Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+---
+
+# 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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4391b7f3c04555a6c0f8019a3edb28bed01114620fae3b95953968aa121e2dc
+size 239135488

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
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.614759667923576,
+    "train_runtime": 422.1655,
+    "train_samples_per_second": 1.393,
+    "train_steps_per_second": 0.045
+}

checkpoint-10/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+---
+
+# 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-10/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-10/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837cc2c295b03e4d59fdc12dab5f7f44a0e0f418a22eff5cdf5d4ab89a99072b
+size 239135488

checkpoint-10/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-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab2c6ee2b4bfbd959aedb11e2b7374723c5b6508ed012fa87b7316127829aef
+size 478419450

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944c1325c6568a3378188af307c33a14f3ba306b0b372887eb1f7c5e30329bd5
+size 14244

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3794a4d9ab6950d1911af011590ac861ce477ee78c5af1ac7ae6691d6db51051
+size 1064

checkpoint-10/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10/tokenizer.model

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

checkpoint-10/tokenizer_config.json

@@ -0,0 +1,130 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-10/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": 1.5293647050857544,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-10_15-16-32/checkpoint-10",
+  "epoch": 0.5263157894736842,
+  "eval_steps": 1,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 22.303813934326172,
+      "learning_rate": 0.0002,
+      "loss": 5.2005,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 5.126399993896484,
+      "eval_runtime": 8.3738,
+      "eval_samples_per_second": 7.404,
+      "eval_steps_per_second": 0.478,
+      "step": 1
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 21.968650817871094,
+      "learning_rate": 0.0004,
+      "loss": 5.1548,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 2.035064935684204,
+      "eval_runtime": 8.1279,
+      "eval_samples_per_second": 7.628,
+      "eval_steps_per_second": 0.492,
+      "step": 2
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 4.796197891235352,
+      "learning_rate": 0.00037647058823529414,
+      "loss": 1.9739,
+      "step": 3
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "eval_loss": 1.565435767173767,
+      "eval_runtime": 8.1953,
+      "eval_samples_per_second": 7.565,
+      "eval_steps_per_second": 0.488,
+      "step": 3
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.5580379962921143,
+      "learning_rate": 0.00035294117647058826,
+      "loss": 1.5127,
+      "step": 4
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.5319403409957886,
+      "eval_runtime": 8.2189,
+      "eval_samples_per_second": 7.544,
+      "eval_steps_per_second": 0.487,
+      "step": 4
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.5636128187179565,
+      "learning_rate": 0.0003294117647058824,
+      "loss": 1.5023,
+      "step": 5
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "eval_loss": 1.4795572757720947,
+      "eval_runtime": 8.1979,
+      "eval_samples_per_second": 7.563,
+      "eval_steps_per_second": 0.488,
+      "step": 5
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.6475034952163696,
+      "learning_rate": 0.00030588235294117644,
+      "loss": 1.4094,
+      "step": 6
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 1.4736040830612183,
+      "eval_runtime": 8.1682,
+      "eval_samples_per_second": 7.59,
+      "eval_steps_per_second": 0.49,
+      "step": 6
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 1.273154616355896,
+      "learning_rate": 0.0002823529411764706,
+      "loss": 1.2526,
+      "step": 7
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "eval_loss": 1.801269292831421,
+      "eval_runtime": 8.1796,
+      "eval_samples_per_second": 7.58,
+      "eval_steps_per_second": 0.489,
+      "step": 7
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.148282527923584,
+      "learning_rate": 0.00025882352941176474,
+      "loss": 1.2184,
+      "step": 8
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 1.6574877500534058,
+      "eval_runtime": 8.2558,
+      "eval_samples_per_second": 7.51,
+      "eval_steps_per_second": 0.485,
+      "step": 8
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.6692990064620972,
+      "learning_rate": 0.00023529411764705883,
+      "loss": 1.1489,
+      "step": 9
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "eval_loss": 1.5531737804412842,
+      "eval_runtime": 8.2574,
+      "eval_samples_per_second": 7.508,
+      "eval_steps_per_second": 0.484,
+      "step": 9
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.5520226955413818,
+      "learning_rate": 0.00021176470588235295,
+      "loss": 1.1021,
+      "step": 10
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 1.5293647050857544,
+      "eval_runtime": 8.3253,
+      "eval_samples_per_second": 7.447,
+      "eval_steps_per_second": 0.48,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7436398315438080.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6baa230af705158600df21adac8b38aaca8ef649bb26a5d16b6033d78f8522
+size 5688

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,130 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.614759667923576,
+    "train_runtime": 422.1655,
+    "train_samples_per_second": 1.393,
+    "train_steps_per_second": 0.045
+}

