Upload folder using huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+tags:
+- autotrain
+- text-generation
+- peft
+library_name: transformers
+widget:
+ - messages:
+ - role: user
+ content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+ model_path,
+ device_map="auto",
+ torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+ {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,30 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "microsoft/DialoGPT-large",
+ "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": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "c_attn",
+ "c_proj",
+ "c_fc"
+ ],
+ "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 sha256:455b7911778b546a0b8c688a664f918e6971047f244603d6c89aceaa09f41669
+size 47223184

checkpoint-3378/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/DialoGPT-large
+---
+
+# 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 0.10.0

checkpoint-3378/adapter_config.json

@@ -0,0 +1,30 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "microsoft/DialoGPT-large",
+ "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": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "c_attn",
+ "c_proj",
+ "c_fc"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}

checkpoint-3378/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455b7911778b546a0b8c688a664f918e6971047f244603d6c89aceaa09f41669
+size 47223184

checkpoint-3378/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f130d2d0fd7374a5fde58a5f219d425e61d84f25d78b03ad5e6491c6be4526
+size 94613754

checkpoint-3378/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-3378/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20af66882f0fa57a1f376d363cf28643224ecc6a15357ea78a306e0d7aee6b54
+size 14244

checkpoint-3378/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fa34f5781617cf77a11d974f6d692c9b5d2c5946ecf9f7c66d46bc8f3e0c20
+size 1064

checkpoint-3378/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|endoftext|>",
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-3378/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "50256": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 1024,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>"
+}

checkpoint-3378/trainer_state.json

@@ -0,0 +1,966 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.9980031062791213,
+ "eval_steps": 500,
+ "global_step": 3378,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.02,
+ "grad_norm": 3.863227128982544,
+ "learning_rate": 2.0414201183431953e-06,
+ "loss": 10.8959,
+ "step": 25
+ },
+ {
+ "epoch": 0.04,
+ "grad_norm": 3.9202582836151123,
+ "learning_rate": 4.171597633136095e-06,
+ "loss": 10.7254,
+ "step": 50
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 3.297222375869751,
+ "learning_rate": 6.390532544378699e-06,
+ "loss": 10.3548,
+ "step": 75
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 2.734739065170288,
+ "learning_rate": 8.609467455621303e-06,
+ "loss": 9.7686,
+ "step": 100
+ },
+ {
+ "epoch": 0.11,
+ "grad_norm": 2.3171167373657227,
+ "learning_rate": 1.0828402366863907e-05,
+ "loss": 8.8642,
+ "step": 125
+ },
+ {
+ "epoch": 0.13,
+ "grad_norm": 1.8683223724365234,
+ "learning_rate": 1.304733727810651e-05,
+ "loss": 7.7751,
+ "step": 150
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 1.3291046619415283,
