Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "Wqkv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec272f418af250953f9687d3b4b0ff297995374e7d84ac68e9f8faa1766fcf7
+size 104873776

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "Wqkv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f906c5d3e388a2d5ecf61895773db50c72d8f9c64591ffacee8915d519574823
+size 104873776

checkpoint-1000/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59605945d3e848f116f8cc0e54bcbbb505127367cb69aaee24479ca6910f98a1
+size 209823354

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d6cc51498722af828d93423d42881fb037f68835c5e85d908dc45eac89019e
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013b53308e69e629de6afff115b44bf446b1e9de2528156efbf815a68d926414
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,329 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,759 @@
+{
+  "best_metric": 0.48148148148148145,
+  "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-1000",
+  "epoch": 0.2907399331298154,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029073993312981536,
+      "grad_norm": 4.615232944488525,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 6.6211,
+      "step": 10
+    },
+    {
+      "epoch": 0.005814798662596307,
+      "grad_norm": 5.528043746948242,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 6.5222,
+      "step": 20
+    },
+    {
+      "epoch": 0.00872219799389446,
+      "grad_norm": 6.019925594329834,
+      "learning_rate": 3e-06,
+      "loss": 6.4104,
+      "step": 30
+    },
+    {
+      "epoch": 0.011629597325192614,
+      "grad_norm": 7.163036823272705,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 6.0366,
+      "step": 40
+    },
+    {
+      "epoch": 0.01453699665649077,
+      "grad_norm": 7.888458251953125,
+      "learning_rate": 5e-06,
+      "loss": 5.4618,
+      "step": 50
+    },
+    {
+      "epoch": 0.01744439598778892,
+      "grad_norm": 9.86289119720459,
+      "learning_rate": 6e-06,
+      "loss": 4.526,
+      "step": 60
+    },
+    {
+      "epoch": 0.020351795319087075,
+      "grad_norm": 9.114004135131836,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 3.2234,
+      "step": 70
+    },
+    {
+      "epoch": 0.02325919465038523,
+      "grad_norm": 6.198110103607178,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6796,
+      "step": 80
+    },
+    {
+      "epoch": 0.026166593981683386,
+      "grad_norm": 1.2424126863479614,
+      "learning_rate": 9e-06,
+      "loss": 0.6189,
+      "step": 90
+    },
+    {
+      "epoch": 0.02907399331298154,
+      "grad_norm": 0.20757392048835754,
+      "learning_rate": 1e-05,
+      "loss": 0.2989,
+      "step": 100
+    },
+    {
+      "epoch": 0.03198139264427969,
+      "grad_norm": 0.19180330634117126,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.3434,
+      "step": 110
+    },
+    {
+      "epoch": 0.03488879197557784,
+      "grad_norm": 0.17373745143413544,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2775,
+      "step": 120
+    },
+    {
+      "epoch": 0.037796191306876,
+      "grad_norm": 0.14247311651706696,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.291,
+      "step": 130
+    },
+    {
+      "epoch": 0.04070359063817415,
+      "grad_norm": 0.1189289391040802,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.2549,
+      "step": 140
+    },
+    {
+      "epoch": 0.043610989969472304,
+      "grad_norm": 0.11715172231197357,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2334,
+      "step": 150
+    },
+    {
+      "epoch": 0.04651838930077046,
+      "grad_norm": 0.16550108790397644,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2515,
+      "step": 160
+    },
+    {
+      "epoch": 0.04942578863206862,
+      "grad_norm": 0.13685165345668793,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.2757,
+      "step": 170
+    },
+    {
+      "epoch": 0.05233318796336677,
+      "grad_norm": 0.13247624039649963,
+      "learning_rate": 1.8e-05,
+      "loss": 0.2336,
+      "step": 180
+    },
+    {
+      "epoch": 0.055240587294664925,
+      "grad_norm": 0.13763906061649323,
+      "learning_rate": 1.9e-05,
+      "loss": 0.2169,
+      "step": 190
+    },
+    {
+      "epoch": 0.05814798662596308,
+      "grad_norm": 0.1327727884054184,
+      "learning_rate": 2e-05,
+      "loss": 0.2007,
+      "step": 200
+    },
+    {
+      "epoch": 0.06105538595726123,
+      "grad_norm": 0.1083875447511673,
+      "learning_rate": 2.1e-05,
+      "loss": 0.2181,
+      "step": 210
+    },
+    {
+      "epoch": 0.06396278528855938,
+      "grad_norm": 0.12445604056119919,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.2969,
+      "step": 220
+    },
+    {
+      "epoch": 0.06687018461985754,
+      "grad_norm": 0.15511994063854218,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.1868,
+      "step": 230
+    },
+    {
+      "epoch": 0.06977758395115569,
+      "grad_norm": 0.13466577231884003,
+      "learning_rate": 2.4e-05,
+      "loss": 0.25,
+      "step": 240
+    },
+    {
+      "epoch": 0.07268498328245385,
+      "grad_norm": 0.06756726652383804,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1809,
+      "step": 250
+    },
+    {
+      "epoch": 0.075592382613752,
+      "grad_norm": 0.1573372632265091,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1963,
+      "step": 260
+    },
+    {
+      "epoch": 0.07849978194505015,
+      "grad_norm": 0.13099811971187592,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.1984,
+      "step": 270
+    },
+    {
+      "epoch": 0.0814071812763483,
+      "grad_norm": 0.11419626325368881,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.1665,
+      "step": 280
+    },
+    {
+      "epoch": 0.08431458060764646,
+      "grad_norm": 0.10189209878444672,
+      "learning_rate": 2.9e-05,
+      "loss": 0.1749,
+      "step": 290
+    },
+    {
+      "epoch": 0.08722197993894461,
+      "grad_norm": 0.12042666226625443,
+      "learning_rate": 3e-05,
+      "loss": 0.1528,
+      "step": 300
+    },
+    {
+      "epoch": 0.09012937927024277,
+      "grad_norm": 0.08344505727291107,
+      "learning_rate": 3.1e-05,
+      "loss": 0.181,
+      "step": 310
+    },
+    {
+      "epoch": 0.09303677860154091,
+      "grad_norm": 0.11566774547100067,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.09594417793283908,
+      "grad_norm": 0.1531219631433487,
+      "learning_rate": 3.3e-05,
+      "loss": 0.1564,
+      "step": 330
+    },
+    {
+      "epoch": 0.09885157726413724,
+      "grad_norm": 0.08966905623674393,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.1281,
+      "step": 340
+    },
+    {
+      "epoch": 0.10175897659543538,
+      "grad_norm": 0.08444681763648987,
+      "learning_rate": 3.5e-05,
+      "loss": 0.1258,
+      "step": 350
+    },
+    {
+      "epoch": 0.10466637592673354,
+      "grad_norm": 0.10482101142406464,
+      "learning_rate": 3.6e-05,
+      "loss": 0.1292,
+      "step": 360
+    },
+    {
+      "epoch": 0.10757377525803169,
+      "grad_norm": 0.14638499915599823,
+      "learning_rate": 3.7e-05,
+      "loss": 0.1829,
+      "step": 370
+    },
+    {
+      "epoch": 0.11048117458932985,
+      "grad_norm": 0.1461925059556961,
+      "learning_rate": 3.8e-05,
+      "loss": 0.2158,
+      "step": 380
+    },
+    {
+      "epoch": 0.113388573920628,
+      "grad_norm": 0.16068245470523834,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.2219,
+      "step": 390
+    },
+    {
+      "epoch": 0.11629597325192616,
+      "grad_norm": 0.13314808905124664,
+      "learning_rate": 4e-05,
+      "loss": 0.1622,
+      "step": 400
+    },
+    {
+      "epoch": 0.1192033725832243,
+      "grad_norm": 0.13541767001152039,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1363,
+      "step": 410
+    },
+    {
+      "epoch": 0.12211077191452246,
+      "grad_norm": 0.14549389481544495,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1664,
+      "step": 420
+    },
+    {
+      "epoch": 0.12501817124582063,
+      "grad_norm": 0.09966716170310974,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1446,
+      "step": 430
+    },
+    {
+      "epoch": 0.12792557057711876,
+      "grad_norm": 0.10374356061220169,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1302,
+      "step": 440
+    },
+    {
+      "epoch": 0.13083296990841692,
+      "grad_norm": 0.10534253716468811,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1612,
+      "step": 450
+    },
+    {
+      "epoch": 0.13374036923971508,
+      "grad_norm": 0.14981906116008759,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1782,
+      "step": 460
+    },
+    {
+      "epoch": 0.13664776857101324,
+      "grad_norm": 0.08772515505552292,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1303,
+      "step": 470
+    },
+    {
+      "epoch": 0.13955516790231137,
+      "grad_norm": 0.14555956423282623,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1259,
+      "step": 480
+    },
+    {
+      "epoch": 0.14246256723360953,
+      "grad_norm": 0.08366917818784714,
+      "learning_rate": 4.9e-05,
+      "loss": 0.1827,
+      "step": 490
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "grad_norm": 0.13676565885543823,
+      "learning_rate": 5e-05,
+      "loss": 0.1563,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_accuracy": 0.4444444444444444,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_loss": 0.15286579728126526,
+      "eval_runtime": 120.6585,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
+      "step": 500
+    },
+    {
+      "epoch": 0.14827736589620585,
+      "grad_norm": 0.16602879762649536,
+      "learning_rate": 4.982987410683906e-05,
+      "loss": 0.1322,
+      "step": 510
+    },
+    {
+      "epoch": 0.151184765227504,
+      "grad_norm": 0.12974093854427338,
+      "learning_rate": 4.965974821367813e-05,
+      "loss": 0.1432,
+      "step": 520
+    },
+    {
+      "epoch": 0.15409216455880215,
+      "grad_norm": 0.10730555653572083,
+      "learning_rate": 4.948962232051719e-05,
+      "loss": 0.1344,
+      "step": 530
+    },
+    {
+      "epoch": 0.1569995638901003,
+      "grad_norm": 0.09881391376256943,
+      "learning_rate": 4.931949642735625e-05,
+      "loss": 0.1207,
+      "step": 540
+    },
+    {
+      "epoch": 0.15990696322139847,
+      "grad_norm": 0.15530119836330414,
+      "learning_rate": 4.9149370534195306e-05,
+      "loss": 0.2084,
+      "step": 550
+    },
+    {
+      "epoch": 0.1628143625526966,
+      "grad_norm": 0.1018906682729721,
+      "learning_rate": 4.8979244641034366e-05,
+      "loss": 0.1465,
+      "step": 560
+    },
