Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6181/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,115 @@
----
-license: mit
----
+---
+base_model:
+- google/gemma-3-1b-it
+library_name: peft
+model_name: Gemma-3-1B-it-Medical-LoRA
+tags:
+- generated_from_trainer
+- unsloth
+- sft
+- trl
+licence: license
+datasets:
+- tmnam20/ViMedAQA
+language:
+- vi
+---
+
+# Model Card for Gemma-3-1B-it-Medical-LoRA
+
+This model is a fine-tuned version of [unsloth/gemma-3-1b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-1b-it-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from peft import PeftModel
+
+# Define model and LoRA adapter paths
+base_model_name = "unsloth/gemma-3-1b-it"
+lora_adapter_name = "heboya8/Gemma-3-1B-it-Medical-LoRA"
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+
+# Load base model with optimized settings
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.float16,  # Use FP16 for efficiency
+    device_map="cpu",         # Explicitly map to CUDA device
+    trust_remote_code=True
+)
+
+# Apply LoRA adapter
+model = PeftModel.from_pretrained(model, lora_adapter_name)
+
+# Set model to evaluation mode
+model.eval()
+
+# Create text generation pipeline
+generator = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.float16,
+    device_map="cuda",
+    max_new_tokens=128,  # Limit response length as per original script
+)
+
+# Define the question
+question = ("Khi nghi ngờ bị loét dạ dày tá tràng nên đến khoa nào "
+          "tại bệnh viện để thăm khám?")
+          
+# Format input for the pipeline
+input_prompt = [{"role": "user", "content": question}]
+
+# Generate response
+output = generator(input_prompt, return_full_text=False)[0]
+
+# Print the generated text
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.14.0
+- TRL: 0.19.0
+- Transformers: 4.52.4
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c3a35b62a6eb804c7c1bfb5aaafe834771f22ddecd95d3e047e3258c04327e
+size 52231312

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-6000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-6000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-6000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b1053833338eb57c64634fe9ad64f75cc8785bef8fb40de94b728d05a30ffe
+size 52231312

checkpoint-6000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-6000/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6fb6de75cc68b2f2f25923e5d3596560d5c0bb4014aaf4af4a95699579d03b
+size 27860634

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b0d4622ef35d3b8f3ea1592bf278ce61bee81cf5bac712353ad99788b7c094
+size 14244

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb7c2ebce9830404798c55c6276c8d7b7170eeb57676ad2aee60c7d64a8a777
+size 1064

checkpoint-6000/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-6000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-6000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-6000/trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.57286536693573,
+  "best_model_checkpoint": "Gemma-3-1B-it-Medical-LoRA/checkpoint-800",
+  "epoch": 6.795242141036534,
+  "eval_steps": 200,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7655816078186035,
+      "learning_rate": 0.0001955451348182884,
+      "loss": 0.9427,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.7325181365013123,
+      "learning_rate": 0.00018382180539273154,
+      "loss": 0.6075,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6365712881088257,
+      "learning_rate": 0.00017209847596717467,
+      "loss": 0.675,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 0.9989428520202637,
+      "learning_rate": 0.00016037514654161782,
+      "loss": 0.6585,
+      "step": 200
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "eval_loss": 0.6068728566169739,
+      "eval_runtime": 154.0009,
+      "eval_samples_per_second": 10.188,
+      "eval_steps_per_second": 2.552,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.6311811208724976,
+      "learning_rate": 0.00014865181711606098,
+      "loss": 0.6311,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.831785261631012,
+      "learning_rate": 0.0001369284876905041,
+      "loss": 0.5715,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.7572771310806274,
+      "learning_rate": 0.00012520515826494724,
+      "loss": 0.5482,
+      "step": 350
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.715999960899353,
+      "learning_rate": 0.0001134818288393904,
+      "loss": 0.5674,
+      "step": 400
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "eval_loss": 0.5926390290260315,
+      "eval_runtime": 144.007,
+      "eval_samples_per_second": 10.895,
+      "eval_steps_per_second": 2.729,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.8048545122146606,
+      "learning_rate": 0.00010175849941383353,
+      "loss": 0.5664,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.994825541973114,
+      "learning_rate": 9.003516998827668e-05,
+      "loss": 0.6381,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8860945105552673,
+      "learning_rate": 7.831184056271981e-05,
+      "loss": 0.5774,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.7308331727981567,
+      "learning_rate": 6.658851113716296e-05,
+      "loss": 0.5827,
+      "step": 600
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "eval_loss": 0.580059826374054,
+      "eval_runtime": 144.3097,
+      "eval_samples_per_second": 10.872,
+      "eval_steps_per_second": 2.723,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.8322684168815613,
+      "learning_rate": 5.486518171160609e-05,
+      "loss": 0.599,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.0585319995880127,
+      "learning_rate": 4.3141852286049237e-05,
+      "loss": 0.631,
+      "step": 700
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.00983726978302,
+      "learning_rate": 3.1418522860492386e-05,
+      "loss": 0.5947,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6543359160423279,
+      "learning_rate": 1.9695193434935523e-05,
+      "loss": 0.5665,
+      "step": 800
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "eval_loss": 0.57286536693573,
+      "eval_runtime": 144.191,
+      "eval_samples_per_second": 10.881,
+      "eval_steps_per_second": 2.726,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 0.960976779460907,
+      "learning_rate": 7.971864009378664e-06,
+      "loss": 0.5712,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.8420133590698242,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5028,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.8027368187904358,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.5148,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7591931223869324,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4944,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "eval_loss": 0.5851833820343018,
+      "eval_runtime": 144.0876,
+      "eval_samples_per_second": 10.889,
