First model version

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89546f1cfae05459838f8ecf9be2a4c4d6a451ed955044b1776f32db6abb292e
+size 37803066

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6658bb803792a8187620edfb12529ca0e583a5f5c3f4c2680804c9b8a8152cf
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5b5a8b0c711f0f2e32411bb3a51d421097b304182a799a979fcef82fd40741
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.16326530612245,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 4.8025,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": NaN,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 4.1014,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": NaN,
+      "eval_runtime": 53.4777,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.0,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 4.7645,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-05,
+      "loss": 4.3747,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6778,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": NaN,
+      "learning_rate": 0.000102,
+      "loss": 5.0924,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 4.3234,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7614,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.911,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 4.1684,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 4.3018,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6674,
+      "eval_samples_per_second": 7.211,
+      "eval_steps_per_second": 0.913,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 2.5324407405674496e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f6bb506054796e9e714a7ca32503916b4a84a4d68384f001ba913152b2ec2
+size 4856

checkpoint-120/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-120/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdf10e8bd7abae1cbe41e713657356fab124df9737617b40e6dbf8a20a97e6c
+size 37803066

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3201b9328a8797a342d60e68ac1db3faf1e570a609d56a74a19418179c1013
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0293f0ef471ab336f010a06133785c4b0a8abde856102589019680f63c506b
+size 1064

checkpoint-120/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.795918367346939,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 4.8025,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": NaN,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 4.1014,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": NaN,
+      "eval_runtime": 53.4777,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.0,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 4.7645,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-05,
+      "loss": 4.3747,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6778,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": NaN,
+      "learning_rate": 0.000102,
+      "loss": 5.0924,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 4.3234,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7614,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.911,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 4.1684,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 4.3018,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6674,
+      "eval_samples_per_second": 7.211,
+      "eval_steps_per_second": 0.913,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "grad_norm": NaN,
+      "learning_rate": 0.000162,
+      "loss": 4.8328,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 3.8634,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": NaN,
+      "eval_runtime": 53.8298,
+      "eval_samples_per_second": 7.189,
+      "eval_steps_per_second": 0.91,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 3.040578886267699e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f6bb506054796e9e714a7ca32503916b4a84a4d68384f001ba913152b2ec2
+size 4856

checkpoint-140/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-140/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-140/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2507b3e5648f990de5bba05fe789ffa15356143e24e38c1084ce8c0970886314
+size 37803066

checkpoint-140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d46991217c6d21a6618c7cd7c5d36c9b48595eb1380dec7899ffa770f517389
+size 14244

checkpoint-140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf42dc04fd68d790bde68418c2c0cdd87da27fb120bf5bde1029d4bdb19665c
+size 1064

checkpoint-140/trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.428571428571429,
+  "eval_steps": 20,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 4.8025,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": NaN,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 4.1014,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": NaN,
+      "eval_runtime": 53.4777,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.0,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 4.7645,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-05,
+      "loss": 4.3747,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6778,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": NaN,
+      "learning_rate": 0.000102,
+      "loss": 5.0924,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 4.3234,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7614,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.911,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 4.1684,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 4.3018,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6674,
+      "eval_samples_per_second": 7.211,
+      "eval_steps_per_second": 0.913,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "grad_norm": NaN,
+      "learning_rate": 0.000162,
+      "loss": 4.8328,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 3.8634,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": NaN,
+      "eval_runtime": 53.8298,
+      "eval_samples_per_second": 7.189,
+      "eval_steps_per_second": 0.91,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 4.8214,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000195,
+      "loss": 5.3188,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6779,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 3.5458651842871296e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f6bb506054796e9e714a7ca32503916b4a84a4d68384f001ba913152b2ec2
+size 4856

checkpoint-160/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-160/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-160/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890f55baf5e8c007117520504265367020a0a770a43606d7b93aa2b1f05cbfe4
+size 37803066

