Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8345c2bf60f6a18dc631fcbdf28bf0efc2234e3f8b8237d8a3bbdec7524babc
+size 27308941

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-31260/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: bn22/Mistral-7B-Instruct-v0.1-sharded
+---
+
+# 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: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-31260/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-31260/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8345c2bf60f6a18dc631fcbdf28bf0efc2234e3f8b8237d8a3bbdec7524babc
+size 27308941

checkpoint-31260/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-31260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117f2b9bfba59d93f7c7281e1e1ebaa4adbe184421e340f2cb336356c0ef28f5
+size 54633541

checkpoint-31260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211a72378786e31fb9757a4393e7d4395079c1749717fae09b8665064c433f79
+size 14575

checkpoint-31260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557bc69e57c83f26ba009569bb2e0852d0722c16428034ff4492cd462efe18b0
+size 627

checkpoint-31260/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-31260/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-31260/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-31260/trainer_state.json

@@ -0,0 +1,1819 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.72936660268714,
+  "eval_steps": 500,
+  "global_step": 31260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.326935380678183e-06,
+      "loss": 0.9276,
+      "step": 104
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.653870761356366e-06,
+      "loss": 0.8349,
+      "step": 208
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.948816378758798e-06,
+      "loss": 0.7345,
+      "step": 312
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3243761996161231e-05,
+      "loss": 0.6139,
+      "step": 416
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.657069737683941e-05,
+      "loss": 0.495,
+      "step": 520
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.9897632757517596e-05,
+      "loss": 0.4694,
+      "step": 624
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.322456813819578e-05,
+      "loss": 0.4558,
+      "step": 728
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.6551503518873962e-05,
+      "loss": 0.402,
+      "step": 832
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.9878438899552147e-05,
+      "loss": 0.3865,
+      "step": 936
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.320537428023033e-05,
+      "loss": 0.3576,
+      "step": 1040
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.653230966090851e-05,
+      "loss": 0.3395,
+      "step": 1144
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 3.98592450415867e-05,
+      "loss": 0.355,
+      "step": 1248
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.318618042226488e-05,
+      "loss": 0.3237,
+      "step": 1352
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 4.651311580294306e-05,
+      "loss": 0.3006,
+      "step": 1456
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.984005118362124e-05,
+      "loss": 0.3352,
+      "step": 1560
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 5.3166986564299424e-05,
+      "loss": 0.2761,
+      "step": 1664
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 5.649392194497761e-05,
+      "loss": 0.2918,
+      "step": 1768
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.982085732565579e-05,
+      "loss": 0.2906,
+      "step": 1872
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 6.314779270633397e-05,
+      "loss": 0.2698,
+      "step": 1976
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.647472808701216e-05,
+      "loss": 0.2749,
+      "step": 2080
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 6.980166346769034e-05,
+      "loss": 0.2739,
+      "step": 2184
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 7.312859884836853e-05,
+      "loss": 0.2477,
+      "step": 2288
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.645553422904671e-05,
+      "loss": 0.2419,
+      "step": 2392
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 7.97824696097249e-05,
+      "loss": 0.2501,
+      "step": 2496
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.310940499040308e-05,
+      "loss": 0.2325,
+      "step": 2600
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.643634037108127e-05,
+      "loss": 0.215,
+      "step": 2704
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 8.976327575175944e-05,
+      "loss": 0.2277,
+      "step": 2808
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.309021113243761e-05,
+      "loss": 0.2002,
+      "step": 2912
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 9.638515674984006e-05,
+      "loss": 0.2191,
+      "step": 3016
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 9.971209213051824e-05,
+      "loss": 0.1843,