+      "eval_steps_per_second": 2.728,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.8245683312416077,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.5582,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8791372776031494,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.5125,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8794203400611877,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5383,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.9652652144432068,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.5184,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "eval_loss": 0.5808290243148804,
+      "eval_runtime": 144.5522,
+      "eval_samples_per_second": 10.854,
+      "eval_steps_per_second": 2.719,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8952807784080505,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5398,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.8340632319450378,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.5066,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.2093769311904907,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5347,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.3850702047348022,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4901,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "eval_loss": 0.5830569267272949,
+      "eval_runtime": 144.2996,
+      "eval_samples_per_second": 10.873,
+      "eval_steps_per_second": 2.723,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 0.809190571308136,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.5241,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 1.0073446035385132,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.5114,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.0417332649230957,
+      "learning_rate": 2.5e-05,
+      "loss": 0.519,
+      "step": 1550
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9849772453308105,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.5156,
+      "step": 1600
+    },
+    {
+      "epoch": 1.812234494477485,
+      "eval_loss": 0.5755766034126282,
+      "eval_runtime": 143.8724,
+      "eval_samples_per_second": 10.905,
+      "eval_steps_per_second": 2.732,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.2943501472473145,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5483,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8810242414474487,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.5168,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9415161609649658,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.5176,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 1.0487638711929321,
+      "learning_rate": 6.491027109583811e-05,
+      "loss": 0.4455,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "eval_loss": 0.587023138999939,
+      "eval_runtime": 144.0009,
+      "eval_samples_per_second": 10.896,
+      "eval_steps_per_second": 2.729,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.317651391029358,
+      "learning_rate": 6.109201985490646e-05,
+      "loss": 0.4665,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.219244360923767,
+      "learning_rate": 5.72737686139748e-05,
+      "loss": 0.4964,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.2626948356628418,
+      "learning_rate": 5.345551737304315e-05,
+      "loss": 0.479,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.3026907444000244,
+      "learning_rate": 4.963726613211149e-05,
+      "loss": 0.4713,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "eval_loss": 0.5911725759506226,
+      "eval_runtime": 144.1844,
+      "eval_samples_per_second": 10.882,
+      "eval_steps_per_second": 2.726,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 1.0047467947006226,
+      "learning_rate": 4.581901489117984e-05,
+      "loss": 0.4794,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.2122581005096436,
+      "learning_rate": 4.2000763650248184e-05,
+      "loss": 0.4771,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.2274476289749146,
+      "learning_rate": 3.818251240931654e-05,
+      "loss": 0.4691,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 1.0465933084487915,
+      "learning_rate": 3.4364261168384884e-05,
+      "loss": 0.4267,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "eval_loss": 0.5909530520439148,
+      "eval_runtime": 143.9787,
+      "eval_samples_per_second": 10.897,
+      "eval_steps_per_second": 2.73,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.1270743608474731,
+      "learning_rate": 3.054600992745323e-05,
+      "loss": 0.4587,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0416178703308105,
+      "learning_rate": 2.6727758686521576e-05,
+      "loss": 0.4875,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 0.9418396353721619,
+      "learning_rate": 2.290950744558992e-05,
+      "loss": 0.4756,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.9481875896453857,
+      "learning_rate": 1.909125620465827e-05,
+      "loss": 0.4626,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "eval_loss": 0.587207555770874,
+      "eval_runtime": 144.1702,
+      "eval_samples_per_second": 10.883,
+      "eval_steps_per_second": 2.726,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.8298775553703308,
+      "learning_rate": 1.5273004963726615e-05,
+      "loss": 0.4396,
+      "step": 2450
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.2271429300308228,
+      "learning_rate": 1.145475372279496e-05,
+      "loss": 0.4531,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 1.2411454916000366,
+      "learning_rate": 7.636502481863307e-06,
+      "loss": 0.4647,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.449476718902588,
+      "learning_rate": 3.818251240931654e-06,
+      "loss": 0.4635,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "eval_loss": 0.5865218639373779,
+      "eval_runtime": 143.9267,
+      "eval_samples_per_second": 10.901,
+      "eval_steps_per_second": 2.731,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 0.9472671151161194,
+      "learning_rate": 0.0,
+      "loss": 0.3542,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 1.101803183555603,
+      "learning_rate": 0.00011321736303040155,
+      "loss": 0.4194,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 1.1706457138061523,
+      "learning_rate": 0.00011159161112014307,
+      "loss": 0.4313,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.2929370403289795,
+      "learning_rate": 0.00010996585920988458,
+      "loss": 0.4418,
+      "step": 2800
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "eval_loss": 0.60947585105896,
+      "eval_runtime": 153.6833,
+      "eval_samples_per_second": 10.209,
+      "eval_steps_per_second": 2.557,
+      "step": 2800
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.3731728792190552,
+      "learning_rate": 0.00010834010729962609,
+      "loss": 0.4868,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 1.343711256980896,
+      "learning_rate": 0.00010671435538936759,
+      "loss": 0.4336,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.5197447538375854,
+      "learning_rate": 0.0001050886034791091,
+      "loss": 0.4789,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 0.834096372127533,
+      "learning_rate": 0.00010346285156885061,
+      "loss": 0.4639,
+      "step": 3000
+    },
+    {
+      "epoch": 3.397621070518267,
+      "eval_loss": 0.6121659278869629,
