Upload folder using huggingface_hub

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031ce246a19a329e3cb9bdf5e3fc6afdd30f76ba134e50cb192e38a4ba0b1d08
+size 9462656

checkpoint-420/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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 0.7.1

checkpoint-420/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031ce246a19a329e3cb9bdf5e3fc6afdd30f76ba134e50cb192e38a4ba0b1d08
+size 9462656

checkpoint-420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c51d057bd70fae940d78a535a56825788c26b0f5cb106ff387aaeba085dd76
+size 19035578

checkpoint-420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702b4e425c61cce81cc0dcaa0fc047a76e0ab39434bd10a7b3f1d79d834f3c6f
+size 14244

checkpoint-420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4b8b0cda23a3828a66220f9a9280c566890455294190f981aefd27a0c15d9d
+size 1064

checkpoint-420/trainer_state.json

@@ -0,0 +1,693 @@
+{
+  "best_metric": 0.07559170573949814,
+  "best_model_checkpoint": "./trained_models/Mistral-7B-Instruct-v0.2_-1pos_-1neg_perNE_top-1NEs_TrueDef-IT/checkpoint-420",
+  "epoch": 0.7190241814680077,
+  "eval_steps": 20,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 6.4943,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 3.9486,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.5e-05,
+      "loss": 0.4566,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 0.3512,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.3139978051185608,
+      "eval_runtime": 222.18,
+      "eval_samples_per_second": 7.84,
+      "eval_steps_per_second": 7.84,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000125,
+      "loss": 0.1879,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00015,
+      "loss": 0.1468,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000175,
+      "loss": 0.152,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 0.1357,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.20455242693424225,
+      "eval_runtime": 222.1053,
+      "eval_samples_per_second": 7.843,
+      "eval_steps_per_second": 7.843,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000225,
+      "loss": 0.1162,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00025,
+      "loss": 0.1099,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00027499999999999996,
+      "loss": 0.3812,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.2093,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.12376075983047485,
+      "eval_runtime": 222.1103,
+      "eval_samples_per_second": 7.843,
+      "eval_steps_per_second": 7.843,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0002999994460825163,
+      "loss": 0.1396,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002999977843341562,
+      "loss": 0.1036,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00029999501476719257,
+      "loss": 0.0634,
+      "step": 75
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002999911374020804,
+      "loss": 0.0933,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.1939181536436081,
+      "eval_runtime": 222.0528,
+      "eval_samples_per_second": 7.845,
+      "eval_steps_per_second": 7.845,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00029998615226745605,
+      "loss": 0.0656,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002999800594001376,
+      "loss": 0.0519,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002999728588451245,
+      "loss": 0.0476,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0002999645506555967,
+      "loss": 0.0098,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.24784570932388306,
+      "eval_runtime": 222.2602,
+      "eval_samples_per_second": 7.838,
+      "eval_steps_per_second": 7.838,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00029995513489291506,
+      "loss": 0.356,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00029994461162662024,
+      "loss": 0.1972,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00029993298093443246,
+      "loss": 0.1255,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000299920242902251,
+      "loss": 0.0923,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.12546367943286896,
+      "eval_runtime": 222.0682,
+      "eval_samples_per_second": 7.844,
+      "eval_steps_per_second": 7.844,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002999063976241536,
+      "loss": 0.0504,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002998914452023953,
+      "loss": 0.1582,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00029987538574740826,
+      "loss": 0.0452,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002998582193778006,
+      "loss": 0.0258,
+      "step": 140
