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": "mistralai/Mistral-7B-v0.1",
+  "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": 0.1,
+  "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 sha256:18346e398b72e07c1810e0b6c60a97317390db6239e83b9b33904e9ff16dba62
+size 27309386

checkpoint-2291/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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: QuantizationMethod.BITS_AND_BYTES
+- 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
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- 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

checkpoint-2291/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2291/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86b00b459d977a2d60c779f1afe9eaec0ff560cbb53130159b9154e2fe4053b
+size 27309386

checkpoint-2291/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa2e4fcce1c0f89068366daed02a9c9bf0dd39f78e9cc483777f936a5e83ea4
+size 54633978

checkpoint-2291/pytorch_model.bin

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

checkpoint-2291/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223e5621556cbb49d52d608b8c4048ed3bfb2411dc70e2a65159931f125654b2
+size 15024

checkpoint-2291/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b76c8cb7f7ef22f51dc331ff3b7090985a8859ae5bc57f059da6c17a0a19f2
+size 15024

checkpoint-2291/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc96946dd4ccd9830c48d164825b3e507405df68552b7e8ea88ef86d5804c54
+size 15024

checkpoint-2291/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f7b8933538f611630d1bf9fb4de8bc4fbdd35a8b66710a4805112df9e7ea1a
+size 15024

checkpoint-2291/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42de674bf7e7bb40c1b7196fdd7c7b1e1660a7d8b00b80f687ca74b13809b48d
+size 1064

checkpoint-2291/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
+  }
+}

checkpoint-2291/tokenizer.model

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

checkpoint-2291/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2291/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 88.97087378640776,
+  "eval_steps": 500,
+  "global_step": 2291,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.000324,
+      "loss": 1.6248,
+      "step": 81
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.000648,
+      "loss": 1.5109,
+      "step": 162
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 0.000972,
+      "loss": 1.4155,
+      "step": 243
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 0.0009671111111111112,
+      "loss": 1.328,
+      "step": 324
+    },
+    {
+      "epoch": 15.73,
+      "learning_rate": 0.0009311111111111112,
+      "loss": 1.2665,
+      "step": 405
+    },
+    {
+      "epoch": 18.87,
+      "learning_rate": 0.0008951111111111111,
+      "loss": 1.2178,
+      "step": 486
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0008591111111111112,
+      "loss": 1.1829,
+      "step": 567
+    },
+    {
+      "epoch": 25.17,
+      "learning_rate": 0.0008231111111111112,
+      "loss": 1.1523,
+      "step": 648
+    },
+    {
+      "epoch": 28.31,
+      "learning_rate": 0.0007871111111111111,
+      "loss": 1.1296,
+      "step": 729
+    },
+    {
+      "epoch": 31.46,
+      "learning_rate": 0.000751111111111111,
+      "loss": 1.1084,
+      "step": 810
+    },
+    {
+      "epoch": 34.6,
+      "learning_rate": 0.0007151111111111111,
+      "loss": 1.0855,
+      "step": 891
+    },
+    {
+      "epoch": 37.75,
+      "learning_rate": 0.0006791111111111111,
+      "loss": 1.0708,
+      "step": 972
+    },
+    {
+      "epoch": 40.89,
+      "learning_rate": 0.0006431111111111111,
+      "loss": 1.0536,
+      "step": 1053
+    },
+    {
+      "epoch": 44.04,
+      "learning_rate": 0.0006071111111111112,
+      "loss": 1.0359,
+      "step": 1134
+    },
+    {
+      "epoch": 47.18,
+      "learning_rate": 0.0005711111111111111,
+      "loss": 1.0246,
+      "step": 1215
+    },
+    {
+      "epoch": 50.33,
+      "learning_rate": 0.0005351111111111111,
+      "loss": 1.0132,
+      "step": 1296
+    },
+    {
+      "epoch": 53.48,
+      "learning_rate": 0.0004991111111111111,
+      "loss": 1.0013,
+      "step": 1377
+    },
+    {
+      "epoch": 56.62,
+      "learning_rate": 0.0004631111111111111,
+      "loss": 0.9878,
+      "step": 1458
+    },
+    {
+      "epoch": 59.77,
+      "learning_rate": 0.0004271111111111111,
+      "loss": 0.9766,
+      "step": 1539
+    },
+    {
+      "epoch": 62.91,
+      "learning_rate": 0.0003911111111111111,
+      "loss": 0.9643,
+      "step": 1620
+    },
+    {
+      "epoch": 66.06,
+      "learning_rate": 0.0003551111111111111,
+      "loss": 0.9538,
+      "step": 1701
+    },
+    {
+      "epoch": 69.2,
+      "learning_rate": 0.0003191111111111111,
+      "loss": 0.9486,
+      "step": 1782
+    },
+    {
+      "epoch": 72.35,
+      "learning_rate": 0.0002831111111111111,
+      "loss": 0.9382,
+      "step": 1863
+    },
+    {
+      "epoch": 75.5,
+      "learning_rate": 0.00024711111111111114,
+      "loss": 0.9255,
+      "step": 1944
+    },
+    {
+      "epoch": 78.64,
+      "learning_rate": 0.0002111111111111111,
+      "loss": 0.9153,
+      "step": 2025
+    },
+    {
+      "epoch": 81.79,
+      "learning_rate": 0.0001751111111111111,
+      "loss": 0.9069,
+      "step": 2106
+    },
+    {
+      "epoch": 84.93,
+      "learning_rate": 0.0001391111111111111,
+      "loss": 0.8996,
+      "step": 2187
+    },
+    {
+      "epoch": 88.08,
+      "learning_rate": 0.00010311111111111111,
+      "loss": 0.888,
+      "step": 2268
+    }
+  ],
+  "logging_steps": 81,
+  "max_steps": 2500,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.5655732556322046e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2291/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f619e6ebfb366a3ea09e3eb87674c967c8536ccf26fb2a93c22903d6f9bb566a
+size 4472

