
+      "grad_norm": 1.7815808057785034,
+      "learning_rate": 9.415785077124474e-06,
+      "loss": 0.5866,
+      "step": 520
+    },
+    {
+      "epoch": 0.603043663774712,
+      "grad_norm": 1.5812064409255981,
+      "learning_rate": 9.386000351111602e-06,
+      "loss": 0.6007,
+      "step": 530
+    },
+    {
+      "epoch": 0.6144218461100839,
+      "grad_norm": 1.4948545694351196,
+      "learning_rate": 9.355524684030841e-06,
+      "loss": 0.5773,
+      "step": 540
+    },
+    {
+      "epoch": 0.6258000284454558,
+      "grad_norm": 2.1749398708343506,
+      "learning_rate": 9.324362876814315e-06,
+      "loss": 0.5891,
+      "step": 550
+    },
+    {
+      "epoch": 0.6371782107808278,
+      "grad_norm": 2.3155527114868164,
+      "learning_rate": 9.292519838484052e-06,
+      "loss": 0.5753,
+      "step": 560
+    },
+    {
+      "epoch": 0.6485563931161997,
+      "grad_norm": 1.5408862829208374,
+      "learning_rate": 9.260000585378664e-06,
+      "loss": 0.583,
+      "step": 570
+    },
+    {
+      "epoch": 0.6599345754515716,
+      "grad_norm": 2.3708317279815674,
+      "learning_rate": 9.2268102403631e-06,
+      "loss": 0.582,
+      "step": 580
+    },
+    {
+      "epoch": 0.6713127577869435,
+      "grad_norm": 1.5664266347885132,
+      "learning_rate": 9.192954032021626e-06,
+      "loss": 0.5687,
+      "step": 590
+    },
+    {
+      "epoch": 0.6826909401223155,
+      "grad_norm": 1.8958492279052734,
+      "learning_rate": 9.15843729383415e-06,
+      "loss": 0.5689,
+      "step": 600
+    },
+    {
+      "epoch": 0.6940691224576874,
+      "grad_norm": 1.5079455375671387,
+      "learning_rate": 9.123265463336022e-06,
+      "loss": 0.5787,
+      "step": 610
+    },
+    {
+      "epoch": 0.7054473047930593,
+      "grad_norm": 1.612349033355713,
+      "learning_rate": 9.087444081261433e-06,
+      "loss": 0.584,
+      "step": 620
+    },
+    {
+      "epoch": 0.7168254871284312,
+      "grad_norm": 1.7752846479415894,
+      "learning_rate": 9.050978790670575e-06,
+      "loss": 0.5744,
+      "step": 630
+    },
+    {
+      "epoch": 0.7282036694638031,
+      "grad_norm": 1.5847499370574951,
+      "learning_rate": 9.013875336060671e-06,
+      "loss": 0.5908,
+      "step": 640
+    },
+    {
+      "epoch": 0.7395818517991751,
+      "grad_norm": 1.6264406442642212,
+      "learning_rate": 8.976139562461018e-06,
+      "loss": 0.57,
+      "step": 650
+    },
+    {
+      "epoch": 0.750960034134547,
+      "grad_norm": 1.783176064491272,
+      "learning_rate": 8.937777414512198e-06,
+      "loss": 0.5759,
+      "step": 660
+    },
+    {
+      "epoch": 0.762338216469919,
+      "grad_norm": 1.7870570421218872,
+      "learning_rate": 8.89879493552962e-06,
+      "loss": 0.5782,
+      "step": 670
+    },
+    {
+      "epoch": 0.7737163988052909,
+      "grad_norm": 1.666524052619934,
+      "learning_rate": 8.85919826655147e-06,
+      "loss": 0.5734,
+      "step": 680
+    },
+    {
+      "epoch": 0.7850945811406628,
+      "grad_norm": 1.7140533924102783,
+      "learning_rate": 8.81899364537131e-06,
+      "loss": 0.5854,
+      "step": 690
+    },
+    {
+      "epoch": 0.7964727634760347,
+      "grad_norm": 1.655806303024292,
+      "learning_rate": 8.778187405555412e-06,
+      "loss": 0.581,
+      "step": 700
+    },
+    {
+      "epoch": 0.8078509458114066,
+      "grad_norm": 1.8484113216400146,
+      "learning_rate": 8.736785975445009e-06,
+      "loss": 0.5722,
+      "step": 710
+    },
+    {
+      "epoch": 0.8192291281467785,
+      "grad_norm": 1.7415412664413452,
+      "learning_rate": 8.694795877143625e-06,
+      "loss": 0.5804,
+      "step": 720
+    },
+    {
+      "epoch": 0.8306073104821505,
+      "grad_norm": 1.6867784261703491,
+      "learning_rate": 8.652223725489614e-06,
+      "loss": 0.5675,
+      "step": 730
+    },
+    {
+      "epoch": 0.8419854928175224,
+      "grad_norm": 1.7585080862045288,
+      "learning_rate": 8.60907622701412e-06,
+      "loss": 0.5766,
+      "step": 740
+    },
+    {
+      "epoch": 0.8533636751528944,
+      "grad_norm": 1.9183036088943481,
+      "learning_rate": 8.565360178884554e-06,
+      "loss": 0.5763,
+      "step": 750
+    },
+    {
+      "epoch": 0.8647418574882663,
+      "grad_norm": 1.7552123069763184,
+      "learning_rate": 8.521082467833832e-06,
+      "loss": 0.5734,
+      "step": 760
+    },
+    {
+      "epoch": 0.8761200398236382,
+      "grad_norm": 1.8437159061431885,
+      "learning_rate": 8.476250069075476e-06,
+      "loss": 0.5796,
+      "step": 770
+    },
+    {
+      "epoch": 0.8874982221590101,
+      "grad_norm": 1.8383750915527344,
+      "learning_rate": 8.430870045204787e-06,
+      "loss": 0.5711,
+      "step": 780
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 1.6691679954528809,
+      "learning_rate": 8.384949545086255e-06,
+      "loss": 0.5922,
+      "step": 790
+    },
+    {
+      "epoch": 0.9102545868297539,
+      "grad_norm": 2.3490517139434814,
+      "learning_rate": 8.338495802727364e-06,
+      "loss": 0.5772,
+      "step": 800
+    },
+    {
+      "epoch": 0.9216327691651258,
+      "grad_norm": 1.8429322242736816,
+      "learning_rate": 8.291516136139017e-06,
+      "loss": 0.561,
+      "step": 810
+    },
+    {
+      "epoch": 0.9330109515004978,
+      "grad_norm": 1.7698525190353394,
+      "learning_rate": 8.244017946182676e-06,