+      "eval_runtime": 143.8631,
+      "eval_samples_per_second": 10.906,
+      "eval_steps_per_second": 2.732,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 1.1350237131118774,
+      "learning_rate": 0.0001018370996585921,
+      "loss": 0.4591,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 1.269223928451538,
+      "learning_rate": 0.00010021134774833361,
+      "loss": 0.4679,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.1300125122070312,
+      "learning_rate": 9.858559583807512e-05,
+      "loss": 0.4619,
+      "step": 3150
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.2352793216705322,
+      "learning_rate": 9.695984392781662e-05,
+      "loss": 0.48,
+      "step": 3200
+    },
+    {
+      "epoch": 3.624185783064288,
+      "eval_loss": 0.6045758724212646,
+      "eval_runtime": 144.0294,
+      "eval_samples_per_second": 10.894,
+      "eval_steps_per_second": 2.729,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.3493255376815796,
+      "learning_rate": 9.533409201755813e-05,
+      "loss": 0.4838,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.3916635513305664,
+      "learning_rate": 9.370834010729963e-05,
+      "loss": 0.4899,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 1.4167906045913696,
+      "learning_rate": 9.208258819704113e-05,
+      "loss": 0.5017,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 0.8912964463233948,
+      "learning_rate": 9.045683628678264e-05,
+      "loss": 0.4587,
+      "step": 3400
+    },
+    {
+      "epoch": 3.850750495610309,
+      "eval_loss": 0.5994317531585693,
+      "eval_runtime": 143.7834,
+      "eval_samples_per_second": 10.912,
+      "eval_steps_per_second": 2.733,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 1.2601457834243774,
+      "learning_rate": 8.883108437652414e-05,
+      "loss": 0.4766,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 1.1677194833755493,
+      "learning_rate": 8.720533246626565e-05,
+      "loss": 0.4616,
+      "step": 3500
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.2599579095840454,
+      "learning_rate": 8.557958055600716e-05,
+      "loss": 0.4602,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 0.9038525819778442,
+      "learning_rate": 8.395382864574867e-05,
+      "loss": 0.3565,
+      "step": 3600
+    },
+    {
+      "epoch": 4.077032002265647,
+      "eval_loss": 0.6232873797416687,
+      "eval_runtime": 143.721,
+      "eval_samples_per_second": 10.917,
+      "eval_steps_per_second": 2.734,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.4113986492156982,
+      "learning_rate": 8.232807673549017e-05,
+      "loss": 0.4193,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 1.1578692197799683,
+      "learning_rate": 8.070232482523168e-05,
+      "loss": 0.372,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.4185764789581299,
+      "learning_rate": 7.907657291497318e-05,
+      "loss": 0.3647,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.3464981317520142,
+      "learning_rate": 7.745082100471468e-05,
+      "loss": 0.3745,
+      "step": 3800
+    },
+    {
+      "epoch": 4.303596714811668,
+      "eval_loss": 0.6339591145515442,
+      "eval_runtime": 143.7966,
+      "eval_samples_per_second": 10.911,
+      "eval_steps_per_second": 2.733,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.323198676109314,
+      "learning_rate": 7.582506909445619e-05,
+      "loss": 0.3839,
+      "step": 3850
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.8854613304138184,
+      "learning_rate": 7.419931718419769e-05,
+      "loss": 0.4328,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 0.9551966786384583,
+      "learning_rate": 7.25735652739392e-05,
+      "loss": 0.3816,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.1180638074874878,
+      "learning_rate": 7.09478133636807e-05,
+      "loss": 0.4019,
+      "step": 4000
+    },
+    {
+      "epoch": 4.530161427357689,
+      "eval_loss": 0.629741907119751,
+      "eval_runtime": 144.0805,
+      "eval_samples_per_second": 10.89,
+      "eval_steps_per_second": 2.728,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.5229169130325317,
+      "learning_rate": 6.932206145342221e-05,
+      "loss": 0.3794,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 1.1407935619354248,
+      "learning_rate": 6.769630954316372e-05,
+      "loss": 0.3911,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 1.4342515468597412,
+      "learning_rate": 6.607055763290522e-05,
+      "loss": 0.3757,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.471047282218933,
+      "learning_rate": 6.444480572264673e-05,
+      "loss": 0.4043,
+      "step": 4200
+    },
+    {
+      "epoch": 4.75672613990371,
+      "eval_loss": 0.6323012709617615,
+      "eval_runtime": 143.8107,
+      "eval_samples_per_second": 10.91,
+      "eval_steps_per_second": 2.733,
+      "step": 4200
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.6963218450546265,
+      "learning_rate": 6.281905381238823e-05,
+      "loss": 0.3817,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.4788011312484741,
+      "learning_rate": 6.119330190212974e-05,
+      "loss": 0.3879,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 1.5147647857666016,
+      "learning_rate": 5.956754999187124e-05,
+      "loss": 0.3874,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 1.027481198310852,
+      "learning_rate": 5.794179808161275e-05,
+      "loss": 0.3736,
+      "step": 4400
+    },
+    {
+      "epoch": 4.983290852449731,
+      "eval_loss": 0.6303974390029907,
+      "eval_runtime": 143.9543,
+      "eval_samples_per_second": 10.899,
+      "eval_steps_per_second": 2.73,
+      "step": 4400
+    },
+    {
+      "epoch": 5.039648824695553,
+      "grad_norm": 1.2473069429397583,
+      "learning_rate": 5.631604617135425e-05,
+      "loss": 0.33,
+      "step": 4450
+    },
+    {
+      "epoch": 5.096290002832059,
+      "grad_norm": 1.439157485961914,
+      "learning_rate": 5.469029426109576e-05,
+      "loss": 0.3065,
+      "step": 4500
+    },
+    {
+      "epoch": 5.152931180968564,
+      "grad_norm": 1.172194480895996,
+      "learning_rate": 5.306454235083727e-05,
+      "loss": 0.3038,
+      "step": 4550
+    },
+    {
+      "epoch": 5.20957235910507,
+      "grad_norm": 2.9354825019836426,
+      "learning_rate": 5.1438790440578765e-05,
+      "loss": 0.2961,
+      "step": 4600
+    },
+    {
+      "epoch": 5.20957235910507,
+      "eval_loss": 0.6725755929946899,
+      "eval_runtime": 143.751,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 2.734,
+      "step": 4600
+    },
+    {
+      "epoch": 5.266213537241574,
+      "grad_norm": 1.7553826570510864,
+      "learning_rate": 4.981303853032028e-05,
+      "loss": 0.3055,
+      "step": 4650
+    },
+    {
+      "epoch": 5.32285471537808,
+      "grad_norm": 1.1259921789169312,
+      "learning_rate": 4.818728662006178e-05,
+      "loss": 0.3052,
+      "step": 4700
+    },
+    {
+      "epoch": 5.379495893514585,
+      "grad_norm": 1.2912168502807617,
+      "learning_rate": 4.656153470980329e-05,
+      "loss": 0.3168,
+      "step": 4750
+    },
+    {
