Upload 36 files

README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008bbc8739da4f4bce6c17b891923db0c8b31313bbb4f011ed151c378f7970fe
+size 16822989

checkpoint-200/README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-200/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227ed95b71341cba0d563077f7f37f2dbed7750ff47f21b80ab4ddae118b2b02
+size 16822989

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b689890ddc96ee40858d9c1f1b534cb4e569ac2a86d09e0d379b529dfefef430
+size 33661637

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5b0ef21e8ad5b1640860623f386cdd56278312f5d51ba39c68c7c42afbb165
+size 14575

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3898e4de90d9c8915ce5bbd04cb758a9544095ecaac7b312d62a9e296d14033
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 1.4036030769348145,
+  "best_model_checkpoint": "Models/checkpoint-200",
+  "epoch": 0.9269988412514485,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.1801,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.1794,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.0713,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.8861,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 1.8091,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.7075,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.5947,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.6255,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00027,
+      "loss": 1.598,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 1.5142,
+      "step": 100
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00029449541284403666,
+      "loss": 1.5258,
+      "step": 110
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00028899082568807334,
+      "loss": 1.4687,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002834862385321101,
+      "loss": 1.4434,
+      "step": 130
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027798165137614677,
+      "loss": 1.4302,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00027247706422018345,
+      "loss": 1.3928,
+      "step": 150
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026697247706422014,
+      "loss": 1.4525,
+      "step": 160
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002614678899082569,
+      "loss": 1.4681,
+      "step": 170
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00025596330275229356,
+      "loss": 1.4105,
+      "step": 180
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00025045871559633025,
+      "loss": 1.3371,
+      "step": 190
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00024495412844036693,
+      "loss": 1.3493,
+      "step": 200
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.4036030769348145,
+      "eval_runtime": 87.4611,
+      "eval_samples_per_second": 22.867,
+      "eval_steps_per_second": 2.858,
+      "step": 200
+    }
+  ],
+  "max_steps": 645,
+  "num_train_epochs": 3,
+  "total_flos": 1.934247850750771e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1e74b7fd803a8e839b9c21fc0d7bfcb1a92e1832553d910fd90676ffabb4da
+size 3899

checkpoint-400/README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-400/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-400/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c749067fbcac98d950a1f94214ce1941dcaa372fc8b22daed090b4b392bec3ca
+size 16822989

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654c67b775ce84bb0b0d453e70848b7d68bc4757376a64a3d0509b5edffbb01a
+size 33661637

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45fca335d96ca7b8fb4a0b1cb0cc4726c0ad880949f8527c79c2179de5df25f
+size 14575

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7750c5ed289c824618797f9da4f70517efa2b1edb6d1db386283493f4ef80d
+size 627

checkpoint-400/trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 1.3160691261291504,
+  "best_model_checkpoint": "Models/checkpoint-400",
+  "epoch": 1.853997682502897,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.1801,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.1794,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.0713,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.8861,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 1.8091,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.7075,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.5947,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.6255,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00027,
+      "loss": 1.598,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 1.5142,
+      "step": 100
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00029449541284403666,
+      "loss": 1.5258,
+      "step": 110
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00028899082568807334,
+      "loss": 1.4687,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002834862385321101,
+      "loss": 1.4434,
+      "step": 130
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027798165137614677,
+      "loss": 1.4302,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00027247706422018345,
+      "loss": 1.3928,
+      "step": 150
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026697247706422014,
+      "loss": 1.4525,
+      "step": 160
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002614678899082569,
+      "loss": 1.4681,
+      "step": 170
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00025596330275229356,
+      "loss": 1.4105,
+      "step": 180
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00025045871559633025,
+      "loss": 1.3371,
+      "step": 190
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00024495412844036693,
+      "loss": 1.3493,
+      "step": 200
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.4036030769348145,
+      "eval_runtime": 87.4611,
+      "eval_samples_per_second": 22.867,
+      "eval_steps_per_second": 2.858,
+      "step": 200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00023944954128440364,
+      "loss": 1.3139,
+      "step": 210
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00023394495412844035,
+      "loss": 1.3878,
+      "step": 220
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022844036697247704,
+      "loss": 1.3011,
+      "step": 230
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00022293577981651375,
+      "loss": 1.3121,
+      "step": 240
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00021743119266055044,
+      "loss": 1.3234,
+      "step": 250
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00021192660550458712,
+      "loss": 1.2722,
+      "step": 260
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00020642201834862383,
+      "loss": 1.2897,
+      "step": 270
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00020091743119266052,
+      "loss": 1.2723,
+      "step": 280
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00019541284403669723,
+      "loss": 1.2375,
+      "step": 290
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00018990825688073391,
+      "loss": 1.2756,
+      "step": 300
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00018440366972477063,
+      "loss": 1.2567,
+      "step": 310
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001788990825688073,
+      "loss": 1.2491,
+      "step": 320
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00017339449541284402,
+      "loss": 1.2501,
+      "step": 330
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0001678899082568807,
+      "loss": 1.2702,
+      "step": 340
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00016238532110091742,
+      "loss": 1.2882,
+      "step": 350
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001568807339449541,
+      "loss": 1.2681,
+      "step": 360
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00015137614678899082,
+      "loss": 1.2652,
+      "step": 370
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00014587155963302753,
+      "loss": 1.2324,
+      "step": 380
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0001403669724770642,
+      "loss": 1.2817,
+      "step": 390
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00013486238532110092,
+      "loss": 1.2244,
+      "step": 400
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 1.3160691261291504,
+      "eval_runtime": 87.8417,
+      "eval_samples_per_second": 22.768,
+      "eval_steps_per_second": 2.846,
+      "step": 400
+    }
+  ],
+  "max_steps": 645,
+  "num_train_epochs": 3,
+  "total_flos": 3.853804232717107e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1e74b7fd803a8e839b9c21fc0d7bfcb1a92e1832553d910fd90676ffabb4da
+size 3899

