Upload merged fine-tuned risk prediction model

README.md

@@ -0,0 +1,207 @@
+---
+base_model: distilgpt2
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:distilgpt2
+- lora
+- transformers
+---
+
+# 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 0.16.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilgpt2",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_proj",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca4e2f5a94bd360d8b66e5a9280a8231c9e81dea5ff61e6be52c065b554f4dc
+size 9443272

checkpoint-4956/README.md

@@ -0,0 +1,207 @@
+---
+base_model: distilgpt2
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:distilgpt2
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-4956/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilgpt2",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_proj",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-4956/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca4e2f5a94bd360d8b66e5a9280a8231c9e81dea5ff61e6be52c065b554f4dc
+size 9443272

checkpoint-4956/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca3f6beee55a38e0290e6f3d9e3ffd9ad152c2f9a3f20b9b439f112e91cb734
+size 18915130

checkpoint-4956/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536bd56ad7ff485b11a2fc8972a9e63fb7c1274d81b6fd4fd15cc31dab088144
+size 14244

checkpoint-4956/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5082fbaa6978fd5c61eaa5acebd280eb3935bb03225f3458659290901e16f235
+size 988

checkpoint-4956/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824136799744b1e2966d1f476ebd9979fa860ee0d6f3bae5bb5451850918dcde
+size 1064