+      "loss": 0.5755,
+      "step": 820
+    },
+    {
+      "epoch": 0.9443891338358698,
+      "grad_norm": 1.839783787727356,
+      "learning_rate": 8.196008715404506e-06,
+      "loss": 0.5781,
+      "step": 830
+    },
+    {
+      "epoch": 0.9557673161712417,
+      "grad_norm": 1.793582558631897,
+      "learning_rate": 8.14749600685661e-06,
+      "loss": 0.5734,
+      "step": 840
+    },
+    {
+      "epoch": 0.9671454985066136,
+      "grad_norm": 1.85206139087677,
+      "learning_rate": 8.098487462905603e-06,
+      "loss": 0.5633,
+      "step": 850
+    },
+    {
+      "epoch": 0.9785236808419855,
+      "grad_norm": 1.9638901948928833,
+      "learning_rate": 8.048990804028678e-06,
+      "loss": 0.5568,
+      "step": 860
+    },
+    {
+      "epoch": 0.9899018631773574,
+      "grad_norm": 2.9568979740142822,
+      "learning_rate": 7.999013827597381e-06,
+      "loss": 0.573,
+      "step": 870
+    },
+    {
+      "epoch": 1.0014222727919215,
+      "grad_norm": 3.1088480949401855,
+      "learning_rate": 7.948564406649268e-06,
+      "loss": 0.5728,
+      "step": 880
+    },
+    {
+      "epoch": 1.0128004551272933,
+      "grad_norm": 2.6320693492889404,
+      "learning_rate": 7.897650488647628e-06,
+      "loss": 0.5593,
+      "step": 890
+    },
+    {
+      "epoch": 1.0241786374626654,
+      "grad_norm": 3.3647408485412598,
+      "learning_rate": 7.846280094229498e-06,
+      "loss": 0.5741,
+      "step": 900
+    },
+    {
+      "epoch": 1.0355568197980372,
+      "grad_norm": 3.51078724861145,
+      "learning_rate": 7.794461315942154e-06,
+      "loss": 0.5617,
+      "step": 910
+    },
+    {
+      "epoch": 1.0469350021334092,
+      "grad_norm": 3.4864909648895264,
+      "learning_rate": 7.742202316968254e-06,
+      "loss": 0.5707,
+      "step": 920
+    },
+    {
+      "epoch": 1.0583131844687812,
+      "grad_norm": 3.092726469039917,
+      "learning_rate": 7.689511329839868e-06,
+      "loss": 0.5787,
+      "step": 930
+    },
+    {
+      "epoch": 1.069691366804153,
+      "grad_norm": 5.743341445922852,
+      "learning_rate": 7.636396655141585e-06,
+      "loss": 0.5667,
+      "step": 940
+    },
+    {
+      "epoch": 1.081069549139525,
+      "grad_norm": 3.3752024173736572,
+      "learning_rate": 7.5828666602028886e-06,
+      "loss": 0.5665,
+      "step": 950
+    },
+    {
+      "epoch": 1.0924477314748968,
+      "grad_norm": 3.439068555831909,
+      "learning_rate": 7.5289297777800275e-06,
+      "loss": 0.5666,
+      "step": 960
+    },
+    {
+      "epoch": 1.1038259138102688,
+      "grad_norm": 2.710096597671509,
+      "learning_rate": 7.474594504727576e-06,
+      "loss": 0.5643,
+      "step": 970
+    },
+    {
+      "epoch": 1.1152040961456406,
+      "grad_norm": 3.292506456375122,
+      "learning_rate": 7.419869400659889e-06,
+      "loss": 0.5651,
+      "step": 980
+    },
+    {
+      "epoch": 1.1265822784810127,
+      "grad_norm": 4.223087787628174,
+      "learning_rate": 7.364763086602696e-06,
+      "loss": 0.5614,
+      "step": 990
+    },
+    {
+      "epoch": 1.1379604608163847,
+      "grad_norm": 3.193408966064453,
+      "learning_rate": 7.3092842436349776e-06,
+      "loss": 0.5671,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1493386431517565,
+      "grad_norm": 3.6121826171875,
+      "learning_rate": 7.253441611521426e-06,
+      "loss": 0.582,
+      "step": 1010
+    },
+    {
+      "epoch": 1.1607168254871285,
+      "grad_norm": 3.511631965637207,
+      "learning_rate": 7.197243987335636e-06,
+      "loss": 0.5687,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1720950078225003,
+      "grad_norm": 3.4007201194763184,
+      "learning_rate": 7.140700224074269e-06,
+      "loss": 0.5655,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1834731901578723,
+      "grad_norm": 3.5121917724609375,
+      "learning_rate": 7.083819229262413e-06,
+      "loss": 0.5763,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1948513724932441,
+      "grad_norm": 2.648864507675171,
+      "learning_rate": 7.026609963550353e-06,
+      "loss": 0.5648,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2062295548286162,
+      "grad_norm": 3.010129451751709,
+      "learning_rate": 6.969081439301975e-06,
+      "loss": 0.559,
+      "step": 1060
+    },
+    {
+      "epoch": 1.217607737163988,
+      "grad_norm": 2.5858263969421387,
+      "learning_rate": 6.9112427191749975e-06,
+      "loss": 0.5686,
+      "step": 1070
+    },
+    {
+      "epoch": 1.22898591949936,
+      "grad_norm": 3.160468578338623,
+      "learning_rate": 6.853102914693336e-06,
+      "loss": 0.5676,
+      "step": 1080
+    },
+    {
+      "epoch": 1.2403641018347318,
+      "grad_norm": 3.4577555656433105,
+      "learning_rate": 6.794671184811699e-06,
+      "loss": 0.5652,
+      "step": 1090
+    },
+    {
+      "epoch": 1.2517422841701038,
+      "grad_norm": 2.875277042388916,
+      "learning_rate": 6.735956734472772e-06,
+      "loss": 0.5652,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2631204665054758,
+      "grad_norm": 3.1883442401885986,
+      "learning_rate": 6.6769688131571255e-06,
+      "loss": 0.575,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2744986488408476,
+      "grad_norm": 2.6882236003875732,
+      "learning_rate": 6.617716713426105e-06,
+      "loss": 0.5731,
+      "step": 1120
+    },
+    {