+ "learning_rate": 1.5266272189349113e-05,
+ "loss": 7.0121,
+ "step": 175
+ },
+ {
+ "epoch": 0.18,
+ "grad_norm": 1.4056954383850098,
+ "learning_rate": 1.7485207100591714e-05,
+ "loss": 6.3242,
+ "step": 200
+ },
+ {
+ "epoch": 0.2,
+ "grad_norm": 1.1085917949676514,
+ "learning_rate": 1.9704142011834322e-05,
+ "loss": 5.7192,
+ "step": 225
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 1.3172917366027832,
+ "learning_rate": 2.1923076923076924e-05,
+ "loss": 5.0999,
+ "step": 250
+ },
+ {
+ "epoch": 0.24,
+ "grad_norm": 1.0901626348495483,
+ "learning_rate": 2.414201183431953e-05,
+ "loss": 4.6548,
+ "step": 275
+ },
+ {
+ "epoch": 0.27,
+ "grad_norm": 1.2347195148468018,
+ "learning_rate": 2.6360946745562133e-05,
+ "loss": 4.3473,
+ "step": 300
+ },
+ {
+ "epoch": 0.29,
+ "grad_norm": 1.0249868631362915,
+ "learning_rate": 2.8579881656804735e-05,
+ "loss": 4.0633,
+ "step": 325
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 1.2612847089767456,
+ "learning_rate": 2.9911184210526318e-05,
+ "loss": 3.8203,
+ "step": 350
+ },
+ {
+ "epoch": 0.33,
+ "grad_norm": 1.0956445932388306,
+ "learning_rate": 2.9664473684210528e-05,
+ "loss": 3.5213,
+ "step": 375
+ },
+ {
+ "epoch": 0.36,
+ "grad_norm": 1.187477946281433,
+ "learning_rate": 2.9417763157894738e-05,
+ "loss": 3.4107,
+ "step": 400
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 1.2866570949554443,
+ "learning_rate": 2.9171052631578948e-05,
+ "loss": 3.2937,
+ "step": 425
+ },
+ {
+ "epoch": 0.4,
+ "grad_norm": 1.3654049634933472,
+ "learning_rate": 2.8924342105263158e-05,
+ "loss": 3.148,
+ "step": 450
+ },
+ {
+ "epoch": 0.42,
+ "grad_norm": 3.0226898193359375,
+ "learning_rate": 2.8677631578947368e-05,
+ "loss": 2.992,
+ "step": 475
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 1.858105182647705,
+ "learning_rate": 2.843092105263158e-05,
+ "loss": 2.8713,
+ "step": 500
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 2.1696932315826416,
+ "learning_rate": 2.818421052631579e-05,
+ "loss": 2.6683,
+ "step": 525
+ },
+ {
+ "epoch": 0.49,
+ "grad_norm": 4.214972972869873,
+ "learning_rate": 2.79375e-05,
+ "loss": 2.5497,
+ "step": 550
+ },
+ {
+ "epoch": 0.51,
+ "grad_norm": 2.712171792984009,
+ "learning_rate": 2.769078947368421e-05,
+ "loss": 2.5092,
+ "step": 575
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 3.073754072189331,
+ "learning_rate": 2.744407894736842e-05,
+ "loss": 2.3336,
+ "step": 600
+ },
+ {
+ "epoch": 0.55,
+ "grad_norm": 3.3905112743377686,
+ "learning_rate": 2.719736842105263e-05,
+ "loss": 2.2231,
+ "step": 625
+ },
+ {
+ "epoch": 0.58,
+ "grad_norm": 2.6293680667877197,
+ "learning_rate": 2.695065789473684e-05,
+ "loss": 2.149,
+ "step": 650
+ },
+ {
+ "epoch": 0.6,
+ "grad_norm": 2.6342837810516357,
+ "learning_rate": 2.6703947368421052e-05,
+ "loss": 2.1733,
+ "step": 675
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 5.107319355010986,
+ "learning_rate": 2.6457236842105262e-05,
+ "loss": 2.0175,
+ "step": 700
+ },
+ {
+ "epoch": 0.64,
+ "grad_norm": 3.6173806190490723,
+ "learning_rate": 2.6210526315789475e-05,
+ "loss": 1.9354,
+ "step": 725
+ },
+ {
+ "epoch": 0.67,
+ "grad_norm": 2.709559440612793,
+ "learning_rate": 2.5963815789473685e-05,
+ "loss": 1.8339,
+ "step": 750
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 2.523397922515869,