checkpoint-4956/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-4956/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-4956/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 4956,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012106537530266344,
+      "grad_norm": 1.145218849182129,
+      "learning_rate": 0.0,
+      "loss": 4.1864,
+      "step": 1
+    },
+    {
+      "epoch": 0.06053268765133172,
+      "grad_norm": 1.148585557937622,
+      "learning_rate": 2.45e-05,
+      "loss": 4.4157,
+      "step": 50
+    },
+    {
+      "epoch": 0.12106537530266344,
+      "grad_norm": 2.0597307682037354,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 3.892,
+      "step": 100
+    },
+    {
+      "epoch": 0.18159806295399517,
+      "grad_norm": 1.9923838376998901,
+      "learning_rate": 4.99874394634245e-05,
+      "loss": 3.2562,
+      "step": 150
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 4.029146671295166,
+      "learning_rate": 4.9948740504890754e-05,
+      "loss": 2.7958,
+      "step": 200
+    },
+    {
+      "epoch": 0.3026634382566586,
+      "grad_norm": 2.815180778503418,
+      "learning_rate": 4.988393838221347e-05,
+      "loss": 2.3195,
+      "step": 250
+    },
+    {
+      "epoch": 0.36319612590799033,
+      "grad_norm": 2.436539649963379,
+      "learning_rate": 4.979310089602749e-05,
+      "loss": 2.1945,
+      "step": 300
+    },
+    {
+      "epoch": 0.423728813559322,
+      "grad_norm": 3.213885545730591,
+      "learning_rate": 4.967632308703485e-05,
+      "loss": 2.096,
+      "step": 350
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 2.9719736576080322,
+      "learning_rate": 4.953372713656633e-05,
+      "loss": 2.0549,
+      "step": 400
+    },
+    {
+      "epoch": 0.5447941888619855,
+      "grad_norm": 3.2433812618255615,
+      "learning_rate": 4.936546223874662e-05,
+      "loss": 1.9792,
+      "step": 450
+    },
+    {
+      "epoch": 0.6053268765133172,
+      "grad_norm": 2.406186103820801,
+      "learning_rate": 4.917170444439664e-05,
+      "loss": 1.9175,
+      "step": 500
+    },
+    {
+      "epoch": 0.6658595641646489,
+      "grad_norm": 3.1496739387512207,
+      "learning_rate": 4.895265647683661e-05,
+      "loss": 1.953,
+      "step": 550
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 2.9170095920562744,
+      "learning_rate": 4.8708547519782295e-05,
+      "loss": 1.8685,
+      "step": 600
+    },
+    {
+      "epoch": 0.7869249394673123,
+      "grad_norm": 2.7137584686279297,
+      "learning_rate": 4.843963297755655e-05,
+      "loss": 1.8412,
+      "step": 650
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 2.466970443725586,
+      "learning_rate": 4.814619420786698e-05,
+      "loss": 1.8587,
+      "step": 700
+    },
+    {
+      "epoch": 0.9079903147699758,
+      "grad_norm": 2.87086820602417,
+      "learning_rate": 4.782853822742932e-05,
+      "loss": 1.8333,
+      "step": 750
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 2.2721059322357178,
+      "learning_rate": 4.748699739074447e-05,
+      "loss": 1.7413,
+      "step": 800
+    },
+    {
+      "epoch": 1.0290556900726393,
+      "grad_norm": 2.7987253665924072,
+      "learning_rate": 4.7121929042365355e-05,
+      "loss": 1.7451,
+      "step": 850
+    },
+    {
+      "epoch": 1.089588377723971,
+      "grad_norm": 3.276827096939087,
+      "learning_rate": 4.673371514301737e-05,
+      "loss": 1.7614,
+      "step": 900
+    },
+    {
+      "epoch": 1.1501210653753027,
+      "grad_norm": 3.5362303256988525,
+      "learning_rate": 4.632276186996369e-05,
+      "loss": 1.8002,
+      "step": 950
+    },
+    {
+      "epoch": 1.2106537530266344,
+      "grad_norm": 2.2871510982513428,
+      "learning_rate": 4.588949919203338e-05,
+      "loss": 1.7262,
+      "step": 1000
+    },
+    {
+      "epoch": 1.271186440677966,
+      "grad_norm": 2.405946969985962,
+      "learning_rate": 4.5434380419757184e-05,
+      "loss": 1.7707,
+      "step": 1050
+    },
+    {
+      "epoch": 1.331719128329298,
+      "grad_norm": 3.359639883041382,
+      "learning_rate": 4.495788173108143e-05,
+      "loss": 1.7167,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3922518159806296,
+      "grad_norm": 2.4497766494750977,
+      "learning_rate": 4.4460501673156526e-05,
+      "loss": 1.6081,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4527845036319613,
+      "grad_norm": 2.275221109390259,
+      "learning_rate": 4.3942760640721084e-05,
+      "loss": 1.6354,
+      "step": 1200
+    },
+    {
+      "epoch": 1.513317191283293,
+      "grad_norm": 2.781876802444458,
