Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_attn",
+    "c_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:d9ff5e1c3f8a1ad91cdccc081a6c163c6477e3a5ebc7962db2f6c679b32d7493
+size 9449344

checkpoint-6366/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openai-community/gpt2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-6366/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_attn",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-6366/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ff5e1c3f8a1ad91cdccc081a6c163c6477e3a5ebc7962db2f6c679b32d7493
+size 9449344

checkpoint-6366/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d30031b9ee39eca8403fa753c7495804d32c38376fd89ab9284aa1c813ca2d
+size 18955258

checkpoint-6366/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-6366/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087add2a618d3fc14510cd2ca22f1aefb1c83125c7d42f5389e6f90436f5363c
+size 14244

checkpoint-6366/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a8eea645e5d8b4dd952697b6ba6565c956e27b3327524d93be41a93401c0b3
+size 1064

checkpoint-6366/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-6366/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-6366/trainer_state.json

@@ -0,0 +1,1799 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 6366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4550137519836426,
+      "learning_rate": 1.1773940345368917e-06,
+      "loss": 2.7174,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.3239152431488037,
+      "learning_rate": 2.3547880690737835e-06,
+      "loss": 2.7301,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.2503877878189087,
+      "learning_rate": 3.532182103610675e-06,
+      "loss": 2.7177,
+      "step": 75
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.4258066415786743,
+      "learning_rate": 4.709576138147567e-06,
+      "loss": 2.6627,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5414007902145386,
+      "learning_rate": 5.886970172684459e-06,
+      "loss": 2.5528,
+      "step": 125
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.1376500129699707,
+      "learning_rate": 7.06436420722135e-06,
+      "loss": 2.4215,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.903887152671814,
+      "learning_rate": 8.241758241758243e-06,
+      "loss": 2.2661,
+      "step": 175
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.7810421586036682,
+      "learning_rate": 9.419152276295134e-06,
+      "loss": 2.1661,
+      "step": 200
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.806953489780426,
+      "learning_rate": 1.054945054945055e-05,
+      "loss": 2.0261,
+      "step": 225
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.6058614253997803,
+      "learning_rate": 1.1726844583987441e-05,
+      "loss": 1.9551,
+      "step": 250
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.528014063835144,
+      "learning_rate": 1.2904238618524332e-05,
+      "loss": 1.8942,
+      "step": 275
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.47531402111053467,
+      "learning_rate": 1.4081632653061225e-05,
+      "loss": 1.7891,
+      "step": 300
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.47076013684272766,
+      "learning_rate": 1.5259026687598116e-05,
+      "loss": 1.7725,
+      "step": 325
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5390304327011108,
+      "learning_rate": 1.643642072213501e-05,
+      "loss": 1.7132,
+      "step": 350
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.6033918857574463,
+      "learning_rate": 1.7613814756671898e-05,
+      "loss": 1.7432,
+      "step": 375
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.6497958302497864,
+      "learning_rate": 1.8791208791208793e-05,
+      "loss": 1.7009,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3979990780353546,
+      "learning_rate": 1.9968602825745684e-05,
+      "loss": 1.6574,
+      "step": 425
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.39559292793273926,
+      "learning_rate": 2.1145996860282575e-05,
+      "loss": 1.596,
+      "step": 450
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4321981370449066,
+      "learning_rate": 2.2323390894819466e-05,
+      "loss": 1.5367,
+      "step": 475
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4313070476055145,
+      "learning_rate": 2.350078492935636e-05,
+      "loss": 1.5457,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4958736002445221,
+      "learning_rate": 2.4678178963893248e-05,
+      "loss": 1.5258,
+      "step": 525
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5069326758384705,
+      "learning_rate": 2.5855572998430143e-05,
+      "loss": 1.5096,
+      "step": 550
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5262688994407654,
+      "learning_rate": 2.7032967032967034e-05,
+      "loss": 1.4645,
+      "step": 575
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.6320958137512207,
+      "learning_rate": 2.821036106750393e-05,
+      "loss": 1.4081,
+      "step": 600
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.44404885172843933,
+      "learning_rate": 2.9387755102040816e-05,
+      "loss": 1.4278,
+      "step": 625
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5611394047737122,
+      "learning_rate": 2.9937161808343517e-05,
+      "loss": 1.359,
+      "step": 650
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.50496906042099,