+    {
+      "epoch": 0.16572176188399476,
+      "grad_norm": 0.11174057424068451,
+      "learning_rate": 4.8809118747873425e-05,
+      "loss": 0.1704,
+      "step": 570
+    },
+    {
+      "epoch": 0.16862916121529292,
+      "grad_norm": 0.13199737668037415,
+      "learning_rate": 4.863899285471249e-05,
+      "loss": 0.1376,
+      "step": 580
+    },
+    {
+      "epoch": 0.17153656054659108,
+      "grad_norm": 0.12376833707094193,
+      "learning_rate": 4.846886696155155e-05,
+      "loss": 0.1848,
+      "step": 590
+    },
+    {
+      "epoch": 0.17444395987788922,
+      "grad_norm": 0.10838288813829422,
+      "learning_rate": 4.829874106839061e-05,
+      "loss": 0.1327,
+      "step": 600
+    },
+    {
+      "epoch": 0.17735135920918738,
+      "grad_norm": 0.09848768264055252,
+      "learning_rate": 4.8128615175229676e-05,
+      "loss": 0.1807,
+      "step": 610
+    },
+    {
+      "epoch": 0.18025875854048554,
+      "grad_norm": 0.10199768096208572,
+      "learning_rate": 4.7958489282068736e-05,
+      "loss": 0.1475,
+      "step": 620
+    },
+    {
+      "epoch": 0.1831661578717837,
+      "grad_norm": 0.1114463359117508,
+      "learning_rate": 4.7788363388907795e-05,
+      "loss": 0.1458,
+      "step": 630
+    },
+    {
+      "epoch": 0.18607355720308183,
+      "grad_norm": 0.09931254386901855,
+      "learning_rate": 4.7618237495746855e-05,
+      "loss": 0.1572,
+      "step": 640
+    },
+    {
+      "epoch": 0.18898095653438,
+      "grad_norm": 0.07883786410093307,
+      "learning_rate": 4.7448111602585914e-05,
+      "loss": 0.1502,
+      "step": 650
+    },
+    {
+      "epoch": 0.19188835586567815,
+      "grad_norm": 0.1312653124332428,
+      "learning_rate": 4.7277985709424973e-05,
+      "loss": 0.1306,
+      "step": 660
+    },
+    {
+      "epoch": 0.1947957551969763,
+      "grad_norm": 0.10453817993402481,
+      "learning_rate": 4.710785981626404e-05,
+      "loss": 0.1516,
+      "step": 670
+    },
+    {
+      "epoch": 0.19770315452827447,
+      "grad_norm": 0.13967570662498474,
+      "learning_rate": 4.69377339231031e-05,
+      "loss": 0.1976,
+      "step": 680
+    },
+    {
+      "epoch": 0.2006105538595726,
+      "grad_norm": 0.09553707391023636,
+      "learning_rate": 4.676760802994216e-05,
+      "loss": 0.1291,
+      "step": 690
+    },
+    {
+      "epoch": 0.20351795319087077,
+      "grad_norm": 0.14968940615653992,
+      "learning_rate": 4.6597482136781225e-05,
+      "loss": 0.1669,
+      "step": 700
+    },
+    {
+      "epoch": 0.20642535252216893,
+      "grad_norm": 0.10163428634405136,
+      "learning_rate": 4.642735624362028e-05,
+      "loss": 0.1727,
+      "step": 710
+    },
+    {
+      "epoch": 0.2093327518534671,
+      "grad_norm": 0.13607974350452423,
+      "learning_rate": 4.6257230350459343e-05,
+      "loss": 0.1473,
+      "step": 720
+    },
+    {
+      "epoch": 0.21224015118476522,
+      "grad_norm": 0.0766085609793663,
+      "learning_rate": 4.60871044572984e-05,
+      "loss": 0.1419,
+      "step": 730
+    },
+    {
+      "epoch": 0.21514755051606338,
+      "grad_norm": 0.11004997789859772,
+      "learning_rate": 4.591697856413746e-05,
+      "loss": 0.1344,
+      "step": 740
+    },
+    {
+      "epoch": 0.21805494984736154,
+      "grad_norm": 0.10307681560516357,
+      "learning_rate": 4.574685267097653e-05,
+      "loss": 0.1355,
+      "step": 750
+    },
+    {
+      "epoch": 0.2209623491786597,
+      "grad_norm": 0.098714679479599,
+      "learning_rate": 4.557672677781559e-05,
+      "loss": 0.1565,
+      "step": 760
+    },
+    {
+      "epoch": 0.22386974850995783,
+      "grad_norm": 0.1346523016691208,
+      "learning_rate": 4.540660088465465e-05,
+      "loss": 0.1675,
+      "step": 770
+    },
+    {
+      "epoch": 0.226777147841256,
+      "grad_norm": 0.12962771952152252,
+      "learning_rate": 4.5236474991493714e-05,
+      "loss": 0.1058,
+      "step": 780
+    },
+    {
+      "epoch": 0.22968454717255415,
+      "grad_norm": 0.14412884414196014,
+      "learning_rate": 4.5066349098332766e-05,
+      "loss": 0.198,
+      "step": 790
+    },
+    {
+      "epoch": 0.23259194650385231,
+      "grad_norm": 0.14253386855125427,
+      "learning_rate": 4.4896223205171826e-05,
+      "loss": 0.1319,
+      "step": 800
+    },
+    {
+      "epoch": 0.23549934583515045,
+      "grad_norm": 0.2203107625246048,
+      "learning_rate": 4.472609731201089e-05,
+      "loss": 0.1729,
+      "step": 810
+    },
+    {
+      "epoch": 0.2384067451664486,
+      "grad_norm": 0.09438087791204453,
+      "learning_rate": 4.455597141884995e-05,
+      "loss": 0.1558,
+      "step": 820
+    },
+    {
+      "epoch": 0.24131414449774677,
+      "grad_norm": 0.09754593670368195,
+      "learning_rate": 4.438584552568901e-05,
+      "loss": 0.1729,
+      "step": 830
+    },
+    {
+      "epoch": 0.24422154382904493,
+      "grad_norm": 0.1403294950723648,
+      "learning_rate": 4.421571963252808e-05,
+      "loss": 0.1871,
+      "step": 840
+    },
+    {
+      "epoch": 0.24712894316034306,
+      "grad_norm": 0.11251681298017502,
+      "learning_rate": 4.4045593739367136e-05,
+      "loss": 0.1726,
+      "step": 850
+    },
+    {
+      "epoch": 0.25003634249164125,
+      "grad_norm": 0.13492991030216217,
+      "learning_rate": 4.3875467846206196e-05,
+      "loss": 0.1349,
+      "step": 860
+    },
+    {
+      "epoch": 0.2529437418229394,
+      "grad_norm": 0.11674369871616364,
+      "learning_rate": 4.3705341953045255e-05,
+      "loss": 0.2088,
+      "step": 870
+    },
+    {
+      "epoch": 0.2558511411542375,
+      "grad_norm": 0.09339413791894913,
+      "learning_rate": 4.3535216059884315e-05,
+      "loss": 0.1656,
+      "step": 880
+    },
+    {
+      "epoch": 0.2587585404855357,
+      "grad_norm": 0.10234147310256958,
+      "learning_rate": 4.3365090166723374e-05,
+      "loss": 0.1495,
+      "step": 890
+    },
+    {
+      "epoch": 0.26166593981683384,
+      "grad_norm": 0.09566229581832886,
+      "learning_rate": 4.319496427356244e-05,
+      "loss": 0.109,
+      "step": 900
+    },
+    {
+      "epoch": 0.26457333914813197,
+      "grad_norm": 0.10038291662931442,
+      "learning_rate": 4.30248383804015e-05,
+      "loss": 0.1849,
+      "step": 910
+    },
+    {
+      "epoch": 0.26748073847943016,
+      "grad_norm": 0.12414570152759552,
+      "learning_rate": 4.285471248724056e-05,
+      "loss": 0.1476,
+      "step": 920
+    },
+    {
+      "epoch": 0.2703881378107283,
+      "grad_norm": 0.0866188034415245,
+      "learning_rate": 4.2684586594079625e-05,
+      "loss": 0.1339,
+      "step": 930
+    },
+    {
+      "epoch": 0.2732955371420265,
+      "grad_norm": 0.20008312165737152,
+      "learning_rate": 4.2514460700918685e-05,
+      "loss": 0.1865,
+      "step": 940
+    },
+    {
+      "epoch": 0.2762029364733246,
+      "grad_norm": 0.09849795699119568,
+      "learning_rate": 4.2344334807757744e-05,
+      "loss": 0.1293,
+      "step": 950
+    },
+    {
+      "epoch": 0.27911033580462274,
+      "grad_norm": 0.11204036325216293,
+      "learning_rate": 4.2174208914596803e-05,
+      "loss": 0.1817,
+      "step": 960
+    },
+    {
+      "epoch": 0.28201773513592093,
+      "grad_norm": 0.0960935726761818,
+      "learning_rate": 4.200408302143586e-05,
+      "loss": 0.1454,
+      "step": 970
+    },
+    {
+      "epoch": 0.28492513446721907,
+      "grad_norm": 0.12531103193759918,
+      "learning_rate": 4.183395712827492e-05,
+      "loss": 0.126,
+      "step": 980
+    },
+    {
+      "epoch": 0.28783253379851725,
+      "grad_norm": 0.1162460595369339,
+      "learning_rate": 4.166383123511399e-05,
+      "loss": 0.1634,
+      "step": 990
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "grad_norm": 0.06354565173387527,
+      "learning_rate": 4.149370534195305e-05,
+      "loss": 0.0986,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_accuracy": 0.48148148148148145,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_loss": 0.14855271577835083,
+      "eval_runtime": 120.8042,
+      "eval_samples_per_second": 2.012,
+      "eval_steps_per_second": 2.012,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3439,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3147305934848e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b868ef95d608a436278794d3830d43d18443ff20bb16e5eb13dcb771311e6732
+size 5048

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "Wqkv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92aeff9cd4b114ba319266ab97754d3b3d4fd1fa4e1197e785b1dda8501c5cf
+size 104873776

checkpoint-1500/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90992d94e23125e6b51312994998a24764316e8a153ee140959905c3c9003aa9
+size 209823354

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9d5db3ac6e1968c5cff607b860e169b88d974d4b197abaf8c9a9c47cded8c7
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186c3a558bf54c54cbd2d1a2fa1a350e481f8d649e5aa7ee7c2ff361fa2540dd
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,329 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1122 @@
+{
+  "best_metric": 0.48148148148148145,
+  "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-1000",
+  "epoch": 0.4361098996947231,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029073993312981536,
+      "grad_norm": 4.615232944488525,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 6.6211,
+      "step": 10
+    },
+    {
+      "epoch": 0.005814798662596307,
+      "grad_norm": 5.528043746948242,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 6.5222,
+      "step": 20
+    },
+    {
+      "epoch": 0.00872219799389446,
+      "grad_norm": 6.019925594329834,
+      "learning_rate": 3e-06,
+      "loss": 6.4104,
+      "step": 30
+    },
+    {
+      "epoch": 0.011629597325192614,
+      "grad_norm": 7.163036823272705,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 6.0366,
+      "step": 40
+    },
+    {
+      "epoch": 0.01453699665649077,
+      "grad_norm": 7.888458251953125,
+      "learning_rate": 5e-06,
+      "loss": 5.4618,
+      "step": 50
+    },
+    {
+      "epoch": 0.01744439598778892,
+      "grad_norm": 9.86289119720459,
+      "learning_rate": 6e-06,
+      "loss": 4.526,
+      "step": 60
+    },
+    {
+      "epoch": 0.020351795319087075,
+      "grad_norm": 9.114004135131836,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 3.2234,
+      "step": 70
+    },
+    {
+      "epoch": 0.02325919465038523,
+      "grad_norm": 6.198110103607178,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6796,
+      "step": 80
+    },
+    {
+      "epoch": 0.026166593981683386,