+      "step": 3120
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 9.966588469467548e-05,
+      "loss": 0.2207,
+      "step": 3224
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 9.929622520793347e-05,
+      "loss": 0.2072,
+      "step": 3328
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 9.892656572119144e-05,
+      "loss": 0.191,
+      "step": 3432
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 9.855690623444942e-05,
+      "loss": 0.2003,
+      "step": 3536
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 9.81872467477074e-05,
+      "loss": 0.187,
+      "step": 3640
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 9.781758726096538e-05,
+      "loss": 0.1657,
+      "step": 3744
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 9.744792777422336e-05,
+      "loss": 0.185,
+      "step": 3848
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.707826828748135e-05,
+      "loss": 0.166,
+      "step": 3952
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.670860880073932e-05,
+      "loss": 0.1557,
+      "step": 4056
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.633894931399731e-05,
+      "loss": 0.1519,
+      "step": 4160
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 9.596928982725528e-05,
+      "loss": 0.1572,
+      "step": 4264
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 9.559963034051326e-05,
+      "loss": 0.1578,
+      "step": 4368
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 9.522997085377124e-05,
+      "loss": 0.1465,
+      "step": 4472
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 9.486031136702922e-05,
+      "loss": 0.1508,
+      "step": 4576
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 9.44906518802872e-05,
+      "loss": 0.154,
+      "step": 4680
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 9.412099239354518e-05,
+      "loss": 0.1574,
+      "step": 4784
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 9.375133290680316e-05,
+      "loss": 0.1455,
+      "step": 4888
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 9.338167342006115e-05,
+      "loss": 0.1587,
+      "step": 4992
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 9.301201393331912e-05,
+      "loss": 0.1352,
+      "step": 5096
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 9.26423544465771e-05,
+      "loss": 0.119,
+      "step": 5200
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 9.227269495983508e-05,
+      "loss": 0.1299,
+      "step": 5304
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 9.190303547309305e-05,
+      "loss": 0.1246,
+      "step": 5408
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 9.153337598635103e-05,
+      "loss": 0.1273,
+      "step": 5512
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 9.116371649960901e-05,
+      "loss": 0.1236,
+      "step": 5616
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 9.0794057012867e-05,
+      "loss": 0.1307,
+      "step": 5720
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 9.042439752612499e-05,
+      "loss": 0.1286,
+      "step": 5824
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 9.005473803938296e-05,
+      "loss": 0.1071,
+      "step": 5928
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 8.968507855264093e-05,
+      "loss": 0.111,
+      "step": 6032
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 8.931541906589892e-05,
+      "loss": 0.109,
+      "step": 6136
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 8.894575957915689e-05,
+      "loss": 0.1136,
+      "step": 6240
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 8.857610009241487e-05,
+      "loss": 0.1069,
+      "step": 6344
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 8.820644060567285e-05,
+      "loss": 0.1136,
+      "step": 6448
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 8.783678111893084e-05,
+      "loss": 0.1115,
+      "step": 6552
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 8.746712163218883e-05,
+      "loss": 0.0999,
+      "step": 6656
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 8.70974621454468e-05,
+      "loss": 0.0966,
+      "step": 6760
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 8.672780265870477e-05,
+      "loss": 0.1099,
+      "step": 6864
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 8.635814317196276e-05,
+      "loss": 0.1033,
+      "step": 6968
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 8.598848368522073e-05,
+      "loss": 0.1022,
+      "step": 7072
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 8.56188241984787e-05,
+      "loss": 0.0991,
+      "step": 7176
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 8.524916471173669e-05,
+      "loss": 0.1082,
+      "step": 7280
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 8.487950522499466e-05,
+      "loss": 0.0936,
+      "step": 7384
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 8.450984573825265e-05,