trainer_state.json

@@ -0,0 +1,327 @@
+{
+  "best_metric": 1.5293647050857544,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-10_15-16-32/checkpoint-10",
+  "epoch": 1.0,
+  "eval_steps": 1,
+  "global_step": 19,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 22.303813934326172,
+      "learning_rate": 0.0002,
+      "loss": 5.2005,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 5.126399993896484,
+      "eval_runtime": 8.3738,
+      "eval_samples_per_second": 7.404,
+      "eval_steps_per_second": 0.478,
+      "step": 1
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 21.968650817871094,
+      "learning_rate": 0.0004,
+      "loss": 5.1548,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 2.035064935684204,
+      "eval_runtime": 8.1279,
+      "eval_samples_per_second": 7.628,
+      "eval_steps_per_second": 0.492,
+      "step": 2
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 4.796197891235352,
+      "learning_rate": 0.00037647058823529414,
+      "loss": 1.9739,
+      "step": 3
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "eval_loss": 1.565435767173767,
+      "eval_runtime": 8.1953,
+      "eval_samples_per_second": 7.565,
+      "eval_steps_per_second": 0.488,
+      "step": 3
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.5580379962921143,
+      "learning_rate": 0.00035294117647058826,
+      "loss": 1.5127,
+      "step": 4
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.5319403409957886,
+      "eval_runtime": 8.2189,
+      "eval_samples_per_second": 7.544,
+      "eval_steps_per_second": 0.487,
+      "step": 4
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.5636128187179565,
+      "learning_rate": 0.0003294117647058824,
+      "loss": 1.5023,
+      "step": 5
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "eval_loss": 1.4795572757720947,
+      "eval_runtime": 8.1979,
+      "eval_samples_per_second": 7.563,
+      "eval_steps_per_second": 0.488,
+      "step": 5
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.6475034952163696,
+      "learning_rate": 0.00030588235294117644,
+      "loss": 1.4094,
+      "step": 6
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 1.4736040830612183,
+      "eval_runtime": 8.1682,
+      "eval_samples_per_second": 7.59,
+      "eval_steps_per_second": 0.49,
+      "step": 6
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 1.273154616355896,
+      "learning_rate": 0.0002823529411764706,
+      "loss": 1.2526,
+      "step": 7
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "eval_loss": 1.801269292831421,
+      "eval_runtime": 8.1796,
+      "eval_samples_per_second": 7.58,
+      "eval_steps_per_second": 0.489,
+      "step": 7
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.148282527923584,
+      "learning_rate": 0.00025882352941176474,
+      "loss": 1.2184,
+      "step": 8
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 1.6574877500534058,
+      "eval_runtime": 8.2558,
+      "eval_samples_per_second": 7.51,
+      "eval_steps_per_second": 0.485,
+      "step": 8
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.6692990064620972,
+      "learning_rate": 0.00023529411764705883,
+      "loss": 1.1489,
+      "step": 9
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "eval_loss": 1.5531737804412842,
+      "eval_runtime": 8.2574,
+      "eval_samples_per_second": 7.508,
+      "eval_steps_per_second": 0.484,
+      "step": 9
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.5520226955413818,
+      "learning_rate": 0.00021176470588235295,
+      "loss": 1.1021,
+      "step": 10
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 1.5293647050857544,
+      "eval_runtime": 8.3253,
+      "eval_samples_per_second": 7.447,
+      "eval_steps_per_second": 0.48,
+      "step": 10
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.3798828423023224,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 1.0751,
+      "step": 11
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "eval_loss": 1.565451979637146,
+      "eval_runtime": 8.1863,
+      "eval_samples_per_second": 7.574,
+      "eval_steps_per_second": 0.489,
+      "step": 11
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.2520289719104767,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 1.0487,
+      "step": 12
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 1.6195383071899414,
+      "eval_runtime": 8.2116,
+      "eval_samples_per_second": 7.55,
+      "eval_steps_per_second": 0.487,
+      "step": 12
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.26942452788352966,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 1.0435,
+      "step": 13
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "eval_loss": 1.635750412940979,
+      "eval_runtime": 8.2868,
+      "eval_samples_per_second": 7.482,
+      "eval_steps_per_second": 0.483,
+      "step": 13
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.23508282005786896,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 1.0481,
+      "step": 14
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "eval_loss": 1.625639796257019,
+      "eval_runtime": 8.2755,
+      "eval_samples_per_second": 7.492,
+      "eval_steps_per_second": 0.483,
+      "step": 14
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.21778114140033722,
+      "learning_rate": 9.411764705882353e-05,
+      "loss": 1.0049,
+      "step": 15
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "eval_loss": 1.6122336387634277,
+      "eval_runtime": 8.2527,
+      "eval_samples_per_second": 7.513,
+      "eval_steps_per_second": 0.485,
+      "step": 15
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.27773982286453247,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 1.0006,
+      "step": 16
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 1.5968810319900513,
+      "eval_runtime": 8.3129,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 0.481,
+      "step": 16
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2526203393936157,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.9965,
+      "step": 17
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "eval_loss": 1.5880597829818726,
+      "eval_runtime": 8.2366,
+      "eval_samples_per_second": 7.527,
+      "eval_steps_per_second": 0.486,
+      "step": 17
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.20632648468017578,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.9902,
+      "step": 18
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 1.5857887268066406,
+      "eval_runtime": 8.2438,
+      "eval_samples_per_second": 7.521,
+      "eval_steps_per_second": 0.485,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2954784333705902,
+      "learning_rate": 0.0,
+      "loss": 0.9972,
+      "step": 19
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5857279300689697,
+      "eval_runtime": 8.3407,
+      "eval_samples_per_second": 7.433,
+      "eval_steps_per_second": 0.48,
+      "step": 19
+    },
+    {
+      "epoch": 1.0,
+      "step": 19,
+      "total_flos": 1.3664381904617472e+16,
+      "train_loss": 1.614759667923576,
+      "train_runtime": 422.1655,
+      "train_samples_per_second": 1.393,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3664381904617472e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6baa230af705158600df21adac8b38aaca8ef649bb26a5d16b6033d78f8522
+size 5688