Upload folder using huggingface_hub

adapter_config.json

@@ -25,8 +25,8 @@
   "target_modules": [
     "o_proj",
     "qkv_proj",
-    "gate_up_proj",
-    "down_proj"
+    "down_proj",
+    "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1fa574614bd2c4f4b60446fc1e1704a6309cd03a1bee5f601b80009c317b85b
+oid sha256:efba871ec7eb1a23519c21f472dd76116bb3611a5b9a592b42a1dfed040d47ec
 size 100697728

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 2.48,
-    "total_flos": 1.2752346185220096e+16,
-    "train_loss": 0.643518532647027,
-    "train_runtime": 231.7259,
-    "train_samples_per_second": 1.554,
-    "train_steps_per_second": 0.194
+    "epoch": 4.470588235294118,
+    "eval_loss": 0.5844668745994568,
+    "eval_runtime": 3.3894,
+    "eval_samples": 15,
+    "eval_samples_per_second": 4.426,
+    "eval_steps_per_second": 0.59,
+    "total_flos": 2.1241123003551744e+16,
+    "train_loss": 0.5959263980388642,
+    "train_runtime": 411.3164,
+    "train_samples_per_second": 1.556,
+    "train_steps_per_second": 0.097
 }

checkpoint-18/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+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 0.14.0

checkpoint-18/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fcf9d1cc1f9b7c39ae76786db6912d0de5206572d916225969affba579fd493
+size 100697728

checkpoint-18/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac952308ff56e9c1363300f5e9d8fa4c1c9352b43ec5acb04ee7990ab03172af
+size 201541754

checkpoint-18/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31aa8ca868cba691e0b29d18354aeaf7ae7c79709e5f6c19eb74734157771210
+size 14244

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+size 1064

checkpoint-18/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-18/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-18/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-18/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_global_step": 18,
+  "best_metric": 0.6461538076400757,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-18",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3697907328605652,
+      "learning_rate": 5e-05,
+      "loss": 0.801,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7140461802482605,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.23551630973815918,
+      "learning_rate": 0.0001,
+      "loss": 0.7259,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.197063609957695,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6883,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6461538076400757,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 18
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 9507503792148480.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbb49059cad2a21b53b046b184b0f6b571f903ce4eedecacdce52b76528c167
+size 5624

checkpoint-27/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+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 0.14.0

checkpoint-27/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-27/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42a629040796fae95dbbd77068d0723eda9c68191ce4e373949a6a6ed7c0881
+size 100697728

checkpoint-27/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f63e2504638bddbca94ab27df9ca0a9ab069ca5a027bbfa74f7c3f90ae8e3e0
+size 201541754

checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e64dac40ba173bacca43da1c2f8d06bd604cd010c45a36fa0bb45c3bacdc23
+size 14244

checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943e1b79923d42c37ee763b8ae34a16e6ef98e92a9dd0dd04db3c0896ac60703
+size 1064

checkpoint-27/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-27/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-27/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-27/trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_global_step": 27,
+  "best_metric": 0.6003979444503784,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3697907328605652,
+      "learning_rate": 5e-05,
+      "loss": 0.801,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7140461802482605,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.23551630973815918,
+      "learning_rate": 0.0001,
+      "loss": 0.7259,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.197063609957695,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6883,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6461538076400757,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.18328554928302765,
+      "learning_rate": 0.0002,
+      "loss": 0.6152,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17514856159687042,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.527,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6003979444503784,
+      "eval_runtime": 3.3785,
+      "eval_samples_per_second": 4.44,
+      "eval_steps_per_second": 0.592,
+      "step": 27
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.4113699481217024e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbb49059cad2a21b53b046b184b0f6b571f903ce4eedecacdce52b76528c167
+size 5624

checkpoint-36/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+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 0.14.0

checkpoint-36/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-36/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36424f524438af6168e030635805af393e9566995185457a1c14d8f6c6f2f3a
+size 100697728

checkpoint-36/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d01893bd8f19f5364f6e4cde1bf6a2b21d9db500d7b9120760ae48635997b5
+size 201541754