+      "learning_rate": 2.980624890905917e-05,
+      "loss": 1.3366,
+      "step": 675
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.49874988198280334,
+      "learning_rate": 2.967533600977483e-05,
+      "loss": 1.3175,
+      "step": 700
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4491003453731537,
+      "learning_rate": 2.954442311049049e-05,
+      "loss": 1.351,
+      "step": 725
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.6342208981513977,
+      "learning_rate": 2.9413510211206147e-05,
+      "loss": 1.353,
+      "step": 750
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4711619019508362,
+      "learning_rate": 2.9282597311921802e-05,
+      "loss": 1.2784,
+      "step": 775
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.533415675163269,
+      "learning_rate": 2.9151684412637457e-05,
+      "loss": 1.2759,
+      "step": 800
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6422008872032166,
+      "learning_rate": 2.9020771513353116e-05,
+      "loss": 1.2829,
+      "step": 825
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5320819616317749,
+      "learning_rate": 2.8889858614068774e-05,
+      "loss": 1.294,
+      "step": 850
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6057177782058716,
+      "learning_rate": 2.8758945714784433e-05,
+      "loss": 1.2728,
+      "step": 875
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.47568175196647644,
+      "learning_rate": 2.8628032815500088e-05,
+      "loss": 1.2308,
+      "step": 900
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.5981771349906921,
+      "learning_rate": 2.8497119916215743e-05,
+      "loss": 1.2759,
+      "step": 925
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5540325045585632,
+      "learning_rate": 2.83662070169314e-05,
+      "loss": 1.2731,
+      "step": 950
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4720264673233032,
+      "learning_rate": 2.823529411764706e-05,
+      "loss": 1.1777,
+      "step": 975
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5205626487731934,
+      "learning_rate": 2.8104381218362718e-05,
+      "loss": 1.2607,
+      "step": 1000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6065472960472107,
+      "learning_rate": 2.7973468319078373e-05,
+      "loss": 1.2371,
+      "step": 1025
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5618084669113159,
+      "learning_rate": 2.7842555419794032e-05,
+      "loss": 1.2351,
+      "step": 1050
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49749478697776794,
+      "learning_rate": 2.7711642520509687e-05,
+      "loss": 1.229,
+      "step": 1075
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.5713375210762024,
+      "learning_rate": 2.7580729621225345e-05,
+      "loss": 1.2189,
+      "step": 1100
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.5449201464653015,
+      "learning_rate": 2.7449816721941004e-05,
+      "loss": 1.2217,
+      "step": 1125
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5718939304351807,
+      "learning_rate": 2.731890382265666e-05,
+      "loss": 1.2169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.5724524259567261,
+      "learning_rate": 2.7187990923372317e-05,
+      "loss": 1.1946,
+      "step": 1175
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.4745756685733795,
+      "learning_rate": 2.7057078024087976e-05,
+      "loss": 1.1995,
+      "step": 1200
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.679215669631958,
+      "learning_rate": 2.692616512480363e-05,
+      "loss": 1.1511,
+      "step": 1225
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.5852200388908386,
+      "learning_rate": 2.679525222551929e-05,
+      "loss": 1.1293,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5490656495094299,
+      "learning_rate": 2.6664339326234944e-05,
+      "loss": 1.192,
+      "step": 1275
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.7541109919548035,
+      "learning_rate": 2.6533426426950603e-05,
+      "loss": 1.2221,
+      "step": 1300
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.7117947340011597,
+      "learning_rate": 2.640251352766626e-05,
+      "loss": 1.1575,
+      "step": 1325
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.5711504817008972,
+      "learning_rate": 2.627160062838192e-05,
+      "loss": 1.1758,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.6238616108894348,
+      "learning_rate": 2.614068772909757e-05,
+      "loss": 1.1511,
+      "step": 1375
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.5755292773246765,
+      "learning_rate": 2.600977482981323e-05,
+      "loss": 1.1309,
+      "step": 1400
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.5652589797973633,
+      "learning_rate": 2.587886193052889e-05,
+      "loss": 1.1294,
+      "step": 1425
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.5230275988578796,
+      "learning_rate": 2.5747949031244547e-05,
+      "loss": 1.1318,
+      "step": 1450
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.6454095840454102,
+      "learning_rate": 2.5617036131960205e-05,
+      "loss": 1.1668,
+      "step": 1475
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.7409027218818665,
+      "learning_rate": 2.5486123232675857e-05,
+      "loss": 1.1187,
+      "step": 1500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5434130430221558,
+      "learning_rate": 2.5355210333391516e-05,
