Upload 19 files

README.md

@@ -0,0 +1,63 @@
+---
+license: llama2
+base_model: TheBloke/Llama-2-7B-GPTQ
+tags:
+- generated_from_trainer
+model-index:
+- name: gptq-small-nids-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# gptq-small-nids-out
+
+This model is a fine-tuned version of [TheBloke/Llama-2-7B-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-GPTQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0027
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.7e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0028        | 1.0   | 371  | 0.0027          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c97df72b52c910c995b44cc7244f338a09b2218be6ede1c4f3ccc163c21728b
+size 33646413

checkpoint-371/README.md

@@ -0,0 +1,226 @@
+---
+library_name: peft
+base_model: TheBloke/Llama-2-7B-GPTQ
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 4
+- tokenizer: None
+- dataset: None
+- group_size: 128
+- damp_percent: 0.01
+- desc_act: False
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: False
+- model_seqlen: None
+- block_name_to_quantize: None
+- module_name_preceding_first_block: None
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

checkpoint-371/adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-371/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c97df72b52c910c995b44cc7244f338a09b2218be6ede1c4f3ccc163c21728b
+size 33646413

checkpoint-371/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb43403cfbb1109a098075a858073e303f577349e6bd3e49ba5427fb6135d00
+size 67323205

checkpoint-371/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5ee3732dff954ad7ea41db595d78b727cbd8bf29185d51be3bb90ff95cdc9a
+size 17655

checkpoint-371/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b958143ecfeef80fa7d9537dea1fe6f5e5f2a53a836306881a6b806dffe99dae
+size 17655

checkpoint-371/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b2f0a767703037fc989da759a4ac6765f659abe387e669596bb66fb2e7006a
+size 17655

checkpoint-371/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f6590950ac33ec8dacf0ef35f376ff34518940844eddb17511250c6ecbfbad
+size 17655

checkpoint-371/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee62a9e4560eb1ecbb7cf6bc92c71370f025e7640fd733939a3f74258fd7c6b1
+size 627