+      "grad_norm": 1.2424126863479614,
+      "learning_rate": 9e-06,
+      "loss": 0.6189,
+      "step": 90
+    },
+    {
+      "epoch": 0.02907399331298154,
+      "grad_norm": 0.20757392048835754,
+      "learning_rate": 1e-05,
+      "loss": 0.2989,
+      "step": 100
+    },
+    {
+      "epoch": 0.03198139264427969,
+      "grad_norm": 0.19180330634117126,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.3434,
+      "step": 110
+    },
+    {
+      "epoch": 0.03488879197557784,
+      "grad_norm": 0.17373745143413544,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2775,
+      "step": 120
+    },
+    {
+      "epoch": 0.037796191306876,
+      "grad_norm": 0.14247311651706696,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.291,
+      "step": 130
+    },
+    {
+      "epoch": 0.04070359063817415,
+      "grad_norm": 0.1189289391040802,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.2549,
+      "step": 140
+    },
+    {
+      "epoch": 0.043610989969472304,
+      "grad_norm": 0.11715172231197357,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2334,
+      "step": 150
+    },
+    {
+      "epoch": 0.04651838930077046,
+      "grad_norm": 0.16550108790397644,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2515,
+      "step": 160
+    },
+    {
+      "epoch": 0.04942578863206862,
+      "grad_norm": 0.13685165345668793,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.2757,
+      "step": 170
+    },
+    {
+      "epoch": 0.05233318796336677,
+      "grad_norm": 0.13247624039649963,
+      "learning_rate": 1.8e-05,
+      "loss": 0.2336,
+      "step": 180
+    },
+    {
+      "epoch": 0.055240587294664925,
+      "grad_norm": 0.13763906061649323,
+      "learning_rate": 1.9e-05,
+      "loss": 0.2169,
+      "step": 190
+    },
+    {
+      "epoch": 0.05814798662596308,
+      "grad_norm": 0.1327727884054184,
+      "learning_rate": 2e-05,
+      "loss": 0.2007,
+      "step": 200
+    },
+    {
+      "epoch": 0.06105538595726123,
+      "grad_norm": 0.1083875447511673,
+      "learning_rate": 2.1e-05,
+      "loss": 0.2181,
+      "step": 210
+    },
+    {
+      "epoch": 0.06396278528855938,
+      "grad_norm": 0.12445604056119919,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.2969,
+      "step": 220
+    },
+    {
+      "epoch": 0.06687018461985754,
+      "grad_norm": 0.15511994063854218,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.1868,
+      "step": 230
+    },
+    {
+      "epoch": 0.06977758395115569,
+      "grad_norm": 0.13466577231884003,
+      "learning_rate": 2.4e-05,
+      "loss": 0.25,
+      "step": 240
+    },
+    {
+      "epoch": 0.07268498328245385,
+      "grad_norm": 0.06756726652383804,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1809,
+      "step": 250
+    },
+    {
+      "epoch": 0.075592382613752,
+      "grad_norm": 0.1573372632265091,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1963,
+      "step": 260
+    },
+    {
+      "epoch": 0.07849978194505015,
+      "grad_norm": 0.13099811971187592,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.1984,
+      "step": 270
+    },
+    {
+      "epoch": 0.0814071812763483,
+      "grad_norm": 0.11419626325368881,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.1665,
+      "step": 280
+    },
+    {
+      "epoch": 0.08431458060764646,
+      "grad_norm": 0.10189209878444672,
+      "learning_rate": 2.9e-05,
+      "loss": 0.1749,
+      "step": 290
+    },
+    {
+      "epoch": 0.08722197993894461,
+      "grad_norm": 0.12042666226625443,
+      "learning_rate": 3e-05,
+      "loss": 0.1528,
+      "step": 300
+    },
+    {
+      "epoch": 0.09012937927024277,
+      "grad_norm": 0.08344505727291107,
+      "learning_rate": 3.1e-05,
+      "loss": 0.181,
+      "step": 310
+    },
+    {
+      "epoch": 0.09303677860154091,
+      "grad_norm": 0.11566774547100067,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.09594417793283908,
+      "grad_norm": 0.1531219631433487,
+      "learning_rate": 3.3e-05,
+      "loss": 0.1564,
+      "step": 330
+    },
+    {
+      "epoch": 0.09885157726413724,
+      "grad_norm": 0.08966905623674393,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.1281,
+      "step": 340
+    },
+    {
+      "epoch": 0.10175897659543538,
+      "grad_norm": 0.08444681763648987,
+      "learning_rate": 3.5e-05,
+      "loss": 0.1258,
+      "step": 350
+    },
+    {
+      "epoch": 0.10466637592673354,
+      "grad_norm": 0.10482101142406464,
+      "learning_rate": 3.6e-05,
+      "loss": 0.1292,
+      "step": 360
+    },
+    {
+      "epoch": 0.10757377525803169,
+      "grad_norm": 0.14638499915599823,
+      "learning_rate": 3.7e-05,
+      "loss": 0.1829,
+      "step": 370
+    },
+    {
+      "epoch": 0.11048117458932985,
+      "grad_norm": 0.1461925059556961,
+      "learning_rate": 3.8e-05,
+      "loss": 0.2158,
+      "step": 380
+    },
+    {
+      "epoch": 0.113388573920628,
+      "grad_norm": 0.16068245470523834,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.2219,
+      "step": 390
+    },
+    {
+      "epoch": 0.11629597325192616,
+      "grad_norm": 0.13314808905124664,
+      "learning_rate": 4e-05,
+      "loss": 0.1622,
+      "step": 400
+    },
+    {
+      "epoch": 0.1192033725832243,
+      "grad_norm": 0.13541767001152039,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1363,
+      "step": 410
+    },
+    {
+      "epoch": 0.12211077191452246,
+      "grad_norm": 0.14549389481544495,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1664,
+      "step": 420
+    },
+    {
+      "epoch": 0.12501817124582063,
+      "grad_norm": 0.09966716170310974,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1446,
+      "step": 430
+    },
+    {
+      "epoch": 0.12792557057711876,
+      "grad_norm": 0.10374356061220169,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1302,
+      "step": 440
+    },
+    {
+      "epoch": 0.13083296990841692,
+      "grad_norm": 0.10534253716468811,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1612,
+      "step": 450
+    },
+    {
+      "epoch": 0.13374036923971508,
+      "grad_norm": 0.14981906116008759,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1782,
+      "step": 460
+    },
+    {
+      "epoch": 0.13664776857101324,
+      "grad_norm": 0.08772515505552292,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1303,
+      "step": 470
+    },
+    {
+      "epoch": 0.13955516790231137,
+      "grad_norm": 0.14555956423282623,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1259,
+      "step": 480
+    },
+    {
+      "epoch": 0.14246256723360953,
+      "grad_norm": 0.08366917818784714,
+      "learning_rate": 4.9e-05,
+      "loss": 0.1827,
+      "step": 490
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "grad_norm": 0.13676565885543823,
+      "learning_rate": 5e-05,
+      "loss": 0.1563,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_accuracy": 0.4444444444444444,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_loss": 0.15286579728126526,
+      "eval_runtime": 120.6585,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
+      "step": 500
+    },
+    {
+      "epoch": 0.14827736589620585,
+      "grad_norm": 0.16602879762649536,
+      "learning_rate": 4.982987410683906e-05,
+      "loss": 0.1322,
+      "step": 510
+    },
+    {
+      "epoch": 0.151184765227504,
+      "grad_norm": 0.12974093854427338,
+      "learning_rate": 4.965974821367813e-05,
+      "loss": 0.1432,
+      "step": 520
+    },
+    {
+      "epoch": 0.15409216455880215,
+      "grad_norm": 0.10730555653572083,
+      "learning_rate": 4.948962232051719e-05,
+      "loss": 0.1344,
+      "step": 530
+    },
+    {
+      "epoch": 0.1569995638901003,
+      "grad_norm": 0.09881391376256943,
+      "learning_rate": 4.931949642735625e-05,
+      "loss": 0.1207,
+      "step": 540
+    },
+    {
+      "epoch": 0.15990696322139847,
+      "grad_norm": 0.15530119836330414,
+      "learning_rate": 4.9149370534195306e-05,
+      "loss": 0.2084,
+      "step": 550
+    },
+    {
+      "epoch": 0.1628143625526966,
+      "grad_norm": 0.1018906682729721,
+      "learning_rate": 4.8979244641034366e-05,
+      "loss": 0.1465,
+      "step": 560
+    },
+    {
+      "epoch": 0.16572176188399476,
+      "grad_norm": 0.11174057424068451,
+      "learning_rate": 4.8809118747873425e-05,
+      "loss": 0.1704,
+      "step": 570
+    },
+    {
+      "epoch": 0.16862916121529292,
+      "grad_norm": 0.13199737668037415,
+      "learning_rate": 4.863899285471249e-05,
+      "loss": 0.1376,
+      "step": 580
+    },
+    {
+      "epoch": 0.17153656054659108,
+      "grad_norm": 0.12376833707094193,
+      "learning_rate": 4.846886696155155e-05,
+      "loss": 0.1848,
+      "step": 590
+    },
+    {
+      "epoch": 0.17444395987788922,
+      "grad_norm": 0.10838288813829422,
+      "learning_rate": 4.829874106839061e-05,
+      "loss": 0.1327,
+      "step": 600
+    },
+    {
+      "epoch": 0.17735135920918738,
+      "grad_norm": 0.09848768264055252,
+      "learning_rate": 4.8128615175229676e-05,
+      "loss": 0.1807,
+      "step": 610
+    },
+    {
+      "epoch": 0.18025875854048554,
+      "grad_norm": 0.10199768096208572,
+      "learning_rate": 4.7958489282068736e-05,
+      "loss": 0.1475,
+      "step": 620
+    },
+    {
+      "epoch": 0.1831661578717837,
+      "grad_norm": 0.1114463359117508,
+      "learning_rate": 4.7788363388907795e-05,
+      "loss": 0.1458,
+      "step": 630
+    },
+    {
+      "epoch": 0.18607355720308183,
+      "grad_norm": 0.09931254386901855,
+      "learning_rate": 4.7618237495746855e-05,
+      "loss": 0.1572,
+      "step": 640
+    },
+    {
+      "epoch": 0.18898095653438,
+      "grad_norm": 0.07883786410093307,
+      "learning_rate": 4.7448111602585914e-05,
+      "loss": 0.1502,
+      "step": 650
+    },
+    {
+      "epoch": 0.19188835586567815,
+      "grad_norm": 0.1312653124332428,
+      "learning_rate": 4.7277985709424973e-05,
+      "loss": 0.1306,
+      "step": 660
+    },
+    {
+      "epoch": 0.1947957551969763,
+      "grad_norm": 0.10453817993402481,
+      "learning_rate": 4.710785981626404e-05,
+      "loss": 0.1516,
+      "step": 670
+    },
+    {
+      "epoch": 0.19770315452827447,
+      "grad_norm": 0.13967570662498474,
+      "learning_rate": 4.69377339231031e-05,
+      "loss": 0.1976,
+      "step": 680
+    },
+    {
+      "epoch": 0.2006105538595726,
+      "grad_norm": 0.09553707391023636,
+      "learning_rate": 4.676760802994216e-05,
+      "loss": 0.1291,
+      "step": 690
+    },
+    {
+      "epoch": 0.20351795319087077,
+      "grad_norm": 0.14968940615653992,