+ "learning_rate": 2.5717105263157895e-05,
+ "loss": 1.9872,
+ "step": 775
+ },
+ {
+ "epoch": 0.71,
+ "grad_norm": 2.3423144817352295,
+ "learning_rate": 2.5470394736842105e-05,
+ "loss": 1.8357,
+ "step": 800
+ },
+ {
+ "epoch": 0.73,
+ "grad_norm": 2.349581241607666,
+ "learning_rate": 2.5223684210526315e-05,
+ "loss": 1.7938,
+ "step": 825
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 3.185107707977295,
+ "learning_rate": 2.4976973684210526e-05,
+ "loss": 1.7019,
+ "step": 850
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 1.9526580572128296,
+ "learning_rate": 2.4730263157894736e-05,
+ "loss": 1.7636,
+ "step": 875
+ },
+ {
+ "epoch": 0.8,
+ "grad_norm": 2.120420455932617,
+ "learning_rate": 2.4483552631578946e-05,
+ "loss": 1.7237,
+ "step": 900
+ },
+ {
+ "epoch": 0.82,
+ "grad_norm": 2.198755979537964,
+ "learning_rate": 2.4236842105263156e-05,
+ "loss": 1.6563,
+ "step": 925
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 2.3641481399536133,
+ "learning_rate": 2.3990131578947366e-05,
+ "loss": 1.7045,
+ "step": 950
+ },
+ {
+ "epoch": 0.87,
+ "grad_norm": 2.742950916290283,
+ "learning_rate": 2.3743421052631583e-05,
+ "loss": 1.6134,
+ "step": 975
+ },
+ {
+ "epoch": 0.89,
+ "grad_norm": 2.467517614364624,
+ "learning_rate": 2.3496710526315793e-05,
+ "loss": 1.5613,
+ "step": 1000
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 1.6223593950271606,
+ "learning_rate": 2.3250000000000003e-05,
+ "loss": 1.6858,
+ "step": 1025
+ },
+ {
+ "epoch": 0.93,
+ "grad_norm": 2.8574585914611816,
+ "learning_rate": 2.3003289473684213e-05,
+ "loss": 1.5701,
+ "step": 1050
+ },
+ {
+ "epoch": 0.95,
+ "grad_norm": 2.3951303958892822,
+ "learning_rate": 2.2756578947368423e-05,
+ "loss": 1.4515,
+ "step": 1075
+ },
+ {
+ "epoch": 0.98,
+ "grad_norm": 2.0053939819335938,
+ "learning_rate": 2.2509868421052633e-05,
+ "loss": 1.4744,
+ "step": 1100
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 1.9645187854766846,
+ "learning_rate": 2.2263157894736843e-05,
+ "loss": 1.4719,
+ "step": 1125
+ },
+ {
+ "epoch": 1.02,
+ "grad_norm": 1.9311598539352417,
+ "learning_rate": 2.2016447368421053e-05,
+ "loss": 1.5421,
+ "step": 1150
+ },
+ {
+ "epoch": 1.04,
+ "grad_norm": 2.094773054122925,
+ "learning_rate": 2.1769736842105263e-05,
+ "loss": 1.4853,
+ "step": 1175
+ },
+ {
+ "epoch": 1.07,
+ "grad_norm": 1.9455292224884033,
+ "learning_rate": 2.1523026315789476e-05,
+ "loss": 1.4912,
+ "step": 1200
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 2.0593693256378174,
+ "learning_rate": 2.1276315789473687e-05,
+ "loss": 1.3928,
+ "step": 1225
+ },
+ {
+ "epoch": 1.11,
+ "grad_norm": 1.7141344547271729,
+ "learning_rate": 2.1029605263157897e-05,
+ "loss": 1.3613,
+ "step": 1250
+ },
+ {
+ "epoch": 1.13,
+ "grad_norm": 2.213785409927368,
+ "learning_rate": 2.0782894736842107e-05,
+ "loss": 1.3813,
+ "step": 1275
+ },
+ {
+ "epoch": 1.15,
+ "grad_norm": 2.477902412414551,
+ "learning_rate": 2.0536184210526317e-05,
+ "loss": 1.4228,
+ "step": 1300
+ },
+ {
+ "epoch": 1.18,
+ "grad_norm": 1.996187686920166,
+ "learning_rate": 2.0289473684210527e-05,
+ "loss": 1.3857,
+ "step": 1325
+ },
+ {
+ "epoch": 1.2,
+ "grad_norm": 1.7344149351119995,
+ "learning_rate": 2.0042763157894737e-05,
+ "loss": 1.341,
+ "step": 1350
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 2.0151705741882324,
