Upload folder using huggingface_hub

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f909ebba2b6a7eb55fed136da12c288de713f72d0324899e5111f6c0844d2a99
+size 109069176

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd28a92936a3fc92b97f8db7fbfc215ce458a7093cbff1aa04680c1ea9c42b8
+size 109069176

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e3b16797757158a3fc5f8dc255ecc10728f61b50e4d14a09d9327054bff0a0
+size 55532538

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff9cee57491cba4e360bb74e53c798ed6573bc1419aa2da49abcf5d2332b5e
+size 14244

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbaf7ffce1271ac44bd0c0f634e14076e09a101c401209a54ba8cdb178ba9b4
+size 1064

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/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
+  }
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 1.3715622425079346,
+  "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-49",
+  "epoch": 4.979591836734694,
+  "eval_steps": 10,
+  "global_step": 122,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.1506130695343018,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 10
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.8620133996009827,
+      "learning_rate": 0.0002,
+      "loss": 1.5759,
+      "step": 20
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "eval_loss": 1.4961365461349487,
+      "eval_runtime": 1.5168,
+      "eval_samples_per_second": 13.186,
+      "eval_steps_per_second": 1.978,
+      "step": 24
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.6956524848937988,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 30
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.952648937702179,
+      "learning_rate": 0.0002,
+      "loss": 1.4203,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3715622425079346,
+      "eval_runtime": 1.5232,
+      "eval_samples_per_second": 13.13,
+      "eval_steps_per_second": 1.97,
+      "step": 49
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.8767076134681702,
+      "learning_rate": 0.0002,
+      "loss": 1.2128,
+      "step": 50
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 1.109923005104065,
+      "learning_rate": 0.0002,
+      "loss": 1.15,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.020828127861023,
+      "learning_rate": 0.0002,
+      "loss": 1.1245,
+      "step": 70
+    },
+    {
+      "epoch": 2.979591836734694,
+      "eval_loss": 1.4046821594238281,
+      "eval_runtime": 1.5254,
+      "eval_samples_per_second": 13.111,
+      "eval_steps_per_second": 1.967,
+      "step": 73
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 1.7557268142700195,
+      "learning_rate": 0.0002,
+      "loss": 1.0261,
+      "step": 80
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 1.7829153537750244,
+      "learning_rate": 0.0002,
+      "loss": 0.9001,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4633442163467407,
+      "eval_runtime": 1.5242,
+      "eval_samples_per_second": 13.122,
+      "eval_steps_per_second": 1.968,
+      "step": 98
+    },
+    {
+      "epoch": 4.081632653061225,
+      "grad_norm": 1.4434747695922852,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 100
+    },
+    {
+      "epoch": 4.489795918367347,
+      "grad_norm": 1.200379490852356,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 110
+    },
+    {
+      "epoch": 4.8979591836734695,
+      "grad_norm": 1.5186196565628052,
+      "learning_rate": 0.0002,
+      "loss": 0.7127,
+      "step": 120
+    },
+    {
+      "epoch": 4.979591836734694,
+      "eval_loss": 1.5558929443359375,
+      "eval_runtime": 1.5263,
+      "eval_samples_per_second": 13.103,
+      "eval_steps_per_second": 1.965,
+      "step": 122
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5374654021632000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-122/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab9f6f788f3e5df540eb47a8a0606d20035801115c0a0be996f95dd23bd3686
+size 5560

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245e01df512089ccd49d52031c69b7f2db007425237d51e0c86b261f486f83b5
+size 109069176

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3351c0694ebb2ac6354cadba30816389c749d811f78c15b037c079307d27bca3
+size 55532538

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b2e3c96ec68abf9f3c1f9508f11f26d4aa82d03d8b51b4e857a5b4b90fafe5
+size 14244

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a9f5272dca00a67a663299f7fc10187d6643ce612719de5c600d2a9add79bf
+size 1064