+      "learning_rate": 4.6597482136781225e-05,
+      "loss": 0.1669,
+      "step": 700
+    },
+    {
+      "epoch": 0.20642535252216893,
+      "grad_norm": 0.10163428634405136,
+      "learning_rate": 4.642735624362028e-05,
+      "loss": 0.1727,
+      "step": 710
+    },
+    {
+      "epoch": 0.2093327518534671,
+      "grad_norm": 0.13607974350452423,
+      "learning_rate": 4.6257230350459343e-05,
+      "loss": 0.1473,
+      "step": 720
+    },
+    {
+      "epoch": 0.21224015118476522,
+      "grad_norm": 0.0766085609793663,
+      "learning_rate": 4.60871044572984e-05,
+      "loss": 0.1419,
+      "step": 730
+    },
+    {
+      "epoch": 0.21514755051606338,
+      "grad_norm": 0.11004997789859772,
+      "learning_rate": 4.591697856413746e-05,
+      "loss": 0.1344,
+      "step": 740
+    },
+    {
+      "epoch": 0.21805494984736154,
+      "grad_norm": 0.10307681560516357,
+      "learning_rate": 4.574685267097653e-05,
+      "loss": 0.1355,
+      "step": 750
+    },
+    {
+      "epoch": 0.2209623491786597,
+      "grad_norm": 0.098714679479599,
+      "learning_rate": 4.557672677781559e-05,
+      "loss": 0.1565,
+      "step": 760
+    },
+    {
+      "epoch": 0.22386974850995783,
+      "grad_norm": 0.1346523016691208,
+      "learning_rate": 4.540660088465465e-05,
+      "loss": 0.1675,
+      "step": 770
+    },
+    {
+      "epoch": 0.226777147841256,
+      "grad_norm": 0.12962771952152252,
+      "learning_rate": 4.5236474991493714e-05,
+      "loss": 0.1058,
+      "step": 780
+    },
+    {
+      "epoch": 0.22968454717255415,
+      "grad_norm": 0.14412884414196014,
+      "learning_rate": 4.5066349098332766e-05,
+      "loss": 0.198,
+      "step": 790
+    },
+    {
+      "epoch": 0.23259194650385231,
+      "grad_norm": 0.14253386855125427,
+      "learning_rate": 4.4896223205171826e-05,
+      "loss": 0.1319,
+      "step": 800
+    },
+    {
+      "epoch": 0.23549934583515045,
+      "grad_norm": 0.2203107625246048,
+      "learning_rate": 4.472609731201089e-05,
+      "loss": 0.1729,
+      "step": 810
+    },
+    {
+      "epoch": 0.2384067451664486,
+      "grad_norm": 0.09438087791204453,
+      "learning_rate": 4.455597141884995e-05,
+      "loss": 0.1558,
+      "step": 820
+    },
+    {
+      "epoch": 0.24131414449774677,
+      "grad_norm": 0.09754593670368195,
+      "learning_rate": 4.438584552568901e-05,
+      "loss": 0.1729,
+      "step": 830
+    },
+    {
+      "epoch": 0.24422154382904493,
+      "grad_norm": 0.1403294950723648,
+      "learning_rate": 4.421571963252808e-05,
+      "loss": 0.1871,
+      "step": 840
+    },
+    {
+      "epoch": 0.24712894316034306,
+      "grad_norm": 0.11251681298017502,
+      "learning_rate": 4.4045593739367136e-05,
+      "loss": 0.1726,
+      "step": 850
+    },
+    {
+      "epoch": 0.25003634249164125,
+      "grad_norm": 0.13492991030216217,
+      "learning_rate": 4.3875467846206196e-05,
+      "loss": 0.1349,
+      "step": 860
+    },
+    {
+      "epoch": 0.2529437418229394,
+      "grad_norm": 0.11674369871616364,
+      "learning_rate": 4.3705341953045255e-05,
+      "loss": 0.2088,
+      "step": 870
+    },
+    {
+      "epoch": 0.2558511411542375,
+      "grad_norm": 0.09339413791894913,
+      "learning_rate": 4.3535216059884315e-05,
+      "loss": 0.1656,
+      "step": 880
+    },
+    {
+      "epoch": 0.2587585404855357,
+      "grad_norm": 0.10234147310256958,
+      "learning_rate": 4.3365090166723374e-05,
+      "loss": 0.1495,
+      "step": 890
+    },
+    {
+      "epoch": 0.26166593981683384,
+      "grad_norm": 0.09566229581832886,
+      "learning_rate": 4.319496427356244e-05,
+      "loss": 0.109,
+      "step": 900
+    },
+    {
+      "epoch": 0.26457333914813197,
+      "grad_norm": 0.10038291662931442,
+      "learning_rate": 4.30248383804015e-05,
+      "loss": 0.1849,
+      "step": 910
+    },
+    {
+      "epoch": 0.26748073847943016,
+      "grad_norm": 0.12414570152759552,
+      "learning_rate": 4.285471248724056e-05,
+      "loss": 0.1476,
+      "step": 920
+    },
+    {
+      "epoch": 0.2703881378107283,
+      "grad_norm": 0.0866188034415245,
+      "learning_rate": 4.2684586594079625e-05,
+      "loss": 0.1339,
+      "step": 930
+    },
+    {
+      "epoch": 0.2732955371420265,
+      "grad_norm": 0.20008312165737152,
+      "learning_rate": 4.2514460700918685e-05,
+      "loss": 0.1865,
+      "step": 940
+    },
+    {
+      "epoch": 0.2762029364733246,
+      "grad_norm": 0.09849795699119568,
+      "learning_rate": 4.2344334807757744e-05,
+      "loss": 0.1293,
+      "step": 950
+    },
+    {
+      "epoch": 0.27911033580462274,
+      "grad_norm": 0.11204036325216293,
+      "learning_rate": 4.2174208914596803e-05,
+      "loss": 0.1817,
+      "step": 960
+    },
+    {
+      "epoch": 0.28201773513592093,
+      "grad_norm": 0.0960935726761818,
+      "learning_rate": 4.200408302143586e-05,
+      "loss": 0.1454,
+      "step": 970
+    },
+    {
+      "epoch": 0.28492513446721907,
+      "grad_norm": 0.12531103193759918,
+      "learning_rate": 4.183395712827492e-05,
+      "loss": 0.126,
+      "step": 980
+    },
+    {
+      "epoch": 0.28783253379851725,
+      "grad_norm": 0.1162460595369339,
+      "learning_rate": 4.166383123511399e-05,
+      "loss": 0.1634,
+      "step": 990
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "grad_norm": 0.06354565173387527,
+      "learning_rate": 4.149370534195305e-05,
+      "loss": 0.0986,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_accuracy": 0.48148148148148145,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_loss": 0.14855271577835083,
+      "eval_runtime": 120.8042,
+      "eval_samples_per_second": 2.012,
+      "eval_steps_per_second": 2.012,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2936473324611135,
+      "grad_norm": 0.0838373601436615,
+      "learning_rate": 4.132357944879211e-05,
+      "loss": 0.1266,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2965547317924117,
+      "grad_norm": 0.10404589027166367,
+      "learning_rate": 4.1153453555631173e-05,
+      "loss": 0.1411,
+      "step": 1020
+    },
+    {
+      "epoch": 0.29946213112370984,
+      "grad_norm": 0.137540802359581,
+      "learning_rate": 4.0983327662470226e-05,
+      "loss": 0.1719,
+      "step": 1030
+    },
+    {
+      "epoch": 0.302369530455008,
+      "grad_norm": 0.10742737352848053,
+      "learning_rate": 4.081320176930929e-05,
+      "loss": 0.181,
+      "step": 1040
+    },
+    {
+      "epoch": 0.30527692978630616,
+      "grad_norm": 0.14736784994602203,
+      "learning_rate": 4.064307587614835e-05,
+      "loss": 0.1544,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3081843291176043,
+      "grad_norm": 0.15068358182907104,
+      "learning_rate": 4.047294998298741e-05,
+      "loss": 0.1359,
+      "step": 1060
+    },
+    {
+      "epoch": 0.3110917284489025,
+      "grad_norm": 0.12078270316123962,
+      "learning_rate": 4.030282408982648e-05,
+      "loss": 0.1304,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3139991277802006,
+      "grad_norm": 0.12046414613723755,
+      "learning_rate": 4.013269819666554e-05,
+      "loss": 0.1379,
+      "step": 1080
+    },
+    {
+      "epoch": 0.31690652711149875,
+      "grad_norm": 0.13933445513248444,
+      "learning_rate": 3.9962572303504596e-05,
+      "loss": 0.1413,
+      "step": 1090
+    },
+    {
+      "epoch": 0.31981392644279694,
+      "grad_norm": 0.09172947704792023,
+      "learning_rate": 3.9792446410343656e-05,
+      "loss": 0.1316,
+      "step": 1100
+    },
+    {
+      "epoch": 0.32272132577409507,
+      "grad_norm": 0.11812902987003326,
+      "learning_rate": 3.9622320517182715e-05,
+      "loss": 0.1322,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3256287251053932,
+      "grad_norm": 0.1187342032790184,
+      "learning_rate": 3.9452194624021774e-05,
+      "loss": 0.138,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3285361244366914,
+      "grad_norm": 0.10506665706634521,
+      "learning_rate": 3.928206873086084e-05,
+      "loss": 0.1324,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3314435237679895,
+      "grad_norm": 0.06862190365791321,
+      "learning_rate": 3.91119428376999e-05,
+      "loss": 0.1375,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3343509230992877,
+      "grad_norm": 0.07644759863615036,
+      "learning_rate": 3.894181694453896e-05,
+      "loss": 0.1384,
+      "step": 1150
+    },
+    {
+      "epoch": 0.33725832243058584,
+      "grad_norm": 0.12909413874149323,
+      "learning_rate": 3.8771691051378026e-05,
+      "loss": 0.1251,
+      "step": 1160
+    },
+    {
+      "epoch": 0.340165721761884,
+      "grad_norm": 0.10902974754571915,
+      "learning_rate": 3.8601565158217085e-05,
+      "loss": 0.1,
+      "step": 1170
+    },
+    {
+      "epoch": 0.34307312109318217,
+      "grad_norm": 0.09570310264825821,
+      "learning_rate": 3.8431439265056145e-05,
+      "loss": 0.1901,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3459805204244803,
+      "grad_norm": 0.11525869369506836,
+      "learning_rate": 3.8261313371895204e-05,
+      "loss": 0.1072,
+      "step": 1190
+    },
+    {
+      "epoch": 0.34888791975577843,
+      "grad_norm": 0.1647326499223709,
+      "learning_rate": 3.809118747873426e-05,
+      "loss": 0.2477,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3517953190870766,
+      "grad_norm": 0.1333259642124176,
+      "learning_rate": 3.792106158557332e-05,
+      "loss": 0.1682,
+      "step": 1210
+    },
+    {
+      "epoch": 0.35470271841837475,
+      "grad_norm": 0.11220316588878632,
+      "learning_rate": 3.775093569241239e-05,
+      "loss": 0.1399,
+      "step": 1220
+    },
+    {
+      "epoch": 0.35761011774967294,
+      "grad_norm": 0.11679007858037949,
+      "learning_rate": 3.758080979925145e-05,
+      "loss": 0.1792,
+      "step": 1230
+    },
+    {
+      "epoch": 0.3605175170809711,
+      "grad_norm": 0.11699705570936203,
+      "learning_rate": 3.741068390609051e-05,
+      "loss": 0.159,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3634249164122692,
+      "grad_norm": 0.13930341601371765,
+      "learning_rate": 3.7240558012929574e-05,
+      "loss": 0.1233,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3663323157435674,
+      "grad_norm": 0.11168822646141052,
+      "learning_rate": 3.7070432119768633e-05,
+      "loss": 0.1277,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3692397150748655,
+      "grad_norm": 0.10844167321920395,
+      "learning_rate": 3.6900306226607686e-05,
+      "loss": 0.1857,
+      "step": 1270
+    },
+    {
+      "epoch": 0.37214711440616366,