+      "loss": 1.186,
+      "step": 1525
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.5816170573234558,
+      "learning_rate": 2.5224297434107174e-05,
+      "loss": 1.126,
+      "step": 1550
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5217471122741699,
+      "learning_rate": 2.5093384534822833e-05,
+      "loss": 1.1651,
+      "step": 1575
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.6262175440788269,
+      "learning_rate": 2.496247163553849e-05,
+      "loss": 1.1083,
+      "step": 1600
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.7060381174087524,
+      "learning_rate": 2.4831558736254146e-05,
+      "loss": 1.1523,
+      "step": 1625
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.627524197101593,
+      "learning_rate": 2.47006458369698e-05,
+      "loss": 1.1575,
+      "step": 1650
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.6749070286750793,
+      "learning_rate": 2.456973293768546e-05,
+      "loss": 1.1535,
+      "step": 1675
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6341940760612488,
+      "learning_rate": 2.4438820038401118e-05,
+      "loss": 1.1009,
+      "step": 1700
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.5389090776443481,
+      "learning_rate": 2.4307907139116777e-05,
+      "loss": 1.1221,
+      "step": 1725
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.6468391418457031,
+      "learning_rate": 2.417699423983243e-05,
+      "loss": 1.1398,
+      "step": 1750
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.5632995367050171,
+      "learning_rate": 2.404608134054809e-05,
+      "loss": 1.098,
+      "step": 1775
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.5900394320487976,
+      "learning_rate": 2.3915168441263745e-05,
+      "loss": 1.1081,
+      "step": 1800
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5528013110160828,
+      "learning_rate": 2.3784255541979404e-05,
+      "loss": 1.1314,
+      "step": 1825
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.5529065132141113,
+      "learning_rate": 2.3653342642695062e-05,
+      "loss": 1.151,
+      "step": 1850
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.6382936835289001,
+      "learning_rate": 2.3522429743410717e-05,
+      "loss": 1.0977,
+      "step": 1875
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.6123020648956299,
+      "learning_rate": 2.3391516844126376e-05,
+      "loss": 1.1206,
+      "step": 1900
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.5873188376426697,
+      "learning_rate": 2.3260603944842034e-05,
+      "loss": 1.1202,
+      "step": 1925
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.6366047859191895,
+      "learning_rate": 2.312969104555769e-05,
+      "loss": 1.1159,
+      "step": 1950
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.6183773875236511,
+      "learning_rate": 2.2998778146273344e-05,
+      "loss": 1.1617,
+      "step": 1975
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.6744990944862366,
+      "learning_rate": 2.2867865246989003e-05,
+      "loss": 1.1109,
+      "step": 2000
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.6510053277015686,
+      "learning_rate": 2.273695234770466e-05,
+      "loss": 1.0807,
+      "step": 2025
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.637360692024231,
+      "learning_rate": 2.260603944842032e-05,
+      "loss": 1.122,
+      "step": 2050
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.65646892786026,
+      "learning_rate": 2.2475126549135978e-05,
+      "loss": 1.1264,
+      "step": 2075
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.5863879919052124,
+      "learning_rate": 2.234421364985163e-05,
+      "loss": 1.0748,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6076034903526306,
+      "learning_rate": 2.221330075056729e-05,
+      "loss": 1.0891,
+      "step": 2125
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.6606038808822632,
+      "learning_rate": 2.2082387851282947e-05,
+      "loss": 1.1157,
+      "step": 2150
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.7062047719955444,
+      "learning_rate": 2.1951474951998605e-05,
+      "loss": 1.0886,
+      "step": 2175
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.5990228056907654,
+      "learning_rate": 2.1820562052714264e-05,
+      "loss": 1.1008,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.6606985926628113,
+      "learning_rate": 2.168964915342992e-05,
+      "loss": 1.0696,
+      "step": 2225
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6489419937133789,
+      "learning_rate": 2.1558736254145574e-05,
+      "loss": 1.1455,
+      "step": 2250
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.6855771541595459,
+      "learning_rate": 2.1427823354861232e-05,
+      "loss": 1.099,
+      "step": 2275
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.620990514755249,
+      "learning_rate": 2.129691045557689e-05,
+      "loss": 1.0636,
+      "step": 2300
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.6790271401405334,
+      "learning_rate": 2.116599755629255e-05,
+      "loss": 1.1138,
+      "step": 2325
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.7244608998298645,
+      "learning_rate": 2.1035084657008204e-05,
+      "loss": 1.1204,
+      "step": 2350
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.627005934715271,
+      "learning_rate": 2.090417175772386e-05,