checkpoint-371/trainer_state.json

@@ -0,0 +1,2253 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 371,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.7000000000000001e-09,
+      "loss": 5.7677,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.8000000000000005e-09,
+      "loss": 5.78,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5299999999999998e-08,
+      "loss": 5.7759,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7200000000000002e-08,
+      "loss": 5.7423,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.250000000000001e-08,
+      "loss": 5.7502,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.119999999999999e-08,
+      "loss": 5.2505,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.330000000000001e-08,
+      "loss": 5.7644,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0880000000000001e-07,
+      "loss": 5.7474,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.377e-07,
+      "loss": 5.2204,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7000000000000004e-07,
+      "loss": 5.7827,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.057e-07,
+      "loss": 5.7714,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4479999999999997e-07,
+      "loss": 5.7684,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.8730000000000004e-07,
+      "loss": 5.7647,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.3320000000000005e-07,
+      "loss": 5.7798,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.825e-07,
+      "loss": 5.7671,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.3520000000000003e-07,
+      "loss": 5.7531,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.913000000000001e-07,
+      "loss": 5.7502,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.508e-07,
+      "loss": 5.7472,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.137e-07,
+      "loss": 5.2499,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.800000000000002e-07,
+      "loss": 5.7571,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.496999999999999e-07,
+      "loss": 5.7718,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.228e-07,
+      "loss": 5.7527,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.993e-07,
+      "loss": 5.7096,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.791999999999999e-07,
+      "loss": 5.7555,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.0625e-06,
+      "loss": 5.7236,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1492000000000002e-06,
+      "loss": 5.7228,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2393000000000001e-06,
+      "loss": 5.2193,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3328000000000002e-06,
+      "loss": 5.7129,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4296999999999998e-06,
+      "loss": 5.7019,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.53e-06,
+      "loss": 5.6959,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6337000000000001e-06,
+      "loss": 5.668,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7408000000000001e-06,
+      "loss": 5.6676,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8513000000000002e-06,
+      "loss": 5.6193,
+      "step": 33
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9652000000000003e-06,
+      "loss": 5.6317,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0824999999999995e-06,
+      "loss": 5.0984,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.2032e-06,
+      "loss": 5.5622,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.3272999999999997e-06,
+      "loss": 5.5116,
+      "step": 37
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.4548e-06,
+      "loss": 5.0124,
+      "step": 38
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.5857e-06,
+      "loss": 5.4656,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.7200000000000006e-06,
+      "loss": 5.4529,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8576999999999993e-06,
+      "loss": 4.9268,
+      "step": 41
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9987999999999996e-06,
+      "loss": 5.3852,
+      "step": 42
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.1432999999999996e-06,
+      "loss": 4.8709,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.2912e-06,
+      "loss": 5.2857,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.4425e-06,
+      "loss": 5.2313,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.5972e-06,
+      "loss": 5.187,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.7553e-06,
+      "loss": 4.7334,
+      "step": 47
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.9167999999999995e-06,
+      "loss": 5.1158,
+      "step": 48
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.081699999999999e-06,
+      "loss": 5.0368,
+      "step": 49
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.25e-06,
+      "loss": 5.0124,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.4216999999999995e-06,
+      "loss": 4.9181,
+      "step": 51
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.596800000000001e-06,
+      "loss": 4.8915,
+      "step": 52
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.775300000000001e-06,
+      "loss": 4.7926,
+      "step": 53
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.957200000000001e-06,
+      "loss": 4.7338,
+      "step": 54
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.142500000000001e-06,
+      "loss": 4.6507,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.331200000000001e-06,
+      "loss": 4.5809,
+      "step": 56
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.523299999999999e-06,
+      "loss": 4.4997,
+      "step": 57
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.718799999999999e-06,
+      "loss": 4.4298,
+      "step": 58
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.917699999999999e-06,
+      "loss": 4.3173,
+      "step": 59
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.12e-06,
+      "loss": 3.936,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.325699999999999e-06,