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/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
+  }
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 1.3715622425079346,
+  "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-49",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.1506130695343018,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 10
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.8620133996009827,
+      "learning_rate": 0.0002,
+      "loss": 1.5759,
+      "step": 20
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "eval_loss": 1.4961365461349487,
+      "eval_runtime": 1.5168,
+      "eval_samples_per_second": 13.186,
+      "eval_steps_per_second": 1.978,
+      "step": 24
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.6956524848937988,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 30
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.952648937702179,
+      "learning_rate": 0.0002,
+      "loss": 1.4203,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3715622425079346,
+      "eval_runtime": 1.5232,
+      "eval_samples_per_second": 13.13,
+      "eval_steps_per_second": 1.97,
+      "step": 49
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.8767076134681702,
+      "learning_rate": 0.0002,
+      "loss": 1.2128,
+      "step": 50
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 1.109923005104065,
+      "learning_rate": 0.0002,
+      "loss": 1.15,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.020828127861023,
+      "learning_rate": 0.0002,
+      "loss": 1.1245,
+      "step": 70
+    },
+    {
+      "epoch": 2.979591836734694,
+      "eval_loss": 1.4046821594238281,
+      "eval_runtime": 1.5254,
+      "eval_samples_per_second": 13.111,
+      "eval_steps_per_second": 1.967,
+      "step": 73
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 1.7557268142700195,
+      "learning_rate": 0.0002,
+      "loss": 1.0261,
+      "step": 80
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 1.7829153537750244,
+      "learning_rate": 0.0002,
+      "loss": 0.9001,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4633442163467407,
+      "eval_runtime": 1.5242,
+      "eval_samples_per_second": 13.122,
+      "eval_steps_per_second": 1.968,
+      "step": 98
+    },
+    {
+      "epoch": 4.081632653061225,
+      "grad_norm": 1.4434747695922852,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 100
+    },
+    {
+      "epoch": 4.489795918367347,
+      "grad_norm": 1.200379490852356,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 110
+    },
+    {
+      "epoch": 4.8979591836734695,
+      "grad_norm": 1.5186196565628052,
+      "learning_rate": 0.0002,
+      "loss": 0.7127,
+      "step": 120
+    },
+    {
+      "epoch": 4.979591836734694,
+      "eval_loss": 1.5558929443359375,
+      "eval_runtime": 1.5263,
+      "eval_samples_per_second": 13.103,
+      "eval_steps_per_second": 1.965,
+      "step": 122
+    },
+    {
+      "epoch": 5.3061224489795915,
+      "grad_norm": 2.504272222518921,
+      "learning_rate": 0.0002,
+      "loss": 0.6669,
+      "step": 130
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.9125874042510986,
+      "learning_rate": 0.0002,
+      "loss": 0.6513,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.6925510168075562,
+      "eval_runtime": 1.5255,
+      "eval_samples_per_second": 13.11,
+      "eval_steps_per_second": 1.967,
+      "step": 147
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6449584825958400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-147/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab9f6f788f3e5df540eb47a8a0606d20035801115c0a0be996f95dd23bd3686
+size 5560

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98aef622a9c2203f3b7c84e98d951d28ec57719baa7e0ba7dcfa44f33ce6ddb9
+size 109069176

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71b3fae21fa7bf61cb766daacfc4918da3b5089f11b140e897e0a296cbd43ea
+size 55532538

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86430975a9f646b684fcc04f0040f749179c220bc87d59f794aaa00e6955bc0
+size 14244

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945f7993f30b9121a7da18f292a2d9e42881b72ea1d20d6ff8ccdc55e14e5b77
+size 1064