checkpoint-36/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7264c08c6c156135fc8067b25ec9e3f47ec1ad8779ddc4d8b66ac913b140787
+size 14244

checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa606f67d54ed48b5aa68c4a463368d9d0645944303ea8893e154fa045340a7d
+size 1064

checkpoint-36/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-36/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-36/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-36/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_global_step": 36,
+  "best_metric": 0.5861222147941589,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-36",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3697907328605652,
+      "learning_rate": 5e-05,
+      "loss": 0.801,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7140461802482605,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.23551630973815918,
+      "learning_rate": 0.0001,
+      "loss": 0.7259,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.197063609957695,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6883,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6461538076400757,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.18328554928302765,
+      "learning_rate": 0.0002,
+      "loss": 0.6152,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17514856159687042,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.527,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6003979444503784,
+      "eval_runtime": 3.3785,
+      "eval_samples_per_second": 4.44,
+      "eval_steps_per_second": 0.592,
+      "step": 27
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.24001598358154297,
+      "learning_rate": 0.0001,
+      "loss": 0.5294,
+      "step": 30
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.2075182944536209,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4269,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5861222147941589,
+      "eval_runtime": 3.3731,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
+      "step": 36
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.8777505502859264e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-36/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbb49059cad2a21b53b046b184b0f6b571f903ce4eedecacdce52b76528c167
+size 5624

checkpoint-40/adapter_config.json

@@ -12,20 +12,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "o_proj",
     "qkv_proj",
+    "down_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-40/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96598129fb589de78d066d94d06e49f9a9971f1fb8f92adde36318a6390af0b1
-size 805341552
+oid sha256:efba871ec7eb1a23519c21f472dd76116bb3611a5b9a592b42a1dfed040d47ec
+size 100697728

checkpoint-40/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b7d33741b6fb7b61d5ee4cd98e905d0974061246a240bd54e923610c5f7859
-size 409252308
+oid sha256:3f0f160141065da104fc904ee4245a1772395254392dd2d5ab1acc2e6f5370b8
+size 201541754

checkpoint-40/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c79b41a7c769fd3552001d973539854bf1117838b86db0753443a34965eaa7
+oid sha256:b1de7c967ce2416a4581accf012d024c4a85b04576a7eee201878eaac2b5b61e
 size 14244

checkpoint-40/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5fc52ecbc811cf8c3969c1073ba49c5ec4288905574552319850bcb54c0249
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