+      "learning_rate": 4.340520033162758e-05,
+      "loss": 1.6963,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5738498789346247,
+      "grad_norm": 2.2864878177642822,
+      "learning_rate": 4.284838318007915e-05,
+      "loss": 1.7686,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6343825665859564,
+      "grad_norm": 3.4569664001464844,
+      "learning_rate": 4.227289176817055e-05,
+      "loss": 1.6833,
+      "step": 1350
+    },
+    {
+      "epoch": 1.694915254237288,
+      "grad_norm": 3.410222291946411,
+      "learning_rate": 4.167932821634893e-05,
+      "loss": 1.6721,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7554479418886197,
+      "grad_norm": 2.8878772258758545,
+      "learning_rate": 4.106831355343213e-05,
+      "loss": 1.6283,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8159806295399514,
+      "grad_norm": 2.131619930267334,
+      "learning_rate": 4.04404870668438e-05,
+      "loss": 1.5914,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8765133171912833,
+      "grad_norm": 2.774812698364258,
+      "learning_rate": 3.9796505633744906e-05,
+      "loss": 1.6481,
+      "step": 1550
+    },
+    {
+      "epoch": 1.937046004842615,
+      "grad_norm": 2.571086883544922,
+      "learning_rate": 3.913704303376174e-05,
+      "loss": 1.6737,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9975786924939467,
+      "grad_norm": 2.756775140762329,
+      "learning_rate": 3.8462789244029254e-05,
+      "loss": 1.6977,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0581113801452786,
+      "grad_norm": 2.6481270790100098,
+      "learning_rate": 3.77744497172874e-05,
+      "loss": 1.6309,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1186440677966103,
+      "grad_norm": 2.9829535484313965,
+      "learning_rate": 3.7072744643785835e-05,
+      "loss": 1.6208,
+      "step": 1750
+    },
+    {
+      "epoch": 2.179176755447942,
+      "grad_norm": 2.707387685775757,
+      "learning_rate": 3.6358408197769165e-05,
+      "loss": 1.6691,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2397094430992737,
+      "grad_norm": 2.654651403427124,
+      "learning_rate": 3.5632187769331124e-05,
+      "loss": 1.5447,
+      "step": 1850
+    },
+    {
+      "epoch": 2.3002421307506054,
+      "grad_norm": 2.1011345386505127,
+      "learning_rate": 3.489484318244132e-05,
+      "loss": 1.6002,
+      "step": 1900
+    },
+    {
+      "epoch": 2.360774818401937,
+      "grad_norm": 2.945044994354248,
+      "learning_rate": 3.414714589996293e-05,
+      "loss": 1.6616,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4213075060532687,
+      "grad_norm": 3.048288345336914,
+      "learning_rate": 3.338987821649276e-05,
+      "loss": 1.5644,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4818401937046004,
+      "grad_norm": 3.1781957149505615,
+      "learning_rate": 3.26238324398685e-05,
+      "loss": 1.5523,
+      "step": 2050
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 2.9750406742095947,
+      "learning_rate": 3.186536345534672e-05,
+      "loss": 1.5924,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6029055690072638,
+      "grad_norm": 3.542684316635132,
+      "learning_rate": 3.108430966338403e-05,
+      "loss": 1.4964,
+      "step": 2150
+    },
+    {
+      "epoch": 2.663438256658596,
+      "grad_norm": 3.2517852783203125,
+      "learning_rate": 3.0296890029674245e-05,
+      "loss": 1.6493,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7239709443099276,
+      "grad_norm": 3.009824752807617,
+      "learning_rate": 2.9503928409190907e-05,
+      "loss": 1.5178,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7845036319612593,
+      "grad_norm": 3.2098660469055176,
+      "learning_rate": 2.870625445533215e-05,
+      "loss": 1.5265,
+      "step": 2300
+    },
+    {
+      "epoch": 2.845036319612591,
+      "grad_norm": 2.256084442138672,
+      "learning_rate": 2.790470275187772e-05,
+      "loss": 1.5272,
+      "step": 2350
+    },
+    {
+      "epoch": 2.9055690072639226,
+      "grad_norm": 3.0556230545043945,
+      "learning_rate": 2.7100111939787502e-05,
+      "loss": 1.5736,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9661016949152543,
+      "grad_norm": 2.940830707550049,
+      "learning_rate": 2.6293323839755102e-05,
+      "loss": 1.569,
+      "step": 2450
+    },
+    {
+      "epoch": 3.026634382566586,
+      "grad_norm": 3.9955949783325195,
+      "learning_rate": 2.5485182571434574e-05,
+      "loss": 1.5216,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0871670702179177,
+      "grad_norm": 2.831310749053955,