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.21805395185947418,
+      "eval_runtime": 224.118,
+      "eval_samples_per_second": 7.773,
+      "eval_steps_per_second": 7.773,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029983994622035585,
+      "loss": 0.032,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029982056641003147,
+      "loss": 0.0224,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029980008008995834,
+      "loss": 0.2454,
+      "step": 155
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029977848741143966,
+      "loss": 0.1583,
+      "step": 160
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 0.10049739480018616,
+      "eval_runtime": 224.1576,
+      "eval_samples_per_second": 7.771,
+      "eval_steps_per_second": 7.771,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002997557885339494,
+      "loss": 0.1388,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002997319836251319,
+      "loss": 0.0962,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029970707286079966,
+      "loss": 0.0602,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029968105642493286,
+      "loss": 0.0642,
+      "step": 180
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.10171639919281006,
+      "eval_runtime": 223.682,
+      "eval_samples_per_second": 7.788,
+      "eval_steps_per_second": 7.788,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002996539345096776,
+      "loss": 0.0499,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002996257073153446,
+      "loss": 0.0486,
+      "step": 190
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029959637505040773,
+      "loss": 0.0198,
+      "step": 195
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00029956593793150233,
+      "loss": 0.0359,
+      "step": 200
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.1516859233379364,
+      "eval_runtime": 228.4243,
+      "eval_samples_per_second": 7.626,
+      "eval_steps_per_second": 7.626,
+      "step": 200
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002995343961834238,
+      "loss": 0.2612,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00029950175003912573,
+      "loss": 0.1232,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002994679997397185,
+      "loss": 0.0861,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00029943314553446706,
+      "loss": 0.0867,
+      "step": 220
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.08929727226495743,
+      "eval_runtime": 229.1014,
+      "eval_samples_per_second": 7.604,
+      "eval_steps_per_second": 7.604,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002993971876807896,
+      "loss": 0.0485,
+      "step": 225
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00029936012644425517,
+      "loss": 0.0516,
+      "step": 230
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00029932196209858197,
+      "loss": 0.0583,
+      "step": 235
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00029928269492563537,
+      "loss": 0.0271,
+      "step": 240
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.13832463324069977,
+      "eval_runtime": 227.2299,
+      "eval_samples_per_second": 7.666,
+      "eval_steps_per_second": 7.666,
+      "step": 240
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00029924232521542557,
+      "loss": 0.0213,
+      "step": 245
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029920085326610595,
+      "loss": 0.0388,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00029915827938397017,
+      "loss": 0.3212,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002991146038834505,
+      "loss": 0.1213,
+      "step": 260
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.09067531675100327,
+      "eval_runtime": 228.6975,
+      "eval_samples_per_second": 7.617,
+      "eval_steps_per_second": 7.617,
+      "step": 260
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00029906982708711533,
+      "loss": 0.0905,
+      "step": 265
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00029902394932566657,
+      "loss": 0.0397,
+      "step": 270
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029897697093793753,
+      "loss": 0.0497,
+      "step": 275
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002989288922708902,
+      "loss": 0.0549,
+      "step": 280
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.10685621201992035,
+      "eval_runtime": 227.369,
+      "eval_samples_per_second": 7.662,
+      "eval_steps_per_second": 7.662,
+      "step": 280
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002988797136796128,
+      "loss": 0.0281,
+      "step": 285