+      "loss": 1.0882,
+      "step": 2375
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.6555240750312805,
+      "learning_rate": 2.0773258858439518e-05,
+      "loss": 1.1137,
+      "step": 2400
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.5681769847869873,
+      "learning_rate": 2.0642345959155177e-05,
+      "loss": 1.0877,
+      "step": 2425
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.7020453810691833,
+      "learning_rate": 2.051143305987083e-05,
+      "loss": 1.0683,
+      "step": 2450
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.569598376750946,
+      "learning_rate": 2.038052016058649e-05,
+      "loss": 1.0832,
+      "step": 2475
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.6652840971946716,
+      "learning_rate": 2.024960726130215e-05,
+      "loss": 1.0934,
+      "step": 2500
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.5610460042953491,
+      "learning_rate": 2.0118694362017804e-05,
+      "loss": 1.0266,
+      "step": 2525
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8069761395454407,
+      "learning_rate": 1.9987781462733462e-05,
+      "loss": 1.1016,
+      "step": 2550
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.5885408520698547,
+      "learning_rate": 1.9856868563449117e-05,
+      "loss": 1.0981,
+      "step": 2575
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.7160201072692871,
+      "learning_rate": 1.9725955664164776e-05,
+      "loss": 1.064,
+      "step": 2600
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.6466575264930725,
+      "learning_rate": 1.9595042764880434e-05,
+      "loss": 1.103,
+      "step": 2625
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.826030969619751,
+      "learning_rate": 1.9464129865596093e-05,
+      "loss": 1.1049,
+      "step": 2650
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.6309208273887634,
+      "learning_rate": 1.9333216966311748e-05,
+      "loss": 1.1226,
+      "step": 2675
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.7945444583892822,
+      "learning_rate": 1.9202304067027403e-05,
+      "loss": 1.0658,
+      "step": 2700
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.5897024869918823,
+      "learning_rate": 1.907139116774306e-05,
+      "loss": 1.1115,
+      "step": 2725
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.6963732242584229,
+      "learning_rate": 1.894047826845872e-05,
+      "loss": 1.0736,
+      "step": 2750
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.6119255423545837,
+      "learning_rate": 1.8809565369174378e-05,
+      "loss": 1.0645,
+      "step": 2775
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.674546480178833,
+      "learning_rate": 1.8678652469890037e-05,
+      "loss": 1.087,
+      "step": 2800
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.6722444891929626,
+      "learning_rate": 1.854773957060569e-05,
+      "loss": 1.0613,
+      "step": 2825
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.6713480949401855,
+      "learning_rate": 1.8416826671321347e-05,
+      "loss": 1.0695,
+      "step": 2850
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.7733056545257568,
+      "learning_rate": 1.8285913772037005e-05,
+      "loss": 1.0502,
+      "step": 2875
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.6311067938804626,
+      "learning_rate": 1.8155000872752664e-05,
+      "loss": 1.056,
+      "step": 2900
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.6068445444107056,
+      "learning_rate": 1.8024087973468322e-05,
+      "loss": 1.0751,
+      "step": 2925
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.6926267743110657,
+      "learning_rate": 1.7893175074183977e-05,
+      "loss": 1.0392,
+      "step": 2950
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6936379075050354,
+      "learning_rate": 1.7762262174899632e-05,
+      "loss": 1.0896,
+      "step": 2975
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.6111378073692322,
+      "learning_rate": 1.763134927561529e-05,
+      "loss": 1.068,
+      "step": 3000
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.5566198229789734,
+      "learning_rate": 1.750043637633095e-05,
+      "loss": 1.094,
+      "step": 3025
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.6551353335380554,
+      "learning_rate": 1.7369523477046604e-05,
+      "loss": 1.0362,
+      "step": 3050
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.702276349067688,
+      "learning_rate": 1.7238610577762263e-05,
+      "loss": 1.0609,
+      "step": 3075
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.5946235060691833,
+      "learning_rate": 1.7107697678477918e-05,
+      "loss": 1.0816,
+      "step": 3100
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.5896125435829163,
+      "learning_rate": 1.6976784779193576e-05,
+      "loss": 1.0511,
+      "step": 3125
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.7790045738220215,
+      "learning_rate": 1.6845871879909235e-05,
+      "loss": 1.0315,
+      "step": 3150
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.6814244985580444,
+      "learning_rate": 1.671495898062489e-05,
+      "loss": 1.0399,
+      "step": 3175
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 0.6677020788192749,
+      "learning_rate": 1.658404608134055e-05,
+      "loss": 1.0403,
+      "step": 3200
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.5795513987541199,