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/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
+  }
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": 1.3715622425079346,
+  "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-49",
+  "epoch": 6.979591836734694,
+  "eval_steps": 10,
+  "global_step": 171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.1506130695343018,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 10
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.8620133996009827,
+      "learning_rate": 0.0002,
+      "loss": 1.5759,
+      "step": 20
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "eval_loss": 1.4961365461349487,
+      "eval_runtime": 1.5168,
+      "eval_samples_per_second": 13.186,
+      "eval_steps_per_second": 1.978,
+      "step": 24
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.6956524848937988,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 30
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.952648937702179,
+      "learning_rate": 0.0002,
+      "loss": 1.4203,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3715622425079346,
+      "eval_runtime": 1.5232,
+      "eval_samples_per_second": 13.13,
+      "eval_steps_per_second": 1.97,
+      "step": 49
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.8767076134681702,
+      "learning_rate": 0.0002,
+      "loss": 1.2128,
+      "step": 50
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 1.109923005104065,
+      "learning_rate": 0.0002,
+      "loss": 1.15,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.020828127861023,
+      "learning_rate": 0.0002,
+      "loss": 1.1245,
+      "step": 70
+    },
+    {
+      "epoch": 2.979591836734694,
+      "eval_loss": 1.4046821594238281,
+      "eval_runtime": 1.5254,
+      "eval_samples_per_second": 13.111,
+      "eval_steps_per_second": 1.967,
+      "step": 73
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 1.7557268142700195,
+      "learning_rate": 0.0002,
+      "loss": 1.0261,
+      "step": 80
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 1.7829153537750244,
+      "learning_rate": 0.0002,
+      "loss": 0.9001,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4633442163467407,
+      "eval_runtime": 1.5242,
+      "eval_samples_per_second": 13.122,
+      "eval_steps_per_second": 1.968,
+      "step": 98
+    },
+    {
+      "epoch": 4.081632653061225,
+      "grad_norm": 1.4434747695922852,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 100
+    },
+    {
+      "epoch": 4.489795918367347,
+      "grad_norm": 1.200379490852356,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 110
+    },
+    {
+      "epoch": 4.8979591836734695,
+      "grad_norm": 1.5186196565628052,
+      "learning_rate": 0.0002,
+      "loss": 0.7127,
+      "step": 120
+    },
+    {
+      "epoch": 4.979591836734694,
+      "eval_loss": 1.5558929443359375,
+      "eval_runtime": 1.5263,
+      "eval_samples_per_second": 13.103,
+      "eval_steps_per_second": 1.965,
+      "step": 122
+    },
+    {
+      "epoch": 5.3061224489795915,
+      "grad_norm": 2.504272222518921,
+      "learning_rate": 0.0002,
+      "loss": 0.6669,
+      "step": 130
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.9125874042510986,
+      "learning_rate": 0.0002,
+      "loss": 0.6513,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.6925510168075562,
+      "eval_runtime": 1.5255,
+      "eval_samples_per_second": 13.11,
+      "eval_steps_per_second": 1.967,
+      "step": 147
+    },
+    {
+      "epoch": 6.122448979591836,
+      "grad_norm": 1.454830527305603,
+      "learning_rate": 0.0002,
+      "loss": 0.5761,
+      "step": 150
+    },
+    {
+      "epoch": 6.530612244897959,
+      "grad_norm": 1.862570881843567,
+      "learning_rate": 0.0002,
+      "loss": 0.5292,
+      "step": 160
+    },
+    {
+      "epoch": 6.938775510204081,
+      "grad_norm": 1.7489290237426758,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 170
+    },
+    {
+      "epoch": 6.979591836734694,
+      "eval_loss": 1.7374471426010132,
+      "eval_runtime": 1.5275,
+      "eval_samples_per_second": 13.093,
+      "eval_steps_per_second": 1.964,
+      "step": 171
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7524515630284800.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-171/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab9f6f788f3e5df540eb47a8a0606d20035801115c0a0be996f95dd23bd3686
+size 5560

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88474d7e05466aee50c5124ba2ce34a0987f45110c4ed10b9e16f20bbcd12f32
+size 109069176

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f278c7d6ca12164c4043c4a2628e90978908e7fe0363df0e1256a8938826bc96
+size 55532538

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52d9c9a6394f52d9873a26327e801b103c1b653fca8113e887d07c88d02a2fd
+size 14244

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76015119c98234dbe8c1d65422400b7fb946e39b0099582dc30ebc93cd79241f
+size 1064

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/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
+  }
+}