+ "learning_rate": 1.9796052631578947e-05,
+ "loss": 1.3863,
+ "step": 1375
+ },
+ {
+ "epoch": 1.24,
+ "grad_norm": 1.9713648557662964,
+ "learning_rate": 1.9549342105263157e-05,
+ "loss": 1.397,
+ "step": 1400
+ },
+ {
+ "epoch": 1.26,
+ "grad_norm": 1.835036039352417,
+ "learning_rate": 1.9302631578947367e-05,
+ "loss": 1.4165,
+ "step": 1425
+ },
+ {
+ "epoch": 1.29,
+ "grad_norm": 2.019484043121338,
+ "learning_rate": 1.905592105263158e-05,
+ "loss": 1.3714,
+ "step": 1450
+ },
+ {
+ "epoch": 1.31,
+ "grad_norm": 1.829540491104126,
+ "learning_rate": 1.880921052631579e-05,
+ "loss": 1.3149,
+ "step": 1475
+ },
+ {
+ "epoch": 1.33,
+ "grad_norm": 1.961879014968872,
+ "learning_rate": 1.85625e-05,
+ "loss": 1.3801,
+ "step": 1500
+ },
+ {
+ "epoch": 1.35,
+ "grad_norm": 2.2035787105560303,
+ "learning_rate": 1.831578947368421e-05,
+ "loss": 1.3486,
+ "step": 1525
+ },
+ {
+ "epoch": 1.38,
+ "grad_norm": 1.8642491102218628,
+ "learning_rate": 1.806907894736842e-05,
+ "loss": 1.3207,
+ "step": 1550
+ },
+ {
+ "epoch": 1.4,
+ "grad_norm": 1.992825984954834,
+ "learning_rate": 1.782236842105263e-05,
+ "loss": 1.3175,
+ "step": 1575
+ },
+ {
+ "epoch": 1.42,
+ "grad_norm": 2.385167121887207,
+ "learning_rate": 1.757565789473684e-05,
+ "loss": 1.286,
+ "step": 1600
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 1.328168272972107,
+ "learning_rate": 1.732894736842105e-05,
+ "loss": 1.2824,
+ "step": 1625
+ },
+ {
+ "epoch": 1.46,
+ "grad_norm": 1.647040605545044,
+ "learning_rate": 1.708223684210526e-05,
+ "loss": 1.3084,
+ "step": 1650
+ },
+ {
+ "epoch": 1.49,
+ "grad_norm": 1.4075373411178589,
+ "learning_rate": 1.6835526315789474e-05,
+ "loss": 1.3287,
+ "step": 1675
+ },
+ {
+ "epoch": 1.51,
+ "grad_norm": 1.74918794631958,
+ "learning_rate": 1.6588815789473684e-05,
+ "loss": 1.3314,
+ "step": 1700
+ },
+ {
+ "epoch": 1.53,
+ "grad_norm": 1.8052846193313599,
+ "learning_rate": 1.6342105263157894e-05,
+ "loss": 1.2832,
+ "step": 1725
+ },
+ {
+ "epoch": 1.55,
+ "grad_norm": 1.4929707050323486,
+ "learning_rate": 1.6095394736842105e-05,
+ "loss": 1.2565,
+ "step": 1750
+ },
+ {
+ "epoch": 1.58,
+ "grad_norm": 1.5688847303390503,
+ "learning_rate": 1.5848684210526318e-05,
+ "loss": 1.2811,
+ "step": 1775
+ },
+ {
+ "epoch": 1.6,
+ "grad_norm": 1.8629792928695679,
+ "learning_rate": 1.5601973684210528e-05,
+ "loss": 1.3485,
+ "step": 1800
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 1.946643352508545,
+ "learning_rate": 1.5355263157894738e-05,
+ "loss": 1.3489,
+ "step": 1825
+ },
+ {
+ "epoch": 1.64,
+ "grad_norm": 1.6834330558776855,
+ "learning_rate": 1.5108552631578946e-05,
+ "loss": 1.2513,
+ "step": 1850
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 2.3857834339141846,
+ "learning_rate": 1.4861842105263158e-05,
+ "loss": 1.263,
+ "step": 1875
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 1.413714051246643,
+ "learning_rate": 1.4615131578947368e-05,
+ "loss": 1.2398,
+ "step": 1900
+ },
+ {
+ "epoch": 1.71,
+ "grad_norm": 1.75337815284729,
+ "learning_rate": 1.4368421052631578e-05,
+ "loss": 1.3227,
+ "step": 1925
+ },
+ {
+ "epoch": 1.73,
+ "grad_norm": 2.1332099437713623,
+ "learning_rate": 1.4121710526315788e-05,
+ "loss": 1.3663,
+ "step": 1950
+ },
+ {
+ "epoch": 1.75,
+ "grad_norm": 2.0604429244995117,
+ "learning_rate": 1.3875000000000002e-05,
+ "loss": 1.1767,