+      "loss": 0.094,
+      "step": 7488
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 8.414018625151064e-05,
+      "loss": 0.096,
+      "step": 7592
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 8.377052676476861e-05,
+      "loss": 0.0836,
+      "step": 7696
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 8.340442169616834e-05,
+      "loss": 0.0918,
+      "step": 7800
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 8.303476220942632e-05,
+      "loss": 0.078,
+      "step": 7904
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 8.266865714082605e-05,
+      "loss": 0.0866,
+      "step": 8008
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 8.229899765408404e-05,
+      "loss": 0.0716,
+      "step": 8112
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 8.192933816734201e-05,
+      "loss": 0.0783,
+      "step": 8216
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 8.15596786806e-05,
+      "loss": 0.0864,
+      "step": 8320
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 8.119001919385797e-05,
+      "loss": 0.0801,
+      "step": 8424
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 8.082035970711594e-05,
+      "loss": 0.0801,
+      "step": 8528
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 8.045070022037393e-05,
+      "loss": 0.0787,
+      "step": 8632
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 8.00810407336319e-05,
+      "loss": 0.082,
+      "step": 8736
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 7.971138124688989e-05,
+      "loss": 0.0783,
+      "step": 8840
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 7.934172176014788e-05,
+      "loss": 0.0823,
+      "step": 8944
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 7.897206227340585e-05,
+      "loss": 0.0796,
+      "step": 9048
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 7.860240278666384e-05,
+      "loss": 0.0835,
+      "step": 9152
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 7.823274329992181e-05,
+      "loss": 0.085,
+      "step": 9256
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 7.786308381317978e-05,
+      "loss": 0.071,
+      "step": 9360
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 7.749342432643777e-05,
+      "loss": 0.0662,
+      "step": 9464
+    },
+    {
+      "epoch": 7.55,
+      "learning_rate": 7.712376483969574e-05,
+      "loss": 0.0635,
+      "step": 9568
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 7.675410535295371e-05,
+      "loss": 0.075,
+      "step": 9672
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 7.63844458662117e-05,
+      "loss": 0.0587,
+      "step": 9776
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 7.601478637946969e-05,
+      "loss": 0.0631,
+      "step": 9880
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 7.564868131086942e-05,
+      "loss": 0.0626,
+      "step": 9984
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 7.528257624226914e-05,
+      "loss": 0.0741,
+      "step": 10088
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 7.491291675552711e-05,
+      "loss": 0.0522,
+      "step": 10192
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 7.45432572687851e-05,
+      "loss": 0.0622,
+      "step": 10296
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 7.417359778204309e-05,
+      "loss": 0.0602,
+      "step": 10400
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 7.380393829530107e-05,
+      "loss": 0.0639,
+      "step": 10504
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 7.343427880855905e-05,
+      "loss": 0.0723,
+      "step": 10608
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 7.306461932181702e-05,
+      "loss": 0.0607,
+      "step": 10712
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 7.2694959835075e-05,
+      "loss": 0.0655,
+      "step": 10816
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 7.232530034833298e-05,
+      "loss": 0.069,
+      "step": 10920
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 7.195564086159095e-05,
+      "loss": 0.0664,
+      "step": 11024
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 7.158598137484894e-05,
+      "loss": 0.0568,
+      "step": 11128
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 7.121632188810691e-05,
+      "loss": 0.0612,
+      "step": 11232
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 7.08466624013649e-05,
+      "loss": 0.055,
+      "step": 11336
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 7.047700291462288e-05,
+      "loss": 0.0501,
+      "step": 11440
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 7.010734342788086e-05,
+      "loss": 0.057,
+      "step": 11544
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 6.973768394113884e-05,
+      "loss": 0.0502,
+      "step": 11648
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 6.936802445439682e-05,
+      "loss": 0.0539,
+      "step": 11752