checkpoint-600/README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-600/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-600/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008bbc8739da4f4bce6c17b891923db0c8b31313bbb4f011ed151c378f7970fe
+size 16822989

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60130c639e2ec9e64e2c7e4fc30a09266c9db1d1fe7b088371be1dde1c9ded5b
+size 33661637

checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2022b9084eaad35fa39d9d60b11022a55cb483af58466916262380e7162eb400
+size 14575

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b90feb287dc996919e3b117741d0e5fc1a9046b137a2edeb80b96eee09400ac
+size 627

checkpoint-600/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_metric": 1.285245418548584,
+  "best_model_checkpoint": "Models/checkpoint-600",
+  "epoch": 2.7809965237543453,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.1801,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.1794,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.0713,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.8861,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 1.8091,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.7075,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.5947,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.6255,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00027,
+      "loss": 1.598,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 1.5142,
+      "step": 100
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00029449541284403666,
+      "loss": 1.5258,
+      "step": 110
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00028899082568807334,
+      "loss": 1.4687,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002834862385321101,
+      "loss": 1.4434,
+      "step": 130
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027798165137614677,
+      "loss": 1.4302,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00027247706422018345,
+      "loss": 1.3928,
+      "step": 150
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026697247706422014,
+      "loss": 1.4525,
+      "step": 160
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002614678899082569,
+      "loss": 1.4681,
+      "step": 170
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00025596330275229356,
+      "loss": 1.4105,
+      "step": 180
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00025045871559633025,
+      "loss": 1.3371,
+      "step": 190
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00024495412844036693,
+      "loss": 1.3493,
+      "step": 200
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.4036030769348145,
+      "eval_runtime": 87.4611,
+      "eval_samples_per_second": 22.867,
+      "eval_steps_per_second": 2.858,
+      "step": 200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00023944954128440364,
+      "loss": 1.3139,
+      "step": 210
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00023394495412844035,
+      "loss": 1.3878,
+      "step": 220
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022844036697247704,
+      "loss": 1.3011,
+      "step": 230
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00022293577981651375,
+      "loss": 1.3121,
+      "step": 240
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00021743119266055044,
+      "loss": 1.3234,
+      "step": 250
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00021192660550458712,
+      "loss": 1.2722,
+      "step": 260
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00020642201834862383,
+      "loss": 1.2897,
+      "step": 270
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00020091743119266052,
+      "loss": 1.2723,
+      "step": 280
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00019541284403669723,
+      "loss": 1.2375,
+      "step": 290
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00018990825688073391,
+      "loss": 1.2756,
+      "step": 300
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00018440366972477063,
+      "loss": 1.2567,
+      "step": 310
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001788990825688073,
+      "loss": 1.2491,
+      "step": 320
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00017339449541284402,
+      "loss": 1.2501,
+      "step": 330
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0001678899082568807,
+      "loss": 1.2702,
+      "step": 340
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00016238532110091742,
+      "loss": 1.2882,
+      "step": 350
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001568807339449541,
+      "loss": 1.2681,
+      "step": 360
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00015137614678899082,
+      "loss": 1.2652,
+      "step": 370
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00014587155963302753,
+      "loss": 1.2324,
+      "step": 380
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0001403669724770642,
+      "loss": 1.2817,
+      "step": 390
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00013486238532110092,
+      "loss": 1.2244,
+      "step": 400
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 1.3160691261291504,
+      "eval_runtime": 87.8417,
+      "eval_samples_per_second": 22.768,
+      "eval_steps_per_second": 2.846,
+      "step": 400
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0001293577981651376,
+      "loss": 1.2933,
+      "step": 410
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00012385321100917432,
+      "loss": 1.2248,
+      "step": 420
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.000118348623853211,
+      "loss": 1.2437,
+      "step": 430
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0001128440366972477,
+      "loss": 1.1904,
+      "step": 440
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.0001073394495412844,
+      "loss": 1.1809,
+      "step": 450
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0001018348623853211,
+      "loss": 1.1475,
+      "step": 460
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.63302752293578e-05,
+      "loss": 1.1345,
+      "step": 470
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.08256880733945e-05,
+      "loss": 1.1766,
+      "step": 480
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.53211009174312e-05,
+      "loss": 1.1694,
+      "step": 490
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 7.981651376146788e-05,
+      "loss": 1.1736,
+      "step": 500
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 7.431192660550458e-05,
+      "loss": 1.1543,
+      "step": 510
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 6.880733944954128e-05,
+      "loss": 1.1707,
+      "step": 520
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.330275229357798e-05,
+      "loss": 1.112,
+      "step": 530
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.7798165137614674e-05,
+      "loss": 1.1202,
+      "step": 540
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.229357798165137e-05,
+      "loss": 1.1136,
+      "step": 550
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.678899082568807e-05,
+      "loss": 1.1451,
+      "step": 560
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.128440366972477e-05,
+      "loss": 1.1713,
+      "step": 570
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 3.577981651376147e-05,
+      "loss": 1.1593,
+      "step": 580
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.0275229357798166e-05,
+      "loss": 1.1583,
+      "step": 590
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.477064220183486e-05,
+      "loss": 1.1867,
+      "step": 600
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 1.285245418548584,
+      "eval_runtime": 87.6765,
+      "eval_samples_per_second": 22.811,
+      "eval_steps_per_second": 2.851,
+      "step": 600
+    }
+  ],
+  "max_steps": 645,
+  "num_train_epochs": 3,
+  "total_flos": 5.779417623743693e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1e74b7fd803a8e839b9c21fc0d7bfcb1a92e1832553d910fd90676ffabb4da
+size 3899