checkpoint-40/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "best_global_step": 40,
+  "best_metric": 0.5844668745994568,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-40",
+  "epoch": 4.470588235294118,
   "eval_steps": 500,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -10,290 +10,106 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03333333333333333,
-      "grad_norm": 1.4103977680206299,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.7057,
-      "step": 1
-    },
-    {
-      "epoch": 0.06666666666666667,
-      "grad_norm": 2.652712345123291,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 1.2078,
-      "step": 2
-    },
-    {
-      "epoch": 0.1,
-      "grad_norm": 2.5933852195739746,
-      "learning_rate": 6e-06,
-      "loss": 0.8002,
-      "step": 3
-    },
-    {
-      "epoch": 0.13333333333333333,
-      "grad_norm": 1.2952778339385986,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 0.6465,
-      "step": 4
-    },
-    {
-      "epoch": 0.16666666666666666,
-      "grad_norm": 1.0414550304412842,
-      "learning_rate": 1e-05,
-      "loss": 0.5417,
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3697907328605652,
+      "learning_rate": 5e-05,
+      "loss": 0.801,
       "step": 5
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.959168553352356,
-      "learning_rate": 1.2e-05,
-      "loss": 0.54,
-      "step": 6
-    },
-    {
-      "epoch": 0.23333333333333334,
-      "grad_norm": 1.0308184623718262,
-      "learning_rate": 1.4000000000000001e-05,
-      "loss": 0.7153,
-      "step": 7
-    },
-    {
-      "epoch": 0.26666666666666666,
-      "grad_norm": 1.0031462907791138,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.7742,
-      "step": 8
-    },
-    {
-      "epoch": 0.3,
-      "grad_norm": 1.8405858278274536,
-      "learning_rate": 1.8e-05,
-      "loss": 1.2656,
+      "epoch": 1.0,
+      "eval_loss": 0.7140461802482605,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
       "step": 9
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.9309498071670532,
-      "learning_rate": 2e-05,
-      "loss": 0.7102,
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.23551630973815918,
+      "learning_rate": 0.0001,
+      "loss": 0.7259,
       "step": 10
     },
     {
-      "epoch": 0.36666666666666664,
-      "grad_norm": 1.0451229810714722,
-      "learning_rate": 2.2000000000000003e-05,
-      "loss": 0.9053,
-      "step": 11
-    },
-    {
-      "epoch": 0.4,
-      "grad_norm": 1.0207494497299194,
-      "learning_rate": 2.4e-05,
-      "loss": 0.7412,
-      "step": 12
-    },
-    {
-      "epoch": 0.43333333333333335,
-      "grad_norm": 1.2170029878616333,
-      "learning_rate": 2.6000000000000002e-05,
-      "loss": 1.053,
-      "step": 13
-    },
-    {
-      "epoch": 0.4666666666666667,
-      "grad_norm": 0.6286157965660095,
-      "learning_rate": 2.8000000000000003e-05,
-      "loss": 0.6928,
-      "step": 14
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 0.5481535792350769,
-      "learning_rate": 3e-05,
-      "loss": 0.6515,
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.197063609957695,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6883,
       "step": 15
     },
     {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 0.4317009150981903,
-      "learning_rate": 3.2000000000000005e-05,
-      "loss": 0.4639,
-      "step": 16
-    },
-    {
-      "epoch": 0.5666666666666667,
-      "grad_norm": 0.5328466296195984,
-      "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.4826,
-      "step": 17
-    },
-    {
-      "epoch": 0.6,
-      "grad_norm": 0.6660459041595459,
-      "learning_rate": 3.6e-05,
-      "loss": 0.6048,
+      "epoch": 2.0,
+      "eval_loss": 0.6461538076400757,
+      "eval_runtime": 3.3729,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
       "step": 18
     },
     {
-      "epoch": 0.6333333333333333,
-      "grad_norm": 0.370059609413147,
-      "learning_rate": 3.8e-05,
-      "loss": 0.4087,
-      "step": 19
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.4025858938694,
-      "learning_rate": 4e-05,
-      "loss": 0.423,
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.18328554928302765,
+      "learning_rate": 0.0002,
+      "loss": 0.6152,
       "step": 20
     },
     {
-      "epoch": 0.7,
-      "grad_norm": 0.5669470429420471,
-      "learning_rate": 4.2e-05,
-      "loss": 0.6043,
-      "step": 21
-    },
-    {
-      "epoch": 0.7333333333333333,
-      "grad_norm": 1.0960888862609863,
-      "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.7556,
-      "step": 22
-    },
-    {
-      "epoch": 0.7666666666666667,