+      "epoch": 1.2858768311762196,
+      "grad_norm": 2.7670583724975586,
+      "learning_rate": 6.55820976945796e-06,
+      "loss": 0.5742,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2972550135115914,
+      "grad_norm": 3.168198823928833,
+      "learning_rate": 6.498457355577385e-06,
+      "loss": 0.5652,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3086331958469635,
+      "grad_norm": 3.868013620376587,
+      "learning_rate": 6.438468884778762e-06,
+      "loss": 0.5647,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3200113781823353,
+      "grad_norm": 2.759697437286377,
+      "learning_rate": 6.3782538072432935e-06,
+      "loss": 0.5648,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3313895605177073,
+      "grad_norm": 3.8222415447235107,
+      "learning_rate": 6.317821608850287e-06,
+      "loss": 0.5529,
+      "step": 1170
+    },
+    {
+      "epoch": 1.3427677428530793,
+      "grad_norm": 2.72162127494812,
+      "learning_rate": 6.257181809682813e-06,
+      "loss": 0.5659,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3541459251884511,
+      "grad_norm": 3.477682590484619,
+      "learning_rate": 6.196343962527975e-06,
+      "loss": 0.5576,
+      "step": 1190
+    },
+    {
+      "epoch": 1.3655241075238231,
+      "grad_norm": 58.64210891723633,
+      "learning_rate": 6.135317651372031e-06,
+      "loss": 0.5649,
+      "step": 1200
+    },
+    {
+      "epoch": 1.376902289859195,
+      "grad_norm": 4.460225582122803,
+      "learning_rate": 6.07411248989059e-06,
+      "loss": 0.5554,
+      "step": 1210
+    },
+    {
+      "epoch": 1.388280472194567,
+      "grad_norm": 3.014174461364746,
+      "learning_rate": 6.012738119934141e-06,
+      "loss": 0.5624,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3996586545299388,
+      "grad_norm": 3.1429977416992188,
+      "learning_rate": 5.951204210009141e-06,
+      "loss": 0.5656,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4110368368653108,
+      "grad_norm": 2.938356399536133,
+      "learning_rate": 5.889520453754904e-06,
+      "loss": 0.5623,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4224150192006828,
+      "grad_norm": 3.665616512298584,
+      "learning_rate": 5.827696568416532e-06,
+      "loss": 0.5623,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4337932015360546,
+      "grad_norm": 3.3361687660217285,
+      "learning_rate": 5.765742293314119e-06,
+      "loss": 0.5649,
+      "step": 1260
+    },
+    {
+      "epoch": 1.4451713838714264,
+      "grad_norm": 2.919668436050415,
+      "learning_rate": 5.703667388308487e-06,
+      "loss": 0.5633,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4565495662067984,
+      "grad_norm": 2.943481683731079,
+      "learning_rate": 5.641481632263687e-06,
+      "loss": 0.5662,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4679277485421705,
+      "grad_norm": 3.160897731781006,
+      "learning_rate": 5.579194821506497e-06,
+      "loss": 0.5564,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4793059308775423,
+      "grad_norm": 3.4720726013183594,
+      "learning_rate": 5.516816768283174e-06,
+      "loss": 0.5624,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4906841132129143,
+      "grad_norm": 3.757178544998169,
+      "learning_rate": 5.454357299213708e-06,
+      "loss": 0.5597,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5020622955482863,
+      "grad_norm": 3.1537322998046875,
+      "learning_rate": 5.391826253743788e-06,
+      "loss": 0.5587,
+      "step": 1320
+    },
+    {
+      "epoch": 1.513440477883658,
+      "grad_norm": 3.478196382522583,
+      "learning_rate": 5.329233482594771e-06,
+      "loss": 0.5532,
+      "step": 1330
+    },
+    {
+      "epoch": 1.52481866021903,
+      "grad_norm": 4.120450496673584,
+      "learning_rate": 5.266588846211865e-06,
+      "loss": 0.5504,
+      "step": 1340
+    },
+    {
+      "epoch": 1.536196842554402,
+      "grad_norm": 2.9817895889282227,
+      "learning_rate": 5.20390221321078e-06,
+      "loss": 0.5551,
+      "step": 1350
+    },
+    {
+      "epoch": 1.547575024889774,
+      "grad_norm": 3.2641355991363525,
+      "learning_rate": 5.141183458823085e-06,
+      "loss": 0.5533,
+      "step": 1360
+    },
+    {
+      "epoch": 1.5589532072251457,
+      "grad_norm": 3.226193428039551,
+      "learning_rate": 5.078442463340543e-06,
+      "loss": 0.5521,
+      "step": 1370
+    },
+    {
+      "epoch": 1.5703313895605175,
+      "grad_norm": 2.790149211883545,
+      "learning_rate": 5.01568911055863e-06,
+      "loss": 0.5627,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5817095718958898,
+      "grad_norm": 2.948485851287842,
+      "learning_rate": 4.952933286219503e-06,
+      "loss": 0.5697,
+      "step": 1390
+    },
+    {
+      "epoch": 1.5930877542312616,
+      "grad_norm": 2.847878932952881,
+      "learning_rate": 4.890184876454675e-06,
+      "loss": 0.5624,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6044659365666334,
+      "grad_norm": 3.067723512649536,
+      "learning_rate": 4.827453766227617e-06,
+      "loss": 0.5634,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6158441189020054,
+      "grad_norm": 3.5816497802734375,
+      "learning_rate": 4.764749837776545e-06,
+      "loss": 0.5607,
+      "step": 1420
+    },
+    {
+      "epoch": 1.6272223012373774,
+      "grad_norm": 3.231588840484619,