+      "grad_norm": 0.1075616255402565,
+      "learning_rate": 3.673018033344675e-05,
+      "loss": 0.1169,
+      "step": 1280
+    },
+    {
+      "epoch": 0.37505451373746185,
+      "grad_norm": 0.12448868900537491,
+      "learning_rate": 3.656005444028581e-05,
+      "loss": 0.2439,
+      "step": 1290
+    },
+    {
+      "epoch": 0.37796191306876,
+      "grad_norm": 0.10500267148017883,
+      "learning_rate": 3.638992854712487e-05,
+      "loss": 0.117,
+      "step": 1300
+    },
+    {
+      "epoch": 0.38086931240005817,
+      "grad_norm": 0.12791551649570465,
+      "learning_rate": 3.621980265396394e-05,
+      "loss": 0.13,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3837767117313563,
+      "grad_norm": 0.1264408826828003,
+      "learning_rate": 3.6049676760803e-05,
+      "loss": 0.1121,
+      "step": 1320
+    },
+    {
+      "epoch": 0.38668411106265443,
+      "grad_norm": 0.1253873109817505,
+      "learning_rate": 3.5879550867642056e-05,
+      "loss": 0.1384,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3895915103939526,
+      "grad_norm": 0.08832169324159622,
+      "learning_rate": 3.570942497448112e-05,
+      "loss": 0.1477,
+      "step": 1340
+    },
+    {
+      "epoch": 0.39249890972525076,
+      "grad_norm": 0.14027167856693268,
+      "learning_rate": 3.5539299081320175e-05,
+      "loss": 0.2171,
+      "step": 1350
+    },
+    {
+      "epoch": 0.39540630905654894,
+      "grad_norm": 0.11315055191516876,
+      "learning_rate": 3.536917318815924e-05,
+      "loss": 0.1606,
+      "step": 1360
+    },
+    {
+      "epoch": 0.3983137083878471,
+      "grad_norm": 0.09444567561149597,
+      "learning_rate": 3.51990472949983e-05,
+      "loss": 0.1284,
+      "step": 1370
+    },
+    {
+      "epoch": 0.4012211077191452,
+      "grad_norm": 0.11262746155261993,
+      "learning_rate": 3.502892140183736e-05,
+      "loss": 0.1411,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4041285070504434,
+      "grad_norm": 0.17679522931575775,
+      "learning_rate": 3.4858795508676426e-05,
+      "loss": 0.1981,
+      "step": 1390
+    },
+    {
+      "epoch": 0.40703590638174153,
+      "grad_norm": 0.18890735507011414,
+      "learning_rate": 3.4688669615515486e-05,
+      "loss": 0.1676,
+      "step": 1400
+    },
+    {
+      "epoch": 0.40994330571303966,
+      "grad_norm": 0.09281571209430695,
+      "learning_rate": 3.4518543722354545e-05,
+      "loss": 0.1136,
+      "step": 1410
+    },
+    {
+      "epoch": 0.41285070504433785,
+      "grad_norm": 0.13167564570903778,
+      "learning_rate": 3.4348417829193604e-05,
+      "loss": 0.1586,
+      "step": 1420
+    },
+    {
+      "epoch": 0.415758104375636,
+      "grad_norm": 0.09986082464456558,
+      "learning_rate": 3.4178291936032664e-05,
+      "loss": 0.1607,
+      "step": 1430
+    },
+    {
+      "epoch": 0.4186655037069342,
+      "grad_norm": 0.13981035351753235,
+      "learning_rate": 3.400816604287172e-05,
+      "loss": 0.1439,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4215729030382323,
+      "grad_norm": 0.11107143759727478,
+      "learning_rate": 3.383804014971079e-05,
+      "loss": 0.1382,
+      "step": 1450
+    },
+    {
+      "epoch": 0.42448030236953044,
+      "grad_norm": 0.06783778220415115,
+      "learning_rate": 3.366791425654985e-05,
+      "loss": 0.1138,
+      "step": 1460
+    },
+    {
+      "epoch": 0.4273877017008286,
+      "grad_norm": 0.11150864511728287,
+      "learning_rate": 3.349778836338891e-05,
+      "loss": 0.1709,
+      "step": 1470
+    },
+    {
+      "epoch": 0.43029510103212676,
+      "grad_norm": 0.1245250254869461,
+      "learning_rate": 3.3327662470227975e-05,
+      "loss": 0.1323,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4332025003634249,
+      "grad_norm": 0.13299217820167542,
+      "learning_rate": 3.3157536577067034e-05,
+      "loss": 0.1311,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "grad_norm": 0.09196653217077255,
+      "learning_rate": 3.298741068390609e-05,
+      "loss": 0.121,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "eval_accuracy": 0.46502057613168724,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "eval_loss": 0.1465623825788498,
+      "eval_runtime": 120.6266,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3439,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9720958902272e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b868ef95d608a436278794d3830d43d18443ff20bb16e5eb13dcb771311e6732
+size 5048

checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-2000/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "Wqkv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da144c06f41caa881cb383136e02e4f2afd2710261932dc3a3b69cef3af2b333
+size 104873776

checkpoint-2000/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc1eb76f44e74e37dfb0e0269276850657ad5f713a22a7d5649d7873517b110
+size 209823354

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67acc19d1a1adda10f278f73078f439aafef38f712c4bdef542d316fed4f954
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d649c849d465cd321718271b4711f3d54508a4cd6a069f8c03c040a60fc0f6f
+size 1064

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,329 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1485 @@
+{
+  "best_metric": 0.49794238683127573,
+  "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-2000",
+  "epoch": 0.5814798662596308,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029073993312981536,
+      "grad_norm": 4.615232944488525,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 6.6211,
+      "step": 10
+    },
+    {
+      "epoch": 0.005814798662596307,
+      "grad_norm": 5.528043746948242,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 6.5222,
+      "step": 20
+    },
+    {
+      "epoch": 0.00872219799389446,
+      "grad_norm": 6.019925594329834,
+      "learning_rate": 3e-06,
+      "loss": 6.4104,
+      "step": 30
+    },
+    {
+      "epoch": 0.011629597325192614,
+      "grad_norm": 7.163036823272705,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 6.0366,
+      "step": 40
+    },
+    {
+      "epoch": 0.01453699665649077,
+      "grad_norm": 7.888458251953125,
+      "learning_rate": 5e-06,
+      "loss": 5.4618,
+      "step": 50
+    },
+    {
+      "epoch": 0.01744439598778892,
+      "grad_norm": 9.86289119720459,
+      "learning_rate": 6e-06,
+      "loss": 4.526,
+      "step": 60
+    },
+    {
+      "epoch": 0.020351795319087075,
+      "grad_norm": 9.114004135131836,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 3.2234,
+      "step": 70
+    },
+    {
+      "epoch": 0.02325919465038523,
+      "grad_norm": 6.198110103607178,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.6796,
+      "step": 80
+    },
+    {
+      "epoch": 0.026166593981683386,
+      "grad_norm": 1.2424126863479614,
+      "learning_rate": 9e-06,
+      "loss": 0.6189,
+      "step": 90
+    },
+    {
+      "epoch": 0.02907399331298154,
+      "grad_norm": 0.20757392048835754,
+      "learning_rate": 1e-05,
+      "loss": 0.2989,
+      "step": 100
+    },
+    {
+      "epoch": 0.03198139264427969,
+      "grad_norm": 0.19180330634117126,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.3434,
+      "step": 110
+    },
+    {
+      "epoch": 0.03488879197557784,
+      "grad_norm": 0.17373745143413544,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2775,
+      "step": 120
+    },
+    {
+      "epoch": 0.037796191306876,
+      "grad_norm": 0.14247311651706696,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.291,
+      "step": 130
+    },
+    {
+      "epoch": 0.04070359063817415,
+      "grad_norm": 0.1189289391040802,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.2549,
+      "step": 140
+    },
+    {
+      "epoch": 0.043610989969472304,
+      "grad_norm": 0.11715172231197357,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2334,
+      "step": 150
+    },
+    {
+      "epoch": 0.04651838930077046,
+      "grad_norm": 0.16550108790397644,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2515,
+      "step": 160
+    },
+    {
+      "epoch": 0.04942578863206862,
+      "grad_norm": 0.13685165345668793,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.2757,
+      "step": 170
+    },
+    {
+      "epoch": 0.05233318796336677,
+      "grad_norm": 0.13247624039649963,
+      "learning_rate": 1.8e-05,
+      "loss": 0.2336,
+      "step": 180
+    },
+    {
+      "epoch": 0.055240587294664925,
+      "grad_norm": 0.13763906061649323,
+      "learning_rate": 1.9e-05,
+      "loss": 0.2169,
+      "step": 190
+    },
+    {
+      "epoch": 0.05814798662596308,
+      "grad_norm": 0.1327727884054184,
+      "learning_rate": 2e-05,
+      "loss": 0.2007,
+      "step": 200
+    },
+    {
+      "epoch": 0.06105538595726123,
+      "grad_norm": 0.1083875447511673,
+      "learning_rate": 2.1e-05,
+      "loss": 0.2181,
+      "step": 210
+    },
+    {
+      "epoch": 0.06396278528855938,
+      "grad_norm": 0.12445604056119919,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.2969,
+      "step": 220
+    },
+    {
+      "epoch": 0.06687018461985754,
+      "grad_norm": 0.15511994063854218,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.1868,
+      "step": 230
+    },
+    {
+      "epoch": 0.06977758395115569,
+      "grad_norm": 0.13466577231884003,
+      "learning_rate": 2.4e-05,
+      "loss": 0.25,
+      "step": 240
+    },
+    {
+      "epoch": 0.07268498328245385,
+      "grad_norm": 0.06756726652383804,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1809,
+      "step": 250
+    },
+    {
+      "epoch": 0.075592382613752,
+      "grad_norm": 0.1573372632265091,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1963,
+      "step": 260
+    },
+    {
+      "epoch": 0.07849978194505015,
+      "grad_norm": 0.13099811971187592,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.1984,
+      "step": 270
+    },
+    {
+      "epoch": 0.0814071812763483,
+      "grad_norm": 0.11419626325368881,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.1665,
+      "step": 280
+    },
+    {
+      "epoch": 0.08431458060764646,
+      "grad_norm": 0.10189209878444672,
+      "learning_rate": 2.9e-05,
+      "loss": 0.1749,
+      "step": 290
+    },
+    {
+      "epoch": 0.08722197993894461,
+      "grad_norm": 0.12042666226625443,
+      "learning_rate": 3e-05,
+      "loss": 0.1528,
+      "step": 300
+    },
+    {
+      "epoch": 0.09012937927024277,
+      "grad_norm": 0.08344505727291107,
+      "learning_rate": 3.1e-05,
+      "loss": 0.181,
+      "step": 310
+    },
+    {
+      "epoch": 0.09303677860154091,
