Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_up_proj",
+    "down_proj",
+    "qkv_proj"
+  ],
+  "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 sha256:576143ac7b78beb57007331ff62538cacdc10cdc4e331b6b944e55154a821cf2
+size 201361312

added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010,
+  "eos_token": 32011
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2254687315887876,
+    "train_runtime": 391.2151,
+    "train_samples_per_second": 1.403,
+    "train_steps_per_second": 0.046
+}

checkpoint-10/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_up_proj",
+    "down_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-10/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7277b6348acdefaa51be2dbc0aaf4e7f0ee58b3009b439ce023bdb143ccc27
+size 201361312

checkpoint-10/added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010,
+  "eos_token": 32011
+}

checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765a72e2a5b23ace4c0120ba6084780600b481f59b19884e713188413c3aa899
+size 402807738

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d25458d250308b66b3252c4b210a54c82239cfc07eac3e5e9e49c8c3fee9f7
+size 14180

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbbc78a3ecb200e12b13ea331485ab67c548808398aea3b142a636fbddac3e5
+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 +1,139 @@
+{
+  "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
+    },
+    "32011": {
+      "content": "eos_token",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "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",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-10/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": 1.3153774738311768,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-11_10-50-46/checkpoint-10",
+  "epoch": 0.5555555555555556,
+  "eval_steps": 1,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.9254094362258911,
+      "learning_rate": 0.0002,
+      "loss": 3.544,
+      "step": 1
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": 3.981394052505493,
+      "eval_runtime": 12.6022,
+      "eval_samples_per_second": 11.347,
+      "eval_steps_per_second": 0.714,
+      "step": 1
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 2.0063693523406982,
+      "learning_rate": 0.0004,
+      "loss": 3.6373,
+      "step": 2
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 3.173820972442627,
+      "eval_runtime": 12.6737,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 0.71,
+      "step": 2
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.0154714584350586,
+      "learning_rate": 0.000375,
+      "loss": 2.7246,
+      "step": 3
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "eval_loss": 1.9138473272323608,
+      "eval_runtime": 12.6464,
+      "eval_samples_per_second": 11.308,
+      "eval_steps_per_second": 0.712,
+      "step": 3
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.1926450729370117,
+      "learning_rate": 0.00035,
+      "loss": 1.4998,
+      "step": 4
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 1.4986788034439087,
+      "eval_runtime": 12.7087,
+      "eval_samples_per_second": 11.252,
+      "eval_steps_per_second": 0.708,
+      "step": 4
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.8283662796020508,
+      "learning_rate": 0.00032500000000000004,
+      "loss": 1.1373,
+      "step": 5
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "eval_loss": 1.3153411149978638,
+      "eval_runtime": 12.7034,
+      "eval_samples_per_second": 11.257,
+      "eval_steps_per_second": 0.708,
+      "step": 5
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6860641241073608,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.9828,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 1.247497797012329,
+      "eval_runtime": 12.6669,
+      "eval_samples_per_second": 11.289,
+      "eval_steps_per_second": 0.711,
+      "step": 6
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.2969834506511688,
+      "learning_rate": 0.000275,
+      "loss": 0.91,
+      "step": 7
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "eval_loss": 1.2433477640151978,
+      "eval_runtime": 12.6841,
+      "eval_samples_per_second": 11.274,
+      "eval_steps_per_second": 0.71,
+      "step": 7
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.1941613256931305,
+      "learning_rate": 0.00025,
+      "loss": 0.839,
+      "step": 8
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 1.2696853876113892,
+      "eval_runtime": 12.7426,
+      "eval_samples_per_second": 11.222,
+      "eval_steps_per_second": 0.706,
+      "step": 8
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.19763241708278656,
+      "learning_rate": 0.00022500000000000002,
+      "loss": 0.7744,
+      "step": 9
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.3031294345855713,
+      "eval_runtime": 12.7085,
+      "eval_samples_per_second": 11.252,
+      "eval_steps_per_second": 0.708,
+      "step": 9
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.20671840012073517,
+      "learning_rate": 0.0002,
+      "loss": 0.7289,
+      "step": 10
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 1.3153774738311768,
+      "eval_runtime": 12.6745,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 0.71,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 18,
+  "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": 3708922028359680.0,
+  "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 sha256:71267f87e623261564b6c34b005f8da1c7f442260ffcb3f3e2e0703063ea6485
+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 +1,139 @@
+{
+  "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
+    },
+    "32011": {
+      "content": "eos_token",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "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",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2254687315887876,
+    "train_runtime": 391.2151,
+    "train_samples_per_second": 1.403,
+    "train_steps_per_second": 0.046
+}