+      "learning_rate": 1.6453133182056207e-05,
+      "loss": 1.076,
+      "step": 3225
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 0.8617599606513977,
+      "learning_rate": 1.6322220282771862e-05,
+      "loss": 1.0515,
+      "step": 3250
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 0.6513819098472595,
+      "learning_rate": 1.619130738348752e-05,
+      "loss": 1.0493,
+      "step": 3275
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 0.7479323148727417,
+      "learning_rate": 1.6060394484203176e-05,
+      "loss": 1.0876,
+      "step": 3300
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 0.718534529209137,
+      "learning_rate": 1.5929481584918834e-05,
+      "loss": 1.029,
+      "step": 3325
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.6990604400634766,
+      "learning_rate": 1.5798568685634493e-05,
+      "loss": 1.015,
+      "step": 3350
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 0.6723743677139282,
+      "learning_rate": 1.566765578635015e-05,
+      "loss": 1.0693,
+      "step": 3375
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.7294295430183411,
+      "learning_rate": 1.5536742887065806e-05,
+      "loss": 1.0229,
+      "step": 3400
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 0.7458708882331848,
+      "learning_rate": 1.540582998778146e-05,
+      "loss": 1.0861,
+      "step": 3425
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.702514111995697,
+      "learning_rate": 1.527491708849712e-05,
+      "loss": 1.0729,
+      "step": 3450
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 0.6749513745307922,
+      "learning_rate": 1.5144004189212778e-05,
+      "loss": 1.0461,
+      "step": 3475
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.6903010010719299,
+      "learning_rate": 1.5013091289928435e-05,
+      "loss": 1.0243,
+      "step": 3500
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.6058205366134644,
+      "learning_rate": 1.4882178390644092e-05,
+      "loss": 1.058,
+      "step": 3525
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.7527756690979004,
+      "learning_rate": 1.475126549135975e-05,
+      "loss": 1.0847,
+      "step": 3550
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 0.7360561490058899,
+      "learning_rate": 1.4620352592075405e-05,
+      "loss": 1.05,
+      "step": 3575
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 0.616054356098175,
+      "learning_rate": 1.4489439692791064e-05,
+      "loss": 1.0508,
+      "step": 3600
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 0.6187878847122192,
+      "learning_rate": 1.435852679350672e-05,
+      "loss": 1.0636,
+      "step": 3625
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.7025036215782166,
+      "learning_rate": 1.4227613894222377e-05,
+      "loss": 1.061,
+      "step": 3650
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 0.6583489179611206,
+      "learning_rate": 1.4096700994938036e-05,
+      "loss": 1.0788,
+      "step": 3675
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 0.6254659295082092,
+      "learning_rate": 1.3965788095653692e-05,
+      "loss": 1.0755,
+      "step": 3700
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.6398507356643677,
+      "learning_rate": 1.383487519636935e-05,
+      "loss": 1.0371,
+      "step": 3725
+    },
+    {
+      "epoch": 3.53,
+      "grad_norm": 0.684704065322876,
+      "learning_rate": 1.3703962297085006e-05,
+      "loss": 1.0261,
+      "step": 3750
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.6592278480529785,
+      "learning_rate": 1.3573049397800665e-05,
+      "loss": 1.0256,
+      "step": 3775
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 0.7980201244354248,
+      "learning_rate": 1.344213649851632e-05,
+      "loss": 1.0478,
+      "step": 3800
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.6509789228439331,
+      "learning_rate": 1.3311223599231978e-05,
+      "loss": 1.0565,
+      "step": 3825
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 0.6620888113975525,
+      "learning_rate": 1.3180310699947637e-05,
+      "loss": 1.0396,
+      "step": 3850
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.9185547828674316,
+      "learning_rate": 1.3049397800663292e-05,
+      "loss": 1.0543,
+      "step": 3875
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.6710821986198425,
+      "learning_rate": 1.291848490137895e-05,
+      "loss": 1.0762,
+      "step": 3900
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.7180879712104797,
+      "learning_rate": 1.2787572002094607e-05,
+      "loss": 1.0178,
+      "step": 3925
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 0.7070004343986511,
+      "learning_rate": 1.2656659102810264e-05,
+      "loss": 1.111,
+      "step": 3950
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.6417202353477478,
+      "learning_rate": 1.2525746203525922e-05,
+      "loss": 1.0187,
+      "step": 3975
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 0.6464525461196899,
+      "learning_rate": 1.2394833304241579e-05,
+      "loss": 1.0538,
+      "step": 4000
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 0.7412322759628296,
+      "learning_rate": 1.2263920404957236e-05,
+      "loss": 0.9896,
+      "step": 4025
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 0.6961266398429871,
+      "learning_rate": 1.2133007505672892e-05,
+      "loss": 1.038,
+      "step": 4050