+      "learning_rate": 4.702082969057646e-06,
+      "loss": 0.5555,
+      "step": 1430
+    },
+    {
+      "epoch": 1.6386004835727492,
+      "grad_norm": 3.1863789558410645,
+      "learning_rate": 4.6394630321889535e-06,
+      "loss": 0.5555,
+      "step": 1440
+    },
+    {
+      "epoch": 1.649978665908121,
+      "grad_norm": 3.0723366737365723,
+      "learning_rate": 4.576899891895185e-06,
+      "loss": 0.5543,
+      "step": 1450
+    },
+    {
+      "epoch": 1.661356848243493,
+      "grad_norm": 2.7250912189483643,
+      "learning_rate": 4.5144034039537e-06,
+      "loss": 0.5568,
+      "step": 1460
+    },
+    {
+      "epoch": 1.672735030578865,
+      "grad_norm": 3.2123124599456787,
+      "learning_rate": 4.451983413641894e-06,
+      "loss": 0.5556,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6841132129142369,
+      "grad_norm": 3.832956552505493,
+      "learning_rate": 4.389649754186242e-06,
+      "loss": 0.5606,
+      "step": 1480
+    },
+    {
+      "epoch": 1.695491395249609,
+      "grad_norm": 3.1121504306793213,
+      "learning_rate": 4.327412245213232e-06,
+      "loss": 0.5494,
+      "step": 1490
+    },
+    {
+      "epoch": 1.706869577584981,
+      "grad_norm": 3.0781760215759277,
+      "learning_rate": 4.265280691202449e-06,
+      "loss": 0.5625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7182477599203527,
+      "grad_norm": 3.1622416973114014,
+      "learning_rate": 4.20326487994205e-06,
+      "loss": 0.5525,
+      "step": 1510
+    },
+    {
+      "epoch": 1.7296259422557245,
+      "grad_norm": 3.425814628601074,
+      "learning_rate": 4.141374580986853e-06,
+      "loss": 0.5642,
+      "step": 1520
+    },
+    {
+      "epoch": 1.7410041245910965,
+      "grad_norm": 3.0332634449005127,
+      "learning_rate": 4.079619544119303e-06,
+      "loss": 0.5682,
+      "step": 1530
+    },
+    {
+      "epoch": 1.7523823069264686,
+      "grad_norm": 3.9311952590942383,
+      "learning_rate": 4.018009497813575e-06,
+      "loss": 0.5496,
+      "step": 1540
+    },
+    {
+      "epoch": 1.7637604892618404,
+      "grad_norm": 3.6143958568573,
+      "learning_rate": 3.956554147702994e-06,
+      "loss": 0.5607,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7751386715972124,
+      "grad_norm": 3.6590614318847656,
+      "learning_rate": 3.895263175051089e-06,
+      "loss": 0.5686,
+      "step": 1560
+    },
+    {
+      "epoch": 1.7865168539325844,
+      "grad_norm": 3.8076541423797607,
+      "learning_rate": 3.834146235226467e-06,
+      "loss": 0.5724,
+      "step": 1570
+    },
+    {
+      "epoch": 1.7978950362679562,
+      "grad_norm": 3.879667043685913,
+      "learning_rate": 3.7732129561817687e-06,
+      "loss": 0.5481,
+      "step": 1580
+    },
+    {
+      "epoch": 1.809273218603328,
+      "grad_norm": 2.696838855743408,
+      "learning_rate": 3.7124729369369473e-06,
+      "loss": 0.5684,
+      "step": 1590
+    },
+    {
+      "epoch": 1.8206514009387,
+      "grad_norm": 3.3719265460968018,
+      "learning_rate": 3.6519357460671096e-06,
+      "loss": 0.5645,
+      "step": 1600
+    },
+    {
+      "epoch": 1.832029583274072,
+      "grad_norm": 2.9818122386932373,
+      "learning_rate": 3.5916109201951355e-06,
+      "loss": 0.5591,
+      "step": 1610
+    },
+    {
+      "epoch": 1.8434077656094439,
+      "grad_norm": 2.6824517250061035,
+      "learning_rate": 3.531507962489349e-06,
+      "loss": 0.5672,
+      "step": 1620
+    },
+    {
+      "epoch": 1.8547859479448157,
+      "grad_norm": 3.0721547603607178,
+      "learning_rate": 3.4716363411664517e-06,
+      "loss": 0.5513,
+      "step": 1630
+    },
+    {
+      "epoch": 1.866164130280188,
+      "grad_norm": 3.090949535369873,
+      "learning_rate": 3.4120054879999654e-06,
+      "loss": 0.568,
+      "step": 1640
+    },
+    {
+      "epoch": 1.8775423126155597,
+      "grad_norm": 3.357748031616211,
+      "learning_rate": 3.3526247968344084e-06,
+      "loss": 0.5602,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8889204949509315,
+      "grad_norm": 3.1600940227508545,
+      "learning_rate": 3.2935036221054638e-06,
+      "loss": 0.5555,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9002986772863035,
+      "grad_norm": 4.0066447257995605,
+      "learning_rate": 3.234651277366325e-06,
+      "loss": 0.5771,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9116768596216756,
+      "grad_norm": 3.6013309955596924,
+      "learning_rate": 3.1760770338205204e-06,
+      "loss": 0.5724,
+      "step": 1680
+    },
+    {
+      "epoch": 1.9230550419570474,
+      "grad_norm": 3.687427043914795,
+      "learning_rate": 3.11779011886138e-06,
+      "loss": 0.5551,
+      "step": 1690
+    },
+    {
+      "epoch": 1.9344332242924192,
+      "grad_norm": 3.2290844917297363,
+      "learning_rate": 3.0597997146184183e-06,
+      "loss": 0.5619,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9458114066277912,
+      "grad_norm": 3.9673118591308594,
+      "learning_rate": 3.0021149565108355e-06,
+      "loss": 0.555,
+      "step": 1710
+    },
+    {
+      "epoch": 1.9571895889631632,
+      "grad_norm": 3.0431714057922363,
+      "learning_rate": 2.9447449318083964e-06,
+      "loss": 0.5549,
+      "step": 1720
+    },
+    {
+      "epoch": 1.968567771298535,
+      "grad_norm": 2.991881847381592,
+      "learning_rate": 2.887698678199872e-06,
