0304997e v10 4-GPU 3 epochs

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: unsloth/Qwen2-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2-7B
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "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 sha256:4f72c30696d6ee278c87d682d2f1d33ac1212db5e35cb07475a11b742dfda8c5
+size 1291899160

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|PAD_TOKEN|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

loss.txt

@@ -0,0 +1 @@
+100,0.2199000120162964

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
+size 11418456

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8790523409843445,
+      "learning_rate": 5.189352851781284e-06,
+      "loss": 0.3238,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6200674176216125,
+      "learning_rate": 1.1676043916507888e-05,
+      "loss": 0.2928,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.40642672777175903,
+      "learning_rate": 1.8162734981234494e-05,
+      "loss": 0.2758,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.35607966780662537,
+      "learning_rate": 2.4649426045961095e-05,
+      "loss": 0.2607,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.32907894253730774,
+      "learning_rate": 3.1136117110687706e-05,
+      "loss": 0.2394,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.3127606511116028,
+      "learning_rate": 3.7622808175414306e-05,
+      "loss": 0.2514,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3379378020763397,
+      "learning_rate": 4.4109499240140914e-05,
+      "loss": 0.2482,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3318215310573578,
+      "learning_rate": 4.538769625476793e-05,
+      "loss": 0.243,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.28706055879592896,
+      "learning_rate": 4.531000888596653e-05,
+      "loss": 0.244,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2560233175754547,
+      "learning_rate": 4.517285169131251e-05,
+      "loss": 0.2213,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.25494974851608276,
+      "learning_rate": 4.497670644045438e-05,
+      "loss": 0.2259,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.24735252559185028,
+      "learning_rate": 4.472226210073948e-05,
+      "loss": 0.2298,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2560272812843323,
+      "learning_rate": 4.441041241719098e-05,
+      "loss": 0.2461,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2997988164424896,
+      "learning_rate": 4.4042252773195925e-05,
+      "loss": 0.2365,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.25254151225090027,
+      "learning_rate": 4.361907634293114e-05,
+      "loss": 0.2197,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2556798756122589,
+      "learning_rate": 4.314236954904174e-05,
+      "loss": 0.2234,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2567313313484192,
+      "learning_rate": 4.261380684152741e-05,
+      "loss": 0.2187,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.26947030425071716,
+      "learning_rate": 4.203524481617568e-05,
+      "loss": 0.2196,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.25609439611434937,
+      "learning_rate": 4.1408715693201555e-05,
+      "loss": 0.2116,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.24521243572235107,
+      "learning_rate": 4.073642017899985e-05,
+      "loss": 0.2365,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2199000120162964,
+      "eval_runtime": 5.0293,
+      "eval_samples_per_second": 11.135,
+      "eval_steps_per_second": 2.784,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0877297825153024e+17,
+  "train_batch_size": 14,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8439c33528676781b6d37f83bf1ef286a6016403cbaf8fa9e6a875e1df82e58
+size 6225