+      "epoch": 5.43613707165109,
+      "grad_norm": 1.3614895343780518,
+      "learning_rate": 4.493578279954479e-05,
+      "loss": 0.3024,
+      "step": 4800
+    },
+    {
+      "epoch": 5.43613707165109,
+      "eval_loss": 0.6745353937149048,
+      "eval_runtime": 143.4345,
+      "eval_samples_per_second": 10.939,
+      "eval_steps_per_second": 2.74,
+      "step": 4800
+    },
+    {
+      "epoch": 5.492778249787595,
+      "grad_norm": 1.4940049648284912,
+      "learning_rate": 4.33100308892863e-05,
+      "loss": 0.3281,
+      "step": 4850
+    },
+    {
+      "epoch": 5.549419427924101,
+      "grad_norm": 1.3145006895065308,
+      "learning_rate": 4.16842789790278e-05,
+      "loss": 0.2955,
+      "step": 4900
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 1.6090342998504639,
+      "learning_rate": 4.005852706876931e-05,
+      "loss": 0.3351,
+      "step": 4950
+    },
+    {
+      "epoch": 5.662701784197111,
+      "grad_norm": 1.2353523969650269,
+      "learning_rate": 3.843277515851081e-05,
+      "loss": 0.3146,
+      "step": 5000
+    },
+    {
+      "epoch": 5.662701784197111,
+      "eval_loss": 0.6648290753364563,
+      "eval_runtime": 143.6635,
+      "eval_samples_per_second": 10.921,
+      "eval_steps_per_second": 2.736,
+      "step": 5000
+    },
+    {
+      "epoch": 5.7193429623336165,
+      "grad_norm": 1.4121828079223633,
+      "learning_rate": 3.680702324825232e-05,
+      "loss": 0.3252,
+      "step": 5050
+    },
+    {
+      "epoch": 5.775984140470122,
+      "grad_norm": 1.6109447479248047,
+      "learning_rate": 3.518127133799383e-05,
+      "loss": 0.2894,
+      "step": 5100
+    },
+    {
+      "epoch": 5.8326253186066275,
+      "grad_norm": 1.2615262269973755,
+      "learning_rate": 3.355551942773533e-05,
+      "loss": 0.3233,
+      "step": 5150
+    },
+    {
+      "epoch": 5.889266496743132,
+      "grad_norm": 1.4789379835128784,
+      "learning_rate": 3.192976751747683e-05,
+      "loss": 0.3136,
+      "step": 5200
+    },
+    {
+      "epoch": 5.889266496743132,
+      "eval_loss": 0.6699800491333008,
+      "eval_runtime": 143.914,
+      "eval_samples_per_second": 10.902,
+      "eval_steps_per_second": 2.731,
+      "step": 5200
+    },
+    {
+      "epoch": 5.945907674879638,
+      "grad_norm": 1.5867825746536255,
+      "learning_rate": 3.0304015607218337e-05,
+      "loss": 0.3398,
+      "step": 5250
+    },
+    {
+      "epoch": 6.00226564712546,
+      "grad_norm": 1.981821060180664,
+      "learning_rate": 2.8678263696959846e-05,
+      "loss": 0.2998,
+      "step": 5300
+    },
+    {
+      "epoch": 6.058906825261966,
+      "grad_norm": 1.178331971168518,
+      "learning_rate": 2.705251178670135e-05,
+      "loss": 0.2447,
+      "step": 5350
+    },
+    {
+      "epoch": 6.11554800339847,
+      "grad_norm": 1.5027756690979004,
+      "learning_rate": 2.5426759876442856e-05,
+      "loss": 0.2448,
+      "step": 5400
+    },
+    {
+      "epoch": 6.11554800339847,
+      "eval_loss": 0.7178024053573608,
+      "eval_runtime": 143.9568,
+      "eval_samples_per_second": 10.899,
+      "eval_steps_per_second": 2.73,
+      "step": 5400
+    },
+    {
+      "epoch": 6.172189181534976,
+      "grad_norm": 1.1384133100509644,
+      "learning_rate": 2.380100796618436e-05,
+      "loss": 0.2616,
+      "step": 5450
+    },
+    {
+      "epoch": 6.228830359671481,
+      "grad_norm": 1.4748141765594482,
+      "learning_rate": 2.2175256055925866e-05,
+      "loss": 0.2325,
+      "step": 5500
+    },
+    {
+      "epoch": 6.285471537807986,
+      "grad_norm": 1.6163220405578613,
+      "learning_rate": 2.054950414566737e-05,
+      "loss": 0.2493,
+      "step": 5550
+    },
+    {
+      "epoch": 6.342112715944491,
+      "grad_norm": 1.3263028860092163,
+      "learning_rate": 1.892375223540888e-05,
+      "loss": 0.2615,
+      "step": 5600
+    },
+    {
+      "epoch": 6.342112715944491,
+      "eval_loss": 0.726570725440979,
+      "eval_runtime": 143.4083,
+      "eval_samples_per_second": 10.941,
+      "eval_steps_per_second": 2.74,
+      "step": 5600
+    },
+    {
+      "epoch": 6.398753894080997,
+      "grad_norm": 1.046238660812378,
+      "learning_rate": 1.729800032515038e-05,
+      "loss": 0.2335,
+      "step": 5650
+    },
+    {
+      "epoch": 6.455395072217502,
+      "grad_norm": 1.156273603439331,
+      "learning_rate": 1.567224841489189e-05,
+      "loss": 0.2402,
+      "step": 5700
+    },
+    {
+      "epoch": 6.512036250354007,
+      "grad_norm": 1.6315362453460693,
+      "learning_rate": 1.4046496504633394e-05,
+      "loss": 0.2584,
+      "step": 5750
+    },
+    {
+      "epoch": 6.5686774284905125,
+      "grad_norm": 1.2109113931655884,
+      "learning_rate": 1.24207445943749e-05,
+      "loss": 0.2446,
+      "step": 5800
+    },
+    {
+      "epoch": 6.5686774284905125,
+      "eval_loss": 0.731035590171814,
+      "eval_runtime": 144.0173,
+      "eval_samples_per_second": 10.895,
+      "eval_steps_per_second": 2.729,
+      "step": 5800
+    },
+    {
+      "epoch": 6.625318606627018,
+      "grad_norm": 1.3548364639282227,
+      "learning_rate": 1.0794992684116404e-05,
+      "loss": 0.2511,
+      "step": 5850
+    },
+    {
+      "epoch": 6.681959784763523,
+      "grad_norm": 1.3163737058639526,
+      "learning_rate": 9.16924077385791e-06,
+      "loss": 0.2351,
+      "step": 5900
+    },
+    {
+      "epoch": 6.738600962900028,
+      "grad_norm": 1.1973426342010498,
+      "learning_rate": 7.543488863599415e-06,
+      "loss": 0.2399,
+      "step": 5950
+    },
+    {
+      "epoch": 6.795242141036534,
+      "grad_norm": 1.3192789554595947,
+      "learning_rate": 5.91773695334092e-06,
+      "loss": 0.2559,
+      "step": 6000
+    },
+    {
+      "epoch": 6.795242141036534,
+      "eval_loss": 0.7207013368606567,
+      "eval_runtime": 143.7446,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 2.734,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.021077531715881e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24dbce934bdef4e393ace30f47e87259f49a5fb82c9b1cf4c325f7d12c72c1cf
+size 5688

checkpoint-6181/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-6181/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-6181/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c3a35b62a6eb804c7c1bfb5aaafe834771f22ddecd95d3e047e3258c04327e
+size 52231312

checkpoint-6181/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-6181/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

checkpoint-6181/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff07e4a81a3036a8562fbb12e39e0c02f236eaeb75ea773e4f73c43aa4eb7f8c
+size 27860634

checkpoint-6181/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b0d4622ef35d3b8f3ea1592bf278ce61bee81cf5bac712353ad99788b7c094
+size 14244

checkpoint-6181/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4539b747ab868e03088bf0baa13b51dc06a3deab7873e47bb41efee65f768d
+size 1064

checkpoint-6181/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-6181/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-6181/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-6181/trainer_state.json