+      "loss": 4.1268,
+      "step": 61
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 6.5348000000000005e-06,
+      "loss": 4.0394,
+      "step": 62
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 6.747300000000001e-06,
+      "loss": 3.9413,
+      "step": 63
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 6.9632000000000005e-06,
+      "loss": 3.814,
+      "step": 64
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.1825e-06,
+      "loss": 3.4873,
+      "step": 65
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.405200000000001e-06,
+      "loss": 3.5816,
+      "step": 66
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.631300000000001e-06,
+      "loss": 3.486,
+      "step": 67
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.860800000000001e-06,
+      "loss": 3.3758,
+      "step": 68
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.093699999999998e-06,
+      "loss": 3.2212,
+      "step": 69
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.329999999999998e-06,
+      "loss": 3.0783,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.5697e-06,
+      "loss": 2.9547,
+      "step": 71
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.8128e-06,
+      "loss": 2.7953,
+      "step": 72
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.059299999999998e-06,
+      "loss": 2.6658,
+      "step": 73
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.309199999999999e-06,
+      "loss": 2.4552,
+      "step": 74
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.5625e-06,
+      "loss": 2.301,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.8192e-06,
+      "loss": 2.2726,
+      "step": 76
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.00793e-05,
+      "loss": 2.1129,
+      "step": 77
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.03428e-05,
+      "loss": 1.9555,
+      "step": 78
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.0609700000000001e-05,
+      "loss": 1.8066,
+      "step": 79
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.0880000000000003e-05,
+      "loss": 1.6639,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.1153700000000001e-05,
+      "loss": 1.5209,
+      "step": 81
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.1430799999999997e-05,
+      "loss": 1.4038,
+      "step": 82
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.17113e-05,
+      "loss": 1.2361,
+      "step": 83
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.1995199999999998e-05,
+      "loss": 1.0943,
+      "step": 84
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.2282499999999998e-05,
+      "loss": 0.9655,
+      "step": 85
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.2573199999999998e-05,
+      "loss": 0.8187,
+      "step": 86
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.28673e-05,
+      "loss": 0.8124,
+      "step": 87
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.31648e-05,
+      "loss": 0.7347,
+      "step": 88
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.34657e-05,
+      "loss": 0.5575,
+      "step": 89
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.377e-05,
+      "loss": 0.4802,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.40777e-05,
+      "loss": 0.4116,
+      "step": 91
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.43888e-05,
+      "loss": 0.494,
+      "step": 92
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.4703300000000002e-05,
+      "loss": 0.2956,
+      "step": 93
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.50212e-05,
+      "loss": 0.2433,
+      "step": 94
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.53425e-05,
+      "loss": 0.397,
+      "step": 95
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.5667199999999998e-05,
+      "loss": 0.1521,
+      "step": 96
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.59953e-05,
+      "loss": 0.1133,
+      "step": 97
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6326799999999998e-05,
+      "loss": 0.084,
+      "step": 98
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.66617e-05,
+      "loss": 0.0583,
+      "step": 99
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7e-05,
+      "loss": 0.041,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6999428856511285e-05,
+      "loss": 0.3927,
+      "step": 101
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6997715502799228e-05,
+      "loss": 0.0198,
+      "step": 102
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6994860169115786e-05,
+      "loss": 0.0146,
+      "step": 103
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.699086323917984e-05,
+      "loss": 0.0101,
+      "step": 104
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6985725250125628e-05,
+      "loss": 0.0075,
+      "step": 105
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6979446892430557e-05,
+      "loss": 0.0052,
+      "step": 106
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6972029009822423e-05,
+      "loss": 0.0038,
+      "step": 107
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6963472599166012e-05,
+      "loss": 0.0026,
+      "step": 108
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.695377881032915e-05,
+      "loss": 0.7339,
+      "step": 109
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6942948946028152e-05,
+      "loss": 0.0014,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.693098446165278e-05,
+      "loss": 0.0013,
+      "step": 111
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.691788696507065e-05,
+      "loss": 0.001,
+      "step": 112
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.690365821641114e-05,
+      "loss": 0.0008,
+      "step": 113
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.688830012782888e-05,
+      "loss": 0.0007,
+      "step": 114
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6871814763246757e-05,
+      "loss": 0.0007,
+      "step": 115
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6854204338078574e-05,
+      "loss": 0.0006,