runs/Oct06_07-23-18_af3493a7af10/events.out.tfevents.1696577001.af3493a7af10.3593.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624986bbd819e1c08f3b251f07891d98c37e5942f4ff726f4def558ad18a3b37
+size 4016

runs/Oct06_07-28-18_af3493a7af10/events.out.tfevents.1696577300.af3493a7af10.5687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3984504f602d0835ef71a7ee4647f6bb3bba6c6d3b40fa080b2f40f7a1fa767
+size 4016

runs/Oct06_07-36-25_af3493a7af10/events.out.tfevents.1696577786.af3493a7af10.7846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2064685f2a9aed164d95fc369b5a0f82ed14022d56ae5cb47fa9646f5215b4
+size 4016

runs/Oct06_07-42-18_af3493a7af10/events.out.tfevents.1696578139.af3493a7af10.9745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ec000a2599c74e3179bf42dc241c91dbce2cb4677531ecff0bb52940a26bfb
+size 88

runs/Oct06_07-44-57_af3493a7af10/events.out.tfevents.1696578298.af3493a7af10.10533.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6e033b826ca00aabd80641751a9cdec7557ee6148d9abf4e7fd762752bb3e7
+size 4016

runs/Oct06_07-50-16_af3493a7af10/events.out.tfevents.1696578617.af3493a7af10.11954.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deae2a597d1df5c64159ff13798ec8a7bd80d0a0c582801b03889f85051fe14d
+size 4983

runs/Oct06_07-53-43_af3493a7af10/events.out.tfevents.1696578824.af3493a7af10.12940.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42e845b25a8cc56363d34bc0ba57408ec67c41e751456c641ba2e9879a309f1
+size 4675

runs/Oct06_07-55-49_af3493a7af10/events.out.tfevents.1696578950.af3493a7af10.13610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f75f08273de4443c7ce4c5be309b50ce7964e6380520296f4148717602f9ce
+size 4675

runs/Oct06_07-58-30_af3493a7af10/events.out.tfevents.1696579111.af3493a7af10.14367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312ac66ed24bd7127635afdfac3fe3c82e527b0d790576a117043456c27ceaa4
+size 15546