+ "step": 1975
+ },
+ {
+ "epoch": 1.78,
+ "grad_norm": 1.452750325202942,
+ "learning_rate": 1.3628289473684212e-05,
+ "loss": 1.2854,
+ "step": 2000
+ },
+ {
+ "epoch": 1.8,
+ "grad_norm": 1.8815256357192993,
+ "learning_rate": 1.3381578947368422e-05,
+ "loss": 1.2671,
+ "step": 2025
+ },
+ {
+ "epoch": 1.82,
+ "grad_norm": 1.517378568649292,
+ "learning_rate": 1.3134868421052632e-05,
+ "loss": 1.2302,
+ "step": 2050
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 1.5040243864059448,
+ "learning_rate": 1.2888157894736842e-05,
+ "loss": 1.2802,
+ "step": 2075
+ },
+ {
+ "epoch": 1.86,
+ "grad_norm": 1.7564135789871216,
+ "learning_rate": 1.2641447368421054e-05,
+ "loss": 1.2337,
+ "step": 2100
+ },
+ {
+ "epoch": 1.89,
+ "grad_norm": 1.5423864126205444,
+ "learning_rate": 1.2394736842105264e-05,
+ "loss": 1.2374,
+ "step": 2125
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 1.9401406049728394,
+ "learning_rate": 1.2148026315789474e-05,
+ "loss": 1.2256,
+ "step": 2150
+ },
+ {
+ "epoch": 1.93,
+ "grad_norm": 2.3875536918640137,
+ "learning_rate": 1.1901315789473684e-05,
+ "loss": 1.2301,
+ "step": 2175
+ },
+ {
+ "epoch": 1.95,
+ "grad_norm": 1.7349203824996948,
+ "learning_rate": 1.1654605263157894e-05,
+ "loss": 1.2379,
+ "step": 2200
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 2.1179356575012207,
+ "learning_rate": 1.1407894736842106e-05,
+ "loss": 1.2672,
+ "step": 2225
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 1.8508802652359009,
+ "learning_rate": 1.1161184210526316e-05,
+ "loss": 1.2543,
+ "step": 2250
+ },
+ {
+ "epoch": 2.02,
+ "grad_norm": 1.7846442461013794,
+ "learning_rate": 1.0914473684210526e-05,
+ "loss": 1.1996,
+ "step": 2275
+ },
+ {
+ "epoch": 2.04,
+ "grad_norm": 1.691226601600647,
+ "learning_rate": 1.0667763157894736e-05,
+ "loss": 1.2433,
+ "step": 2300
+ },
+ {
+ "epoch": 2.06,
+ "grad_norm": 1.7513465881347656,
+ "learning_rate": 1.0421052631578948e-05,
+ "loss": 1.2417,
+ "step": 2325
+ },
+ {
+ "epoch": 2.09,
+ "grad_norm": 2.2930405139923096,
+ "learning_rate": 1.0174342105263158e-05,
+ "loss": 1.2202,
+ "step": 2350
+ },
+ {
+ "epoch": 2.11,
+ "grad_norm": 1.8147985935211182,
+ "learning_rate": 9.92763157894737e-06,
+ "loss": 1.2027,
+ "step": 2375
+ },
+ {
+ "epoch": 2.13,
+ "grad_norm": 2.118342161178589,
+ "learning_rate": 9.68092105263158e-06,
+ "loss": 1.2547,
+ "step": 2400
+ },
+ {
+ "epoch": 2.15,
+ "grad_norm": 1.2660759687423706,
+ "learning_rate": 9.43421052631579e-06,
+ "loss": 1.185,
+ "step": 2425
+ },
+ {
+ "epoch": 2.17,
+ "grad_norm": 1.54926598072052,
+ "learning_rate": 9.187500000000001e-06,
+ "loss": 1.2254,
+ "step": 2450
+ },
+ {
+ "epoch": 2.2,
+ "grad_norm": 1.9687325954437256,
+ "learning_rate": 8.940789473684211e-06,
+ "loss": 1.217,
+ "step": 2475
+ },
+ {
+ "epoch": 2.22,
+ "grad_norm": 1.6193515062332153,
+ "learning_rate": 8.694078947368422e-06,
+ "loss": 1.2075,
+ "step": 2500
+ },
+ {
+ "epoch": 2.24,
+ "grad_norm": 1.7565534114837646,
+ "learning_rate": 8.447368421052632e-06,
+ "loss": 1.2187,
+ "step": 2525
+ },
+ {
+ "epoch": 2.26,
+ "grad_norm": 1.8760586977005005,
+ "learning_rate": 8.200657894736842e-06,
+ "loss": 1.1957,
+ "step": 2550
+ },
+ {
+ "epoch": 2.29,
+ "grad_norm": 5.671737194061279,
+ "learning_rate": 7.963815789473685e-06,
+ "loss": 1.156,
+ "step": 2575