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00029882943552731703,
+      "loss": 0.0586,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002987780581853355,
+      "loss": 0.0284,
+      "step": 295
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00029872558203311914,
+      "loss": 0.0436,
+      "step": 300
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.1119319349527359,
+      "eval_runtime": 221.5402,
+      "eval_samples_per_second": 7.863,
+      "eval_steps_per_second": 7.863,
+      "step": 300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00029867200745823384,
+      "loss": 0.1798,
+      "step": 305
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029861733485635834,
+      "loss": 0.1191,
+      "step": 310
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002985615646312807,
+      "loss": 0.0841,
+      "step": 315
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029850469719489573,
+      "loss": 0.1025,
+      "step": 320
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.08742260932922363,
+      "eval_runtime": 221.4467,
+      "eval_samples_per_second": 7.866,
+      "eval_steps_per_second": 7.866,
+      "step": 320
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029844673296720154,
+      "loss": 0.0457,
+      "step": 325
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029838767237629684,
+      "loss": 0.0465,
+      "step": 330
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002983275158583775,
+      "loss": 0.063,
+      "step": 335
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002982662638577335,
+      "loss": 0.0238,
+      "step": 340
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 0.14248833060264587,
+      "eval_runtime": 225.6871,
+      "eval_samples_per_second": 7.719,
+      "eval_steps_per_second": 7.719,
+      "step": 340
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029820391682674563,
+      "loss": 0.0205,
+      "step": 345
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00029814047522588194,
+      "loss": 0.0218,
+      "step": 350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00029807593952369465,
+      "loss": 0.2612,
+      "step": 355
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00029801031019681645,
+      "loss": 0.1889,
+      "step": 360
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.09468888491392136,
+      "eval_runtime": 228.9494,
+      "eval_samples_per_second": 7.609,
+      "eval_steps_per_second": 7.609,
+      "step": 360
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002979435877299571,
+      "loss": 0.0905,
+      "step": 365
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002978757726158998,
+      "loss": 0.0619,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00029780686535549756,
+      "loss": 0.0625,
+      "step": 375
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002977368664576696,
+      "loss": 0.0585,
+      "step": 380
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.08509568870067596,
+      "eval_runtime": 227.8786,
+      "eval_samples_per_second": 7.644,
+      "eval_steps_per_second": 7.644,
+      "step": 380
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00029766577643939744,
+      "loss": 0.0327,
+      "step": 385
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00029759359582572103,
+      "loss": 0.043,
+      "step": 390
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00029752032514973516,
+      "loss": 0.0234,
+      "step": 395
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00029744596495258525,
+      "loss": 0.0119,
+      "step": 400
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.09636981785297394,
+      "eval_runtime": 228.541,
+      "eval_samples_per_second": 7.622,
+      "eval_steps_per_second": 7.622,
+      "step": 400
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00029737051578346345,
+      "loss": 0.1557,
+      "step": 405
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002972939781996047,
+      "loss": 0.1116,
+      "step": 410
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002972163527662824,
+      "loss": 0.0638,
+      "step": 415
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00029713764005680427,
+      "loss": 0.0726,
+      "step": 420
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.07559170573949814,
+      "eval_runtime": 228.1262,
+      "eval_samples_per_second": 7.636,
+      "eval_steps_per_second": 7.636,
+      "step": 420
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 20,
+  "total_flos": 2.1261537057551155e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790952d63dabcb27434d04a2ca79e0e8844ccfcd3124036a9abca65a2d24669b
+size 4792