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c838e8cb08fdf3fa98e1eae71b7e8c486cc8c28282e66eaab882393e9d12c9ab
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b111cd45660eb1face1bcfa06f33e48dc20123917f55da0a1daffb00d391c810
+size 1064

checkpoint-160/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.061224489795919,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 4.8025,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": NaN,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 4.1014,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": NaN,
+      "eval_runtime": 53.4777,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.0,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 4.7645,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-05,
+      "loss": 4.3747,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6778,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": NaN,
+      "learning_rate": 0.000102,
+      "loss": 5.0924,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 4.3234,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7614,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.911,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 4.1684,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 4.3018,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6674,
+      "eval_samples_per_second": 7.211,
+      "eval_steps_per_second": 0.913,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "grad_norm": NaN,
+      "learning_rate": 0.000162,
+      "loss": 4.8328,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 3.8634,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": NaN,
+      "eval_runtime": 53.8298,
+      "eval_samples_per_second": 7.189,
+      "eval_steps_per_second": 0.91,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 4.8214,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000195,
+      "loss": 5.3188,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6779,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 140
+    },
+    {
+      "epoch": 12.24,
+      "grad_norm": NaN,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 3.932,
+      "step": 150
+    },
+    {
+      "epoch": 13.06,
+      "grad_norm": NaN,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 4.5087,
+      "step": 160
+    },
+    {
+      "epoch": 13.06,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7126,
+      "eval_samples_per_second": 7.205,
+      "eval_steps_per_second": 0.912,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 4.049929261871923e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f6bb506054796e9e714a7ca32503916b4a84a4d68384f001ba913152b2ec2
+size 4856

checkpoint-180/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-180/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44a8aee4a9aebded4b15dca69d9b93da6b2cdd72e835b737c908fac001356e9
+size 37803066

checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a617908633b9e4096bf3a04ee0c0565bf03438029712e268d2687e943ecd9747
+size 14244

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e2940a6b6f7aaca29b769bc58976a81b780ffd50504916097bd9d1c2b94c46
+size 1064

checkpoint-180/trainer_state.json

@@ -0,0 +1,219 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.693877551020408,
+  "eval_steps": 20,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": NaN,
+      "learning_rate": 4.2e-05,
+      "loss": 4.8025,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": NaN,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 4.1014,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": NaN,
+      "eval_runtime": 53.4777,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.0,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 4.7645,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-05,
+      "loss": 4.3747,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6778,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": NaN,
+      "learning_rate": 0.000102,
+      "loss": 5.0924,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 4.3234,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7614,
+      "eval_samples_per_second": 7.198,
+      "eval_steps_per_second": 0.911,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 4.1684,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 4.3018,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6674,
+      "eval_samples_per_second": 7.211,
+      "eval_steps_per_second": 0.913,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "grad_norm": NaN,
+      "learning_rate": 0.000162,
+      "loss": 4.8328,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 3.8634,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": NaN,
+      "eval_runtime": 53.8298,
+      "eval_samples_per_second": 7.189,
+      "eval_steps_per_second": 0.91,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 4.8214,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000195,
+      "loss": 5.3188,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6779,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.913,
+      "step": 140
+    },
+    {
+      "epoch": 12.24,
+      "grad_norm": NaN,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 3.932,
+      "step": 150
+    },
+    {
+      "epoch": 13.06,
+      "grad_norm": NaN,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 4.5087,
+      "step": 160
+    },
+    {
+      "epoch": 13.06,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7126,
+      "eval_samples_per_second": 7.205,
+      "eval_steps_per_second": 0.912,
+      "step": 160
+    },
+    {
+      "epoch": 13.88,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 4.1573,
+      "step": 170
+    },
+    {
+      "epoch": 14.69,
+      "grad_norm": NaN,
+      "learning_rate": 0.000249,
+      "loss": 3.9824,
+      "step": 180
+    },
+    {
+      "epoch": 14.69,
+      "eval_loss": NaN,
+      "eval_runtime": 53.7148,
+      "eval_samples_per_second": 7.205,
+      "eval_steps_per_second": 0.912,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 4.5597988865212416e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f6bb506054796e9e714a7ca32503916b4a84a4d68384f001ba913152b2ec2
+size 4856

checkpoint-20/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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 0.8.2

checkpoint-20/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-20/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c802c2cd6845072a759a7e0126fde304b27888c6bdb51b6b63a6ecfd11d175
+size 37803066

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cbff5311c7f9daf555dae1bb3c44151172e3d399ce87d0ce1da5a72fef680f
+size 14244

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a50562abe9aa2ac417f3ee985d4bb2326b0bd2d9e6a5e360bc96423fce4c04d
+size 1064

checkpoint-20/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6326530612244898,
+  "eval_steps": 20,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1748005896806717,
+      "learning_rate": 2.1e-05,
+      "loss": 4.8309,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.19310609996318817,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 5.0159,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": NaN,
+      "eval_runtime": 53.474,
+      "eval_samples_per_second": 7.237,
+      "eval_steps_per_second": 0.916,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 5.088511076204544e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}