Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1510/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- 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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "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": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d30b056b88583915b8d59ca195abb7317059378fcd8e04920267b67337ab9bc
+size 78480072

checkpoint-1510/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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-1510/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "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": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1510/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d30b056b88583915b8d59ca195abb7317059378fcd8e04920267b67337ab9bc
+size 78480072

checkpoint-1510/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641ee65c2a67bedabc6674748052376f59a07498d3c900e405259fe192cd1907
+size 157104826

checkpoint-1510/pytorch_model.bin

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

checkpoint-1510/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd9e64418b18a213e330b76e3ffade700175d3764a4cda1ccfa4eadd7d9801c
+size 14244

checkpoint-1510/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27983f2cce091d0023355d993bc1dc7ab95e04a7ace916fd95418c8f92b6bc1c
+size 1064

checkpoint-1510/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1510/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

checkpoint-1510/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-1510/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1510/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.987613542526837,
+  "eval_steps": 500,
+  "global_step": 1510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.482018947601318,
+      "learning_rate": 4.768211920529802e-06,
+      "loss": 5.8299,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.826422691345215,
+      "learning_rate": 9.735099337748345e-06,
+      "loss": 5.1849,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.315689563751221,
+      "learning_rate": 1.4701986754966887e-05,
+      "loss": 4.4164,
+      "step": 75
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.3576250076293945,
+      "learning_rate": 1.9668874172185433e-05,
+      "loss": 3.5949,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.602609634399414,
+      "learning_rate": 2.4635761589403972e-05,
+      "loss": 2.9948,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4007989168167114,
+      "learning_rate": 2.9602649006622518e-05,
+      "loss": 2.6452,
+      "step": 150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.107353687286377,
+      "learning_rate": 2.9492273730684327e-05,
+      "loss": 2.4714,
+      "step": 175
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3134864568710327,
+      "learning_rate": 2.894039735099338e-05,
+      "loss": 2.3634,
+      "step": 200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.580680251121521,
+      "learning_rate": 2.838852097130243e-05,
+      "loss": 2.3032,
+      "step": 225
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.3618550300598145,
+      "learning_rate": 2.783664459161148e-05,
+      "loss": 2.2501,
+      "step": 250
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.531614899635315,
+      "learning_rate": 2.728476821192053e-05,
+      "loss": 2.2265,
+      "step": 275
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.4849926233291626,
+      "learning_rate": 2.673289183222958e-05,
+      "loss": 2.1844,
+      "step": 300
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.6642751693725586,
+      "learning_rate": 2.6181015452538634e-05,
+      "loss": 2.1166,
+      "step": 325
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.7284085750579834,
+      "learning_rate": 2.5629139072847685e-05,
+      "loss": 2.1233,
+      "step": 350
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.6671867370605469,
+      "learning_rate": 2.5077262693156735e-05,
+      "loss": 2.1212,
+      "step": 375
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.756274938583374,
+      "learning_rate": 2.4525386313465785e-05,
+      "loss": 2.0726,
+      "step": 400
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.8096344470977783,
+      "learning_rate": 2.3973509933774835e-05,
+      "loss": 2.0875,
+      "step": 425
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.7899348735809326,
+      "learning_rate": 2.3421633554083885e-05,
+      "loss": 2.0833,
+      "step": 450
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.917384386062622,
+      "learning_rate": 2.286975717439294e-05,
+      "loss": 2.0743,
+      "step": 475
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.8895052671432495,
+      "learning_rate": 2.231788079470199e-05,
+      "loss": 2.0609,
+      "step": 500
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.9963146448135376,
+      "learning_rate": 2.176600441501104e-05,
+      "loss": 2.0656,
+      "step": 525
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.9002119302749634,
+      "learning_rate": 2.121412803532009e-05,
+      "loss": 2.0541,
+      "step": 550
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.874874472618103,
+      "learning_rate": 2.066225165562914e-05,
+      "loss": 2.0416,
+      "step": 575
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.7960671186447144,
+      "learning_rate": 2.011037527593819e-05,
+      "loss": 2.0311,
+      "step": 600
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.1183598041534424,
+      "learning_rate": 1.9558498896247242e-05,
+      "loss": 2.0009,
+      "step": 625
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.9861488342285156,
+      "learning_rate": 1.9006622516556292e-05,
+      "loss": 1.9688,
+      "step": 650
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 2.235743284225464,
+      "learning_rate": 1.8454746136865343e-05,
+      "loss": 1.9989,
+      "step": 675
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.955734133720398,
+      "learning_rate": 1.7902869757174393e-05,
+      "loss": 1.9733,
+      "step": 700
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.044551372528076,