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 2.1643118858337402,
+ "learning_rate": 7.717105263157895e-06,
+ "loss": 1.2163,
+ "step": 2600
+ },
+ {
+ "epoch": 2.33,
+ "grad_norm": 1.6212981939315796,
+ "learning_rate": 7.470394736842106e-06,
+ "loss": 1.1774,
+ "step": 2625
+ },
+ {
+ "epoch": 2.35,
+ "grad_norm": 1.421762466430664,
+ "learning_rate": 7.223684210526316e-06,
+ "loss": 1.2097,
+ "step": 2650
+ },
+ {
+ "epoch": 2.37,
+ "grad_norm": 1.7923425436019897,
+ "learning_rate": 6.976973684210526e-06,
+ "loss": 1.2083,
+ "step": 2675
+ },
+ {
+ "epoch": 2.4,
+ "grad_norm": 1.4467811584472656,
+ "learning_rate": 6.730263157894737e-06,
+ "loss": 1.1972,
+ "step": 2700
+ },
+ {
+ "epoch": 2.42,
+ "grad_norm": 1.48775315284729,
+ "learning_rate": 6.483552631578947e-06,
+ "loss": 1.1967,
+ "step": 2725
+ },
+ {
+ "epoch": 2.44,
+ "grad_norm": 1.6732630729675293,
+ "learning_rate": 6.236842105263159e-06,
+ "loss": 1.1978,
+ "step": 2750
+ },
+ {
+ "epoch": 2.46,
+ "grad_norm": 1.5414642095565796,
+ "learning_rate": 5.990131578947369e-06,
+ "loss": 1.2124,
+ "step": 2775
+ },
+ {
+ "epoch": 2.49,
+ "grad_norm": 1.6581816673278809,
+ "learning_rate": 5.74342105263158e-06,
+ "loss": 1.2193,
+ "step": 2800
+ },
+ {
+ "epoch": 2.51,
+ "grad_norm": 1.688584327697754,
+ "learning_rate": 5.49671052631579e-06,
+ "loss": 1.1672,
+ "step": 2825
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 2.130878210067749,
+ "learning_rate": 5.25e-06,
+ "loss": 1.1778,
+ "step": 2850
+ },
+ {
+ "epoch": 2.55,
+ "grad_norm": 2.325465679168701,
+ "learning_rate": 5.003289473684211e-06,
+ "loss": 1.2189,
+ "step": 2875
+ },
+ {
+ "epoch": 2.57,
+ "grad_norm": 1.1922625303268433,
+ "learning_rate": 4.756578947368421e-06,
+ "loss": 1.1062,
+ "step": 2900
+ },
+ {
+ "epoch": 2.6,
+ "grad_norm": 1.36138117313385,
+ "learning_rate": 4.5098684210526316e-06,
+ "loss": 1.2074,
+ "step": 2925
+ },
+ {
+ "epoch": 2.62,
+ "grad_norm": 1.736745834350586,
+ "learning_rate": 4.2631578947368425e-06,
+ "loss": 1.1532,
+ "step": 2950
+ },
+ {
+ "epoch": 2.64,
+ "grad_norm": 1.8273382186889648,
+ "learning_rate": 4.016447368421053e-06,
+ "loss": 1.1977,
+ "step": 2975
+ },
+ {
+ "epoch": 2.66,
+ "grad_norm": 1.504334568977356,
+ "learning_rate": 3.7697368421052634e-06,
+ "loss": 1.1679,
+ "step": 3000
+ },
+ {
+ "epoch": 2.68,
+ "grad_norm": 1.4739781618118286,
+ "learning_rate": 3.523026315789474e-06,
+ "loss": 1.1503,
+ "step": 3025
+ },
+ {
+ "epoch": 2.71,
+ "grad_norm": 1.9392614364624023,
+ "learning_rate": 3.2763157894736844e-06,
+ "loss": 1.126,
+ "step": 3050
+ },
+ {
+ "epoch": 2.73,
+ "grad_norm": 1.8378140926361084,
+ "learning_rate": 3.0296052631578945e-06,
+ "loss": 1.242,
+ "step": 3075
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 1.7033443450927734,
+ "learning_rate": 2.7828947368421054e-06,
+ "loss": 1.1892,
+ "step": 3100
+ },
+ {
+ "epoch": 2.77,
+ "grad_norm": 1.5492761135101318,
+ "learning_rate": 2.536184210526316e-06,
+ "loss": 1.1594,
+ "step": 3125
+ },
+ {
+ "epoch": 2.8,
+ "grad_norm": 1.5671361684799194,
+ "learning_rate": 2.2894736842105263e-06,
+ "loss": 1.179,
+ "step": 3150
+ },
+ {
+ "epoch": 2.82,
+ "grad_norm": 1.7326922416687012,
+ "learning_rate": 2.042763157894737e-06,
+ "loss": 1.2256,
+ "step": 3175
+ },
+ {
+ "epoch": 2.84,
+ "grad_norm": 1.4645403623580933,