@@ -0,0 +1,1135 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.57286536693573,
+  "best_model_checkpoint": "Gemma-3-1B-it-Medical-LoRA/checkpoint-800",
+  "epoch": 7.0,
+  "eval_steps": 200,
+  "global_step": 6181,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05664117813650524,
+      "grad_norm": 0.7655816078186035,
+      "learning_rate": 0.0001955451348182884,
+      "loss": 0.9427,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328235627301048,
+      "grad_norm": 0.7325181365013123,
+      "learning_rate": 0.00018382180539273154,
+      "loss": 0.6075,
+      "step": 100
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.6365712881088257,
+      "learning_rate": 0.00017209847596717467,
+      "loss": 0.675,
+      "step": 150
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "grad_norm": 0.9989428520202637,
+      "learning_rate": 0.00016037514654161782,
+      "loss": 0.6585,
+      "step": 200
+    },
+    {
+      "epoch": 0.22656471254602095,
+      "eval_loss": 0.6068728566169739,
+      "eval_runtime": 154.0009,
+      "eval_samples_per_second": 10.188,
+      "eval_steps_per_second": 2.552,
+      "step": 200
+    },
+    {
+      "epoch": 0.2832058906825262,
+      "grad_norm": 0.6311811208724976,
+      "learning_rate": 0.00014865181711606098,
+      "loss": 0.6311,
+      "step": 250
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.831785261631012,
+      "learning_rate": 0.0001369284876905041,
+      "loss": 0.5715,
+      "step": 300
+    },
+    {
+      "epoch": 0.3964882469555367,
+      "grad_norm": 0.7572771310806274,
+      "learning_rate": 0.00012520515826494724,
+      "loss": 0.5482,
+      "step": 350
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "grad_norm": 0.715999960899353,
+      "learning_rate": 0.0001134818288393904,
+      "loss": 0.5674,
+      "step": 400
+    },
+    {
+      "epoch": 0.4531294250920419,
+      "eval_loss": 0.5926390290260315,
+      "eval_runtime": 144.007,
+      "eval_samples_per_second": 10.895,
+      "eval_steps_per_second": 2.729,
+      "step": 400
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.8048545122146606,
+      "learning_rate": 0.00010175849941383353,
+      "loss": 0.5664,
+      "step": 450
+    },
+    {
+      "epoch": 0.5664117813650524,
+      "grad_norm": 0.994825541973114,
+      "learning_rate": 9.003516998827668e-05,
+      "loss": 0.6381,
+      "step": 500
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.8860945105552673,
+      "learning_rate": 7.831184056271981e-05,
+      "loss": 0.5774,
+      "step": 550
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.7308331727981567,
+      "learning_rate": 6.658851113716296e-05,
+      "loss": 0.5827,
+      "step": 600
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "eval_loss": 0.580059826374054,
+      "eval_runtime": 144.3097,
+      "eval_samples_per_second": 10.872,
+      "eval_steps_per_second": 2.723,
+      "step": 600
+    },
+    {
+      "epoch": 0.7363353157745681,
+      "grad_norm": 0.8322684168815613,
+      "learning_rate": 5.486518171160609e-05,
+      "loss": 0.599,
+      "step": 650
+    },
+    {
+      "epoch": 0.7929764939110734,
+      "grad_norm": 1.0585319995880127,
+      "learning_rate": 4.3141852286049237e-05,
+      "loss": 0.631,
+      "step": 700
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 1.00983726978302,
+      "learning_rate": 3.1418522860492386e-05,
+      "loss": 0.5947,
+      "step": 750
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "grad_norm": 0.6543359160423279,
+      "learning_rate": 1.9695193434935523e-05,
+      "loss": 0.5665,
+      "step": 800
+    },
+    {
+      "epoch": 0.9062588501840838,
+      "eval_loss": 0.57286536693573,
+      "eval_runtime": 144.191,
+      "eval_samples_per_second": 10.881,
+      "eval_steps_per_second": 2.726,
+      "step": 800
+    },
+    {
+      "epoch": 0.9629000283205891,
+      "grad_norm": 0.960976779460907,
+      "learning_rate": 7.971864009378664e-06,
+      "loss": 0.5712,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192580005664118,
+      "grad_norm": 0.8420133590698242,
+      "learning_rate": 9.988479262672812e-05,
+      "loss": 0.5028,
+      "step": 900
+    },
+    {
+      "epoch": 1.075899178702917,
+      "grad_norm": 0.8027368187904358,
+      "learning_rate": 9.412442396313365e-05,
+      "loss": 0.5148,
+      "step": 950
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "grad_norm": 0.7591931223869324,
+      "learning_rate": 8.836405529953917e-05,
+      "loss": 0.4944,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1325403568394223,
+      "eval_loss": 0.5851833820343018,
+      "eval_runtime": 144.0876,
+      "eval_samples_per_second": 10.889,
+      "eval_steps_per_second": 2.728,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891815349759276,
+      "grad_norm": 0.8245683312416077,
+      "learning_rate": 8.26036866359447e-05,
+      "loss": 0.5582,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2458227131124326,
+      "grad_norm": 0.8791372776031494,
+      "learning_rate": 7.684331797235024e-05,
+      "loss": 0.5125,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302463891248938,
+      "grad_norm": 0.8794203400611877,
+      "learning_rate": 7.108294930875576e-05,
+      "loss": 0.5383,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "grad_norm": 0.9652652144432068,
+      "learning_rate": 6.532258064516129e-05,
+      "loss": 0.5184,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3591050693854432,
+      "eval_loss": 0.5808290243148804,
+      "eval_runtime": 144.5522,
+      "eval_samples_per_second": 10.854,
+      "eval_steps_per_second": 2.719,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4157462475219484,
+      "grad_norm": 0.8952807784080505,
+      "learning_rate": 5.956221198156682e-05,
+      "loss": 0.5398,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4723874256584537,
+      "grad_norm": 0.8340632319450378,
+      "learning_rate": 5.3801843317972355e-05,
+      "loss": 0.5066,
+      "step": 1300
+    },
+    {
+      "epoch": 1.529028603794959,
+      "grad_norm": 1.2093769311904907,
+      "learning_rate": 4.8041474654377885e-05,
+      "loss": 0.5347,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "grad_norm": 1.3850702047348022,
+      "learning_rate": 4.228110599078341e-05,
+      "loss": 0.4901,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5856697819314642,
+      "eval_loss": 0.5830569267272949,
+      "eval_runtime": 144.2996,
+      "eval_samples_per_second": 10.873,
+      "eval_steps_per_second": 2.723,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6423109600679693,
+      "grad_norm": 0.809190571308136,
+      "learning_rate": 3.6520737327188945e-05,
+      "loss": 0.5241,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6989521382044748,
+      "grad_norm": 1.0073446035385132,
+      "learning_rate": 3.076036866359447e-05,
+      "loss": 0.5114,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7555933163409798,
+      "grad_norm": 1.0417332649230957,
+      "learning_rate": 2.5e-05,
+      "loss": 0.519,
+      "step": 1550
+    },
+    {
+      "epoch": 1.812234494477485,
+      "grad_norm": 0.9849772453308105,