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 6.899836496765479e-05,
+      "loss": 0.0491,
+      "step": 11856
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 6.862870548091278e-05,
+      "loss": 0.0473,
+      "step": 11960
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 6.825904599417075e-05,
+      "loss": 0.0467,
+      "step": 12064
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 6.788938650742874e-05,
+      "loss": 0.0492,
+      "step": 12168
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 6.751972702068672e-05,
+      "loss": 0.0519,
+      "step": 12272
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 6.71500675339447e-05,
+      "loss": 0.0505,
+      "step": 12376
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 6.678040804720268e-05,
+      "loss": 0.0478,
+      "step": 12480
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 6.641074856046066e-05,
+      "loss": 0.0516,
+      "step": 12584
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 6.604108907371863e-05,
+      "loss": 0.052,
+      "step": 12688
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 6.567142958697662e-05,
+      "loss": 0.0523,
+      "step": 12792
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 6.530177010023459e-05,
+      "loss": 0.0516,
+      "step": 12896
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 6.493211061349258e-05,
+      "loss": 0.0435,
+      "step": 13000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 6.456245112675056e-05,
+      "loss": 0.0503,
+      "step": 13104
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 6.419279164000854e-05,
+      "loss": 0.043,
+      "step": 13208
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 6.382313215326652e-05,
+      "loss": 0.0433,
+      "step": 13312
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 6.34534726665245e-05,
+      "loss": 0.0432,
+      "step": 13416
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 6.308381317978247e-05,
+      "loss": 0.0423,
+      "step": 13520
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 6.271415369304045e-05,
+      "loss": 0.0416,
+      "step": 13624
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 6.234449420629843e-05,
+      "loss": 0.0363,
+      "step": 13728
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 6.19748347195564e-05,
+      "loss": 0.0335,
+      "step": 13832
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 6.160517523281439e-05,
+      "loss": 0.0395,
+      "step": 13936
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 6.123551574607237e-05,
+      "loss": 0.0358,
+      "step": 14040
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 6.0865856259330354e-05,
+      "loss": 0.0397,
+      "step": 14144
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 6.0496196772588334e-05,
+      "loss": 0.0441,
+      "step": 14248
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 6.012653728584631e-05,
+      "loss": 0.0408,
+      "step": 14352
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 5.9756877799104293e-05,
+      "loss": 0.0403,
+      "step": 14456
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 5.9387218312362267e-05,
+      "loss": 0.0379,
+      "step": 14560
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 5.9017558825620246e-05,
+      "loss": 0.0383,
+      "step": 14664
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 5.864789933887823e-05,
+      "loss": 0.0457,
+      "step": 14768
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 5.8278239852136206e-05,
+      "loss": 0.039,
+      "step": 14872
+    },
+    {
+      "epoch": 9.81,
+      "learning_rate": 5.7912134783535946e-05,
+      "loss": 0.0396,
+      "step": 14976
+    },
+    {
+      "epoch": 10.01,
+      "learning_rate": 5.754247529679392e-05,
+      "loss": 0.0379,
+      "step": 15080
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 5.717281581005189e-05,
+      "loss": 0.034,
+      "step": 15184
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 5.680315632330988e-05,
+      "loss": 0.0363,
+      "step": 15288
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 5.643349683656786e-05,
+      "loss": 0.0302,
+      "step": 15392
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 5.606383734982583e-05,
+      "loss": 0.0325,
+      "step": 15496
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 5.569417786308382e-05,
+      "loss": 0.0307,
+      "step": 15600
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 5.532451837634179e-05,
+      "loss": 0.0345,
+      "step": 15704
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 5.495485888959978e-05,
+      "loss": 0.0268,
+      "step": 15808
+    },
+    {
+      "epoch": 8.91,
+      "learning_rate": 5.458519940285776e-05,
+      "loss": 0.0356,
+      "step": 15912
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 5.421553991611573e-05,
+      "loss": 0.0308,