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.6745458245277405,
+      "learning_rate": 1.2002094606388551e-05,
+      "loss": 1.0348,
+      "step": 4075
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 0.7007986307144165,
+      "learning_rate": 1.1871181707104206e-05,
+      "loss": 1.056,
+      "step": 4100
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.6684093475341797,
+      "learning_rate": 1.1740268807819864e-05,
+      "loss": 1.0506,
+      "step": 4125
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 0.6373914480209351,
+      "learning_rate": 1.1609355908535521e-05,
+      "loss": 1.0317,
+      "step": 4150
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.6588457822799683,
+      "learning_rate": 1.1478443009251178e-05,
+      "loss": 1.0408,
+      "step": 4175
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.6651216745376587,
+      "learning_rate": 1.1347530109966836e-05,
+      "loss": 1.0409,
+      "step": 4200
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.6777089834213257,
+      "learning_rate": 1.1216617210682492e-05,
+      "loss": 1.0415,
+      "step": 4225
+    },
+    {
+      "epoch": 4.01,
+      "grad_norm": 0.5962642431259155,
+      "learning_rate": 1.108570431139815e-05,
+      "loss": 1.0276,
+      "step": 4250
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 0.7103810906410217,
+      "learning_rate": 1.0954791412113807e-05,
+      "loss": 1.0398,
+      "step": 4275
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 0.6657726764678955,
+      "learning_rate": 1.0823878512829464e-05,
+      "loss": 1.0295,
+      "step": 4300
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.6180024147033691,
+      "learning_rate": 1.0692965613545122e-05,
+      "loss": 1.0673,
+      "step": 4325
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 0.6927649974822998,
+      "learning_rate": 1.0562052714260779e-05,
+      "loss": 1.006,
+      "step": 4350
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.6404564380645752,
+      "learning_rate": 1.0431139814976436e-05,
+      "loss": 1.0415,
+      "step": 4375
+    },
+    {
+      "epoch": 4.15,
+      "grad_norm": 0.7053262591362,
+      "learning_rate": 1.0300226915692092e-05,
+      "loss": 0.9987,
+      "step": 4400
+    },
+    {
+      "epoch": 4.17,
+      "grad_norm": 0.6685893535614014,
+      "learning_rate": 1.0169314016407751e-05,
+      "loss": 1.0407,
+      "step": 4425
+    },
+    {
+      "epoch": 4.19,
+      "grad_norm": 0.7120438814163208,
+      "learning_rate": 1.0038401117123408e-05,
+      "loss": 1.1023,
+      "step": 4450
+    },
+    {
+      "epoch": 4.22,
+      "grad_norm": 0.765691876411438,
+      "learning_rate": 9.907488217839064e-06,
+      "loss": 1.061,
+      "step": 4475
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.7191650867462158,
+      "learning_rate": 9.776575318554723e-06,
+      "loss": 1.0052,
+      "step": 4500
+    },
+    {
+      "epoch": 4.26,
+      "grad_norm": 0.6924612522125244,
+      "learning_rate": 9.645662419270378e-06,
+      "loss": 1.028,
+      "step": 4525
+    },
+    {
+      "epoch": 4.29,
+      "grad_norm": 0.7597302198410034,
+      "learning_rate": 9.514749519986036e-06,
+      "loss": 1.0309,
+      "step": 4550
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 0.7024239301681519,
+      "learning_rate": 9.383836620701693e-06,
+      "loss": 1.0261,
+      "step": 4575
+    },
+    {
+      "epoch": 4.34,
+      "grad_norm": 0.7462353706359863,
+      "learning_rate": 9.25292372141735e-06,
+      "loss": 1.0323,
+      "step": 4600
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 0.6952032446861267,
+      "learning_rate": 9.122010822133008e-06,
+      "loss": 1.044,
+      "step": 4625
+    },
+    {
+      "epoch": 4.38,
+      "grad_norm": 0.7031837701797485,
+      "learning_rate": 8.991097922848665e-06,
+      "loss": 0.9975,
+      "step": 4650
+    },
+    {
+      "epoch": 4.41,
+      "grad_norm": 0.6907106041908264,
+      "learning_rate": 8.860185023564322e-06,
+      "loss": 1.0763,
+      "step": 4675
+    },
+    {
+      "epoch": 4.43,
+      "grad_norm": 0.6010780334472656,
+      "learning_rate": 8.729272124279979e-06,
+      "loss": 0.9934,
+      "step": 4700
+    },
+    {
+      "epoch": 4.45,
+      "grad_norm": 0.6455862522125244,
+      "learning_rate": 8.598359224995637e-06,
+      "loss": 1.051,
+      "step": 4725
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.6011804342269897,
+      "learning_rate": 8.467446325711294e-06,
+      "loss": 1.0386,
+      "step": 4750
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.7045350074768066,
+      "learning_rate": 8.33653342642695e-06,
+      "loss": 1.051,
+      "step": 4775
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 0.6799806356430054,
+      "learning_rate": 8.20562052714261e-06,
+      "loss": 1.0509,
+      "step": 4800
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 0.6759226322174072,
+      "learning_rate": 8.074707627858264e-06,
+      "loss": 0.983,
+      "step": 4825
+    },
+    {
+      "epoch": 4.57,
+      "grad_norm": 0.6579796671867371,
+      "learning_rate": 7.943794728573923e-06,
+      "loss": 1.0901,
+      "step": 4850
+    },
+    {
+      "epoch": 4.59,
+      "grad_norm": 0.6630005240440369,
+      "learning_rate": 7.812881829289578e-06,
+      "loss": 1.0501,
+      "step": 4875
+    },
+    {
+      "epoch": 4.62,