+      "learning_rate": 2.4676533670261827e-05,
+      "loss": 1.5307,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1476997578692494,
+      "grad_norm": 3.844881534576416,
+      "learning_rate": 2.386822320279472e-05,
+      "loss": 1.5931,
+      "step": 2600
+    },
+    {
+      "epoch": 3.208232445520581,
+      "grad_norm": 2.7776381969451904,
+      "learning_rate": 2.3077222338323607e-05,
+      "loss": 1.5396,
+      "step": 2650
+    },
+    {
+      "epoch": 3.2687651331719128,
+      "grad_norm": 2.4347074031829834,
+      "learning_rate": 2.2272075800760027e-05,
+      "loss": 1.5486,
+      "step": 2700
+    },
+    {
+      "epoch": 3.3292978208232444,
+      "grad_norm": 3.224047899246216,
+      "learning_rate": 2.146978341341417e-05,
+      "loss": 1.4616,
+      "step": 2750
+    },
+    {
+      "epoch": 3.389830508474576,
+      "grad_norm": 2.841210126876831,
+      "learning_rate": 2.0671184592202596e-05,
+      "loss": 1.5278,
+      "step": 2800
+    },
+    {
+      "epoch": 3.450363196125908,
+      "grad_norm": 2.778027057647705,
+      "learning_rate": 1.9877114888567707e-05,
+      "loss": 1.4709,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5108958837772395,
+      "grad_norm": 3.342015504837036,
+      "learning_rate": 1.9088405115263812e-05,
+      "loss": 1.4922,
+      "step": 2900
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 2.86592435836792,
+      "learning_rate": 1.8305880477101156e-05,
+      "loss": 1.5278,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6319612590799033,
+      "grad_norm": 3.3868978023529053,
+      "learning_rate": 1.7530359707557377e-05,
+      "loss": 1.544,
+      "step": 3000
+    },
+    {
+      "epoch": 3.692493946731235,
+      "grad_norm": 3.414026975631714,
+      "learning_rate": 1.676265421215975e-05,
+      "loss": 1.529,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7530266343825667,
+      "grad_norm": 2.757256507873535,
+      "learning_rate": 1.6003567219534436e-05,
+      "loss": 1.5882,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8135593220338984,
+      "grad_norm": 2.658442974090576,
+      "learning_rate": 1.5253892941011019e-05,
+      "loss": 1.5813,
+      "step": 3150
+    },
+    {
+      "epoch": 3.87409200968523,
+      "grad_norm": 3.5918776988983154,
+      "learning_rate": 1.4514415739661552e-05,
+      "loss": 1.5062,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9346246973365617,
+      "grad_norm": 3.3042874336242676,
+      "learning_rate": 1.378590930964361e-05,
+      "loss": 1.5129,
+      "step": 3250
+    },
+    {
+      "epoch": 3.9951573849878934,
+      "grad_norm": 3.065037250518799,
+      "learning_rate": 1.3069135866705862e-05,
+      "loss": 1.4158,
+      "step": 3300
+    },
+    {
+      "epoch": 4.0556900726392255,
+      "grad_norm": 2.601694107055664,
+      "learning_rate": 1.2364845350703233e-05,
+      "loss": 1.4618,
+      "step": 3350
+    },
+    {
+      "epoch": 4.116222760290557,
+      "grad_norm": 2.7289392948150635,
+      "learning_rate": 1.1673774640955954e-05,
+      "loss": 1.4423,
+      "step": 3400
+    },
+    {
+      "epoch": 4.176755447941889,
+      "grad_norm": 3.2083990573883057,
+      "learning_rate": 1.0996646785273507e-05,
+      "loss": 1.5181,
+      "step": 3450
+    },
+    {
+      "epoch": 4.237288135593221,
+      "grad_norm": 2.610212564468384,
+      "learning_rate": 1.0334170243450064e-05,
+      "loss": 1.4867,
+      "step": 3500
+    },
+    {
+      "epoch": 4.297820823244552,
+      "grad_norm": 2.1238436698913574,
+      "learning_rate": 9.687038146022986e-06,
+      "loss": 1.5071,
+      "step": 3550
+    },
+    {
+      "epoch": 4.358353510895884,
+      "grad_norm": 3.779721975326538,
+      "learning_rate": 9.055927569069853e-06,
+      "loss": 1.5731,
+      "step": 3600
+    },
+    {
+      "epoch": 4.418886198547216,
+      "grad_norm": 2.922938585281372,
+      "learning_rate": 8.441498825802854e-06,
+      "loss": 1.5711,
+      "step": 3650
+    },
+    {
+      "epoch": 4.479418886198547,
+      "grad_norm": 2.403140068054199,
+      "learning_rate": 7.844394775701691e-06,
+      "loss": 1.4353,
+      "step": 3700
+    },
+    {
+      "epoch": 4.539951573849879,
+      "grad_norm": 3.37087082862854,
+      "learning_rate": 7.265240151907796e-06,
+      "loss": 1.4466,
+      "step": 3750
+    },
+    {
+      "epoch": 4.600484261501211,
+      "grad_norm": 2.3288798332214355,
+      "learning_rate": 6.7046409075836756e-06,
+      "loss": 1.4493,
+      "step": 3800
+    },
+    {
+      "epoch": 4.661016949152542,
+      "grad_norm": 2.3102521896362305,
+      "learning_rate": 6.163183581921167e-06,