checkpoint-2317/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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: QuantizationMethod.BITS_AND_BYTES
+- 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
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- 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

checkpoint-2317/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2317/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd735f99d54cb6516599683a0e1ab124a025b63ccd5a222bf98196d8c398d03
+size 27309386

checkpoint-2317/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c341def01e145d5c77c68591f180a364f7278369cd2854a04bd86233acd02e4
+size 54633978

checkpoint-2317/pytorch_model.bin

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

checkpoint-2317/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27f15759116e58a804c78dc84fd87f120cdf8c2797db523d10186ffbbedb79d
+size 15024

checkpoint-2317/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e5095551347df0a27f1686b1421b159e72e7d7cd7355aca72dee1d4b4d11c1
+size 15024

checkpoint-2317/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4e04459a416a24194c18a601a319cd08449a4a627840abebc4d4ef9715db4b
+size 15024

checkpoint-2317/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4fd2612a325a4c6b101726b0aaa06e4829045d8346b2f4c1f2d930350e6bb1
+size 15024

checkpoint-2317/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc2a58cc48733c7aa4ede92c5c55f6e8107af5fa4b97efdac30e8110e27a4ec
+size 1064

checkpoint-2317/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
+  }
+}

checkpoint-2317/tokenizer.model

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

checkpoint-2317/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2317/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 89.98058252427184,
+  "eval_steps": 500,
+  "global_step": 2317,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.000324,
+      "loss": 1.6248,
+      "step": 81
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.000648,
+      "loss": 1.5109,
+      "step": 162
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 0.000972,
+      "loss": 1.4155,
+      "step": 243
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 0.0009671111111111112,
+      "loss": 1.328,
+      "step": 324
+    },
+    {
+      "epoch": 15.73,
+      "learning_rate": 0.0009311111111111112,
+      "loss": 1.2665,
+      "step": 405
+    },
+    {
+      "epoch": 18.87,
+      "learning_rate": 0.0008951111111111111,
+      "loss": 1.2178,
+      "step": 486
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0008591111111111112,
+      "loss": 1.1829,
+      "step": 567
+    },
+    {
+      "epoch": 25.17,
+      "learning_rate": 0.0008231111111111112,
+      "loss": 1.1523,
+      "step": 648
+    },
+    {
+      "epoch": 28.31,
+      "learning_rate": 0.0007871111111111111,
+      "loss": 1.1296,
+      "step": 729
+    },
+    {
+      "epoch": 31.46,
+      "learning_rate": 0.000751111111111111,
+      "loss": 1.1084,
+      "step": 810
+    },
+    {
+      "epoch": 34.6,
+      "learning_rate": 0.0007151111111111111,
+      "loss": 1.0855,
+      "step": 891
+    },
+    {
+      "epoch": 37.75,
+      "learning_rate": 0.0006791111111111111,
+      "loss": 1.0708,
+      "step": 972
+    },
+    {
+      "epoch": 40.89,
+      "learning_rate": 0.0006431111111111111,
+      "loss": 1.0536,
+      "step": 1053
+    },
+    {
+      "epoch": 44.04,
+      "learning_rate": 0.0006071111111111112,
+      "loss": 1.0359,
+      "step": 1134
+    },
+    {
+      "epoch": 47.18,