+      "learning_rate": 1.7350993377483443e-05,
+      "loss": 1.9574,
+      "step": 725
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.117047071456909,
+      "learning_rate": 1.6799116997792496e-05,
+      "loss": 1.9654,
+      "step": 750
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.02316951751709,
+      "learning_rate": 1.6247240618101546e-05,
+      "loss": 1.9498,
+      "step": 775
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.2580747604370117,
+      "learning_rate": 1.5695364238410596e-05,
+      "loss": 1.9748,
+      "step": 800
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 2.0818331241607666,
+      "learning_rate": 1.5143487858719647e-05,
+      "loss": 1.984,
+      "step": 825
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 2.1940929889678955,
+      "learning_rate": 1.4591611479028698e-05,
+      "loss": 1.9646,
+      "step": 850
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 2.1697773933410645,
+      "learning_rate": 1.4039735099337748e-05,
+      "loss": 1.958,
+      "step": 875
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 2.0976200103759766,
+      "learning_rate": 1.3487858719646799e-05,
+      "loss": 1.946,
+      "step": 900
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 2.160543441772461,
+      "learning_rate": 1.293598233995585e-05,
+      "loss": 1.9398,
+      "step": 925
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 2.161280393600464,
+      "learning_rate": 1.23841059602649e-05,
+      "loss": 1.9008,
+      "step": 950
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 2.2662644386291504,
+      "learning_rate": 1.183222958057395e-05,
+      "loss": 1.9111,
+      "step": 975
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 2.374934673309326,
+      "learning_rate": 1.1280353200883002e-05,
+      "loss": 1.9087,
+      "step": 1000
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 2.3813648223876953,
+      "learning_rate": 1.0728476821192052e-05,
+      "loss": 1.9116,
+      "step": 1025
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 2.115699529647827,
+      "learning_rate": 1.0176600441501102e-05,
+      "loss": 1.92,
+      "step": 1050
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 2.41668963432312,
+      "learning_rate": 9.624724061810154e-06,
+      "loss": 1.9452,
+      "step": 1075
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 2.383557081222534,
+      "learning_rate": 9.072847682119206e-06,
+      "loss": 1.9209,
+      "step": 1100
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 2.2272610664367676,
+      "learning_rate": 8.520971302428258e-06,
+      "loss": 1.9057,
+      "step": 1125
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 2.5420844554901123,
+      "learning_rate": 7.969094922737308e-06,
+      "loss": 1.9025,
+      "step": 1150
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 2.2384705543518066,
+      "learning_rate": 7.417218543046358e-06,
+      "loss": 1.9072,
+      "step": 1175
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.2767913341522217,
+      "learning_rate": 6.865342163355408e-06,
+      "loss": 1.8947,
+      "step": 1200
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 2.2728919982910156,
+      "learning_rate": 6.313465783664459e-06,
+      "loss": 1.8819,
+      "step": 1225
+    },
+    {
+      "epoch": 4.13,
+      "grad_norm": 2.4492197036743164,
+      "learning_rate": 5.76158940397351e-06,
+      "loss": 1.8914,
+      "step": 1250
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 2.238704204559326,
+      "learning_rate": 5.20971302428256e-06,
+      "loss": 1.8723,
+      "step": 1275
+    },
+    {
+      "epoch": 4.29,
+      "grad_norm": 2.341646194458008,
+      "learning_rate": 4.657836644591612e-06,
+      "loss": 1.8808,
+      "step": 1300
+    },
+    {
+      "epoch": 4.38,
+      "grad_norm": 2.2996695041656494,
+      "learning_rate": 4.105960264900663e-06,
+      "loss": 1.88,
+      "step": 1325
+    },
+    {
+      "epoch": 4.46,
+      "grad_norm": 2.213731050491333,
+      "learning_rate": 3.554083885209713e-06,
+      "loss": 1.8597,
+      "step": 1350
+    },
+    {
+      "epoch": 4.54,
+      "grad_norm": 2.0925798416137695,
+      "learning_rate": 3.002207505518764e-06,
+      "loss": 1.853,
+      "step": 1375
+    },
+    {
+      "epoch": 4.62,
+      "grad_norm": 2.3262617588043213,
+      "learning_rate": 2.450331125827815e-06,
+      "loss": 1.8795,
+      "step": 1400
+    },
+    {
+      "epoch": 4.71,
+      "grad_norm": 2.3422157764434814,
+      "learning_rate": 1.8984547461368651e-06,
+      "loss": 1.865,
+      "step": 1425
+    },
+    {
+      "epoch": 4.79,
+      "grad_norm": 2.6429784297943115,
+      "learning_rate": 1.3465783664459163e-06,
+      "loss": 1.8871,
+      "step": 1450
+    },
+    {
+      "epoch": 4.87,
+      "grad_norm": 2.334404945373535,
+      "learning_rate": 7.947019867549669e-07,
+      "loss": 1.8886,
+      "step": 1475
+    },
+    {
+      "epoch": 4.95,
+      "grad_norm": 2.4886159896850586,
+      "learning_rate": 2.428256070640177e-07,
+      "loss": 1.8998,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 7.427503857598464e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1510/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd7dc4eb8c9290178577870024a0e08d059c556c3752949322998b3f84ab9df
+size 4984

runs/Mar27_21-31-40_r-theoracle-camoscio-oqvxu8bk-2220d-89nt2/events.out.tfevents.1711575101.r-theoracle-camoscio-oqvxu8bk-2220d-89nt2.59.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e190ead842b4f06251ee4e0e6ed3a59cf46929a1d159945b9135b32db6e4be90
-size 17615
+oid sha256:3fb8d6f86b4a84b6476c6e0c8f799c2b0f22da68ae0b0d7ec63a50c2189fe657
+size 18180

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd7dc4eb8c9290178577870024a0e08d059c556c3752949322998b3f84ab9df
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "google/gemma-2b",
+    "project_name": "autotrain-91gzg-9j8r4",
+    "data_path": "autotrain-91gzg-9j8r4/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": 5,
+    "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": "theoracle/autotrain-91gzg-9j8r4",
+    "username": "theoracle"
+}