+      "grad_norm": 0.11566774547100067,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.09594417793283908,
+      "grad_norm": 0.1531219631433487,
+      "learning_rate": 3.3e-05,
+      "loss": 0.1564,
+      "step": 330
+    },
+    {
+      "epoch": 0.09885157726413724,
+      "grad_norm": 0.08966905623674393,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.1281,
+      "step": 340
+    },
+    {
+      "epoch": 0.10175897659543538,
+      "grad_norm": 0.08444681763648987,
+      "learning_rate": 3.5e-05,
+      "loss": 0.1258,
+      "step": 350
+    },
+    {
+      "epoch": 0.10466637592673354,
+      "grad_norm": 0.10482101142406464,
+      "learning_rate": 3.6e-05,
+      "loss": 0.1292,
+      "step": 360
+    },
+    {
+      "epoch": 0.10757377525803169,
+      "grad_norm": 0.14638499915599823,
+      "learning_rate": 3.7e-05,
+      "loss": 0.1829,
+      "step": 370
+    },
+    {
+      "epoch": 0.11048117458932985,
+      "grad_norm": 0.1461925059556961,
+      "learning_rate": 3.8e-05,
+      "loss": 0.2158,
+      "step": 380
+    },
+    {
+      "epoch": 0.113388573920628,
+      "grad_norm": 0.16068245470523834,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.2219,
+      "step": 390
+    },
+    {
+      "epoch": 0.11629597325192616,
+      "grad_norm": 0.13314808905124664,
+      "learning_rate": 4e-05,
+      "loss": 0.1622,
+      "step": 400
+    },
+    {
+      "epoch": 0.1192033725832243,
+      "grad_norm": 0.13541767001152039,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1363,
+      "step": 410
+    },
+    {
+      "epoch": 0.12211077191452246,
+      "grad_norm": 0.14549389481544495,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1664,
+      "step": 420
+    },
+    {
+      "epoch": 0.12501817124582063,
+      "grad_norm": 0.09966716170310974,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1446,
+      "step": 430
+    },
+    {
+      "epoch": 0.12792557057711876,
+      "grad_norm": 0.10374356061220169,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1302,
+      "step": 440
+    },
+    {
+      "epoch": 0.13083296990841692,
+      "grad_norm": 0.10534253716468811,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1612,
+      "step": 450
+    },
+    {
+      "epoch": 0.13374036923971508,
+      "grad_norm": 0.14981906116008759,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1782,
+      "step": 460
+    },
+    {
+      "epoch": 0.13664776857101324,
+      "grad_norm": 0.08772515505552292,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1303,
+      "step": 470
+    },
+    {
+      "epoch": 0.13955516790231137,
+      "grad_norm": 0.14555956423282623,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1259,
+      "step": 480
+    },
+    {
+      "epoch": 0.14246256723360953,
+      "grad_norm": 0.08366917818784714,
+      "learning_rate": 4.9e-05,
+      "loss": 0.1827,
+      "step": 490
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "grad_norm": 0.13676565885543823,
+      "learning_rate": 5e-05,
+      "loss": 0.1563,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_accuracy": 0.4444444444444444,
+      "step": 500
+    },
+    {
+      "epoch": 0.1453699665649077,
+      "eval_loss": 0.15286579728126526,
+      "eval_runtime": 120.6585,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
+      "step": 500
+    },
+    {
+      "epoch": 0.14827736589620585,
+      "grad_norm": 0.16602879762649536,
+      "learning_rate": 4.982987410683906e-05,
+      "loss": 0.1322,
+      "step": 510
+    },
+    {
+      "epoch": 0.151184765227504,
+      "grad_norm": 0.12974093854427338,
+      "learning_rate": 4.965974821367813e-05,
+      "loss": 0.1432,
+      "step": 520
+    },
+    {
+      "epoch": 0.15409216455880215,
+      "grad_norm": 0.10730555653572083,
+      "learning_rate": 4.948962232051719e-05,
+      "loss": 0.1344,
+      "step": 530
+    },
+    {
+      "epoch": 0.1569995638901003,
+      "grad_norm": 0.09881391376256943,
+      "learning_rate": 4.931949642735625e-05,
+      "loss": 0.1207,
+      "step": 540
+    },
+    {
+      "epoch": 0.15990696322139847,
+      "grad_norm": 0.15530119836330414,
+      "learning_rate": 4.9149370534195306e-05,
+      "loss": 0.2084,
+      "step": 550
+    },
+    {
+      "epoch": 0.1628143625526966,
+      "grad_norm": 0.1018906682729721,
+      "learning_rate": 4.8979244641034366e-05,
+      "loss": 0.1465,
+      "step": 560
+    },
+    {
+      "epoch": 0.16572176188399476,
+      "grad_norm": 0.11174057424068451,
+      "learning_rate": 4.8809118747873425e-05,
+      "loss": 0.1704,
+      "step": 570
+    },
+    {
+      "epoch": 0.16862916121529292,
+      "grad_norm": 0.13199737668037415,
+      "learning_rate": 4.863899285471249e-05,
+      "loss": 0.1376,
+      "step": 580
+    },
+    {
+      "epoch": 0.17153656054659108,
+      "grad_norm": 0.12376833707094193,
+      "learning_rate": 4.846886696155155e-05,
+      "loss": 0.1848,
+      "step": 590
+    },
+    {
+      "epoch": 0.17444395987788922,
+      "grad_norm": 0.10838288813829422,
+      "learning_rate": 4.829874106839061e-05,
+      "loss": 0.1327,
+      "step": 600
+    },
+    {
+      "epoch": 0.17735135920918738,
+      "grad_norm": 0.09848768264055252,
+      "learning_rate": 4.8128615175229676e-05,
+      "loss": 0.1807,
+      "step": 610
+    },
+    {
+      "epoch": 0.18025875854048554,
+      "grad_norm": 0.10199768096208572,
+      "learning_rate": 4.7958489282068736e-05,
+      "loss": 0.1475,
+      "step": 620
+    },
+    {
+      "epoch": 0.1831661578717837,
+      "grad_norm": 0.1114463359117508,
+      "learning_rate": 4.7788363388907795e-05,
+      "loss": 0.1458,
+      "step": 630
+    },
+    {
+      "epoch": 0.18607355720308183,
+      "grad_norm": 0.09931254386901855,
+      "learning_rate": 4.7618237495746855e-05,
+      "loss": 0.1572,
+      "step": 640
+    },
+    {
+      "epoch": 0.18898095653438,
+      "grad_norm": 0.07883786410093307,
+      "learning_rate": 4.7448111602585914e-05,
+      "loss": 0.1502,
+      "step": 650
+    },
+    {
+      "epoch": 0.19188835586567815,
+      "grad_norm": 0.1312653124332428,
+      "learning_rate": 4.7277985709424973e-05,
+      "loss": 0.1306,
+      "step": 660
+    },
+    {
+      "epoch": 0.1947957551969763,
+      "grad_norm": 0.10453817993402481,
+      "learning_rate": 4.710785981626404e-05,
+      "loss": 0.1516,
+      "step": 670
+    },
+    {
+      "epoch": 0.19770315452827447,
+      "grad_norm": 0.13967570662498474,
+      "learning_rate": 4.69377339231031e-05,
+      "loss": 0.1976,
+      "step": 680
+    },
+    {
+      "epoch": 0.2006105538595726,
+      "grad_norm": 0.09553707391023636,
+      "learning_rate": 4.676760802994216e-05,
+      "loss": 0.1291,
+      "step": 690
+    },
+    {
+      "epoch": 0.20351795319087077,
+      "grad_norm": 0.14968940615653992,
+      "learning_rate": 4.6597482136781225e-05,
+      "loss": 0.1669,
+      "step": 700
+    },
+    {
+      "epoch": 0.20642535252216893,
+      "grad_norm": 0.10163428634405136,
+      "learning_rate": 4.642735624362028e-05,
+      "loss": 0.1727,
+      "step": 710
+    },
+    {
+      "epoch": 0.2093327518534671,
+      "grad_norm": 0.13607974350452423,
+      "learning_rate": 4.6257230350459343e-05,
+      "loss": 0.1473,
+      "step": 720
+    },
+    {
+      "epoch": 0.21224015118476522,
+      "grad_norm": 0.0766085609793663,
+      "learning_rate": 4.60871044572984e-05,
+      "loss": 0.1419,
+      "step": 730
+    },
+    {
+      "epoch": 0.21514755051606338,
+      "grad_norm": 0.11004997789859772,
+      "learning_rate": 4.591697856413746e-05,
+      "loss": 0.1344,
+      "step": 740
+    },
+    {
+      "epoch": 0.21805494984736154,
+      "grad_norm": 0.10307681560516357,
+      "learning_rate": 4.574685267097653e-05,
+      "loss": 0.1355,
+      "step": 750
+    },
+    {
+      "epoch": 0.2209623491786597,
+      "grad_norm": 0.098714679479599,
+      "learning_rate": 4.557672677781559e-05,
+      "loss": 0.1565,
+      "step": 760
+    },
+    {
+      "epoch": 0.22386974850995783,
+      "grad_norm": 0.1346523016691208,
+      "learning_rate": 4.540660088465465e-05,
+      "loss": 0.1675,
+      "step": 770
+    },
+    {
+      "epoch": 0.226777147841256,
+      "grad_norm": 0.12962771952152252,
+      "learning_rate": 4.5236474991493714e-05,
+      "loss": 0.1058,
+      "step": 780
+    },
+    {
+      "epoch": 0.22968454717255415,
+      "grad_norm": 0.14412884414196014,
+      "learning_rate": 4.5066349098332766e-05,
+      "loss": 0.198,
+      "step": 790
+    },
+    {
+      "epoch": 0.23259194650385231,
+      "grad_norm": 0.14253386855125427,
+      "learning_rate": 4.4896223205171826e-05,
+      "loss": 0.1319,
+      "step": 800
+    },
+    {
+      "epoch": 0.23549934583515045,
+      "grad_norm": 0.2203107625246048,
+      "learning_rate": 4.472609731201089e-05,
+      "loss": 0.1729,
+      "step": 810
+    },
+    {
+      "epoch": 0.2384067451664486,
+      "grad_norm": 0.09438087791204453,
+      "learning_rate": 4.455597141884995e-05,
+      "loss": 0.1558,
+      "step": 820
+    },
+    {
+      "epoch": 0.24131414449774677,
+      "grad_norm": 0.09754593670368195,
+      "learning_rate": 4.438584552568901e-05,
+      "loss": 0.1729,
+      "step": 830
+    },
+    {
+      "epoch": 0.24422154382904493,
+      "grad_norm": 0.1403294950723648,
+      "learning_rate": 4.421571963252808e-05,
+      "loss": 0.1871,
+      "step": 840
+    },
+    {
+      "epoch": 0.24712894316034306,
+      "grad_norm": 0.11251681298017502,
+      "learning_rate": 4.4045593739367136e-05,
+      "loss": 0.1726,
+      "step": 850
+    },
+    {
+      "epoch": 0.25003634249164125,
+      "grad_norm": 0.13492991030216217,
+      "learning_rate": 4.3875467846206196e-05,
+      "loss": 0.1349,
+      "step": 860
+    },
+    {
+      "epoch": 0.2529437418229394,
+      "grad_norm": 0.11674369871616364,
+      "learning_rate": 4.3705341953045255e-05,
+      "loss": 0.2088,
+      "step": 870
+    },
+    {
+      "epoch": 0.2558511411542375,
+      "grad_norm": 0.09339413791894913,
+      "learning_rate": 4.3535216059884315e-05,
+      "loss": 0.1656,
+      "step": 880
+    },
+    {
+      "epoch": 0.2587585404855357,
+      "grad_norm": 0.10234147310256958,
+      "learning_rate": 4.3365090166723374e-05,
+      "loss": 0.1495,
+      "step": 890
+    },
+    {
+      "epoch": 0.26166593981683384,
+      "grad_norm": 0.09566229581832886,
+      "learning_rate": 4.319496427356244e-05,
+      "loss": 0.109,
+      "step": 900
+    },
+    {
+      "epoch": 0.26457333914813197,
+      "grad_norm": 0.10038291662931442,
+      "learning_rate": 4.30248383804015e-05,