+      "learning_rate": 0.0005711111111111111,
+      "loss": 1.0246,
+      "step": 1215
+    },
+    {
+      "epoch": 50.33,
+      "learning_rate": 0.0005351111111111111,
+      "loss": 1.0132,
+      "step": 1296
+    },
+    {
+      "epoch": 53.48,
+      "learning_rate": 0.0004991111111111111,
+      "loss": 1.0013,
+      "step": 1377
+    },
+    {
+      "epoch": 56.62,
+      "learning_rate": 0.0004631111111111111,
+      "loss": 0.9878,
+      "step": 1458
+    },
+    {
+      "epoch": 59.77,
+      "learning_rate": 0.0004271111111111111,
+      "loss": 0.9766,
+      "step": 1539
+    },
+    {
+      "epoch": 62.91,
+      "learning_rate": 0.0003911111111111111,
+      "loss": 0.9643,
+      "step": 1620
+    },
+    {
+      "epoch": 66.06,
+      "learning_rate": 0.0003551111111111111,
+      "loss": 0.9538,
+      "step": 1701
+    },
+    {
+      "epoch": 69.2,
+      "learning_rate": 0.0003191111111111111,
+      "loss": 0.9486,
+      "step": 1782
+    },
+    {
+      "epoch": 72.35,
+      "learning_rate": 0.0002831111111111111,
+      "loss": 0.9382,
+      "step": 1863
+    },
+    {
+      "epoch": 75.5,
+      "learning_rate": 0.00024711111111111114,
+      "loss": 0.9255,
+      "step": 1944
+    },
+    {
+      "epoch": 78.64,
+      "learning_rate": 0.0002111111111111111,
+      "loss": 0.9153,
+      "step": 2025
+    },
+    {
+      "epoch": 81.79,
+      "learning_rate": 0.0001751111111111111,
+      "loss": 0.9069,
+      "step": 2106
+    },
+    {
+      "epoch": 84.93,
+      "learning_rate": 0.0001391111111111111,
+      "loss": 0.8996,
+      "step": 2187
+    },
+    {
+      "epoch": 88.08,
+      "learning_rate": 0.00010311111111111111,
+      "loss": 0.888,
+      "step": 2268
+    }
+  ],
+  "logging_steps": 81,
+  "max_steps": 2500,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.5943999216357474e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2317/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f619e6ebfb366a3ea09e3eb87674c967c8536ccf26fb2a93c22903d6f9bb566a
+size 4472

checkpoint-2343/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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: QuantizationMethod.BITS_AND_BYTES
+- 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
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- 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

checkpoint-2343/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2343/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9536c91747f830d2eec1efe9c2dd2ce282d80e908a679ee24d4e42a8367217ef
+size 27309386

checkpoint-2343/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff9e83e0ed4148d226b5e2268050fcf84357ab06329b4aad75ba8d1939386e4
+size 54633978

checkpoint-2343/pytorch_model.bin

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

checkpoint-2343/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6995b721c65d7e7a19a3ee4cfddf8edb5811c6eb5f700180e35a07e5323ff7c6
+size 15024

checkpoint-2343/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383c091e460ad9b52c662e7e8f7cf0ff07d285cf9f700d12b2645667da4cd7da
+size 15024

checkpoint-2343/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0c30d757a178b0bb42f296af7b8160f574fb716e3c55d66c5adc2438b63fac
+size 15024

checkpoint-2343/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ad714128fff57c7396b54b362ccd281830ccab93db0911ebe96dac6e81feee
+size 15024

checkpoint-2343/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d70a037340d45a084c895b5b2302e7d9f06f88374d56a5ab712d87955ccd67
+size 1064