+      "learning_rate": 1.923963133640553e-05,
+      "loss": 0.5156,
+      "step": 1600
+    },
+    {
+      "epoch": 1.812234494477485,
+      "eval_loss": 0.5755766034126282,
+      "eval_runtime": 143.8724,
+      "eval_samples_per_second": 10.905,
+      "eval_steps_per_second": 2.732,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8688756726139903,
+      "grad_norm": 1.2943501472473145,
+      "learning_rate": 1.3479262672811061e-05,
+      "loss": 0.5483,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9255168507504956,
+      "grad_norm": 0.8810242414474487,
+      "learning_rate": 7.71889400921659e-06,
+      "loss": 0.5168,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9821580288870009,
+      "grad_norm": 0.9415161609649658,
+      "learning_rate": 1.9585253456221198e-06,
+      "loss": 0.5176,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "grad_norm": 1.0487638711929321,
+      "learning_rate": 6.491027109583811e-05,
+      "loss": 0.4455,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0385160011328236,
+      "eval_loss": 0.587023138999939,
+      "eval_runtime": 144.0009,
+      "eval_samples_per_second": 10.896,
+      "eval_steps_per_second": 2.729,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0951571792693287,
+      "grad_norm": 1.317651391029358,
+      "learning_rate": 6.109201985490646e-05,
+      "loss": 0.4665,
+      "step": 1850
+    },
+    {
+      "epoch": 2.151798357405834,
+      "grad_norm": 1.219244360923767,
+      "learning_rate": 5.72737686139748e-05,
+      "loss": 0.4964,
+      "step": 1900
+    },
+    {
+      "epoch": 2.208439535542339,
+      "grad_norm": 1.2626948356628418,
+      "learning_rate": 5.345551737304315e-05,
+      "loss": 0.479,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "grad_norm": 1.3026907444000244,
+      "learning_rate": 4.963726613211149e-05,
+      "loss": 0.4713,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2650807136788447,
+      "eval_loss": 0.5911725759506226,
+      "eval_runtime": 144.1844,
+      "eval_samples_per_second": 10.882,
+      "eval_steps_per_second": 2.726,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3217218918153497,
+      "grad_norm": 1.0047467947006226,
+      "learning_rate": 4.581901489117984e-05,
+      "loss": 0.4794,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378363069951855,
+      "grad_norm": 1.2122581005096436,
+      "learning_rate": 4.2000763650248184e-05,
+      "loss": 0.4771,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4350042480883602,
+      "grad_norm": 1.2274476289749146,
+      "learning_rate": 3.818251240931654e-05,
+      "loss": 0.4691,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "grad_norm": 1.0465933084487915,
+      "learning_rate": 3.4364261168384884e-05,
+      "loss": 0.4267,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4916454262248653,
+      "eval_loss": 0.5909530520439148,
+      "eval_runtime": 143.9787,
+      "eval_samples_per_second": 10.897,
+      "eval_steps_per_second": 2.73,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 1.1270743608474731,
+      "learning_rate": 3.054600992745323e-05,
+      "loss": 0.4587,
+      "step": 2250
+    },
+    {
+      "epoch": 2.604927782497876,
+      "grad_norm": 1.0416178703308105,
+      "learning_rate": 2.6727758686521576e-05,
+      "loss": 0.4875,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6615689606343813,
+      "grad_norm": 0.9418396353721619,
+      "learning_rate": 2.290950744558992e-05,
+      "loss": 0.4756,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "grad_norm": 0.9481875896453857,
+      "learning_rate": 1.909125620465827e-05,
+      "loss": 0.4626,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7182101387708864,
+      "eval_loss": 0.587207555770874,
+      "eval_runtime": 144.1702,
+      "eval_samples_per_second": 10.883,
+      "eval_steps_per_second": 2.726,
+      "step": 2400
+    },
+    {
+      "epoch": 2.774851316907392,
+      "grad_norm": 0.8298775553703308,
+      "learning_rate": 1.5273004963726615e-05,
+      "loss": 0.4396,
+      "step": 2450
+    },
+    {
+      "epoch": 2.831492495043897,
+      "grad_norm": 1.2271429300308228,
+      "learning_rate": 1.145475372279496e-05,
+      "loss": 0.4531,
+      "step": 2500
+    },
+    {
+      "epoch": 2.888133673180402,
+      "grad_norm": 1.2411454916000366,
+      "learning_rate": 7.636502481863307e-06,
+      "loss": 0.4647,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "grad_norm": 1.449476718902588,
+      "learning_rate": 3.818251240931654e-06,
+      "loss": 0.4635,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9447748513169074,
+      "eval_loss": 0.5865218639373779,
+      "eval_runtime": 143.9267,
+      "eval_samples_per_second": 10.901,
+      "eval_steps_per_second": 2.731,
+      "step": 2600
+    },
+    {
+      "epoch": 3.00113282356273,
+      "grad_norm": 0.9472671151161194,
+      "learning_rate": 0.0,
+      "loss": 0.3542,
+      "step": 2650
+    },
+    {
+      "epoch": 3.057774001699235,
+      "grad_norm": 1.101803183555603,
+      "learning_rate": 0.00011321736303040155,
+      "loss": 0.4194,
+      "step": 2700
+    },
+    {
+      "epoch": 3.1144151798357407,
+      "grad_norm": 1.1706457138061523,
+      "learning_rate": 0.00011159161112014307,
+      "loss": 0.4313,
+      "step": 2750
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "grad_norm": 1.2929370403289795,
+      "learning_rate": 0.00010996585920988458,
+      "loss": 0.4418,
+      "step": 2800
+    },
+    {
+      "epoch": 3.1710563579722457,
+      "eval_loss": 0.60947585105896,
+      "eval_runtime": 153.6833,
+      "eval_samples_per_second": 10.209,
+      "eval_steps_per_second": 2.557,
+      "step": 2800
+    },
+    {
+      "epoch": 3.227697536108751,
+      "grad_norm": 1.3731728792190552,
+      "learning_rate": 0.00010834010729962609,
+      "loss": 0.4868,
+      "step": 2850
+    },
+    {
+      "epoch": 3.2843387142452563,
+      "grad_norm": 1.343711256980896,
+      "learning_rate": 0.00010671435538936759,
+      "loss": 0.4336,
+      "step": 2900
+    },
+    {
+      "epoch": 3.3409798923817613,
+      "grad_norm": 1.5197447538375854,
+      "learning_rate": 0.0001050886034791091,
+      "loss": 0.4789,
+      "step": 2950
+    },
+    {
+      "epoch": 3.397621070518267,
+      "grad_norm": 0.834096372127533,
+      "learning_rate": 0.00010346285156885061,
+      "loss": 0.4639,
+      "step": 3000
+    },
+    {
+      "epoch": 3.397621070518267,
+      "eval_loss": 0.6121659278869629,
+      "eval_runtime": 143.8631,
+      "eval_samples_per_second": 10.906,
+      "eval_steps_per_second": 2.732,
+      "step": 3000
+    },
+    {
+      "epoch": 3.454262248654772,
+      "grad_norm": 1.1350237131118774,
+      "learning_rate": 0.0001018370996585921,
+      "loss": 0.4591,
+      "step": 3050
+    },
+    {
+      "epoch": 3.5109034267912773,
+      "grad_norm": 1.269223928451538,
+      "learning_rate": 0.00010021134774833361,
+      "loss": 0.4679,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5675446049277824,
+      "grad_norm": 1.1300125122070312,
+      "learning_rate": 9.858559583807512e-05,