+      "step": 116
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.683547121893131e-05,
+      "loss": 0.7544,
+      "step": 117
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6815617923287087e-05,
+      "loss": 0.0004,
+      "step": 118
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.679464711916486e-05,
+      "loss": 0.6893,
+      "step": 119
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6772561624761852e-05,
+      "loss": 0.0019,
+      "step": 120
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6749364408074844e-05,
+      "loss": 0.0265,
+      "step": 121
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6725058586501322e-05,
+      "loss": 0.001,
+      "step": 122
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6699647426420506e-05,
+      "loss": 0.0034,
+      "step": 123
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6673134342754424e-05,
+      "loss": 0.0009,
+      "step": 124
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.6645522898508988e-05,
+      "loss": 0.5373,
+      "step": 125
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.661681680429516e-05,
+      "loss": 0.0012,
+      "step": 126
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.6587019917830303e-05,
+      "loss": 0.0016,
+      "step": 127
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6556136243419757e-05,
+      "loss": 0.0019,
+      "step": 128
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6524169931418705e-05,
+      "loss": 0.0019,
+      "step": 129
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6491125277674436e-05,
+      "loss": 0.0018,
+      "step": 130
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6457006722949026e-05,
+      "loss": 0.0016,
+      "step": 131
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6421818852322558e-05,
+      "loss": 0.0012,
+      "step": 132
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6385566394576964e-05,
+      "loss": 0.0008,
+      "step": 133
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6348254221560524e-05,
+      "loss": 0.5306,
+      "step": 134
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.630988734753316e-05,
+      "loss": 0.0007,
+      "step": 135
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.627047092849258e-05,
+      "loss": 0.0007,
+      "step": 136
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.62300102614814e-05,
+      "loss": 0.0008,
+      "step": 137
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6188510783875267e-05,
+      "loss": 0.0009,
+      "step": 138
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6145978072652165e-05,
+      "loss": 0.0007,
+      "step": 139
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6102417843642925e-05,
+      "loss": 0.0008,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6057835950763122e-05,
+      "loss": 0.5449,
+      "step": 141
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.601223838522637e-05,
+      "loss": 0.001,
+      "step": 142
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5965631274739165e-05,
+      "loss": 0.0011,
+      "step": 143
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5918020882677436e-05,
+      "loss": 0.0015,
+      "step": 144
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5869413607244815e-05,
+      "loss": 0.0015,
+      "step": 145
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.58198159806128e-05,
+      "loss": 0.0016,
+      "step": 146
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.5769234668042916e-05,
+      "loss": 0.0015,
+      "step": 147
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.5717676466991014e-05,
+      "loss": 0.4688,
+      "step": 148
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.566514830619375e-05,
+      "loss": 0.0015,
+      "step": 149
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.561165724473748e-05,
+      "loss": 0.0019,
+      "step": 150
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.555721047110961e-05,
+      "loss": 0.0021,
+      "step": 151
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.5501815302232545e-05,
+      "loss": 0.0021,
+      "step": 152
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.5445479182480406e-05,
+      "loss": 0.0017,
+      "step": 153
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.5388209682678602e-05,
+      "loss": 0.0015,
+      "step": 154
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.53300144990864e-05,
+      "loss": 0.0012,
+      "step": 155
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.5270901452362678e-05,
+      "loss": 0.0008,
+      "step": 156
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.5210878486514891e-05,
+      "loss": 0.0006,
+      "step": 157
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.5149953667831547e-05,
+      "loss": 0.0004,
+      "step": 158
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.5088135183798168e-05,
+      "loss": 0.0003,
+      "step": 159
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.5025431341997022e-05,
+      "loss": 0.0002,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.4961850568990687e-05,
+      "loss": 0.0002,
+      "step": 161
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.4897401409189638e-05,
+      "loss": 0.0001,
+      "step": 162
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.4832092523703991e-05,
+      "loss": 0.0001,
+      "step": 163
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.476593268917955e-05,
+      "loss": 0.0001,
+      "step": 164
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.4698930796618369e-05,
+      "loss": 0.0001,
+      "step": 165
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.4631095850183895e-05,
+      "loss": 0.0001,
+      "step": 166
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.4562436965990942e-05,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.4492963370880608e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.44226844011803e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.4351609501449064e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.4279748223208351e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.420711022365844e-05,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4133705264380616e-05,