checkpoint-2343/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
+  }
+}

checkpoint-2343/tokenizer.model

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

checkpoint-2343/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2343/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 90.99029126213593,
+  "eval_steps": 500,
+  "global_step": 2343,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.000324,
+      "loss": 1.6248,
+      "step": 81
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.000648,
+      "loss": 1.5109,
+      "step": 162
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 0.000972,
+      "loss": 1.4155,
+      "step": 243
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 0.0009671111111111112,
+      "loss": 1.328,
+      "step": 324
+    },
+    {
+      "epoch": 15.73,
+      "learning_rate": 0.0009311111111111112,
+      "loss": 1.2665,
+      "step": 405
+    },
+    {
+      "epoch": 18.87,
+      "learning_rate": 0.0008951111111111111,
+      "loss": 1.2178,
+      "step": 486
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0008591111111111112,
+      "loss": 1.1829,
+      "step": 567
+    },
+    {
+      "epoch": 25.17,
+      "learning_rate": 0.0008231111111111112,
+      "loss": 1.1523,
+      "step": 648
+    },
+    {
+      "epoch": 28.31,
+      "learning_rate": 0.0007871111111111111,
+      "loss": 1.1296,
+      "step": 729
+    },
+    {
+      "epoch": 31.46,
+      "learning_rate": 0.000751111111111111,
+      "loss": 1.1084,
+      "step": 810
+    },
+    {
+      "epoch": 34.6,
+      "learning_rate": 0.0007151111111111111,
+      "loss": 1.0855,
+      "step": 891
+    },
+    {
+      "epoch": 37.75,
+      "learning_rate": 0.0006791111111111111,
+      "loss": 1.0708,
+      "step": 972
+    },
+    {
+      "epoch": 40.89,
+      "learning_rate": 0.0006431111111111111,
+      "loss": 1.0536,
+      "step": 1053
+    },
+    {
+      "epoch": 44.04,
+      "learning_rate": 0.0006071111111111112,
+      "loss": 1.0359,
+      "step": 1134
+    },
+    {
+      "epoch": 47.18,
+      "learning_rate": 0.0005711111111111111,
+      "loss": 1.0246,
+      "step": 1215
+    },
+    {
+      "epoch": 50.33,
+      "learning_rate": 0.0005351111111111111,
+      "loss": 1.0132,
+      "step": 1296
+    },
+    {
+      "epoch": 53.48,
+      "learning_rate": 0.0004991111111111111,
+      "loss": 1.0013,
+      "step": 1377
+    },
+    {
+      "epoch": 56.62,
+      "learning_rate": 0.0004631111111111111,
+      "loss": 0.9878,
+      "step": 1458
+    },
+    {
+      "epoch": 59.77,
+      "learning_rate": 0.0004271111111111111,
+      "loss": 0.9766,
+      "step": 1539
+    },
+    {
+      "epoch": 62.91,
+      "learning_rate": 0.0003911111111111111,
+      "loss": 0.9643,
+      "step": 1620
+    },
+    {
+      "epoch": 66.06,
+      "learning_rate": 0.0003551111111111111,
+      "loss": 0.9538,
+      "step": 1701
+    },
+    {
+      "epoch": 69.2,
+      "learning_rate": 0.0003191111111111111,
+      "loss": 0.9486,
+      "step": 1782
+    },
+    {
+      "epoch": 72.35,
+      "learning_rate": 0.0002831111111111111,
+      "loss": 0.9382,
+      "step": 1863
+    },
+    {
+      "epoch": 75.5,
+      "learning_rate": 0.00024711111111111114,
+      "loss": 0.9255,
+      "step": 1944
+    },
+    {
+      "epoch": 78.64,
+      "learning_rate": 0.0002111111111111111,
+      "loss": 0.9153,
+      "step": 2025
+    },
+    {
+      "epoch": 81.79,
+      "learning_rate": 0.0001751111111111111,
+      "loss": 0.9069,
+      "step": 2106
+    },
+    {
+      "epoch": 84.93,
+      "learning_rate": 0.0001391111111111111,
+      "loss": 0.8996,
+      "step": 2187
+    },
+    {
+      "epoch": 88.08,
+      "learning_rate": 0.00010311111111111111,
+      "loss": 0.888,
+      "step": 2268
+    }
+  ],
+  "logging_steps": 81,
+  "max_steps": 2500,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.6232265876392903e+19,
+  "trial_name": null,
+  "trial_params": null
+}