+      "loss": 0.5507,
+      "step": 1730
+    },
+    {
+      "epoch": 1.979945953633907,
+      "grad_norm": 3.0121707916259766,
+      "learning_rate": 2.8309851823693114e-06,
+      "loss": 0.5609,
+      "step": 1740
+    },
+    {
+      "epoch": 1.991324135969279,
+      "grad_norm": 3.5490665435791016,
+      "learning_rate": 2.7746133785803363e-06,
+      "loss": 0.5728,
+      "step": 1750
+    },
+    {
+      "epoch": 2.002844545583843,
+      "grad_norm": 5.156729221343994,
+      "learning_rate": 2.71859214726869e-06,
+      "loss": 0.5611,
+      "step": 1760
+    },
+    {
+      "epoch": 2.014222727919215,
+      "grad_norm": 4.809017181396484,
+      "learning_rate": 2.6629303136432873e-06,
+      "loss": 0.5519,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0256009102545867,
+      "grad_norm": 4.811421871185303,
+      "learning_rate": 2.6076366462959368e-06,
+      "loss": 0.5576,
+      "step": 1780
+    },
+    {
+      "epoch": 2.036979092589959,
+      "grad_norm": 3.962195634841919,
+      "learning_rate": 2.5527198558200124e-06,
+      "loss": 0.556,
+      "step": 1790
+    },
+    {
+      "epoch": 2.0483572749253307,
+      "grad_norm": 5.088486194610596,
+      "learning_rate": 2.4981885934382198e-06,
+      "loss": 0.5571,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0597354572607025,
+      "grad_norm": 4.567300319671631,
+      "learning_rate": 2.444051449639766e-06,
+      "loss": 0.5554,
+      "step": 1810
+    },
+    {
+      "epoch": 2.0711136395960743,
+      "grad_norm": 4.686933517456055,
+      "learning_rate": 2.3903169528270564e-06,
+      "loss": 0.5549,
+      "step": 1820
+    },
+    {
+      "epoch": 2.0824918219314466,
+      "grad_norm": 4.070396423339844,
+      "learning_rate": 2.336993567972193e-06,
+      "loss": 0.5686,
+      "step": 1830
+    },
+    {
+      "epoch": 2.0938700042668184,
+      "grad_norm": 4.52924108505249,
+      "learning_rate": 2.2840896952834573e-06,
+      "loss": 0.5661,
+      "step": 1840
+    },
+    {
+      "epoch": 2.10524818660219,
+      "grad_norm": 4.499566078186035,
+      "learning_rate": 2.2316136688820006e-06,
+      "loss": 0.5767,
+      "step": 1850
+    },
+    {
+      "epoch": 2.1166263689375624,
+      "grad_norm": 4.242886543273926,
+      "learning_rate": 2.1795737554889384e-06,
+      "loss": 0.5567,
+      "step": 1860
+    },
+    {
+      "epoch": 2.128004551272934,
+      "grad_norm": 4.661407947540283,
+      "learning_rate": 2.127978153123071e-06,
+      "loss": 0.5549,
+      "step": 1870
+    },
+    {
+      "epoch": 2.139382733608306,
+      "grad_norm": 4.505501747131348,
+      "learning_rate": 2.0768349898094204e-06,
+      "loss": 0.5615,
+      "step": 1880
+    },
+    {
+      "epoch": 2.150760915943678,
+      "grad_norm": 4.7061357498168945,
+      "learning_rate": 2.026152322298791e-06,
+      "loss": 0.5568,
+      "step": 1890
+    },
+    {
+      "epoch": 2.16213909827905,
+      "grad_norm": 4.6892476081848145,
+      "learning_rate": 1.975938134798577e-06,
+      "loss": 0.5377,
+      "step": 1900
+    },
+    {
+      "epoch": 2.173517280614422,
+      "grad_norm": 4.749743938446045,
+      "learning_rate": 1.926200337714968e-06,
+      "loss": 0.5402,
+      "step": 1910
+    },
+    {
+      "epoch": 2.1848954629497936,
+      "grad_norm": 3.927170991897583,
+      "learning_rate": 1.8769467664068058e-06,
+      "loss": 0.5572,
+      "step": 1920
+    },
+    {
+      "epoch": 2.196273645285166,
+      "grad_norm": 4.769582748413086,
+      "learning_rate": 1.8281851799512551e-06,
+      "loss": 0.5634,
+      "step": 1930
+    },
+    {
+      "epoch": 2.2076518276205377,
+      "grad_norm": 5.719987869262695,
+      "learning_rate": 1.779923259921481e-06,
+      "loss": 0.5544,
+      "step": 1940
+    },
+    {
+      "epoch": 2.2190300099559095,
+      "grad_norm": 4.865458965301514,
+      "learning_rate": 1.732168609176556e-06,
+      "loss": 0.5572,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2304081922912813,
+      "grad_norm": 24.83760643005371,
+      "learning_rate": 1.684928750663758e-06,
+      "loss": 0.5581,
+      "step": 1960
+    },
+    {
+      "epoch": 2.2417863746266535,
+      "grad_norm": 5.071547031402588,
+      "learning_rate": 1.6382111262334454e-06,
+      "loss": 0.559,
+      "step": 1970
+    },
+    {
+      "epoch": 2.2531645569620253,
+      "grad_norm": 4.077290058135986,
+      "learning_rate": 1.5920230954667198e-06,
+      "loss": 0.5471,
+      "step": 1980
+    },
+    {
+      "epoch": 2.264542739297397,
+      "grad_norm": 3.790095090866089,
+      "learning_rate": 1.5463719345160571e-06,
+      "loss": 0.558,
+      "step": 1990
+    },
+    {
+      "epoch": 2.2759209216327694,
+      "grad_norm": 5.027350425720215,
+      "learning_rate": 1.501264834959061e-06,
+      "loss": 0.5627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.287299103968141,
+      "grad_norm": 4.2677083015441895,
+      "learning_rate": 1.4567089026655524e-06,
+      "loss": 0.5497,
+      "step": 2010
+    },
+    {
+      "epoch": 2.298677286303513,
+      "grad_norm": 5.105195045471191,
+      "learning_rate": 1.4127111566781664e-06,
+      "loss": 0.5419,
+      "step": 2020
+    },
+    {
+      "epoch": 2.310055468638885,
+      "grad_norm": 4.892566680908203,
+      "learning_rate": 1.369278528106603e-06,
+      "loss": 0.553,
+      "step": 2030
+    },
+    {