-      "grad_norm": 0.629870593547821,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 0.5916,
-      "step": 23
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 1.13870370388031,
-      "learning_rate": 4.8e-05,
-      "loss": 1.0355,
-      "step": 24
-    },
-    {
-      "epoch": 0.8333333333333334,
-      "grad_norm": 1.1995460987091064,
-      "learning_rate": 5e-05,
-      "loss": 1.0187,
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17514856159687042,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.527,
       "step": 25
     },
     {
-      "epoch": 0.8666666666666667,
-      "grad_norm": 0.4150194823741913,
-      "learning_rate": 5.2000000000000004e-05,
-      "loss": 0.3633,
-      "step": 26
-    },
-    {
-      "epoch": 0.9,
-      "grad_norm": 0.889624834060669,
-      "learning_rate": 5.4000000000000005e-05,
-      "loss": 0.71,
+      "epoch": 3.0,
+      "eval_loss": 0.6003979444503784,
+      "eval_runtime": 3.3785,
+      "eval_samples_per_second": 4.44,
+      "eval_steps_per_second": 0.592,
       "step": 27
     },
     {
-      "epoch": 0.9333333333333333,
-      "grad_norm": 0.8311097025871277,
-      "learning_rate": 5.6000000000000006e-05,
-      "loss": 0.8872,
-      "step": 28
-    },
-    {
-      "epoch": 0.9666666666666667,
-      "grad_norm": 0.7439779043197632,
-      "learning_rate": 5.8e-05,
-      "loss": 0.5705,
-      "step": 29
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 0.7776324152946472,
-      "learning_rate": 6e-05,
-      "loss": 0.7965,
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.24001598358154297,
+      "learning_rate": 0.0001,
+      "loss": 0.5294,
       "step": 30
     },
     {
-      "epoch": 1.0333333333333334,
-      "grad_norm": 0.7862611413002014,
-      "learning_rate": 6.2e-05,
-      "loss": 0.9504,
-      "step": 31
-    },
-    {
-      "epoch": 1.0666666666666667,
-      "grad_norm": 0.2827726900577545,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 0.3123,
-      "step": 32
-    },
-    {
-      "epoch": 1.1,
-      "grad_norm": 0.3456995189189911,
-      "learning_rate": 6.6e-05,
-      "loss": 0.2998,
-      "step": 33
-    },
-    {
-      "epoch": 1.1333333333333333,
-      "grad_norm": 0.5150557160377502,
-      "learning_rate": 6.800000000000001e-05,
-      "loss": 0.5643,
-      "step": 34
-    },
-    {
-      "epoch": 1.1666666666666667,
-      "grad_norm": 0.6454989910125732,
-      "learning_rate": 7e-05,
-      "loss": 0.4744,
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.2075182944536209,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4269,
       "step": 35
     },
     {
-      "epoch": 1.2,
-      "grad_norm": 0.6500647068023682,
-      "learning_rate": 7.2e-05,
-      "loss": 0.5346,
+      "epoch": 4.0,
+      "eval_loss": 0.5861222147941589,
+      "eval_runtime": 3.3731,
+      "eval_samples_per_second": 4.447,
+      "eval_steps_per_second": 0.593,
       "step": 36
     },
     {
-      "epoch": 1.2333333333333334,
-      "grad_norm": 0.5693295001983643,
-      "learning_rate": 7.4e-05,
-      "loss": 0.4489,
-      "step": 37
-    },
-    {
-      "epoch": 1.2666666666666666,
-      "grad_norm": 0.4546714723110199,
-      "learning_rate": 7.6e-05,
-      "loss": 0.3024,
-      "step": 38
-    },
-    {
-      "epoch": 1.3,
-      "grad_norm": 1.0788987874984741,
-      "learning_rate": 7.800000000000001e-05,
-      "loss": 0.838,
-      "step": 39
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.21187624335289001,
+      "learning_rate": 0.0,
+      "loss": 0.4538,
+      "step": 40
     },
     {
-      "epoch": 1.3333333333333333,
-      "grad_norm": 0.6230797171592712,
-      "learning_rate": 8e-05,
-      "loss": 0.5216,
+      "epoch": 4.470588235294118,
+      "eval_loss": 0.5844668745994568,
+      "eval_runtime": 3.3754,
+      "eval_samples_per_second": 4.444,
+      "eval_steps_per_second": 0.593,
       "step": 40
     }
   ],
-  "logging_steps": 1,
+  "logging_steps": 5,
   "max_steps": 40,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -307,8 +123,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3791387398238208.0,
-  "train_batch_size": 1,
+  "total_flos": 2.1241123003551744e+16,
+  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-40/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fd6652c754895813cda9d0241920f5a0f666a6fe1a46fdfd76eefb00b73f5e
+oid sha256:1cbb49059cad2a21b53b046b184b0f6b571f903ce4eedecacdce52b76528c167
 size 5624

checkpoint-45/adapter_config.json

@@ -24,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "down_proj",
     "qkv_proj",
-    "gate_up_proj",
-    "down_proj"
+    "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,