checkpoint-520/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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 0.7.1

checkpoint-520/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-520/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b53ee7dcaeabf5cde29fbb85e1525e09e6ad2c18e60945f0e0ffe3b7921d960
+size 9462656

checkpoint-520/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9370fd4be7d76a08c0b2c8f8848eefe47bd63a3d7bab937ed834b149ed32d9fd
+size 19035578

checkpoint-520/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0776f9f5ebfe31f0df16f250abbeb2c11060eb7e2204e2f7911a5eb73f6b08b
+size 14244

checkpoint-520/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69978fbe25427833c39316fa7fc29c20deed1ef3aa5af8275ccb6eef52a3c68c
+size 1064

checkpoint-520/trainer_state.json

@@ -0,0 +1,853 @@
+{
+  "best_metric": 0.07559170573949814,
+  "best_model_checkpoint": "./trained_models/Mistral-7B-Instruct-v0.2_-1pos_-1neg_perNE_top-1NEs_TrueDef-IT/checkpoint-420",
+  "epoch": 0.8902204151508667,
+  "eval_steps": 20,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4999999999999998e-05,
+      "loss": 6.4943,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9999999999999996e-05,
+      "loss": 3.9486,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.5e-05,
+      "loss": 0.4566,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 0.3512,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.3139978051185608,
+      "eval_runtime": 222.18,
+      "eval_samples_per_second": 7.84,
+      "eval_steps_per_second": 7.84,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000125,
+      "loss": 0.1879,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00015,
+      "loss": 0.1468,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000175,
+      "loss": 0.152,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 0.1357,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.20455242693424225,
+      "eval_runtime": 222.1053,
+      "eval_samples_per_second": 7.843,
+      "eval_steps_per_second": 7.843,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000225,
+      "loss": 0.1162,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00025,
+      "loss": 0.1099,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00027499999999999996,
+      "loss": 0.3812,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.2093,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.12376075983047485,
+      "eval_runtime": 222.1103,
+      "eval_samples_per_second": 7.843,
+      "eval_steps_per_second": 7.843,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0002999994460825163,
+      "loss": 0.1396,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002999977843341562,
+      "loss": 0.1036,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00029999501476719257,
+      "loss": 0.0634,
+      "step": 75
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0002999911374020804,
+      "loss": 0.0933,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.1939181536436081,
+      "eval_runtime": 222.0528,
+      "eval_samples_per_second": 7.845,
+      "eval_steps_per_second": 7.845,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00029998615226745605,
+      "loss": 0.0656,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002999800594001376,
+      "loss": 0.0519,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002999728588451245,
+      "loss": 0.0476,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0002999645506555967,
+      "loss": 0.0098,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.24784570932388306,
+      "eval_runtime": 222.2602,
+      "eval_samples_per_second": 7.838,
+      "eval_steps_per_second": 7.838,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00029995513489291506,
+      "loss": 0.356,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00029994461162662024,
+      "loss": 0.1972,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00029993298093443246,
+      "loss": 0.1255,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000299920242902251,
+      "loss": 0.0923,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.12546367943286896,
+      "eval_runtime": 222.0682,
+      "eval_samples_per_second": 7.844,
+      "eval_steps_per_second": 7.844,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002999063976241536,
+      "loss": 0.0504,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002998914452023953,
+      "loss": 0.1582,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00029987538574740826,
+      "loss": 0.0452,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002998582193778006,
+      "loss": 0.0258,
+      "step": 140
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.21805395185947418,
+      "eval_runtime": 224.118,
+      "eval_samples_per_second": 7.773,
+      "eval_steps_per_second": 7.773,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029983994622035585,
+      "loss": 0.032,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029982056641003147,
+      "loss": 0.0224,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029980008008995834,
+      "loss": 0.2454,
+      "step": 155
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029977848741143966,
+      "loss": 0.1583,
+      "step": 160
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 0.10049739480018616,
+      "eval_runtime": 224.1576,
+      "eval_samples_per_second": 7.771,
+      "eval_steps_per_second": 7.771,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002997557885339494,
+      "loss": 0.1388,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002997319836251319,
+      "loss": 0.0962,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029970707286079966,
+      "loss": 0.0602,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029968105642493286,
+      "loss": 0.0642,
+      "step": 180
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.10171639919281006,
+      "eval_runtime": 223.682,
+      "eval_samples_per_second": 7.788,
+      "eval_steps_per_second": 7.788,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002996539345096776,
+      "loss": 0.0499,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002996257073153446,