+      "step": 16016
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 5.384588042937372e-05,
+      "loss": 0.0311,
+      "step": 16120
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 5.34762209426317e-05,
+      "loss": 0.0314,
+      "step": 16224
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 5.310656145588967e-05,
+      "loss": 0.0316,
+      "step": 16328
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 5.273690196914766e-05,
+      "loss": 0.0322,
+      "step": 16432
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 5.236724248240563e-05,
+      "loss": 0.0348,
+      "step": 16536
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 5.199758299566361e-05,
+      "loss": 0.031,
+      "step": 16640
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 5.1627923508921597e-05,
+      "loss": 0.0308,
+      "step": 16744
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 5.125826402217957e-05,
+      "loss": 0.0317,
+      "step": 16848
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 5.0888604535437556e-05,
+      "loss": 0.0298,
+      "step": 16952
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 5.051894504869553e-05,
+      "loss": 0.0278,
+      "step": 17056
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 5.014928556195351e-05,
+      "loss": 0.0255,
+      "step": 17160
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 4.977962607521149e-05,
+      "loss": 0.0287,
+      "step": 17264
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 4.940996658846947e-05,
+      "loss": 0.0286,
+      "step": 17368
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 4.904030710172745e-05,
+      "loss": 0.027,
+      "step": 17472
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 4.867064761498543e-05,
+      "loss": 0.0227,
+      "step": 17576
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 4.830098812824341e-05,
+      "loss": 0.026,
+      "step": 17680
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 4.793132864150139e-05,
+      "loss": 0.0228,
+      "step": 17784
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 4.756166915475937e-05,
+      "loss": 0.025,
+      "step": 17888
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 4.719200966801735e-05,
+      "loss": 0.0258,
+      "step": 17992
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 4.6825904599417074e-05,
+      "loss": 0.0276,
+      "step": 18096
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 4.6456245112675054e-05,
+      "loss": 0.0278,
+      "step": 18200
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 4.608658562593304e-05,
+      "loss": 0.0224,
+      "step": 18304
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 4.571692613919102e-05,
+      "loss": 0.0267,
+      "step": 18408
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 4.5347266652448994e-05,
+      "loss": 0.026,
+      "step": 18512
+    },
+    {
+      "epoch": 11.39,
+      "learning_rate": 4.4977607165706973e-05,
+      "loss": 0.0268,
+      "step": 18616
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 4.460794767896495e-05,
+      "loss": 0.0237,
+      "step": 18720
+    },
+    {
+      "epoch": 11.79,
+      "learning_rate": 4.423828819222294e-05,
+      "loss": 0.0257,
+      "step": 18824
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 4.386862870548091e-05,
+      "loss": 0.0243,
+      "step": 18928
+    },
+    {
+      "epoch": 12.19,
+      "learning_rate": 4.349896921873889e-05,
+      "loss": 0.0241,
+      "step": 19032
+    },
+    {
+      "epoch": 12.39,
+      "learning_rate": 4.312930973199687e-05,
+      "loss": 0.0209,
+      "step": 19136
+    },
+    {
+      "epoch": 12.59,
+      "learning_rate": 4.275965024525486e-05,
+      "loss": 0.0205,
+      "step": 19240
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 4.238999075851283e-05,
+      "loss": 0.0226,
+      "step": 19344
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 4.202033127177081e-05,
+      "loss": 0.0193,
+      "step": 19448
+    },
+    {
+      "epoch": 10.48,
+      "learning_rate": 4.165067178502879e-05,
+      "loss": 0.0199,
+      "step": 19552
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 4.128101229828677e-05,
+      "loss": 0.0203,
+      "step": 19656
+    },
+    {
+      "epoch": 10.88,
+      "learning_rate": 4.091135281154475e-05,
+      "loss": 0.0204,
+      "step": 19760
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 4.054169332480273e-05,
+      "loss": 0.0201,
+      "step": 19864
+    },
+    {
+      "epoch": 11.28,
+      "learning_rate": 4.017203383806071e-05,
+      "loss": 0.0231,
+      "step": 19968
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 3.980237435131869e-05,
+      "loss": 0.0207,
+      "step": 20072
+    },
+    {
+      "epoch": 11.68,
+      "learning_rate": 3.943271486457667e-05,
+      "loss": 0.0184,
+      "step": 20176
+    },
+    {
+      "epoch": 11.88,