+      "loss": 0.0,
+      "step": 173
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4059543210025357e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.3984634026986654e-05,
+      "loss": 0.9154,
+      "step": 175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.3908987782062657e-05,
+      "loss": 0.0,
+      "step": 176
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.3832614641102833e-05,
+      "loss": 0.8321,
+      "step": 177
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.3755524867641806e-05,
+      "loss": 0.0001,
+      "step": 178
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.3677728821520092e-05,
+      "loss": 0.0001,
+      "step": 179
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3599236957491844e-05,
+      "loss": 0.6109,
+      "step": 180
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3520059823819908e-05,
+      "loss": 0.0005,
+      "step": 181
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3440208060858246e-05,
+      "loss": 0.0009,
+      "step": 182
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3359692399622025e-05,
+      "loss": 0.0015,
+      "step": 183
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3278523660345522e-05,
+      "loss": 0.0025,
+      "step": 184
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.319671275102801e-05,
+      "loss": 0.0031,
+      "step": 185
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.3114270665967886e-05,
+      "loss": 0.0039,
+      "step": 186
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.303120848428516e-05,
+      "loss": 0.0038,
+      "step": 187
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.2947537368432597e-05,
+      "loss": 0.3774,
+      "step": 188
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.2863268562695612e-05,
+      "loss": 0.3549,
+      "step": 189
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.277841339168119e-05,
+      "loss": 0.0063,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.2692983258796016e-05,
+      "loss": 0.0081,
+      "step": 191
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2606989644714005e-05,
+      "loss": 0.0086,
+      "step": 192
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2520444105833453e-05,
+      "loss": 0.0078,
+      "step": 193
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.2433358272724008e-05,
+      "loss": 0.0076,
+      "step": 194
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.234574384856368e-05,
+      "loss": 0.0058,
+      "step": 195
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.225761260756609e-05,
+      "loss": 0.3586,
+      "step": 196
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.2168976393398161e-05,
+      "loss": 0.0038,
+      "step": 197
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.2079847117588505e-05,
+      "loss": 0.0035,
+      "step": 198
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1990236757926658e-05,
+      "loss": 0.0029,
+      "step": 199
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1900157356853431e-05,
+      "loss": 0.0025,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1809621019842562e-05,
+      "loss": 0.8239,
+      "step": 201
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.1718639913773905e-05,
+      "loss": 0.0019,
+      "step": 202
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1627226265298363e-05,
+      "loss": 0.0021,
+      "step": 203
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1535392359194778e-05,
+      "loss": 0.0018,
+      "step": 204
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.1443150536719041e-05,
+      "loss": 0.4161,
+      "step": 205
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1350513193945574e-05,
+      "loss": 0.0022,
+      "step": 206
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1257492780101466e-05,
+      "loss": 0.0023,
+      "step": 207
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1164101795893467e-05,
+      "loss": 0.0024,
+      "step": 208
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1070352791828055e-05,
+      "loss": 0.0024,
+      "step": 209
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.097625836652482e-05,
+      "loss": 0.0027,
+      "step": 210
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0881831165023366e-05,
+      "loss": 0.0024,
+      "step": 211
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0787083877084003e-05,
+      "loss": 0.0022,
+      "step": 212
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.0692029235482393e-05,
+      "loss": 0.4213,
+      "step": 213
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.059668001429845e-05,
+      "loss": 0.4007,
+      "step": 214
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0501049027199663e-05,
+      "loss": 0.7753,
+      "step": 215
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0405149125719116e-05,
+      "loss": 0.004,
+      "step": 216
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0308993197528407e-05,
+      "loss": 0.345,
+      "step": 217
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.021259416470572e-05,
+      "loss": 0.0063,
+      "step": 218
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.0115964981999271e-05,
+      "loss": 0.0091,
+      "step": 219
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.0019118635086362e-05,
+      "loss": 0.0115,
+      "step": 220
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.922068138828272e-06,
+      "loss": 0.0113,
+      "step": 221
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.82482653552124e-06,
+      "loss": 0.0098,
+      "step": 222
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.727406893143751e-06,
+      "loss": 0.0091,
+      "step": 223
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.629822303600373e-06,