+      "grad_norm": 0.693554699420929,
+      "learning_rate": 7.681968930005236e-06,
+      "loss": 1.0399,
+      "step": 4900
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.6797517538070679,
+      "learning_rate": 7.551056030720894e-06,
+      "loss": 1.062,
+      "step": 4925
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 0.671291172504425,
+      "learning_rate": 7.420143131436551e-06,
+      "loss": 1.0045,
+      "step": 4950
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.7400732040405273,
+      "learning_rate": 7.2892302321522084e-06,
+      "loss": 1.041,
+      "step": 4975
+    },
+    {
+      "epoch": 4.71,
+      "grad_norm": 0.5939465165138245,
+      "learning_rate": 7.158317332867866e-06,
+      "loss": 1.0551,
+      "step": 5000
+    },
+    {
+      "epoch": 4.74,
+      "grad_norm": 0.6042287349700928,
+      "learning_rate": 7.027404433583523e-06,
+      "loss": 1.0298,
+      "step": 5025
+    },
+    {
+      "epoch": 4.76,
+      "grad_norm": 0.6053622961044312,
+      "learning_rate": 6.89649153429918e-06,
+      "loss": 1.0218,
+      "step": 5050
+    },
+    {
+      "epoch": 4.78,
+      "grad_norm": 0.6911068558692932,
+      "learning_rate": 6.77081515098621e-06,
+      "loss": 1.0442,
+      "step": 5075
+    },
+    {
+      "epoch": 4.81,
+      "grad_norm": 0.6786155104637146,
+      "learning_rate": 6.639902251701868e-06,
+      "loss": 1.0321,
+      "step": 5100
+    },
+    {
+      "epoch": 4.83,
+      "grad_norm": 0.6624850034713745,
+      "learning_rate": 6.508989352417526e-06,
+      "loss": 1.0696,
+      "step": 5125
+    },
+    {
+      "epoch": 4.85,
+      "grad_norm": 0.850053071975708,
+      "learning_rate": 6.378076453133182e-06,
+      "loss": 0.9769,
+      "step": 5150
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.8631001710891724,
+      "learning_rate": 6.247163553848839e-06,
+      "loss": 0.9791,
+      "step": 5175
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.6453446745872498,
+      "learning_rate": 6.116250654564497e-06,
+      "loss": 1.035,
+      "step": 5200
+    },
+    {
+      "epoch": 4.92,
+      "grad_norm": 0.6186447739601135,
+      "learning_rate": 5.9853377552801536e-06,
+      "loss": 1.0209,
+      "step": 5225
+    },
+    {
+      "epoch": 4.95,
+      "grad_norm": 0.6838425397872925,
+      "learning_rate": 5.854424855995811e-06,
+      "loss": 0.9938,
+      "step": 5250
+    },
+    {
+      "epoch": 4.97,
+      "grad_norm": 0.6573156118392944,
+      "learning_rate": 5.723511956711468e-06,
+      "loss": 1.0532,
+      "step": 5275
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6593102216720581,
+      "learning_rate": 5.592599057427126e-06,
+      "loss": 0.9892,
+      "step": 5300
+    },
+    {
+      "epoch": 5.02,
+      "grad_norm": 0.6164034605026245,
+      "learning_rate": 5.461686158142782e-06,
+      "loss": 1.0142,
+      "step": 5325
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 0.5685546398162842,
+      "learning_rate": 5.330773258858439e-06,
+      "loss": 1.0124,
+      "step": 5350
+    },
+    {
+      "epoch": 5.07,
+      "grad_norm": 0.718358039855957,
+      "learning_rate": 5.199860359574097e-06,
+      "loss": 1.036,
+      "step": 5375
+    },
+    {
+      "epoch": 5.09,
+      "grad_norm": 0.7039633989334106,
+      "learning_rate": 5.068947460289754e-06,
+      "loss": 0.9901,
+      "step": 5400
+    },
+    {
+      "epoch": 5.11,
+      "grad_norm": 0.7492026090621948,
+      "learning_rate": 4.938034561005411e-06,
+      "loss": 1.0949,
+      "step": 5425
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 0.7225030064582825,
+      "learning_rate": 4.807121661721069e-06,
+      "loss": 0.9975,
+      "step": 5450
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 0.7279338240623474,
+      "learning_rate": 4.6762087624367256e-06,
+      "loss": 1.0505,
+      "step": 5475
+    },
+    {
+      "epoch": 5.18,
+      "grad_norm": 0.5847637057304382,
+      "learning_rate": 4.545295863152382e-06,
+      "loss": 1.0111,
+      "step": 5500
+    },
+    {
+      "epoch": 5.21,
+      "grad_norm": 0.647482693195343,
+      "learning_rate": 4.41438296386804e-06,
+      "loss": 1.0477,
+      "step": 5525
+    },
+    {
+      "epoch": 5.23,
+      "grad_norm": 0.6671623587608337,
+      "learning_rate": 4.283470064583698e-06,
+      "loss": 1.0096,
+      "step": 5550
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 0.7235545516014099,
+      "learning_rate": 4.152557165299354e-06,
+      "loss": 1.0466,
+      "step": 5575
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.7705885767936707,
+      "learning_rate": 4.021644266015012e-06,
+      "loss": 1.005,
+      "step": 5600
+    },
+    {
+      "epoch": 5.3,
+      "grad_norm": 0.6789776682853699,
+      "learning_rate": 3.890731366730669e-06,
+      "loss": 1.0132,
+      "step": 5625
+    },
+    {
+      "epoch": 5.33,
+      "grad_norm": 0.6266222596168518,
+      "learning_rate": 3.7598184674463255e-06,
+      "loss": 1.053,
+      "step": 5650
+    },
+    {
+      "epoch": 5.35,
+      "grad_norm": 0.6509959697723389,
+      "learning_rate": 3.628905568161983e-06,
+      "loss": 1.0416,
+      "step": 5675
+    },
+    {
+      "epoch": 5.37,
+      "grad_norm": 0.6754451394081116,
+      "learning_rate": 3.4979926688776404e-06,
+      "loss": 1.0234,
+      "step": 5700
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.6019960045814514,