+      "loss": 0.4619,
+      "step": 3150
+    },
+    {
+      "epoch": 3.624185783064288,
+      "grad_norm": 1.2352793216705322,
+      "learning_rate": 9.695984392781662e-05,
+      "loss": 0.48,
+      "step": 3200
+    },
+    {
+      "epoch": 3.624185783064288,
+      "eval_loss": 0.6045758724212646,
+      "eval_runtime": 144.0294,
+      "eval_samples_per_second": 10.894,
+      "eval_steps_per_second": 2.729,
+      "step": 3200
+    },
+    {
+      "epoch": 3.680826961200793,
+      "grad_norm": 1.3493255376815796,
+      "learning_rate": 9.533409201755813e-05,
+      "loss": 0.4838,
+      "step": 3250
+    },
+    {
+      "epoch": 3.7374681393372984,
+      "grad_norm": 1.3916635513305664,
+      "learning_rate": 9.370834010729963e-05,
+      "loss": 0.4899,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7941093174738034,
+      "grad_norm": 1.4167906045913696,
+      "learning_rate": 9.208258819704113e-05,
+      "loss": 0.5017,
+      "step": 3350
+    },
+    {
+      "epoch": 3.850750495610309,
+      "grad_norm": 0.8912964463233948,
+      "learning_rate": 9.045683628678264e-05,
+      "loss": 0.4587,
+      "step": 3400
+    },
+    {
+      "epoch": 3.850750495610309,
+      "eval_loss": 0.5994317531585693,
+      "eval_runtime": 143.7834,
+      "eval_samples_per_second": 10.912,
+      "eval_steps_per_second": 2.733,
+      "step": 3400
+    },
+    {
+      "epoch": 3.907391673746814,
+      "grad_norm": 1.2601457834243774,
+      "learning_rate": 8.883108437652414e-05,
+      "loss": 0.4766,
+      "step": 3450
+    },
+    {
+      "epoch": 3.964032851883319,
+      "grad_norm": 1.1677194833755493,
+      "learning_rate": 8.720533246626565e-05,
+      "loss": 0.4616,
+      "step": 3500
+    },
+    {
+      "epoch": 4.020390824129142,
+      "grad_norm": 1.2599579095840454,
+      "learning_rate": 8.557958055600716e-05,
+      "loss": 0.4602,
+      "step": 3550
+    },
+    {
+      "epoch": 4.077032002265647,
+      "grad_norm": 0.9038525819778442,
+      "learning_rate": 8.395382864574867e-05,
+      "loss": 0.3565,
+      "step": 3600
+    },
+    {
+      "epoch": 4.077032002265647,
+      "eval_loss": 0.6232873797416687,
+      "eval_runtime": 143.721,
+      "eval_samples_per_second": 10.917,
+      "eval_steps_per_second": 2.734,
+      "step": 3600
+    },
+    {
+      "epoch": 4.133673180402153,
+      "grad_norm": 1.4113986492156982,
+      "learning_rate": 8.232807673549017e-05,
+      "loss": 0.4193,
+      "step": 3650
+    },
+    {
+      "epoch": 4.190314358538657,
+      "grad_norm": 1.1578692197799683,
+      "learning_rate": 8.070232482523168e-05,
+      "loss": 0.372,
+      "step": 3700
+    },
+    {
+      "epoch": 4.246955536675163,
+      "grad_norm": 1.4185764789581299,
+      "learning_rate": 7.907657291497318e-05,
+      "loss": 0.3647,
+      "step": 3750
+    },
+    {
+      "epoch": 4.303596714811668,
+      "grad_norm": 1.3464981317520142,
+      "learning_rate": 7.745082100471468e-05,
+      "loss": 0.3745,
+      "step": 3800
+    },
+    {
+      "epoch": 4.303596714811668,
+      "eval_loss": 0.6339591145515442,
+      "eval_runtime": 143.7966,
+      "eval_samples_per_second": 10.911,
+      "eval_steps_per_second": 2.733,
+      "step": 3800
+    },
+    {
+      "epoch": 4.360237892948174,
+      "grad_norm": 1.323198676109314,
+      "learning_rate": 7.582506909445619e-05,
+      "loss": 0.3839,
+      "step": 3850
+    },
+    {
+      "epoch": 4.416879071084678,
+      "grad_norm": 1.8854613304138184,
+      "learning_rate": 7.419931718419769e-05,
+      "loss": 0.4328,
+      "step": 3900
+    },
+    {
+      "epoch": 4.473520249221184,
+      "grad_norm": 0.9551966786384583,
+      "learning_rate": 7.25735652739392e-05,
+      "loss": 0.3816,
+      "step": 3950
+    },
+    {
+      "epoch": 4.530161427357689,
+      "grad_norm": 1.1180638074874878,
+      "learning_rate": 7.09478133636807e-05,
+      "loss": 0.4019,
+      "step": 4000
+    },
+    {
+      "epoch": 4.530161427357689,
+      "eval_loss": 0.629741907119751,
+      "eval_runtime": 144.0805,
+      "eval_samples_per_second": 10.89,
+      "eval_steps_per_second": 2.728,
+      "step": 4000
+    },
+    {
+      "epoch": 4.586802605494194,
+      "grad_norm": 1.5229169130325317,
+      "learning_rate": 6.932206145342221e-05,
+      "loss": 0.3794,
+      "step": 4050
+    },
+    {
+      "epoch": 4.643443783630699,
+      "grad_norm": 1.1407935619354248,
+      "learning_rate": 6.769630954316372e-05,
+      "loss": 0.3911,
+      "step": 4100
+    },
+    {
+      "epoch": 4.700084961767205,
+      "grad_norm": 1.4342515468597412,
+      "learning_rate": 6.607055763290522e-05,
+      "loss": 0.3757,
+      "step": 4150
+    },
+    {
+      "epoch": 4.75672613990371,
+      "grad_norm": 1.471047282218933,
+      "learning_rate": 6.444480572264673e-05,
+      "loss": 0.4043,
+      "step": 4200
+    },
+    {
+      "epoch": 4.75672613990371,
+      "eval_loss": 0.6323012709617615,
+      "eval_runtime": 143.8107,
+      "eval_samples_per_second": 10.91,
+      "eval_steps_per_second": 2.733,
+      "step": 4200
+    },
+    {
+      "epoch": 4.813367318040215,
+      "grad_norm": 1.6963218450546265,
+      "learning_rate": 6.281905381238823e-05,
+      "loss": 0.3817,
+      "step": 4250
+    },
+    {
+      "epoch": 4.8700084961767205,
+      "grad_norm": 1.4788011312484741,
+      "learning_rate": 6.119330190212974e-05,
+      "loss": 0.3879,
+      "step": 4300
+    },
+    {
+      "epoch": 4.926649674313226,
+      "grad_norm": 1.5147647857666016,
+      "learning_rate": 5.956754999187124e-05,
+      "loss": 0.3874,
+      "step": 4350
+    },
+    {
+      "epoch": 4.983290852449731,
+      "grad_norm": 1.027481198310852,
+      "learning_rate": 5.794179808161275e-05,
+      "loss": 0.3736,
+      "step": 4400
+    },
+    {
+      "epoch": 4.983290852449731,
+      "eval_loss": 0.6303974390029907,
+      "eval_runtime": 143.9543,
+      "eval_samples_per_second": 10.899,
+      "eval_steps_per_second": 2.73,
+      "step": 4400
+    },
+    {
+      "epoch": 5.039648824695553,
+      "grad_norm": 1.2473069429397583,
+      "learning_rate": 5.631604617135425e-05,
+      "loss": 0.33,
+      "step": 4450
+    },
+    {
+      "epoch": 5.096290002832059,
+      "grad_norm": 1.439157485961914,
+      "learning_rate": 5.469029426109576e-05,
+      "loss": 0.3065,
+      "step": 4500
+    },
+    {
+      "epoch": 5.152931180968564,
+      "grad_norm": 1.172194480895996,
+      "learning_rate": 5.306454235083727e-05,
+      "loss": 0.3038,
+      "step": 4550
+    },
+    {
+      "epoch": 5.20957235910507,
+      "grad_norm": 2.9354825019836426,
+      "learning_rate": 5.1438790440578765e-05,
+      "loss": 0.2961,
+      "step": 4600
+    },
+    {
+      "epoch": 5.20957235910507,
+      "eval_loss": 0.6725755929946899,
+      "eval_runtime": 143.751,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 2.734,
+      "step": 4600
+    },
+    {
+      "epoch": 5.266213537241574,
+      "grad_norm": 1.7553826570510864,
+      "learning_rate": 4.981303853032028e-05,
+      "loss": 0.3055,
+      "step": 4650
+    },
+    {
+      "epoch": 5.32285471537808,