+      "learning_rate": 3.906305537783465e-05,
+      "loss": 0.0206,
+      "step": 20280
+    },
+    {
+      "epoch": 12.08,
+      "learning_rate": 3.869339589109263e-05,
+      "loss": 0.0219,
+      "step": 20384
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 3.832373640435061e-05,
+      "loss": 0.0206,
+      "step": 20488
+    },
+    {
+      "epoch": 12.48,
+      "learning_rate": 3.795407691760859e-05,
+      "loss": 0.0242,
+      "step": 20592
+    },
+    {
+      "epoch": 12.68,
+      "learning_rate": 3.758441743086657e-05,
+      "loss": 0.0198,
+      "step": 20696
+    },
+    {
+      "epoch": 12.88,
+      "learning_rate": 3.721475794412455e-05,
+      "loss": 0.0207,
+      "step": 20800
+    },
+    {
+      "epoch": 13.08,
+      "learning_rate": 3.684509845738252e-05,
+      "loss": 0.0183,
+      "step": 20904
+    },
+    {
+      "epoch": 13.28,
+      "learning_rate": 3.647543897064051e-05,
+      "loss": 0.0171,
+      "step": 21008
+    },
+    {
+      "epoch": 13.48,
+      "learning_rate": 3.610577948389849e-05,
+      "loss": 0.0174,
+      "step": 21112
+    },
+    {
+      "epoch": 13.68,
+      "learning_rate": 3.573611999715647e-05,
+      "loss": 0.0182,
+      "step": 21216
+    },
+    {
+      "epoch": 11.17,
+      "learning_rate": 3.536646051041444e-05,
+      "loss": 0.0178,
+      "step": 21320
+    },
+    {
+      "epoch": 11.37,
+      "learning_rate": 3.499680102367243e-05,
+      "loss": 0.0156,
+      "step": 21424
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 3.462714153693041e-05,
+      "loss": 0.0171,
+      "step": 21528
+    },
+    {
+      "epoch": 11.77,
+      "learning_rate": 3.425748205018838e-05,
+      "loss": 0.0156,
+      "step": 21632
+    },
+    {
+      "epoch": 11.97,
+      "learning_rate": 3.388782256344636e-05,
+      "loss": 0.0171,
+      "step": 21736
+    },
+    {
+      "epoch": 12.17,
+      "learning_rate": 3.351816307670435e-05,
+      "loss": 0.0145,
+      "step": 21840
+    },
+    {
+      "epoch": 12.37,
+      "learning_rate": 3.314850358996233e-05,
+      "loss": 0.0153,
+      "step": 21944
+    },
+    {
+      "epoch": 12.57,
+      "learning_rate": 3.27788441032203e-05,
+      "loss": 0.0157,
+      "step": 22048
+    },
+    {
+      "epoch": 12.77,
+      "learning_rate": 3.240918461647828e-05,
+      "loss": 0.0176,
+      "step": 22152
+    },
+    {
+      "epoch": 12.97,
+      "learning_rate": 3.203952512973626e-05,
+      "loss": 0.0152,
+      "step": 22256
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 3.166986564299425e-05,
+      "loss": 0.0196,
+      "step": 22360
+    },
+    {
+      "epoch": 13.37,
+      "learning_rate": 3.130020615625222e-05,
+      "loss": 0.0171,
+      "step": 22464
+    },
+    {
+      "epoch": 13.57,
+      "learning_rate": 3.0934101087651954e-05,
+      "loss": 0.0182,
+      "step": 22568
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 3.0564441600909934e-05,
+      "loss": 0.0194,
+      "step": 22672
+    },
+    {
+      "epoch": 13.97,
+      "learning_rate": 3.0194782114167914e-05,
+      "loss": 0.0163,
+      "step": 22776
+    },
+    {
+      "epoch": 14.17,
+      "learning_rate": 2.9825122627425893e-05,
+      "loss": 0.0136,
+      "step": 22880
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 2.945546314068387e-05,
+      "loss": 0.0136,
+      "step": 22984
+    },
+    {
+      "epoch": 14.57,
+      "learning_rate": 2.908580365394185e-05,
+      "loss": 0.014,
+      "step": 23088
+    },
+    {
+      "epoch": 12.06,
+      "learning_rate": 2.8716144167199833e-05,
+      "loss": 0.0154,
+      "step": 23192
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 2.834648468045781e-05,
+      "loss": 0.0134,
+      "step": 23296
+    },
+    {
+      "epoch": 12.46,
+      "learning_rate": 2.797682519371579e-05,
+      "loss": 0.0124,
+      "step": 23400
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 2.760716570697377e-05,
+      "loss": 0.0127,
+      "step": 23504
+    },
+    {
+      "epoch": 12.86,
+      "learning_rate": 2.7237506220231752e-05,
+      "loss": 0.0127,
+      "step": 23608
+    },
+    {
+      "epoch": 13.06,
+      "learning_rate": 2.6867846733489725e-05,
+      "loss": 0.0126,
+      "step": 23712
+    },
+    {
+      "epoch": 13.26,
+      "learning_rate": 2.649818724674771e-05,
+      "loss": 0.0143,
+      "step": 23816
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 2.612852776000569e-05,
+      "loss": 0.0133,
+      "step": 23920
+    },
+    {
+      "epoch": 13.66,
+      "learning_rate": 2.575886827326367e-05,
+      "loss": 0.0127,
+      "step": 24024
+    },
+    {
+      "epoch": 13.86,
+      "learning_rate": 2.5389208786521645e-05,
+      "loss": 0.0131,
+      "step": 24128
+    },
+    {
+      "epoch": 14.06,
+      "learning_rate": 2.5019549299779628e-05,
+      "loss": 0.0135,
+      "step": 24232
+    },
+    {
+      "epoch": 14.26,