+      "epoch": 2.321433650974257,
+      "grad_norm": 4.721883296966553,
+      "learning_rate": 1.3264178590357607e-06,
+      "loss": 0.5481,
+      "step": 2040
+    },
+    {
+      "epoch": 2.332811833309629,
+      "grad_norm": 4.8671722412109375,
+      "learning_rate": 1.2841359014478772e-06,
+      "loss": 0.5647,
+      "step": 2050
+    },
+    {
+      "epoch": 2.3441900156450006,
+      "grad_norm": 4.7961201667785645,
+      "learning_rate": 1.2424393161588632e-06,
+      "loss": 0.5465,
+      "step": 2060
+    },
+    {
+      "epoch": 2.3555681979803724,
+      "grad_norm": 5.445614337921143,
+      "learning_rate": 1.2013346717690072e-06,
+      "loss": 0.5523,
+      "step": 2070
+    },
+    {
+      "epoch": 2.3669463803157447,
+      "grad_norm": 5.255151271820068,
+      "learning_rate": 1.1608284436281974e-06,
+      "loss": 0.574,
+      "step": 2080
+    },
+    {
+      "epoch": 2.3783245626511165,
+      "grad_norm": 3.8508081436157227,
+      "learning_rate": 1.120927012815844e-06,
+      "loss": 0.539,
+      "step": 2090
+    },
+    {
+      "epoch": 2.3897027449864883,
+      "grad_norm": 5.08436393737793,
+      "learning_rate": 1.081636665135642e-06,
+      "loss": 0.5392,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4010809273218605,
+      "grad_norm": 5.37895393371582,
+      "learning_rate": 1.0429635901253516e-06,
+      "loss": 0.5636,
+      "step": 2110
+    },
+    {
+      "epoch": 2.4124591096572323,
+      "grad_norm": 3.8906028270721436,
+      "learning_rate": 1.0049138800817332e-06,
+      "loss": 0.567,
+      "step": 2120
+    },
+    {
+      "epoch": 2.423837291992604,
+      "grad_norm": 4.598055362701416,
+      "learning_rate": 9.674935291008198e-07,
+      "loss": 0.5522,
+      "step": 2130
+    },
+    {
+      "epoch": 2.435215474327976,
+      "grad_norm": 4.944962501525879,
+      "learning_rate": 9.307084321336357e-07,
+      "loss": 0.5586,
+      "step": 2140
+    },
+    {
+      "epoch": 2.446593656663348,
+      "grad_norm": 4.658571243286133,
+      "learning_rate": 8.94564384057553e-07,
+      "loss": 0.5517,
+      "step": 2150
+    },
+    {
+      "epoch": 2.45797183899872,
+      "grad_norm": 4.260778427124023,
+      "learning_rate": 8.59067078763397e-07,
+      "loss": 0.5527,
+      "step": 2160
+    },
+    {
+      "epoch": 2.4693500213340918,
+      "grad_norm": 4.492344856262207,
+      "learning_rate": 8.242221082584811e-07,
+      "loss": 0.5593,
+      "step": 2170
+    },
+    {
+      "epoch": 2.4807282036694636,
+      "grad_norm": 4.839461326599121,
+      "learning_rate": 7.900349617856684e-07,
+      "loss": 0.5572,
+      "step": 2180
+    },
+    {
+      "epoch": 2.492106386004836,
+      "grad_norm": 4.276406764984131,
+      "learning_rate": 7.5651102495864e-07,
+      "loss": 0.5506,
+      "step": 2190
+    },
+    {
+      "epoch": 2.5034845683402076,
+      "grad_norm": 4.654806137084961,
+      "learning_rate": 7.236555789134769e-07,
+      "loss": 0.5449,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5148627506755794,
+      "grad_norm": 4.328060626983643,
+      "learning_rate": 6.914737994767101e-07,
+      "loss": 0.5614,
+      "step": 2210
+    },
+    {
+      "epoch": 2.5262409330109517,
+      "grad_norm": 6.862987041473389,
+      "learning_rate": 6.599707563499514e-07,
+      "loss": 0.556,
+      "step": 2220
+    },
+    {
+      "epoch": 2.5376191153463235,
+      "grad_norm": 4.085236072540283,
+      "learning_rate": 6.291514123112474e-07,
+      "loss": 0.5636,
+      "step": 2230
+    },
+    {
+      "epoch": 2.5489972976816953,
+      "grad_norm": 4.0781025886535645,
+      "learning_rate": 5.990206224332801e-07,
+      "loss": 0.5598,
+      "step": 2240
+    },
+    {
+      "epoch": 2.5603754800170675,
+      "grad_norm": 4.941834449768066,
+      "learning_rate": 5.695831333185265e-07,
+      "loss": 0.5484,
+      "step": 2250
+    },
+    {
+      "epoch": 2.5717536623524393,
+      "grad_norm": 4.038600444793701,
+      "learning_rate": 5.408435823515145e-07,
+      "loss": 0.575,
+      "step": 2260
+    },
+    {
+      "epoch": 2.583131844687811,
+      "grad_norm": 4.425263404846191,
+      "learning_rate": 5.128064969682778e-07,
+      "loss": 0.5693,
+      "step": 2270
+    },
+    {
+      "epoch": 2.594510027023183,
+      "grad_norm": 4.681412696838379,
+      "learning_rate": 4.854762939431362e-07,
+      "loss": 0.5397,
+      "step": 2280
+    },
+    {
+      "epoch": 2.6058882093585547,
+      "grad_norm": 4.6591267585754395,
+      "learning_rate": 4.5885727869290354e-07,
+      "loss": 0.5561,
+      "step": 2290
+    },
+    {
+      "epoch": 2.617266391693927,
+      "grad_norm": 4.0130157470703125,
+      "learning_rate": 4.32953644598646e-07,
+      "loss": 0.5588,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6286445740292987,
+      "grad_norm": 5.125436305999756,
+      "learning_rate": 4.077694723450815e-07,
+      "loss": 0.5537,
+      "step": 2310
+    },
+    {
+      "epoch": 2.6400227563646705,
+      "grad_norm": 4.90755558013916,
+      "learning_rate": 3.8330872927773544e-07,
+      "loss": 0.5465,
+      "step": 2320
+    },
+    {
+      "epoch": 2.651400938700043,
+      "grad_norm": 4.263889312744141,
+      "learning_rate": 3.595752687779541e-07,
+      "loss": 0.5507,
+      "step": 2330
+    },
+    {
+      "epoch": 2.6627791210354146,
+      "grad_norm": 4.307155609130859,