+      "loss": 0.3068,
+      "step": 224
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.532085880962384e-06,
+      "loss": 0.0076,
+      "step": 225
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.434210759705405e-06,
+      "loss": 0.3079,
+      "step": 226
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.336210092944308e-06,
+      "loss": 0.3096,
+      "step": 227
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.238097050665617e-06,
+      "loss": 0.0079,
+      "step": 228
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.139884817957625e-06,
+      "loss": 0.0084,
+      "step": 229
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.041586593238503e-06,
+      "loss": 0.0088,
+      "step": 230
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.943215586482603e-06,
+      "loss": 0.0087,
+      "step": 231
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.844785017445214e-06,
+      "loss": 0.0074,
+      "step": 232
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.74630811388601e-06,
+      "loss": 0.0065,
+      "step": 233
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.647798109791404e-06,
+      "loss": 0.0053,
+      "step": 234
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.549268243596078e-06,
+      "loss": 0.0049,
+      "step": 235
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.450731756403924e-06,
+      "loss": 0.0038,
+      "step": 236
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.352201890208596e-06,
+      "loss": 0.0032,
+      "step": 237
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.253691886113991e-06,
+      "loss": 0.0023,
+      "step": 238
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.155214982554786e-06,
+      "loss": 0.002,
+      "step": 239
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.056784413517399e-06,
+      "loss": 0.0016,
+      "step": 240
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.9584134067615e-06,
+      "loss": 0.0012,
+      "step": 241
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.860115182042377e-06,
+      "loss": 0.0009,
+      "step": 242
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.761902949334383e-06,
+      "loss": 0.0007,
+      "step": 243
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.663789907055692e-06,
+      "loss": 0.0006,
+      "step": 244
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.565789240294597e-06,
+      "loss": 0.0005,
+      "step": 245
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.467914119037615e-06,
+      "loss": 0.0004,
+      "step": 246
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.370177696399627e-06,
+      "loss": 0.0004,
+      "step": 247
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.2725931068562485e-06,
+      "loss": 0.0003,
+      "step": 248
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.175173464478762e-06,
+      "loss": 0.0002,
+      "step": 249
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.077931861171728e-06,
+      "loss": 0.5576,
+      "step": 250
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.98088136491364e-06,
+      "loss": 0.0003,
+      "step": 251
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.884035018000732e-06,
+      "loss": 0.0003,
+      "step": 252
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.787405835294282e-06,
+      "loss": 0.0003,
+      "step": 253
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.6910068024715965e-06,
+      "loss": 0.0003,
+      "step": 254
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.594850874280886e-06,
+      "loss": 0.0003,
+      "step": 255
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.498950972800336e-06,
+      "loss": 0.0004,
+      "step": 256
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.403319985701548e-06,
+      "loss": 0.0003,
+      "step": 257
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.307970764517606e-06,
+      "loss": 0.0003,
+      "step": 258
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.212916122915996e-06,
+      "loss": 0.0003,
+      "step": 259
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.118168834976634e-06,
+      "loss": 0.0003,
+      "step": 260
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.023741633475184e-06,
+      "loss": 0.5394,
+      "step": 261
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.929647208171945e-06,
+      "loss": 0.5343,
+      "step": 262
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.8358982041065366e-06,
+      "loss": 0.0004,
+      "step": 263
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.742507219898535e-06,
+      "loss": 0.0004,
+      "step": 264
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5.649486806054428e-06,
+      "loss": 0.0006,
+      "step": 265
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.5568494632809586e-06,
+      "loss": 0.9567,
+      "step": 266
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.4646076408052225e-06,
+      "loss": 0.0007,
+      "step": 267
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.372773734701639e-06,
+      "loss": 0.0011,
+      "step": 268
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.2813600862260945e-06,
+      "loss": 0.0013,
+      "step": 269
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.190378980157438e-06,
+      "loss": 0.0011,
+      "step": 270
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.099842643146571e-06,
+      "loss": 0.4145,
+      "step": 271
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.009763242073346e-06,
+      "loss": 0.0015,
+      "step": 272
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.920152882411496e-06,
+      "loss": 0.0017,
+      "step": 273
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.831023606601841e-06,
+      "loss": 0.0019,
+      "step": 274
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.7423873924339135e-06,
+      "loss": 0.0023,
+      "step": 275
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.65425615143632e-06,