+ "learning_rate": 1.7960526315789473e-06,
+ "loss": 1.1041,
+ "step": 3200
+ },
+ {
+ "epoch": 2.86,
+ "grad_norm": 1.4518282413482666,
+ "learning_rate": 1.549342105263158e-06,
+ "loss": 1.1979,
+ "step": 3225
+ },
+ {
+ "epoch": 2.88,
+ "grad_norm": 1.488720417022705,
+ "learning_rate": 1.3026315789473685e-06,
+ "loss": 1.1615,
+ "step": 3250
+ },
+ {
+ "epoch": 2.91,
+ "grad_norm": 1.3193929195404053,
+ "learning_rate": 1.055921052631579e-06,
+ "loss": 1.1275,
+ "step": 3275
+ },
+ {
+ "epoch": 2.93,
+ "grad_norm": 1.5246660709381104,
+ "learning_rate": 8.092105263157895e-07,
+ "loss": 1.1317,
+ "step": 3300
+ },
+ {
+ "epoch": 2.95,
+ "grad_norm": 1.8375893831253052,
+ "learning_rate": 5.625e-07,
+ "loss": 1.1291,
+ "step": 3325
+ },
+ {
+ "epoch": 2.97,
+ "grad_norm": 2.09460186958313,
+ "learning_rate": 3.1578947368421055e-07,
+ "loss": 1.2138,
+ "step": 3350
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 1.9802443981170654,
+ "learning_rate": 6.907894736842104e-08,
+ "loss": 1.1591,
+ "step": 3375
+ }
+ ],
+ "logging_steps": 25,
+ "max_steps": 3378,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 500,
+ "total_flos": 5.978827851300864e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-3378/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c72b17549e2ce90b2e336b81de078fb9ef576657246c021873480952850515d
+size 4984

runs/Mar22_23-21-22_r-jamesb1974-space3-5qos4feg-e6e33-uxeca/events.out.tfevents.1711149683.r-jamesb1974-space3-5qos4feg-e6e33-uxeca.63.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a07ca925b18e005bf1ef204d15efb11f4066479f89ec0a38bc40386a5d450b5
-size 33626
+oid sha256:c8bcb0fb439c2e7cedae1ff3e9b756397e30eafed30e382cf72e4ce3e26dbd49
+size 34191

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|endoftext|>",
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "50256": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "errors": "replace",
+ "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 sha256:9c72b17549e2ce90b2e336b81de078fb9ef576657246c021873480952850515d
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+ "model": "microsoft/DialoGPT-large",
+ "project_name": "autotrain-3v9nj-wa3dz",
+ "data_path": "autotrain-3v9nj-wa3dz/autotrain-data",
+ "train_split": "train",
+ "valid_split": null,
+ "add_eos_token": true,
+ "block_size": 1024,
+ "model_max_length": 2048,
+ "padding": "right",
+ "trainer": "default",
+ "use_flash_attention_2": false,
+ "log": "tensorboard",
+ "disable_gradient_checkpointing": false,
+ "logging_steps": -1,
+ "evaluation_strategy": "epoch",
+ "save_total_limit": 1,
+ "save_strategy": "epoch",
+ "auto_find_batch_size": false,
+ "mixed_precision": "fp16",
+ "lr": 3e-05,
+ "epochs": 3,
+ "batch_size": 1,
+ "warmup_ratio": 0.1,
+ "gradient_accumulation": 4,
+ "optimizer": "adamw_torch",
+ "scheduler": "linear",
+ "weight_decay": 0.0,
+ "max_grad_norm": 1.0,
+ "seed": 42,
+ "chat_template": "none",
+ "quantization": "int4",
+ "target_modules": "all-linear",
+ "merge_adapter": false,
+ "peft": true,
+ "lora_r": 16,
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "model_ref": null,
+ "dpo_beta": 0.1,
+ "prompt_text_column": "autotrain_prompt",
+ "text_column": "autotrain_text",
+ "rejected_text_column": "autotrain_rejected_text",
+ "push_to_hub": true,
+ "repo_id": "Jamesb1974/autotrain-3v9nj-wa3dz",
+ "username": "Jamesb1974"
+}