+      "grad_norm": 1.1259921789169312,
+      "learning_rate": 4.818728662006178e-05,
+      "loss": 0.3052,
+      "step": 4700
+    },
+    {
+      "epoch": 5.379495893514585,
+      "grad_norm": 1.2912168502807617,
+      "learning_rate": 4.656153470980329e-05,
+      "loss": 0.3168,
+      "step": 4750
+    },
+    {
+      "epoch": 5.43613707165109,
+      "grad_norm": 1.3614895343780518,
+      "learning_rate": 4.493578279954479e-05,
+      "loss": 0.3024,
+      "step": 4800
+    },
+    {
+      "epoch": 5.43613707165109,
+      "eval_loss": 0.6745353937149048,
+      "eval_runtime": 143.4345,
+      "eval_samples_per_second": 10.939,
+      "eval_steps_per_second": 2.74,
+      "step": 4800
+    },
+    {
+      "epoch": 5.492778249787595,
+      "grad_norm": 1.4940049648284912,
+      "learning_rate": 4.33100308892863e-05,
+      "loss": 0.3281,
+      "step": 4850
+    },
+    {
+      "epoch": 5.549419427924101,
+      "grad_norm": 1.3145006895065308,
+      "learning_rate": 4.16842789790278e-05,
+      "loss": 0.2955,
+      "step": 4900
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 1.6090342998504639,
+      "learning_rate": 4.005852706876931e-05,
+      "loss": 0.3351,
+      "step": 4950
+    },
+    {
+      "epoch": 5.662701784197111,
+      "grad_norm": 1.2353523969650269,
+      "learning_rate": 3.843277515851081e-05,
+      "loss": 0.3146,
+      "step": 5000
+    },
+    {
+      "epoch": 5.662701784197111,
+      "eval_loss": 0.6648290753364563,
+      "eval_runtime": 143.6635,
+      "eval_samples_per_second": 10.921,
+      "eval_steps_per_second": 2.736,
+      "step": 5000
+    },
+    {
+      "epoch": 5.7193429623336165,
+      "grad_norm": 1.4121828079223633,
+      "learning_rate": 3.680702324825232e-05,
+      "loss": 0.3252,
+      "step": 5050
+    },
+    {
+      "epoch": 5.775984140470122,
+      "grad_norm": 1.6109447479248047,
+      "learning_rate": 3.518127133799383e-05,
+      "loss": 0.2894,
+      "step": 5100
+    },
+    {
+      "epoch": 5.8326253186066275,
+      "grad_norm": 1.2615262269973755,
+      "learning_rate": 3.355551942773533e-05,
+      "loss": 0.3233,
+      "step": 5150
+    },
+    {
+      "epoch": 5.889266496743132,
+      "grad_norm": 1.4789379835128784,
+      "learning_rate": 3.192976751747683e-05,
+      "loss": 0.3136,
+      "step": 5200
+    },
+    {
+      "epoch": 5.889266496743132,
+      "eval_loss": 0.6699800491333008,
+      "eval_runtime": 143.914,
+      "eval_samples_per_second": 10.902,
+      "eval_steps_per_second": 2.731,
+      "step": 5200
+    },
+    {
+      "epoch": 5.945907674879638,
+      "grad_norm": 1.5867825746536255,
+      "learning_rate": 3.0304015607218337e-05,
+      "loss": 0.3398,
+      "step": 5250
+    },
+    {
+      "epoch": 6.00226564712546,
+      "grad_norm": 1.981821060180664,
+      "learning_rate": 2.8678263696959846e-05,
+      "loss": 0.2998,
+      "step": 5300
+    },
+    {
+      "epoch": 6.058906825261966,
+      "grad_norm": 1.178331971168518,
+      "learning_rate": 2.705251178670135e-05,
+      "loss": 0.2447,
+      "step": 5350
+    },
+    {
+      "epoch": 6.11554800339847,
+      "grad_norm": 1.5027756690979004,
+      "learning_rate": 2.5426759876442856e-05,
+      "loss": 0.2448,
+      "step": 5400
+    },
+    {
+      "epoch": 6.11554800339847,
+      "eval_loss": 0.7178024053573608,
+      "eval_runtime": 143.9568,
+      "eval_samples_per_second": 10.899,
+      "eval_steps_per_second": 2.73,
+      "step": 5400
+    },
+    {
+      "epoch": 6.172189181534976,
+      "grad_norm": 1.1384133100509644,
+      "learning_rate": 2.380100796618436e-05,
+      "loss": 0.2616,
+      "step": 5450
+    },
+    {
+      "epoch": 6.228830359671481,
+      "grad_norm": 1.4748141765594482,
+      "learning_rate": 2.2175256055925866e-05,
+      "loss": 0.2325,
+      "step": 5500
+    },
+    {
+      "epoch": 6.285471537807986,
+      "grad_norm": 1.6163220405578613,
+      "learning_rate": 2.054950414566737e-05,
+      "loss": 0.2493,
+      "step": 5550
+    },
+    {
+      "epoch": 6.342112715944491,
+      "grad_norm": 1.3263028860092163,
+      "learning_rate": 1.892375223540888e-05,
+      "loss": 0.2615,
+      "step": 5600
+    },
+    {
+      "epoch": 6.342112715944491,
+      "eval_loss": 0.726570725440979,
+      "eval_runtime": 143.4083,
+      "eval_samples_per_second": 10.941,
+      "eval_steps_per_second": 2.74,
+      "step": 5600
+    },
+    {
+      "epoch": 6.398753894080997,
+      "grad_norm": 1.046238660812378,
+      "learning_rate": 1.729800032515038e-05,
+      "loss": 0.2335,
+      "step": 5650
+    },
+    {
+      "epoch": 6.455395072217502,
+      "grad_norm": 1.156273603439331,
+      "learning_rate": 1.567224841489189e-05,
+      "loss": 0.2402,
+      "step": 5700
+    },
+    {
+      "epoch": 6.512036250354007,
+      "grad_norm": 1.6315362453460693,
+      "learning_rate": 1.4046496504633394e-05,
+      "loss": 0.2584,
+      "step": 5750
+    },
+    {
+      "epoch": 6.5686774284905125,
+      "grad_norm": 1.2109113931655884,
+      "learning_rate": 1.24207445943749e-05,
+      "loss": 0.2446,
+      "step": 5800
+    },
+    {
+      "epoch": 6.5686774284905125,
+      "eval_loss": 0.731035590171814,
+      "eval_runtime": 144.0173,
+      "eval_samples_per_second": 10.895,
+      "eval_steps_per_second": 2.729,
+      "step": 5800
+    },
+    {
+      "epoch": 6.625318606627018,
+      "grad_norm": 1.3548364639282227,
+      "learning_rate": 1.0794992684116404e-05,
+      "loss": 0.2511,
+      "step": 5850
+    },
+    {
+      "epoch": 6.681959784763523,
+      "grad_norm": 1.3163737058639526,
+      "learning_rate": 9.16924077385791e-06,
+      "loss": 0.2351,
+      "step": 5900
+    },
+    {
+      "epoch": 6.738600962900028,
+      "grad_norm": 1.1973426342010498,
+      "learning_rate": 7.543488863599415e-06,
+      "loss": 0.2399,
+      "step": 5950
+    },
+    {
+      "epoch": 6.795242141036534,
+      "grad_norm": 1.3192789554595947,
+      "learning_rate": 5.91773695334092e-06,
+      "loss": 0.2559,
+      "step": 6000
+    },
+    {
+      "epoch": 6.795242141036534,
+      "eval_loss": 0.7207013368606567,
+      "eval_runtime": 143.7446,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 2.734,
+      "step": 6000
+    },
+    {
+      "epoch": 6.851883319173039,
+      "grad_norm": 1.284158706665039,
+      "learning_rate": 4.291985043082425e-06,
+      "loss": 0.2312,
+      "step": 6050
+    },
+    {
+      "epoch": 6.908524497309544,
+      "grad_norm": 1.0552254915237427,
+      "learning_rate": 2.6662331328239313e-06,
+      "loss": 0.2505,
+      "step": 6100
+    },
+    {
+      "epoch": 6.965165675446049,
+      "grad_norm": 1.2282088994979858,
+      "learning_rate": 1.0404812225654365e-06,
+      "loss": 0.252,
+      "step": 6150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6181,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0813416244964864e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6181/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24dbce934bdef4e393ace30f47e87259f49a5fb82c9b1cf4c325f7d12c72c1cf
+size 5688

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074