+      "loss": 0.0486,
+      "step": 190
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029959637505040773,
+      "loss": 0.0198,
+      "step": 195
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00029956593793150233,
+      "loss": 0.0359,
+      "step": 200
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.1516859233379364,
+      "eval_runtime": 228.4243,
+      "eval_samples_per_second": 7.626,
+      "eval_steps_per_second": 7.626,
+      "step": 200
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002995343961834238,
+      "loss": 0.2612,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00029950175003912573,
+      "loss": 0.1232,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002994679997397185,
+      "loss": 0.0861,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00029943314553446706,
+      "loss": 0.0867,
+      "step": 220
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.08929727226495743,
+      "eval_runtime": 229.1014,
+      "eval_samples_per_second": 7.604,
+      "eval_steps_per_second": 7.604,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002993971876807896,
+      "loss": 0.0485,
+      "step": 225
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00029936012644425517,
+      "loss": 0.0516,
+      "step": 230
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00029932196209858197,
+      "loss": 0.0583,
+      "step": 235
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00029928269492563537,
+      "loss": 0.0271,
+      "step": 240
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.13832463324069977,
+      "eval_runtime": 227.2299,
+      "eval_samples_per_second": 7.666,
+      "eval_steps_per_second": 7.666,
+      "step": 240
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00029924232521542557,
+      "loss": 0.0213,
+      "step": 245
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00029920085326610595,
+      "loss": 0.0388,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00029915827938397017,
+      "loss": 0.3212,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002991146038834505,
+      "loss": 0.1213,
+      "step": 260
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.09067531675100327,
+      "eval_runtime": 228.6975,
+      "eval_samples_per_second": 7.617,
+      "eval_steps_per_second": 7.617,
+      "step": 260
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00029906982708711533,
+      "loss": 0.0905,
+      "step": 265
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00029902394932566657,
+      "loss": 0.0397,
+      "step": 270
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029897697093793753,
+      "loss": 0.0497,
+      "step": 275
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002989288922708902,
+      "loss": 0.0549,
+      "step": 280
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.10685621201992035,
+      "eval_runtime": 227.369,
+      "eval_samples_per_second": 7.662,
+      "eval_steps_per_second": 7.662,
+      "step": 280
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002988797136796128,
+      "loss": 0.0281,
+      "step": 285
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00029882943552731703,
+      "loss": 0.0586,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002987780581853355,
+      "loss": 0.0284,
+      "step": 295
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00029872558203311914,
+      "loss": 0.0436,
+      "step": 300
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.1119319349527359,
+      "eval_runtime": 221.5402,
+      "eval_samples_per_second": 7.863,
+      "eval_steps_per_second": 7.863,
+      "step": 300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00029867200745823384,
+      "loss": 0.1798,
+      "step": 305
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00029861733485635834,
+      "loss": 0.1191,
+      "step": 310
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002985615646312807,
+      "loss": 0.0841,
+      "step": 315
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029850469719489573,
+      "loss": 0.1025,
+      "step": 320
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.08742260932922363,
+      "eval_runtime": 221.4467,
+      "eval_samples_per_second": 7.866,
+      "eval_steps_per_second": 7.866,
+      "step": 320
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029844673296720154,
+      "loss": 0.0457,
+      "step": 325
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029838767237629684,
+      "loss": 0.0465,
+      "step": 330
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002983275158583775,
+      "loss": 0.063,
+      "step": 335
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002982662638577335,
+      "loss": 0.0238,
+      "step": 340
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 0.14248833060264587,
+      "eval_runtime": 225.6871,
+      "eval_samples_per_second": 7.719,
+      "eval_steps_per_second": 7.719,
+      "step": 340
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029820391682674563,
+      "loss": 0.0205,
+      "step": 345
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00029814047522588194,
+      "loss": 0.0218,
+      "step": 350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00029807593952369465,
+      "loss": 0.2612,
+      "step": 355
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00029801031019681645,
+      "loss": 0.1889,
+      "step": 360
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.09468888491392136,
+      "eval_runtime": 228.9494,
+      "eval_samples_per_second": 7.609,
+      "eval_steps_per_second": 7.609,
+      "step": 360
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002979435877299571,
+      "loss": 0.0905,
+      "step": 365
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002978757726158998,
+      "loss": 0.0619,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00029780686535549756,
+      "loss": 0.0625,
+      "step": 375
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002977368664576696,
+      "loss": 0.0585,
+      "step": 380