+      "learning_rate": 2.4649889813037608e-05,
+      "loss": 0.0161,
+      "step": 24336
+    },
+    {
+      "epoch": 14.46,
+      "learning_rate": 2.4280230326295588e-05,
+      "loss": 0.0143,
+      "step": 24440
+    },
+    {
+      "epoch": 14.66,
+      "learning_rate": 2.3910570839553567e-05,
+      "loss": 0.0172,
+      "step": 24544
+    },
+    {
+      "epoch": 14.86,
+      "learning_rate": 2.3540911352811544e-05,
+      "loss": 0.0129,
+      "step": 24648
+    },
+    {
+      "epoch": 15.06,
+      "learning_rate": 2.3171251866069527e-05,
+      "loss": 0.0127,
+      "step": 24752
+    },
+    {
+      "epoch": 15.26,
+      "learning_rate": 2.2801592379327504e-05,
+      "loss": 0.0112,
+      "step": 24856
+    },
+    {
+      "epoch": 15.45,
+      "learning_rate": 2.2431932892585487e-05,
+      "loss": 0.0128,
+      "step": 24960
+    },
+    {
+      "epoch": 15.65,
+      "learning_rate": 2.2065827823985213e-05,
+      "loss": 0.0114,
+      "step": 25064
+    },
+    {
+      "epoch": 13.15,
+      "learning_rate": 2.1696168337243193e-05,
+      "loss": 0.0112,
+      "step": 25168
+    },
+    {
+      "epoch": 13.35,
+      "learning_rate": 2.1326508850501173e-05,
+      "loss": 0.0109,
+      "step": 25272
+    },
+    {
+      "epoch": 13.55,
+      "learning_rate": 2.0956849363759153e-05,
+      "loss": 0.0105,
+      "step": 25376
+    },
+    {
+      "epoch": 13.75,
+      "learning_rate": 2.0587189877017133e-05,
+      "loss": 0.0116,
+      "step": 25480
+    },
+    {
+      "epoch": 13.95,
+      "learning_rate": 2.0217530390275112e-05,
+      "loss": 0.0136,
+      "step": 25584
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 1.9847870903533092e-05,
+      "loss": 0.0113,
+      "step": 25688
+    },
+    {
+      "epoch": 14.35,
+      "learning_rate": 1.9478211416791072e-05,
+      "loss": 0.0106,
+      "step": 25792
+    },
+    {
+      "epoch": 14.55,
+      "learning_rate": 1.9108551930049052e-05,
+      "loss": 0.0109,
+      "step": 25896
+    },
+    {
+      "epoch": 14.75,
+      "learning_rate": 1.8738892443307032e-05,
+      "loss": 0.011,
+      "step": 26000
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 1.836923295656501e-05,
+      "loss": 0.0106,
+      "step": 26104
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.799957346982299e-05,
+      "loss": 0.0134,
+      "step": 26208
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 1.762991398308097e-05,
+      "loss": 0.0111,
+      "step": 26312
+    },
+    {
+      "epoch": 15.55,
+      "learning_rate": 1.726025449633895e-05,
+      "loss": 0.0102,
+      "step": 26416
+    },
+    {
+      "epoch": 15.74,
+      "learning_rate": 1.689059500959693e-05,
+      "loss": 0.0104,
+      "step": 26520
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 1.652093552285491e-05,
+      "loss": 0.0095,
+      "step": 26624
+    },
+    {
+      "epoch": 16.14,
+      "learning_rate": 1.615127603611289e-05,
+      "loss": 0.0105,
+      "step": 26728
+    },
+    {
+      "epoch": 16.34,
+      "learning_rate": 1.578161654937087e-05,
+      "loss": 0.0096,
+      "step": 26832
+    },
+    {
+      "epoch": 16.54,
+      "learning_rate": 1.5411957062628847e-05,
+      "loss": 0.0095,
+      "step": 26936
+    },
+    {
+      "epoch": 14.04,
+      "learning_rate": 1.5042297575886827e-05,
+      "loss": 0.009,
+      "step": 27040
+    },
+    {
+      "epoch": 14.24,
+      "learning_rate": 1.4672638089144808e-05,
+      "loss": 0.0083,
+      "step": 27144
+    },
+    {
+      "epoch": 14.44,
+      "learning_rate": 1.4302978602402786e-05,
+      "loss": 0.0091,
+      "step": 27248
+    },
+    {
+      "epoch": 14.64,
+      "learning_rate": 1.3933319115660768e-05,
+      "loss": 0.0121,
+      "step": 27352
+    },
+    {
+      "epoch": 14.84,
+      "learning_rate": 1.3563659628918746e-05,
+      "loss": 0.0105,
+      "step": 27456
+    },
+    {
+      "epoch": 15.04,
+      "learning_rate": 1.3194000142176728e-05,
+      "loss": 0.0083,
+      "step": 27560
+    },
+    {
+      "epoch": 15.24,
+      "learning_rate": 1.2824340655434706e-05,
+      "loss": 0.0089,
+      "step": 27664
+    },
+    {
+      "epoch": 15.44,
+      "learning_rate": 1.2454681168692686e-05,
+      "loss": 0.0093,
+      "step": 27768
+    },
+    {
+      "epoch": 15.64,
+      "learning_rate": 1.2085021681950665e-05,
+      "loss": 0.0087,
+      "step": 27872
+    },
+    {
+      "epoch": 15.83,
+      "learning_rate": 1.1715362195208644e-05,
+      "loss": 0.0087,
+      "step": 27976
+    },
+    {
+      "epoch": 16.03,
+      "learning_rate": 1.1345702708466623e-05,
+      "loss": 0.009,
+      "step": 28080
+    },
+    {
+      "epoch": 16.23,
+      "learning_rate": 1.0976043221724603e-05,
+      "loss": 0.0093,
+      "step": 28184
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 1.0606383734982583e-05,
+      "loss": 0.0086,
+      "step": 28288
+    },
+    {
+      "epoch": 16.63,