+      "loss": 0.1849,
+      "step": 910
+    },
+    {
+      "epoch": 0.26748073847943016,
+      "grad_norm": 0.12414570152759552,
+      "learning_rate": 4.285471248724056e-05,
+      "loss": 0.1476,
+      "step": 920
+    },
+    {
+      "epoch": 0.2703881378107283,
+      "grad_norm": 0.0866188034415245,
+      "learning_rate": 4.2684586594079625e-05,
+      "loss": 0.1339,
+      "step": 930
+    },
+    {
+      "epoch": 0.2732955371420265,
+      "grad_norm": 0.20008312165737152,
+      "learning_rate": 4.2514460700918685e-05,
+      "loss": 0.1865,
+      "step": 940
+    },
+    {
+      "epoch": 0.2762029364733246,
+      "grad_norm": 0.09849795699119568,
+      "learning_rate": 4.2344334807757744e-05,
+      "loss": 0.1293,
+      "step": 950
+    },
+    {
+      "epoch": 0.27911033580462274,
+      "grad_norm": 0.11204036325216293,
+      "learning_rate": 4.2174208914596803e-05,
+      "loss": 0.1817,
+      "step": 960
+    },
+    {
+      "epoch": 0.28201773513592093,
+      "grad_norm": 0.0960935726761818,
+      "learning_rate": 4.200408302143586e-05,
+      "loss": 0.1454,
+      "step": 970
+    },
+    {
+      "epoch": 0.28492513446721907,
+      "grad_norm": 0.12531103193759918,
+      "learning_rate": 4.183395712827492e-05,
+      "loss": 0.126,
+      "step": 980
+    },
+    {
+      "epoch": 0.28783253379851725,
+      "grad_norm": 0.1162460595369339,
+      "learning_rate": 4.166383123511399e-05,
+      "loss": 0.1634,
+      "step": 990
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "grad_norm": 0.06354565173387527,
+      "learning_rate": 4.149370534195305e-05,
+      "loss": 0.0986,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_accuracy": 0.48148148148148145,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2907399331298154,
+      "eval_loss": 0.14855271577835083,
+      "eval_runtime": 120.8042,
+      "eval_samples_per_second": 2.012,
+      "eval_steps_per_second": 2.012,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2936473324611135,
+      "grad_norm": 0.0838373601436615,
+      "learning_rate": 4.132357944879211e-05,
+      "loss": 0.1266,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2965547317924117,
+      "grad_norm": 0.10404589027166367,
+      "learning_rate": 4.1153453555631173e-05,
+      "loss": 0.1411,
+      "step": 1020
+    },
+    {
+      "epoch": 0.29946213112370984,
+      "grad_norm": 0.137540802359581,
+      "learning_rate": 4.0983327662470226e-05,
+      "loss": 0.1719,
+      "step": 1030
+    },
+    {
+      "epoch": 0.302369530455008,
+      "grad_norm": 0.10742737352848053,
+      "learning_rate": 4.081320176930929e-05,
+      "loss": 0.181,
+      "step": 1040
+    },
+    {
+      "epoch": 0.30527692978630616,
+      "grad_norm": 0.14736784994602203,
+      "learning_rate": 4.064307587614835e-05,
+      "loss": 0.1544,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3081843291176043,
+      "grad_norm": 0.15068358182907104,
+      "learning_rate": 4.047294998298741e-05,
+      "loss": 0.1359,
+      "step": 1060
+    },
+    {
+      "epoch": 0.3110917284489025,
+      "grad_norm": 0.12078270316123962,
+      "learning_rate": 4.030282408982648e-05,
+      "loss": 0.1304,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3139991277802006,
+      "grad_norm": 0.12046414613723755,
+      "learning_rate": 4.013269819666554e-05,
+      "loss": 0.1379,
+      "step": 1080
+    },
+    {
+      "epoch": 0.31690652711149875,
+      "grad_norm": 0.13933445513248444,
+      "learning_rate": 3.9962572303504596e-05,
+      "loss": 0.1413,
+      "step": 1090
+    },
+    {
+      "epoch": 0.31981392644279694,
+      "grad_norm": 0.09172947704792023,
+      "learning_rate": 3.9792446410343656e-05,
+      "loss": 0.1316,
+      "step": 1100
+    },
+    {
+      "epoch": 0.32272132577409507,
+      "grad_norm": 0.11812902987003326,
+      "learning_rate": 3.9622320517182715e-05,
+      "loss": 0.1322,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3256287251053932,
+      "grad_norm": 0.1187342032790184,
+      "learning_rate": 3.9452194624021774e-05,
+      "loss": 0.138,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3285361244366914,
+      "grad_norm": 0.10506665706634521,
+      "learning_rate": 3.928206873086084e-05,
+      "loss": 0.1324,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3314435237679895,
+      "grad_norm": 0.06862190365791321,
+      "learning_rate": 3.91119428376999e-05,
+      "loss": 0.1375,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3343509230992877,
+      "grad_norm": 0.07644759863615036,
+      "learning_rate": 3.894181694453896e-05,
+      "loss": 0.1384,
+      "step": 1150
+    },
+    {
+      "epoch": 0.33725832243058584,
+      "grad_norm": 0.12909413874149323,
+      "learning_rate": 3.8771691051378026e-05,
+      "loss": 0.1251,
+      "step": 1160
+    },
+    {
+      "epoch": 0.340165721761884,
+      "grad_norm": 0.10902974754571915,
+      "learning_rate": 3.8601565158217085e-05,
+      "loss": 0.1,
+      "step": 1170
+    },
+    {
+      "epoch": 0.34307312109318217,
+      "grad_norm": 0.09570310264825821,
+      "learning_rate": 3.8431439265056145e-05,
+      "loss": 0.1901,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3459805204244803,
+      "grad_norm": 0.11525869369506836,
+      "learning_rate": 3.8261313371895204e-05,
+      "loss": 0.1072,
+      "step": 1190
+    },
+    {
+      "epoch": 0.34888791975577843,
+      "grad_norm": 0.1647326499223709,
+      "learning_rate": 3.809118747873426e-05,
+      "loss": 0.2477,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3517953190870766,
+      "grad_norm": 0.1333259642124176,
+      "learning_rate": 3.792106158557332e-05,
+      "loss": 0.1682,
+      "step": 1210
+    },
+    {
+      "epoch": 0.35470271841837475,
+      "grad_norm": 0.11220316588878632,
+      "learning_rate": 3.775093569241239e-05,
+      "loss": 0.1399,
+      "step": 1220
+    },
+    {
+      "epoch": 0.35761011774967294,
+      "grad_norm": 0.11679007858037949,
+      "learning_rate": 3.758080979925145e-05,
+      "loss": 0.1792,
+      "step": 1230
+    },
+    {
+      "epoch": 0.3605175170809711,
+      "grad_norm": 0.11699705570936203,
+      "learning_rate": 3.741068390609051e-05,
+      "loss": 0.159,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3634249164122692,
+      "grad_norm": 0.13930341601371765,
+      "learning_rate": 3.7240558012929574e-05,
+      "loss": 0.1233,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3663323157435674,
+      "grad_norm": 0.11168822646141052,
+      "learning_rate": 3.7070432119768633e-05,
+      "loss": 0.1277,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3692397150748655,
+      "grad_norm": 0.10844167321920395,
+      "learning_rate": 3.6900306226607686e-05,
+      "loss": 0.1857,
+      "step": 1270
+    },
+    {
+      "epoch": 0.37214711440616366,
+      "grad_norm": 0.1075616255402565,
+      "learning_rate": 3.673018033344675e-05,
+      "loss": 0.1169,
+      "step": 1280
+    },
+    {
+      "epoch": 0.37505451373746185,
+      "grad_norm": 0.12448868900537491,
+      "learning_rate": 3.656005444028581e-05,
+      "loss": 0.2439,
+      "step": 1290
+    },
+    {
+      "epoch": 0.37796191306876,
+      "grad_norm": 0.10500267148017883,
+      "learning_rate": 3.638992854712487e-05,
+      "loss": 0.117,
+      "step": 1300
+    },
+    {
+      "epoch": 0.38086931240005817,
+      "grad_norm": 0.12791551649570465,
+      "learning_rate": 3.621980265396394e-05,
+      "loss": 0.13,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3837767117313563,
+      "grad_norm": 0.1264408826828003,
+      "learning_rate": 3.6049676760803e-05,
+      "loss": 0.1121,
+      "step": 1320
+    },
+    {
+      "epoch": 0.38668411106265443,
+      "grad_norm": 0.1253873109817505,
+      "learning_rate": 3.5879550867642056e-05,
+      "loss": 0.1384,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3895915103939526,
+      "grad_norm": 0.08832169324159622,
+      "learning_rate": 3.570942497448112e-05,
+      "loss": 0.1477,
+      "step": 1340
+    },
+    {
+      "epoch": 0.39249890972525076,
+      "grad_norm": 0.14027167856693268,
+      "learning_rate": 3.5539299081320175e-05,
+      "loss": 0.2171,
+      "step": 1350
+    },
+    {
+      "epoch": 0.39540630905654894,
+      "grad_norm": 0.11315055191516876,
+      "learning_rate": 3.536917318815924e-05,
+      "loss": 0.1606,
+      "step": 1360
+    },
+    {
+      "epoch": 0.3983137083878471,
+      "grad_norm": 0.09444567561149597,
+      "learning_rate": 3.51990472949983e-05,
+      "loss": 0.1284,
+      "step": 1370
+    },
+    {
+      "epoch": 0.4012211077191452,
+      "grad_norm": 0.11262746155261993,
+      "learning_rate": 3.502892140183736e-05,
+      "loss": 0.1411,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4041285070504434,
+      "grad_norm": 0.17679522931575775,
+      "learning_rate": 3.4858795508676426e-05,
+      "loss": 0.1981,
+      "step": 1390
+    },
+    {
+      "epoch": 0.40703590638174153,
+      "grad_norm": 0.18890735507011414,
+      "learning_rate": 3.4688669615515486e-05,
+      "loss": 0.1676,
+      "step": 1400
+    },
+    {
+      "epoch": 0.40994330571303966,
+      "grad_norm": 0.09281571209430695,
+      "learning_rate": 3.4518543722354545e-05,
+      "loss": 0.1136,
+      "step": 1410
+    },
+    {
+      "epoch": 0.41285070504433785,
+      "grad_norm": 0.13167564570903778,
+      "learning_rate": 3.4348417829193604e-05,
+      "loss": 0.1586,
+      "step": 1420
+    },
+    {
+      "epoch": 0.415758104375636,
+      "grad_norm": 0.09986082464456558,
+      "learning_rate": 3.4178291936032664e-05,
+      "loss": 0.1607,
+      "step": 1430
+    },
+    {
+      "epoch": 0.4186655037069342,
+      "grad_norm": 0.13981035351753235,
+      "learning_rate": 3.400816604287172e-05,
+      "loss": 0.1439,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4215729030382323,
+      "grad_norm": 0.11107143759727478,
+      "learning_rate": 3.383804014971079e-05,
+      "loss": 0.1382,
+      "step": 1450
+    },
+    {
+      "epoch": 0.42448030236953044,
+      "grad_norm": 0.06783778220415115,
+      "learning_rate": 3.366791425654985e-05,
+      "loss": 0.1138,
+      "step": 1460
+    },
+    {
+      "epoch": 0.4273877017008286,
+      "grad_norm": 0.11150864511728287,
+      "learning_rate": 3.349778836338891e-05,
+      "loss": 0.1709,
+      "step": 1470
+    },
+    {
+      "epoch": 0.43029510103212676,
+      "grad_norm": 0.1245250254869461,
+      "learning_rate": 3.3327662470227975e-05,
+      "loss": 0.1323,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4332025003634249,