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.08509568870067596,
+      "eval_runtime": 227.8786,
+      "eval_samples_per_second": 7.644,
+      "eval_steps_per_second": 7.644,
+      "step": 380
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00029766577643939744,
+      "loss": 0.0327,
+      "step": 385
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00029759359582572103,
+      "loss": 0.043,
+      "step": 390
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00029752032514973516,
+      "loss": 0.0234,
+      "step": 395
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00029744596495258525,
+      "loss": 0.0119,
+      "step": 400
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.09636981785297394,
+      "eval_runtime": 228.541,
+      "eval_samples_per_second": 7.622,
+      "eval_steps_per_second": 7.622,
+      "step": 400
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00029737051578346345,
+      "loss": 0.1557,
+      "step": 405
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002972939781996047,
+      "loss": 0.1116,
+      "step": 410
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002972163527662824,
+      "loss": 0.0638,
+      "step": 415
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00029713764005680427,
+      "loss": 0.0726,
+      "step": 420
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.07559170573949814,
+      "eval_runtime": 228.1262,
+      "eval_samples_per_second": 7.636,
+      "eval_steps_per_second": 7.636,
+      "step": 420
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00029705784065250826,
+      "loss": 0.0598,
+      "step": 425
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00029697695514275824,
+      "loss": 0.0352,
+      "step": 430
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002968949841249395,
+      "loss": 0.0284,
+      "step": 435
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00029681192820445445,
+      "loss": 0.0337,
+      "step": 440
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.10360870510339737,
+      "eval_runtime": 227.1852,
+      "eval_samples_per_second": 7.668,
+      "eval_steps_per_second": 7.668,
+      "step": 440
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00029672778799471797,
+      "loss": 0.0068,
+      "step": 445
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002966425641171534,
+      "loss": 0.0303,
+      "step": 450
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002965562572011872,
+      "loss": 0.1159,
+      "step": 455
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00029646886788424487,
+      "loss": 0.1036,
+      "step": 460
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.0761430412530899,
+      "eval_runtime": 228.7927,
+      "eval_samples_per_second": 7.614,
+      "eval_steps_per_second": 7.614,
+      "step": 460
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.000296380396811746,
+      "loss": 0.0702,
+      "step": 465
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00029629084463709957,
+      "loss": 0.0893,
+      "step": 470
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002962002120216992,
+      "loss": 0.0526,
+      "step": 475
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00029610849963491797,
+      "loss": 0.0314,
+      "step": 480
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.08553514629602432,
+      "eval_runtime": 227.4129,
+      "eval_samples_per_second": 7.66,
+      "eval_steps_per_second": 7.66,
+      "step": 480
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002960157081541039,
+      "loss": 0.0269,
+      "step": 485
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002959218382645746,
+      "loss": 0.0281,
+      "step": 490
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00029582689065961237,
+      "loss": 0.0132,
+      "step": 495
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00029573086604045904,
+      "loss": 0.0151,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.09203532338142395,
+      "eval_runtime": 228.4081,
+      "eval_samples_per_second": 7.627,
+      "eval_steps_per_second": 7.627,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002956337651163109,
+      "loss": 0.1379,
+      "step": 505
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00029553558860431317,
+      "loss": 0.1116,
+      "step": 510
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002954363372295551,
+      "loss": 0.0711,
+      "step": 515
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00029533601172506427,
+      "loss": 0.0606,
+      "step": 520
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.086419016122818,
+      "eval_runtime": 228.0366,
+      "eval_samples_per_second": 7.639,
+      "eval_steps_per_second": 7.639,
+      "step": 520
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 20,
+  "total_flos": 2.6286417487016755e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-520/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790952d63dabcb27434d04a2ca79e0e8844ccfcd3124036a9abca65a2d24669b
+size 4792

training_configs.yml

@@ -0,0 +1,44 @@
+# fine-tuning Llama-3-8b instruct version on PileNER with topNE NEs and N samples per NE (N positive + N negative)
+
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+prompt_template_name: llama2_italian
+# using dataset converted from MSEQA format to GenQA format (instruction, input, output) columns
+data_path: None
+val_data_path: None
+select_train_portion: -1
+val_set_size: -1  # if -1 use all validation data
+output_dir: None
+early_stopping_patience: 5
+#training hyperparams
+batch_size: 32
+micro_batch_size: 1
+num_epochs: 10
+learning_rate: 3.0e-4
+cutoff_len: 768
+
+warmup_steps: 60
+eval_steps: 20
+logging_steps: 5
+max_grad_norm: 1.0
+#lora hyperparams
+use_lora: True
+lora_alpha: 16
+lora_dropout: 0.05
+lora_r: 8
+lora_target_modules:
+- q_proj
+- v_proj
+- k_proj
+- v_proj
+#llm hyperparams
+# NTP loss only on Response
+train_on_inputs: False
+group_by_length: True
+#quant params
+load_8bit: False
+load_4bit: False
+#general param
+save_total_limit: 2
+use_flash_attention: False
+shuffle: True
+gradient_checkpointing: False