+      "learning_rate": 3.365728296558668e-07,
+      "loss": 0.5518,
+      "step": 2340
+    },
+    {
+      "epoch": 2.6741573033707864,
+      "grad_norm": 4.401244640350342,
+      "learning_rate": 3.1430503556140026e-07,
+      "loss": 0.5637,
+      "step": 2350
+    },
+    {
+      "epoch": 2.6855354857061586,
+      "grad_norm": 4.537615776062012,
+      "learning_rate": 2.9277539441343204e-07,
+      "loss": 0.5376,
+      "step": 2360
+    },
+    {
+      "epoch": 2.6969136680415304,
+      "grad_norm": 4.655327796936035,
+      "learning_rate": 2.7198729784718047e-07,
+      "loss": 0.5606,
+      "step": 2370
+    },
+    {
+      "epoch": 2.7082918503769022,
+      "grad_norm": 4.768523216247559,
+      "learning_rate": 2.519440206799001e-07,
+      "loss": 0.5588,
+      "step": 2380
+    },
+    {
+      "epoch": 2.7196700327122745,
+      "grad_norm": 5.224249839782715,
+      "learning_rate": 2.326487203949984e-07,
+      "loss": 0.5555,
+      "step": 2390
+    },
+    {
+      "epoch": 2.7310482150476463,
+      "grad_norm": 3.7500874996185303,
+      "learning_rate": 2.141044366446221e-07,
+      "loss": 0.5449,
+      "step": 2400
+    },
+    {
+      "epoch": 2.742426397383018,
+      "grad_norm": 8.473684310913086,
+      "learning_rate": 1.9631409077081277e-07,
+      "loss": 0.558,
+      "step": 2410
+    },
+    {
+      "epoch": 2.75380457971839,
+      "grad_norm": 4.536637783050537,
+      "learning_rate": 1.792804853452962e-07,
+      "loss": 0.5598,
+      "step": 2420
+    },
+    {
+      "epoch": 2.7651827620537617,
+      "grad_norm": 4.456907749176025,
+      "learning_rate": 1.6300630372798666e-07,
+      "loss": 0.5552,
+      "step": 2430
+    },
+    {
+      "epoch": 2.776560944389134,
+      "grad_norm": 4.3202385902404785,
+      "learning_rate": 1.4749410964426558e-07,
+      "loss": 0.5515,
+      "step": 2440
+    },
+    {
+      "epoch": 2.7879391267245057,
+      "grad_norm": 5.083593845367432,
+      "learning_rate": 1.3274634678111187e-07,
+      "loss": 0.5564,
+      "step": 2450
+    },
+    {
+      "epoch": 2.7993173090598775,
+      "grad_norm": 4.5219221115112305,
+      "learning_rate": 1.187653384021381e-07,
+      "loss": 0.5554,
+      "step": 2460
+    },
+    {
+      "epoch": 2.8106954913952498,
+      "grad_norm": 4.617882251739502,
+      "learning_rate": 1.0555328698159951e-07,
+      "loss": 0.5624,
+      "step": 2470
+    },
+    {
+      "epoch": 2.8220736737306216,
+      "grad_norm": 4.936917781829834,
+      "learning_rate": 9.311227385743249e-08,
+      "loss": 0.5511,
+      "step": 2480
+    },
+    {
+      "epoch": 2.8334518560659934,
+      "grad_norm": 4.036168575286865,
+      "learning_rate": 8.144425890337371e-08,
+      "loss": 0.5472,
+      "step": 2490
+    },
+    {
+      "epoch": 2.8448300384013656,
+      "grad_norm": 5.006382465362549,
+      "learning_rate": 7.05510802202125e-08,
+      "loss": 0.5461,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8562082207367374,
+      "grad_norm": 6.169336795806885,
+      "learning_rate": 6.043445384623259e-08,
+      "loss": 0.5496,
+      "step": 2510
+    },
+    {
+      "epoch": 2.867586403072109,
+      "grad_norm": 4.207286834716797,
+      "learning_rate": 5.109597348687545e-08,
+      "loss": 0.554,
+      "step": 2520
+    },
+    {
+      "epoch": 2.878964585407481,
+      "grad_norm": 4.170133113861084,
+      "learning_rate": 4.2537110263682343e-08,
+      "loss": 0.5514,
+      "step": 2530
+    },
+    {
+      "epoch": 2.890342767742853,
+      "grad_norm": 4.8024582862854,
+      "learning_rate": 3.475921248254022e-08,
+      "loss": 0.5471,
+      "step": 2540
+    },
+    {
+      "epoch": 2.901720950078225,
+      "grad_norm": 4.820261478424072,
+      "learning_rate": 2.7763505421281035e-08,
+      "loss": 0.5487,
+      "step": 2550
+    },
+    {
+      "epoch": 2.913099132413597,
+      "grad_norm": 4.229453086853027,
+      "learning_rate": 2.155109113665732e-08,
+      "loss": 0.5615,
+      "step": 2560
+    },
+    {
+      "epoch": 2.9244773147489687,
+      "grad_norm": 4.419139862060547,
+      "learning_rate": 1.612294829073491e-08,
+      "loss": 0.5671,
+      "step": 2570
+    },
+    {
+      "epoch": 2.935855497084341,
+      "grad_norm": 4.717645168304443,
+      "learning_rate": 1.147993199671682e-08,
+      "loss": 0.5434,
+      "step": 2580
+    },
+    {
+      "epoch": 2.9472336794197127,
+      "grad_norm": 4.646683692932129,
+      "learning_rate": 7.62277368423936e-09,
+      "loss": 0.5543,
+      "step": 2590
+    },
+    {
+      "epoch": 2.9586118617550845,
+      "grad_norm": 4.718910217285156,
+      "learning_rate": 4.552080984143725e-09,
+      "loss": 0.553,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9699900440904567,
+      "grad_norm": 3.963477849960327,
+      "learning_rate": 2.2683376327548022e-09,
+      "loss": 0.5507,
+      "step": 2610
+    },
+    {
+      "epoch": 2.9813682264258285,
+      "grad_norm": 8.025522232055664,
+      "learning_rate": 7.719033956782307e-10,
+      "loss": 0.5677,
+      "step": 2620
+    },
+    {
+      "epoch": 2.9927464087612003,
+      "grad_norm": 5.158026695251465,
+      "learning_rate": 6.301401112296379e-11,
+      "loss": 0.5586,
+      "step": 2630