+      "learning_rate": 1.0236724248240563e-05,
+      "loss": 0.0092,
+      "step": 28392
+    },
+    {
+      "epoch": 16.83,
+      "learning_rate": 9.867064761498543e-06,
+      "loss": 0.0098,
+      "step": 28496
+    },
+    {
+      "epoch": 17.03,
+      "learning_rate": 9.497405274756523e-06,
+      "loss": 0.0088,
+      "step": 28600
+    },
+    {
+      "epoch": 17.23,
+      "learning_rate": 9.127745788014502e-06,
+      "loss": 0.0081,
+      "step": 28704
+    },
+    {
+      "epoch": 17.43,
+      "learning_rate": 8.758086301272482e-06,
+      "loss": 0.0086,
+      "step": 28808
+    },
+    {
+      "epoch": 17.63,
+      "learning_rate": 8.388426814530462e-06,
+      "loss": 0.0075,
+      "step": 28912
+    },
+    {
+      "epoch": 15.13,
+      "learning_rate": 8.018767327788442e-06,
+      "loss": 0.0086,
+      "step": 29016
+    },
+    {
+      "epoch": 15.33,
+      "learning_rate": 7.649107841046422e-06,
+      "loss": 0.0071,
+      "step": 29120
+    },
+    {
+      "epoch": 15.53,
+      "learning_rate": 7.279448354304401e-06,
+      "loss": 0.0077,
+      "step": 29224
+    },
+    {
+      "epoch": 15.73,
+      "learning_rate": 6.9133432857041314e-06,
+      "loss": 0.0104,
+      "step": 29328
+    },
+    {
+      "epoch": 15.93,
+      "learning_rate": 6.5436837989621104e-06,
+      "loss": 0.0077,
+      "step": 29432
+    },
+    {
+      "epoch": 16.12,
+      "learning_rate": 6.1740243122200894e-06,
+      "loss": 0.0077,
+      "step": 29536
+    },
+    {
+      "epoch": 16.32,
+      "learning_rate": 5.804364825478069e-06,
+      "loss": 0.0072,
+      "step": 29640
+    },
+    {
+      "epoch": 16.52,
+      "learning_rate": 5.434705338736049e-06,
+      "loss": 0.0079,
+      "step": 29744
+    },
+    {
+      "epoch": 16.72,
+      "learning_rate": 5.065045851994029e-06,
+      "loss": 0.0076,
+      "step": 29848
+    },
+    {
+      "epoch": 16.92,
+      "learning_rate": 4.698940783393759e-06,
+      "loss": 0.0074,
+      "step": 29952
+    },
+    {
+      "epoch": 17.12,
+      "learning_rate": 4.329281296651739e-06,
+      "loss": 0.0099,
+      "step": 30056
+    },
+    {
+      "epoch": 17.32,
+      "learning_rate": 3.9631762280514684e-06,
+      "loss": 0.0078,
+      "step": 30160
+    },
+    {
+      "epoch": 17.52,
+      "learning_rate": 3.5935167413094483e-06,
+      "loss": 0.0071,
+      "step": 30264
+    },
+    {
+      "epoch": 17.72,
+      "learning_rate": 3.2238572545674273e-06,
+      "loss": 0.0076,
+      "step": 30368
+    },
+    {
+      "epoch": 17.92,
+      "learning_rate": 2.854197767825407e-06,
+      "loss": 0.0076,
+      "step": 30472
+    },
+    {
+      "epoch": 18.12,
+      "learning_rate": 2.484538281083387e-06,
+      "loss": 0.007,
+      "step": 30576
+    },
+    {
+      "epoch": 18.32,
+      "learning_rate": 2.1148787943413664e-06,
+      "loss": 0.0069,
+      "step": 30680
+    },
+    {
+      "epoch": 18.52,
+      "learning_rate": 1.745219307599346e-06,
+      "loss": 0.0073,
+      "step": 30784
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 1.3755598208573258e-06,
+      "loss": 0.0069,
+      "step": 30888
+    },
+    {
+      "epoch": 16.21,
+      "learning_rate": 1.0059003341153055e-06,
+      "loss": 0.007,
+      "step": 30992
+    },
+    {
+      "epoch": 16.41,
+      "learning_rate": 6.36240847373285e-07,
+      "loss": 0.0092,
+      "step": 31096
+    },
+    {
+      "epoch": 16.61,
+      "learning_rate": 2.665813606312647e-07,
+      "loss": 0.0068,
+      "step": 31200
+    }
+  ],
+  "logging_steps": 104,
+  "max_steps": 31260,
+  "num_train_epochs": 60,
+  "save_steps": 500,
+  "total_flos": 1.3669926589956096e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-31260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5ae061606ce0aa20ae0429623cb4fbf55f515069c2fc6b9d578cfbbd3dfc36
+size 4091

runs/Oct05_21-32-00_AM-3080TI-VR-PC/events.out.tfevents.1696537920.AM-3080TI-VR-PC.686.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9f591f34e8ecc566b9251f9bae186952734e7c005ce4c7ab58bba471f282e0
+size 4184

runs/Oct05_21-35-02_AM-3080TI-VR-PC/events.out.tfevents.1696538102.AM-3080TI-VR-PC.744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb6d7b642f2f97d36abf33e68bffa9f4458ef9f9f6f7163cb5c407006997e51
+size 52379

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5ae061606ce0aa20ae0429623cb4fbf55f515069c2fc6b9d578cfbbd3dfc36
+size 4091

training_params.json

@@ -0,0 +1 @@
+{"model": "bn22/Mistral-7B-Instruct-v0.1-sharded", "data_path": "YL95/REDL_data_LLM2_0", "project_name": "REDL_LLM2_0", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0001, "epochs": 60, "batch_size": 1, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 95, "add_eos_token": true, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 32768, "repo_id": "YL95/REDL_LLM2_0", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "YL95", "use_flash_attention_2": false}