+      "grad_norm": 0.13299217820167542,
+      "learning_rate": 3.3157536577067034e-05,
+      "loss": 0.1311,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "grad_norm": 0.09196653217077255,
+      "learning_rate": 3.298741068390609e-05,
+      "loss": 0.121,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "eval_accuracy": 0.46502057613168724,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4361098996947231,
+      "eval_loss": 0.1465623825788498,
+      "eval_runtime": 120.6266,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4390172990260212,
+      "grad_norm": 0.08671022951602936,
+      "learning_rate": 3.281728479074515e-05,
+      "loss": 0.1774,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4419246983573194,
+      "grad_norm": 0.1013597920536995,
+      "learning_rate": 3.264715889758421e-05,
+      "loss": 0.147,
+      "step": 1520
+    },
+    {
+      "epoch": 0.44483209768861753,
+      "grad_norm": 0.13395969569683075,
+      "learning_rate": 3.247703300442327e-05,
+      "loss": 0.141,
+      "step": 1530
+    },
+    {
+      "epoch": 0.44773949701991567,
+      "grad_norm": 0.08484592288732529,
+      "learning_rate": 3.230690711126234e-05,
+      "loss": 0.1315,
+      "step": 1540
+    },
+    {
+      "epoch": 0.45064689635121385,
+      "grad_norm": 0.10540632903575897,
+      "learning_rate": 3.21367812181014e-05,
+      "loss": 0.2186,
+      "step": 1550
+    },
+    {
+      "epoch": 0.453554295682512,
+      "grad_norm": 0.08647104352712631,
+      "learning_rate": 3.196665532494046e-05,
+      "loss": 0.1464,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4564616950138101,
+      "grad_norm": 0.11477908492088318,
+      "learning_rate": 3.179652943177952e-05,
+      "loss": 0.1229,
+      "step": 1570
+    },
+    {
+      "epoch": 0.4593690943451083,
+      "grad_norm": 0.139444500207901,
+      "learning_rate": 3.162640353861858e-05,
+      "loss": 0.1722,
+      "step": 1580
+    },
+    {
+      "epoch": 0.46227649367640644,
+      "grad_norm": 0.12302656471729279,
+      "learning_rate": 3.1456277645457635e-05,
+      "loss": 0.161,
+      "step": 1590
+    },
+    {
+      "epoch": 0.46518389300770463,
+      "grad_norm": 0.13583935797214508,
+      "learning_rate": 3.12861517522967e-05,
+      "loss": 0.2173,
+      "step": 1600
+    },
+    {
+      "epoch": 0.46809129233900276,
+      "grad_norm": 0.10586286336183548,
+      "learning_rate": 3.111602585913576e-05,
+      "loss": 0.1394,
+      "step": 1610
+    },
+    {
+      "epoch": 0.4709986916703009,
+      "grad_norm": 0.1407371312379837,
+      "learning_rate": 3.094589996597482e-05,
+      "loss": 0.1452,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4739060910015991,
+      "grad_norm": 0.15980814397335052,
+      "learning_rate": 3.0775774072813886e-05,
+      "loss": 0.1929,
+      "step": 1630
+    },
+    {
+      "epoch": 0.4768134903328972,
+      "grad_norm": 0.1253122240304947,
+      "learning_rate": 3.0605648179652946e-05,
+      "loss": 0.1423,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4797208896641954,
+      "grad_norm": 0.17438402771949768,
+      "learning_rate": 3.043552228649201e-05,
+      "loss": 0.1604,
+      "step": 1650
+    },
+    {
+      "epoch": 0.48262828899549354,
+      "grad_norm": 0.13970227539539337,
+      "learning_rate": 3.0265396393331068e-05,
+      "loss": 0.1355,
+      "step": 1660
+    },
+    {
+      "epoch": 0.48553568832679167,
+      "grad_norm": 0.12440519034862518,
+      "learning_rate": 3.0095270500170124e-05,
+      "loss": 0.1693,
+      "step": 1670
+    },
+    {
+      "epoch": 0.48844308765808986,
+      "grad_norm": 0.136091947555542,
+      "learning_rate": 2.9925144607009187e-05,
+      "loss": 0.118,
+      "step": 1680
+    },
+    {
+      "epoch": 0.491350486989388,
+      "grad_norm": 0.13912110030651093,
+      "learning_rate": 2.975501871384825e-05,
+      "loss": 0.1481,
+      "step": 1690
+    },
+    {
+      "epoch": 0.4942578863206861,
+      "grad_norm": 0.10817007720470428,
+      "learning_rate": 2.958489282068731e-05,
+      "loss": 0.1343,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4971652856519843,
+      "grad_norm": 0.12969084084033966,
+      "learning_rate": 2.941476692752637e-05,
+      "loss": 0.1333,
+      "step": 1710
+    },
+    {
+      "epoch": 0.5000726849832825,
+      "grad_norm": 0.13414813578128815,
+      "learning_rate": 2.9244641034365434e-05,
+      "loss": 0.1526,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5029800843145806,
+      "grad_norm": 0.13201922178268433,
+      "learning_rate": 2.9074515141204494e-05,
+      "loss": 0.1567,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5058874836458788,
+      "grad_norm": 0.14282363653182983,
+      "learning_rate": 2.8904389248043557e-05,
+      "loss": 0.1667,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5087948829771769,
+      "grad_norm": 0.09702622145414352,
+      "learning_rate": 2.8734263354882613e-05,
+      "loss": 0.1246,
+      "step": 1750
+    },
+    {
+      "epoch": 0.511702282308475,
+      "grad_norm": 0.1287912130355835,
+      "learning_rate": 2.8564137461721676e-05,
+      "loss": 0.099,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5146096816397733,
+      "grad_norm": 0.10358964651823044,
+      "learning_rate": 2.8394011568560735e-05,
+      "loss": 0.122,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5175170809710714,
+      "grad_norm": 0.12403380870819092,
+      "learning_rate": 2.8223885675399798e-05,
+      "loss": 0.1731,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5204244803023695,
+      "grad_norm": 0.11310795694589615,
+      "learning_rate": 2.8053759782238857e-05,
+      "loss": 0.1394,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5233318796336677,
+      "grad_norm": 0.15226072072982788,
+      "learning_rate": 2.788363388907792e-05,
+      "loss": 0.1521,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5262392789649658,
+      "grad_norm": 0.11242180317640305,
+      "learning_rate": 2.7713507995916983e-05,
+      "loss": 0.167,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5291466782962639,
+      "grad_norm": 0.10229990631341934,
+      "learning_rate": 2.7543382102756042e-05,
+      "loss": 0.115,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5320540776275622,
+      "grad_norm": 0.11430121213197708,
+      "learning_rate": 2.7373256209595098e-05,
+      "loss": 0.1323,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5349614769588603,
+      "grad_norm": 0.0750517025589943,
+      "learning_rate": 2.720313031643416e-05,
+      "loss": 0.1896,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5378688762901584,
+      "grad_norm": 0.10639439523220062,
+      "learning_rate": 2.7033004423273224e-05,
+      "loss": 0.1511,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5407762756214566,
+      "grad_norm": 0.10970495641231537,
+      "learning_rate": 2.6862878530112283e-05,
+      "loss": 0.1456,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5436836749527547,
+      "grad_norm": 0.14610768854618073,
+      "learning_rate": 2.6692752636951346e-05,
+      "loss": 0.1407,
+      "step": 1870
+    },
+    {
+      "epoch": 0.546591074284053,
+      "grad_norm": 0.0982876867055893,
+      "learning_rate": 2.652262674379041e-05,
+      "loss": 0.1484,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5494984736153511,
+      "grad_norm": 0.10405632108449936,
+      "learning_rate": 2.635250085062947e-05,
+      "loss": 0.147,
+      "step": 1890
+    },
+    {
+      "epoch": 0.5524058729466492,
+      "grad_norm": 0.1323215663433075,
+      "learning_rate": 2.618237495746853e-05,
+      "loss": 0.1866,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5553132722779474,
+      "grad_norm": 0.08775471895933151,
+      "learning_rate": 2.6012249064307587e-05,
+      "loss": 0.098,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5582206716092455,
+      "grad_norm": 0.09187202900648117,
+      "learning_rate": 2.584212317114665e-05,
+      "loss": 0.1555,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5611280709405437,
+      "grad_norm": 0.11878269165754318,
+      "learning_rate": 2.567199727798571e-05,
+      "loss": 0.1181,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5640354702718419,
+      "grad_norm": 0.07616838067770004,
+      "learning_rate": 2.5501871384824772e-05,
+      "loss": 0.1979,
+      "step": 1940
+    },
+    {
+      "epoch": 0.56694286960314,
+      "grad_norm": 0.12157191336154938,
+      "learning_rate": 2.533174549166383e-05,
+      "loss": 0.1479,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5698502689344381,
+      "grad_norm": 0.08891995251178741,
+      "learning_rate": 2.5161619598502894e-05,
+      "loss": 0.1184,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5727576682657363,
+      "grad_norm": 0.12914909422397614,
+      "learning_rate": 2.4991493705341954e-05,
+      "loss": 0.1533,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5756650675970345,
+      "grad_norm": 0.1337321698665619,
+      "learning_rate": 2.4821367812181017e-05,
+      "loss": 0.1564,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5785724669283326,
+      "grad_norm": 0.13483311235904694,
+      "learning_rate": 2.4651241919020076e-05,
+      "loss": 0.1648,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5814798662596308,
+      "grad_norm": 0.10340965539216995,
+      "learning_rate": 2.448111602585914e-05,
+      "loss": 0.125,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5814798662596308,
+      "eval_accuracy": 0.49794238683127573,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5814798662596308,
+      "eval_loss": 0.14546644687652588,
+      "eval_runtime": 121.0771,
+      "eval_samples_per_second": 2.007,
+      "eval_steps_per_second": 2.007,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3439,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6294611869696e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b868ef95d608a436278794d3830d43d18443ff20bb16e5eb13dcb771311e6732
+size 5048

checkpoint-2500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-2500/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc1",
+    "fc2",
+    "Wqkv"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec272f418af250953f9687d3b4b0ff297995374e7d84ac68e9f8faa1766fcf7
+size 104873776

checkpoint-2500/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc989218f683a05f5ddfe7212906b8decb041d4c5f8c5de4caf67577465a477
+size 209823354

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9fce551f4ed5bb9cd976a8385b1ccd39f17f01ed5e8eab82363f95395a3f81
+size 14244