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2634,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.685410418372693e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2634/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e4c92a6537a7e27b01231ccde6b9849bbe08304199b223942ce5edde724247
+size 6456

config.json

@@ -0,0 +1,49 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "ibm-granite/granite-3.1-8b-instruct",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 49184
+}

merged/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end_of_role|>": 49153,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

merged/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "ibm-granite/granite-3.1-8b-instruct",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 49184
+}

merged/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.3"
+}

merged/pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4feeb0015f3aea6db06b9d0de511f2d03b2dc9ab8fdd825f7f50a0f97050ca0b
+size 4974924377

merged/pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0486975e2b9723a2cf6d2dbbd1783e63002e213192d6a2894f5f26b4751cafff
+size 4991474682

merged/pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab150e0bfa5ee35b0d81d8d5ff2074dfd8e4726efc7b187097f82de8d9418ed
+size 4970487165

merged/pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7f3e522f06a84c5f795d71a96baf21e30af279fe8eec103e6cf7a74f3573e0
+size 1405177130

merged/pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 16341934080
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00004.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}

merged/special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

merged/tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n    {%- if tools and documents %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\n\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- elif tools %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n    {%- elif documents %}\n        {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- else %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}    \n    {%- endif %}\n    {%- if 'citations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nIn your response, use the symbols <co> and </co> to indicate when a fact comes from a document in the search result, e.g <co>0</co> for a fact from document 0. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n    {%- endif %}\n    {%- if 'hallucinations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nFinally, after the response is written, include a numbered list of sentences from the response that are potentially hallucinated and not based in the documents.' %}\n    {%- endif %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n{%- if tools %}\n    {{- '<|start_of_role|>tools<|end_of_role|>' }}\n    {{- tools | tojson(indent=4) }}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- if documents %}\n    {{- '<|start_of_role|>documents<|end_of_role|>' }}\n    {%- for document in documents %}\n        {{- 'Document ' + loop.index0 | string + '\n' }}\n        {{- document['text'] }}\n        {%- if not loop.last %}\n            {{- '\n\n'}}\n        {%- endif%}\n    {%- endfor %}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in loop_messages %}\n    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n    {%- if loop.last and add_generation_prompt %}\n        {{- '<|start_of_role|>assistant' }}\n            {%- if controls %}\n                {{- ' ' + controls | tojson()}}\n            {%- endif %}\n        {{- '<|end_of_role|>' }}\n    {%- endif %}\n{%- endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n    {%- if tools and documents %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\n\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- elif tools %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n    {%- elif documents %}\n        {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- else %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}    \n    {%- endif %}\n    {%- if 'citations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nIn your response, use the symbols <co> and </co> to indicate when a fact comes from a document in the search result, e.g <co>0</co> for a fact from document 0. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n    {%- endif %}\n    {%- if 'hallucinations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nFinally, after the response is written, include a numbered list of sentences from the response that are potentially hallucinated and not based in the documents.' %}\n    {%- endif %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n{%- if tools %}\n    {{- '<|start_of_role|>tools<|end_of_role|>' }}\n    {{- tools | tojson(indent=4) }}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- if documents %}\n    {{- '<|start_of_role|>documents<|end_of_role|>' }}\n    {%- for document in documents %}\n        {{- 'Document ' + loop.index0 | string + '\n' }}\n        {{- document['text'] }}\n        {%- if not loop.last %}\n            {{- '\n\n'}}\n        {%- endif%}\n    {%- endfor %}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in loop_messages %}\n    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n    {%- if loop.last and add_generation_prompt %}\n        {{- '<|start_of_role|>assistant' }}\n            {%- if controls %}\n                {{- ' ' + controls | tojson()}}\n            {%- endif %}\n        {{- '<|end_of_role|>' }}\n    {%- endif %}\n{%- endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}