trainer_state.json

@@ -0,0 +1,312 @@
+{
+  "best_metric": 1.3153774738311768,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-11_10-50-46/checkpoint-10",
+  "epoch": 1.0,
+  "eval_steps": 1,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.9254094362258911,
+      "learning_rate": 0.0002,
+      "loss": 3.544,
+      "step": 1
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": 3.981394052505493,
+      "eval_runtime": 12.6022,
+      "eval_samples_per_second": 11.347,
+      "eval_steps_per_second": 0.714,
+      "step": 1
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 2.0063693523406982,
+      "learning_rate": 0.0004,
+      "loss": 3.6373,
+      "step": 2
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 3.173820972442627,
+      "eval_runtime": 12.6737,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 0.71,
+      "step": 2
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.0154714584350586,
+      "learning_rate": 0.000375,
+      "loss": 2.7246,
+      "step": 3
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "eval_loss": 1.9138473272323608,
+      "eval_runtime": 12.6464,
+      "eval_samples_per_second": 11.308,
+      "eval_steps_per_second": 0.712,
+      "step": 3
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.1926450729370117,
+      "learning_rate": 0.00035,
+      "loss": 1.4998,
+      "step": 4
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 1.4986788034439087,
+      "eval_runtime": 12.7087,
+      "eval_samples_per_second": 11.252,
+      "eval_steps_per_second": 0.708,
+      "step": 4
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.8283662796020508,
+      "learning_rate": 0.00032500000000000004,
+      "loss": 1.1373,
+      "step": 5
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "eval_loss": 1.3153411149978638,
+      "eval_runtime": 12.7034,
+      "eval_samples_per_second": 11.257,
+      "eval_steps_per_second": 0.708,
+      "step": 5
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6860641241073608,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.9828,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 1.247497797012329,
+      "eval_runtime": 12.6669,
+      "eval_samples_per_second": 11.289,
+      "eval_steps_per_second": 0.711,
+      "step": 6
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.2969834506511688,
+      "learning_rate": 0.000275,
+      "loss": 0.91,
+      "step": 7
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "eval_loss": 1.2433477640151978,
+      "eval_runtime": 12.6841,
+      "eval_samples_per_second": 11.274,
+      "eval_steps_per_second": 0.71,
+      "step": 7
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.1941613256931305,
+      "learning_rate": 0.00025,
+      "loss": 0.839,
+      "step": 8
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 1.2696853876113892,
+      "eval_runtime": 12.7426,
+      "eval_samples_per_second": 11.222,
+      "eval_steps_per_second": 0.706,
+      "step": 8
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.19763241708278656,
+      "learning_rate": 0.00022500000000000002,
+      "loss": 0.7744,
+      "step": 9
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.3031294345855713,
+      "eval_runtime": 12.7085,
+      "eval_samples_per_second": 11.252,
+      "eval_steps_per_second": 0.708,
+      "step": 9
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.20671840012073517,
+      "learning_rate": 0.0002,
+      "loss": 0.7289,
+      "step": 10
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 1.3153774738311768,
+      "eval_runtime": 12.6745,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 0.71,
+      "step": 10
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.20304171741008759,
+      "learning_rate": 0.000175,
+      "loss": 0.7123,
+      "step": 11
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "eval_loss": 1.3239251375198364,
+      "eval_runtime": 12.736,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 0.707,
+      "step": 11
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.17941166460514069,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6761,
+      "step": 12
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.3320614099502563,
+      "eval_runtime": 12.7074,
+      "eval_samples_per_second": 11.253,
+      "eval_steps_per_second": 0.708,
+      "step": 12
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.12196698784828186,
+      "learning_rate": 0.000125,
+      "loss": 0.6576,
+      "step": 13
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "eval_loss": 1.3407816886901855,
+      "eval_runtime": 12.7455,
+      "eval_samples_per_second": 11.22,
+      "eval_steps_per_second": 0.706,
+      "step": 13
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.09605628997087479,
+      "learning_rate": 0.0001,
+      "loss": 0.6529,
+      "step": 14
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": 1.3476217985153198,
+      "eval_runtime": 12.7567,
+      "eval_samples_per_second": 11.21,
+      "eval_steps_per_second": 0.706,
+      "step": 14
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.12586502730846405,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6339,
+      "step": 15
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_loss": 1.3515379428863525,
+      "eval_runtime": 12.6504,
+      "eval_samples_per_second": 11.304,
+      "eval_steps_per_second": 0.711,
+      "step": 15
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.1299675554037094,
+      "learning_rate": 5e-05,
+      "loss": 0.6455,
+      "step": 16
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.3539159297943115,
+      "eval_runtime": 12.7843,
+      "eval_samples_per_second": 11.186,
+      "eval_steps_per_second": 0.704,
+      "step": 16
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 0.1078740730881691,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6501,
+      "step": 17
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "eval_loss": 1.3558857440948486,
+      "eval_runtime": 12.6716,
+      "eval_samples_per_second": 11.285,
+      "eval_steps_per_second": 0.71,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15631119906902313,
+      "learning_rate": 0.0,
+      "loss": 0.6519,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.357097864151001,
+      "eval_runtime": 12.7301,
+      "eval_samples_per_second": 11.233,
+      "eval_steps_per_second": 0.707,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "step": 18,
+      "total_flos": 6363119354904576.0,
+      "train_loss": 1.2254687315887876,
+      "train_runtime": 391.2151,
+      "train_samples_per_second": 1.403,
+      "train_steps_per_second": 0.046
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 18,
+  "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": 6363119354904576.0,
+  "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 sha256:71267f87e623261564b6c34b005f8da1c7f442260ffcb3f3e2e0703063ea6485
+size 5688