+      "loss": 0.0024,
+      "step": 276
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.566641727275993e-06,
+      "loss": 0.0024,
+      "step": 277
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.47955589416655e-06,
+      "loss": 0.0026,
+      "step": 278
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.393010355285995e-06,
+      "loss": 0.7237,
+      "step": 279
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.307016741203987e-06,
+      "loss": 0.3495,
+      "step": 280
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.221586608318814e-06,
+      "loss": 0.0034,
+      "step": 281
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.136731437304391e-06,
+      "loss": 0.0037,
+      "step": 282
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.052462631567405e-06,
+      "loss": 0.004,
+      "step": 283
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.968791515714841e-06,
+      "loss": 0.324,
+      "step": 284
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.885729334032118e-06,
+      "loss": 0.0045,
+      "step": 285
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.803287248971989e-06,
+      "loss": 0.0053,
+      "step": 286
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.7214763396544796e-06,
+      "loss": 0.006,
+      "step": 287
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.640307600377974e-06,
+      "loss": 0.303,
+      "step": 288
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.5597919391417568e-06,
+      "loss": 0.0057,
+      "step": 289
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4799401761800915e-06,
+      "loss": 0.0059,
+      "step": 290
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4007630425081546e-06,
+      "loss": 0.0059,
+      "step": 291
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.322271178479911e-06,
+      "loss": 0.0068,
+      "step": 292
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.2444751323581937e-06,
+      "loss": 0.0054,
+      "step": 293
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.1673853588971697e-06,
+      "loss": 0.0054,
+      "step": 294
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.091012217937342e-06,
+      "loss": 0.0048,
+      "step": 295
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.015365973013345e-06,
+      "loss": 0.0051,
+      "step": 296
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.940456789974641e-06,
+      "loss": 0.0049,
+      "step": 297
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.866294735619384e-06,
+      "loss": 0.0054,
+      "step": 298
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.792889776341558e-06,
+      "loss": 0.3087,
+      "step": 299
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.720251776791648e-06,
+      "loss": 0.0037,
+      "step": 300
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.648390498550938e-06,
+      "loss": 0.0036,
+      "step": 301
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.577315598819698e-06,
+      "loss": 0.3172,
+      "step": 302
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.507036629119391e-06,
+      "loss": 0.3122,
+      "step": 303
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.437563034009059e-06,
+      "loss": 0.0034,
+      "step": 304
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.368904149816109e-06,
+      "loss": 0.004,
+      "step": 305
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.3010692033816333e-06,
+      "loss": 0.004,
+      "step": 306
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.2340673108204515e-06,
+      "loss": 0.0038,
+      "step": 307
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.1679074762960097e-06,
+      "loss": 0.3062,
+      "step": 308
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.102598590810361e-06,
+      "loss": 0.0039,
+      "step": 309
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.038149431009313e-06,
+      "loss": 0.0043,
+      "step": 310
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9745686580029813e-06,
+      "loss": 0.0039,
+      "step": 311
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9118648162018354e-06,
+      "loss": 0.004,
+      "step": 312
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.8500463321684535e-06,
+      "loss": 0.0034,
+      "step": 313
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7891215134851086e-06,
+      "loss": 0.0043,
+      "step": 314
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7290985476373226e-06,
+      "loss": 0.0037,
+      "step": 315
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6699855009135987e-06,
+      "loss": 0.0038,
+      "step": 316
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6117903173213991e-06,
+      "loss": 0.3084,
+      "step": 317
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.5545208175195947e-06,
+      "loss": 0.0034,
+      "step": 318
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4981846977674559e-06,
+      "loss": 0.2993,
+      "step": 319
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.442789528890392e-06,
+      "loss": 0.0048,
+      "step": 320
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.3883427552625214e-06,
+      "loss": 0.0036,
+      "step": 321
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.334851693806252e-06,
+      "loss": 0.003,
+      "step": 322
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2823235330089876e-06,
+      "loss": 0.0035,
+      "step": 323
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2307653319570816e-06,
+      "loss": 0.0034,
+      "step": 324
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.180184019387201e-06,
+      "loss": 0.0036,
+      "step": 325
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1305863927551828e-06,
+      "loss": 0.3095,
+      "step": 326
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0819791173225632e-06,
+      "loss": 0.0035,
+      "step": 327
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0343687252608348e-06,
+      "loss": 0.0032,