+      "learning_rate": 3.367079769593297e-06,
+      "loss": 1.024,
+      "step": 5725
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.6941302418708801,
+      "learning_rate": 3.2361668703089548e-06,
+      "loss": 1.0429,
+      "step": 5750
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.7364933490753174,
+      "learning_rate": 3.1052539710246115e-06,
+      "loss": 0.9956,
+      "step": 5775
+    },
+    {
+      "epoch": 5.47,
+      "grad_norm": 0.7257634401321411,
+      "learning_rate": 2.9743410717402687e-06,
+      "loss": 1.0185,
+      "step": 5800
+    },
+    {
+      "epoch": 5.49,
+      "grad_norm": 0.7992274761199951,
+      "learning_rate": 2.8434281724559264e-06,
+      "loss": 1.0608,
+      "step": 5825
+    },
+    {
+      "epoch": 5.51,
+      "grad_norm": 0.6821667551994324,
+      "learning_rate": 2.7177517891429567e-06,
+      "loss": 0.98,
+      "step": 5850
+    },
+    {
+      "epoch": 5.54,
+      "grad_norm": 0.8012374043464661,
+      "learning_rate": 2.5868388898586143e-06,
+      "loss": 1.0294,
+      "step": 5875
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 0.6576132774353027,
+      "learning_rate": 2.4559259905742715e-06,
+      "loss": 1.0476,
+      "step": 5900
+    },
+    {
+      "epoch": 5.58,
+      "grad_norm": 0.6078372597694397,
+      "learning_rate": 2.3250130912899283e-06,
+      "loss": 1.0589,
+      "step": 5925
+    },
+    {
+      "epoch": 5.61,
+      "grad_norm": 0.7334024906158447,
+      "learning_rate": 2.194100192005586e-06,
+      "loss": 1.0186,
+      "step": 5950
+    },
+    {
+      "epoch": 5.63,
+      "grad_norm": 0.6493911743164062,
+      "learning_rate": 2.0631872927212427e-06,
+      "loss": 1.0143,
+      "step": 5975
+    },
+    {
+      "epoch": 5.66,
+      "grad_norm": 0.8003960251808167,
+      "learning_rate": 1.9322743934369e-06,
+      "loss": 1.0243,
+      "step": 6000
+    },
+    {
+      "epoch": 5.68,
+      "grad_norm": 0.7148457169532776,
+      "learning_rate": 1.801361494152557e-06,
+      "loss": 1.0195,
+      "step": 6025
+    },
+    {
+      "epoch": 5.7,
+      "grad_norm": 0.6924374103546143,
+      "learning_rate": 1.6704485948682145e-06,
+      "loss": 1.0034,
+      "step": 6050
+    },
+    {
+      "epoch": 5.73,
+      "grad_norm": 0.7333653569221497,
+      "learning_rate": 1.5395356955838715e-06,
+      "loss": 1.0448,
+      "step": 6075
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 0.7860874533653259,
+      "learning_rate": 1.4086227962995287e-06,
+      "loss": 1.0205,
+      "step": 6100
+    },
+    {
+      "epoch": 5.77,
+      "grad_norm": 0.6410927176475525,
+      "learning_rate": 1.2777098970151859e-06,
+      "loss": 0.9727,
+      "step": 6125
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.6415342688560486,
+      "learning_rate": 1.146796997730843e-06,
+      "loss": 1.0137,
+      "step": 6150
+    },
+    {
+      "epoch": 5.82,
+      "grad_norm": 0.6379125118255615,
+      "learning_rate": 1.0158840984465003e-06,
+      "loss": 1.0076,
+      "step": 6175
+    },
+    {
+      "epoch": 5.84,
+      "grad_norm": 0.6775155663490295,
+      "learning_rate": 8.849711991621574e-07,
+      "loss": 1.0328,
+      "step": 6200
+    },
+    {
+      "epoch": 5.87,
+      "grad_norm": 0.614631712436676,
+      "learning_rate": 7.540582998778147e-07,
+      "loss": 0.9982,
+      "step": 6225
+    },
+    {
+      "epoch": 5.89,
+      "grad_norm": 0.7537350058555603,
+      "learning_rate": 6.231454005934718e-07,
+      "loss": 1.0465,
+      "step": 6250
+    },
+    {
+      "epoch": 5.91,
+      "grad_norm": 0.6336871385574341,
+      "learning_rate": 4.92232501309129e-07,
+      "loss": 1.0098,
+      "step": 6275
+    },
+    {
+      "epoch": 5.94,
+      "grad_norm": 0.7179773449897766,
+      "learning_rate": 3.613196020247862e-07,
+      "loss": 1.0218,
+      "step": 6300
+    },
+    {
+      "epoch": 5.96,
+      "grad_norm": 0.6881077289581299,
+      "learning_rate": 2.3040670274044336e-07,
+      "loss": 1.0088,
+      "step": 6325
+    },
+    {
+      "epoch": 5.98,
+      "grad_norm": 0.6044571399688721,
+      "learning_rate": 9.949380345610055e-08,
+      "loss": 1.0526,
+      "step": 6350
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 6366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1.3676194390081536e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6366/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4c22b78d71f5b49da24429145951afb9dfa28993888fc6029bab482e08dde7
+size 5048

runs/Mar26_19-46-04_r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1/events.out.tfevents.1711482377.r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1.59.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df1b2eb4b6b1c5e65c95047a65a32800a25f184c5e1ec19d1a16ee1d10e1f79
-size 58793
+oid sha256:c5cbd21cf48bf92934847ca824792e038ca23fd8a2bb272a7948934f48c2feca
+size 59358

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4c22b78d71f5b49da24429145951afb9dfa28993888fc6029bab482e08dde7
+size 5048

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "openai-community/gpt2",
+    "project_name": "autotraincom-gtp2-ep2-bs2-sft-600T",
+    "data_path": "autotraincom-gtp2-ep2-bs2-sft-600T/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 6,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "Jamesb1974/autotraincom-gtp2-ep2-bs2-sft-600T",
+    "username": "Jamesb1974"
+}