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-192/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_metric": 1.3715622425079346,
+  "best_model_checkpoint": "outputs-001/Mistral-7B-Instruct-v0.3_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-450-sd-1/checkpoint-49",
+  "epoch": 7.836734693877551,
+  "eval_steps": 10,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.1506130695343018,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 10
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.8620133996009827,
+      "learning_rate": 0.0002,
+      "loss": 1.5759,
+      "step": 20
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "eval_loss": 1.4961365461349487,
+      "eval_runtime": 1.5168,
+      "eval_samples_per_second": 13.186,
+      "eval_steps_per_second": 1.978,
+      "step": 24
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.6956524848937988,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 30
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.952648937702179,
+      "learning_rate": 0.0002,
+      "loss": 1.4203,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3715622425079346,
+      "eval_runtime": 1.5232,
+      "eval_samples_per_second": 13.13,
+      "eval_steps_per_second": 1.97,
+      "step": 49
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.8767076134681702,
+      "learning_rate": 0.0002,
+      "loss": 1.2128,
+      "step": 50
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 1.109923005104065,
+      "learning_rate": 0.0002,
+      "loss": 1.15,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.020828127861023,
+      "learning_rate": 0.0002,
+      "loss": 1.1245,
+      "step": 70
+    },
+    {
+      "epoch": 2.979591836734694,
+      "eval_loss": 1.4046821594238281,
+      "eval_runtime": 1.5254,
+      "eval_samples_per_second": 13.111,
+      "eval_steps_per_second": 1.967,
+      "step": 73
+    },
+    {
+      "epoch": 3.2653061224489797,
+      "grad_norm": 1.7557268142700195,
+      "learning_rate": 0.0002,
+      "loss": 1.0261,
+      "step": 80
+    },
+    {
+      "epoch": 3.673469387755102,
+      "grad_norm": 1.7829153537750244,
+      "learning_rate": 0.0002,
+      "loss": 0.9001,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4633442163467407,
+      "eval_runtime": 1.5242,
+      "eval_samples_per_second": 13.122,
+      "eval_steps_per_second": 1.968,
+      "step": 98
+    },
+    {
+      "epoch": 4.081632653061225,
+      "grad_norm": 1.4434747695922852,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 100
+    },
+    {
+      "epoch": 4.489795918367347,
+      "grad_norm": 1.200379490852356,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 110
+    },
+    {
+      "epoch": 4.8979591836734695,
+      "grad_norm": 1.5186196565628052,
+      "learning_rate": 0.0002,
+      "loss": 0.7127,
+      "step": 120
+    },
+    {
+      "epoch": 4.979591836734694,
+      "eval_loss": 1.5558929443359375,
+      "eval_runtime": 1.5263,
+      "eval_samples_per_second": 13.103,
+      "eval_steps_per_second": 1.965,
+      "step": 122
+    },
+    {
+      "epoch": 5.3061224489795915,
+      "grad_norm": 2.504272222518921,
+      "learning_rate": 0.0002,
+      "loss": 0.6669,
+      "step": 130
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.9125874042510986,
+      "learning_rate": 0.0002,
+      "loss": 0.6513,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.6925510168075562,
+      "eval_runtime": 1.5255,
+      "eval_samples_per_second": 13.11,
+      "eval_steps_per_second": 1.967,
+      "step": 147
+    },
+    {
+      "epoch": 6.122448979591836,
+      "grad_norm": 1.454830527305603,
+      "learning_rate": 0.0002,
+      "loss": 0.5761,
+      "step": 150
+    },
+    {
+      "epoch": 6.530612244897959,
+      "grad_norm": 1.862570881843567,
+      "learning_rate": 0.0002,
+      "loss": 0.5292,
+      "step": 160
+    },
+    {
+      "epoch": 6.938775510204081,
+      "grad_norm": 1.7489290237426758,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 170
+    },
+    {
+      "epoch": 6.979591836734694,
+      "eval_loss": 1.7374471426010132,
+      "eval_runtime": 1.5275,
+      "eval_samples_per_second": 13.093,
+      "eval_steps_per_second": 1.964,
+      "step": 171
+    },
+    {
+      "epoch": 7.346938775510204,
+      "grad_norm": 1.6064404249191284,
+      "learning_rate": 0.0002,
+      "loss": 0.4328,
+      "step": 180
+    },
+    {
+      "epoch": 7.755102040816326,
+      "grad_norm": 3.0645978450775146,
+      "learning_rate": 0.0002,
+      "loss": 0.4013,
+      "step": 190
+    },
+    {
+      "epoch": 7.836734693877551,
+      "eval_loss": 1.8650048971176147,
+      "eval_runtime": 1.5234,
+      "eval_samples_per_second": 13.128,
+      "eval_steps_per_second": 1.969,
+      "step": 192
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8423947527782400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}