+      "step": 328
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.877616147736322e-07,
+      "loss": 0.0029,
+      "step": 329
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.42164049236876e-07,
+      "loss": 0.2967,
+      "step": 330
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.975821563570762e-07,
+      "loss": 0.0036,
+      "step": 331
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.540219273478374e-07,
+      "loss": 0.0034,
+      "step": 332
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.114892161247328e-07,
+      "loss": 0.0036,
+      "step": 333
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.699897385185995e-07,
+      "loss": 0.0033,
+      "step": 334
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.295290715074186e-07,
+      "loss": 0.0029,
+      "step": 335
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.901126524668424e-07,
+      "loss": 0.0027,
+      "step": 336
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.51745778439476e-07,
+      "loss": 0.0032,
+      "step": 337
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.144336054230359e-07,
+      "loss": 0.0031,
+      "step": 338
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.781811476774417e-07,
+      "loss": 0.0031,
+      "step": 339
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.429932770509767e-07,
+      "loss": 0.003,
+      "step": 340
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.088747223255645e-07,
+      "loss": 0.0028,
+      "step": 341
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.758300685812951e-07,
+      "loss": 0.3042,
+      "step": 342
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.438637565802444e-07,
+      "loss": 0.0031,
+      "step": 343
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.1298008216969677e-07,
+      "loss": 0.0029,
+      "step": 344
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.8318319570483964e-07,
+      "loss": 0.003,
+      "step": 345
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.544771014910102e-07,
+      "loss": 0.0031,
+      "step": 346
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.268656572455751e-07,
+      "loss": 0.0028,
+      "step": 347
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.003525735794959e-07,
+      "loss": 0.0028,
+      "step": 348
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.749414134986797e-07,
+      "loss": 0.0025,
+      "step": 349
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.506355919251527e-07,
+      "loss": 0.0027,
+      "step": 350
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.2743837523814915e-07,
+      "loss": 0.309,
+      "step": 351
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.053528808351413e-07,
+      "loss": 0.313,
+      "step": 352
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.8438207671291158e-07,
+      "loss": 0.0029,
+      "step": 353
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6452878106868956e-07,
+      "loss": 0.0028,
+      "step": 354
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.4579566192142508e-07,
+      "loss": 0.0027,
+      "step": 355
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.281852367532435e-07,
+      "loss": 0.0032,
+      "step": 356
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1169987217112288e-07,
+      "loss": 0.0029,
+      "step": 357
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.634178358886187e-08,
+      "loss": 0.0029,
+      "step": 358
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.211303492935335e-08,
+      "loss": 0.003,
+      "step": 359
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.90155383472208e-08,
+      "loss": 0.003,
+      "step": 360
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.705105397184973e-08,
+      "loss": 0.3166,
+      "step": 361
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.622118967085098e-08,
+      "loss": 0.0028,
+      "step": 362
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.6527400833985035e-08,
+      "loss": 0.0027,
+      "step": 363
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7970990177575762e-08,
+      "loss": 0.0026,
+      "step": 364
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.055310756944184e-08,
+      "loss": 0.003,
+      "step": 365
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.4274749874372328e-08,
+      "loss": 0.003,
+      "step": 366
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.13676082016046e-09,
+      "loss": 0.3076,
+      "step": 367
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.1398308842146575e-09,
+      "loss": 0.0027,
+      "step": 368
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.284497200773061e-09,
+      "loss": 0.0028,
+      "step": 369
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.711434887160083e-10,
+      "loss": 0.0028,
+      "step": 370
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.0028,
+      "step": 371
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0026911406312137842,
+      "eval_runtime": 1.2764,
+      "eval_samples_per_second": 11.752,
+      "eval_steps_per_second": 3.134,
+      "step": 371
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 371,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 318496730775552.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-371/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4d56f241a2560d0af97f872dca8d7cbee58d237f8fa24d8e9f4ad8c2bc8140
+size 4475

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "TheBloke/Llama-2-7B-GPTQ",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "damp_percent": 0.01,
+    "dataset": null,
+    "desc_act": false,
+    "disable_exllama": true,
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

runs/Nov16_10-22-42_compute-3-6.hamming.cluster/events.out.tfevents.1700158964.compute-3-6.hamming.cluster.84949.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b58d0f1a5cea41a8f57e6820d1f6f4f59033f814a111fff3c49672e87347f6e
+size 63604

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}