+      "loss": 1.4869,
+      "step": 3850
+    },
+    {
+      "epoch": 4.721549636803874,
+      "grad_norm": 6.54373025894165,
+      "learning_rate": 5.641434686462052e-06,
+      "loss": 1.5387,
+      "step": 3900
+    },
+    {
+      "epoch": 4.782082324455206,
+      "grad_norm": 2.690067768096924,
+      "learning_rate": 5.139940112372937e-06,
+      "loss": 1.5167,
+      "step": 3950
+    },
+    {
+      "epoch": 4.842615012106537,
+      "grad_norm": 2.6940579414367676,
+      "learning_rate": 4.659224559294759e-06,
+      "loss": 1.4451,
+      "step": 4000
+    },
+    {
+      "epoch": 4.903147699757869,
+      "grad_norm": 2.6374406814575195,
+      "learning_rate": 4.199790986364299e-06,
+      "loss": 1.4631,
+      "step": 4050
+    },
+    {
+      "epoch": 4.963680387409201,
+      "grad_norm": 2.816666603088379,
+      "learning_rate": 3.762120085982246e-06,
+      "loss": 1.5234,
+      "step": 4100
+    },
+    {
+      "epoch": 5.0242130750605325,
+      "grad_norm": 2.9753060340881348,
+      "learning_rate": 3.3466697808782505e-06,
+      "loss": 1.5474,
+      "step": 4150
+    },
+    {
+      "epoch": 5.084745762711864,
+      "grad_norm": 3.0241904258728027,
+      "learning_rate": 2.9538747449993075e-06,
+      "loss": 1.5836,
+      "step": 4200
+    },
+    {
+      "epoch": 5.145278450363196,
+      "grad_norm": 3.026702404022217,
+      "learning_rate": 2.5841459487226243e-06,
+      "loss": 1.4728,
+      "step": 4250
+    },
+    {
+      "epoch": 5.2058111380145276,
+      "grad_norm": 2.498769521713257,
+      "learning_rate": 2.237870228868924e-06,
+      "loss": 1.5177,
+      "step": 4300
+    },
+    {
+      "epoch": 5.266343825665859,
+      "grad_norm": 2.895362377166748,
+      "learning_rate": 1.9154098839659575e-06,
+      "loss": 1.4706,
+      "step": 4350
+    },
+    {
+      "epoch": 5.326876513317191,
+      "grad_norm": 3.3171792030334473,
+      "learning_rate": 1.617102295185774e-06,
+      "loss": 1.4938,
+      "step": 4400
+    },
+    {
+      "epoch": 5.387409200968523,
+      "grad_norm": 2.228743076324463,
+      "learning_rate": 1.3432595733523235e-06,
+      "loss": 1.5602,
+      "step": 4450
+    },
+    {
+      "epoch": 5.447941888619855,
+      "grad_norm": 3.036306381225586,
+      "learning_rate": 1.0941682323886594e-06,
+      "loss": 1.5802,
+      "step": 4500
+    },
+    {
+      "epoch": 5.508474576271187,
+      "grad_norm": 2.9616992473602295,
+      "learning_rate": 8.700888895455311e-07,
+      "loss": 1.5303,
+      "step": 4550
+    },
+    {
+      "epoch": 5.5690072639225185,
+      "grad_norm": 2.698787212371826,
+      "learning_rate": 6.71255992724873e-07,
+      "loss": 1.4937,
+      "step": 4600
+    },
+    {
+      "epoch": 5.62953995157385,
+      "grad_norm": 3.5385634899139404,
+      "learning_rate": 4.978775751835917e-07,
+      "loss": 1.4137,
+      "step": 4650
+    },
+    {
+      "epoch": 5.690072639225182,
+      "grad_norm": 2.8735620975494385,
+      "learning_rate": 3.5013503787421633e-07,
+      "loss": 1.5051,
+      "step": 4700
+    },
+    {
+      "epoch": 5.750605326876514,
+      "grad_norm": 2.6400601863861084,
+      "learning_rate": 2.2818295965019997e-07,
+      "loss": 1.4013,
+      "step": 4750
+    },
+    {
+      "epoch": 5.811138014527845,
+      "grad_norm": 2.8832826614379883,
+      "learning_rate": 1.338149243583109e-07,
+      "loss": 1.3683,
+      "step": 4800
+    },
+    {
+      "epoch": 5.871670702179177,
+      "grad_norm": 2.9400370121002197,
+      "learning_rate": 6.32782526560044e-08,
+      "loss": 1.4601,
+      "step": 4850
+    },
+    {
+      "epoch": 5.932203389830509,
+      "grad_norm": 3.030094861984253,
+      "learning_rate": 1.8832170209909237e-08,
+      "loss": 1.4406,
+      "step": 4900
+    },
+    {
+      "epoch": 5.99273607748184,
+      "grad_norm": 3.4338512420654297,
+      "learning_rate": 5.231797036125973e-10,
+      "loss": 1.4251,
+      "step": 4950
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4956,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 608965481299968.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4956/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852c6eef48f750cf9bb32ea39070bf2c5ba300837987f00f6e62aa41fe94b26c
+size 5432

runs/Aug03_09-16-21_79c079872d6b/events.out.tfevents.1754212582.79c079872d6b.644.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f3428e946dd1aae3884aa0afbe217bd414de87fef521eba5bf37b3f0873945
+size 26880

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852c6eef48f750cf9bb32ea39070bf2c5ba300837987f00f6e62aa41fe94b26c
+size 5432