Upload fine-tuned GPT-2 on FineWeb (416M tokens) - LoRA adapters + config

README.md

@@ -1,3 +1,209 @@
----
-license: apache-2.0
----
+---
+base_model: openai-community/gpt2
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:openai-community/gpt2
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_proj",
+    "c_attn"
+  ],
+  "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:b8172de31d36e29e0d5d88d78093c92691c379a2cbaf41f69c905f3665acff36
+size 18886632

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7db752d5350424dbf572318ea3054082ca1c80568a995dc6d87a20f9c2e1b02
+size 9700619

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f047e65872f4ea46a47ef2ddbdbc3daf8251ae10bf8e560cc44798452f2d88
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae3778a43ab33194e3eb557cd3e82c54c63f22364e734be5b5c32d5a5037dd
+size 1465

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|>"
+}

trainer_state.json

@@ -0,0 +1,454 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.013714285714285714,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00022857142857142857,
+      "grad_norm": 0.2346513569355011,
+      "learning_rate": 9e-06,
+      "loss": 3.8879,
+      "step": 10
+    },
+    {
+      "epoch": 0.00045714285714285713,
+      "grad_norm": 0.22248627245426178,
+      "learning_rate": 1.9e-05,
+      "loss": 3.9183,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006857142857142857,
+      "grad_norm": 0.20896980166435242,
+      "learning_rate": 2.9e-05,
+      "loss": 3.8078,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009142857142857143,
+      "grad_norm": 0.23850908875465393,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 3.9322,
+      "step": 40
+    },
+    {
+      "epoch": 0.001142857142857143,
+      "grad_norm": 0.20449857413768768,
+      "learning_rate": 4.9e-05,
+      "loss": 3.7764,
+      "step": 50
+    },
+    {
+      "epoch": 0.0013714285714285714,
+      "grad_norm": 0.2402871549129486,
+      "learning_rate": 4.9181818181818183e-05,
+      "loss": 3.779,
+      "step": 60
+    },
+    {
+      "epoch": 0.0016,
+      "grad_norm": 0.24396637082099915,
+      "learning_rate": 4.827272727272727e-05,
+      "loss": 3.778,
+      "step": 70
+    },
+    {
+      "epoch": 0.0018285714285714285,
+      "grad_norm": 0.218296080827713,
+      "learning_rate": 4.736363636363637e-05,
+      "loss": 3.6985,
+      "step": 80
+    },
+    {
+      "epoch": 0.002057142857142857,
+      "grad_norm": 0.2191750556230545,
+      "learning_rate": 4.6454545454545456e-05,
+      "loss": 3.7632,
+      "step": 90
+    },
+    {
+      "epoch": 0.002285714285714286,
+      "grad_norm": 0.2369811236858368,
+      "learning_rate": 4.5545454545454544e-05,
+      "loss": 3.7226,
+      "step": 100
+    },
+    {
+      "epoch": 0.002514285714285714,
+      "grad_norm": 0.2669982612133026,
+      "learning_rate": 4.463636363636364e-05,
+      "loss": 3.7047,
+      "step": 110
+    },
+    {
+      "epoch": 0.002742857142857143,
+      "grad_norm": 0.2281678467988968,
+      "learning_rate": 4.372727272727273e-05,
+      "loss": 3.6731,
+      "step": 120
+    },
+    {
+      "epoch": 0.0029714285714285715,
+      "grad_norm": 0.2538886070251465,
+      "learning_rate": 4.281818181818182e-05,
+      "loss": 3.6279,
+      "step": 130
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 0.2365216612815857,
+      "learning_rate": 4.190909090909091e-05,
+      "loss": 3.6114,
+      "step": 140
+    },
+    {
+      "epoch": 0.0034285714285714284,
+      "grad_norm": 0.2829030156135559,
+      "learning_rate": 4.1e-05,
+      "loss": 3.6339,
+      "step": 150
+    },
+    {
+      "epoch": 0.003657142857142857,
+      "grad_norm": 0.28002238273620605,
+      "learning_rate": 4.009090909090909e-05,
+      "loss": 3.6,
+      "step": 160
+    },
+    {
+      "epoch": 0.0038857142857142857,
+      "grad_norm": 0.28344056010246277,
+      "learning_rate": 3.9181818181818184e-05,
+      "loss": 3.6351,
+      "step": 170
+    },
+    {
+      "epoch": 0.004114285714285714,
+      "grad_norm": 0.25062933564186096,
+      "learning_rate": 3.827272727272728e-05,
+      "loss": 3.6556,
+      "step": 180
+    },
+    {
+      "epoch": 0.004342857142857143,
+      "grad_norm": 0.2557496130466461,
+      "learning_rate": 3.736363636363637e-05,
+      "loss": 3.6196,
+      "step": 190
+    },
+    {
+      "epoch": 0.004571428571428572,
+      "grad_norm": 0.26178061962127686,
+      "learning_rate": 3.645454545454546e-05,
+      "loss": 3.6541,
+      "step": 200
+    },
+    {
+      "epoch": 0.0048,
+      "grad_norm": 0.24720928072929382,
+      "learning_rate": 3.5545454545454545e-05,
+      "loss": 3.6015,
+      "step": 210
+    },
+    {
+      "epoch": 0.005028571428571428,
+      "grad_norm": 0.24621886014938354,
+      "learning_rate": 3.463636363636364e-05,
+      "loss": 3.5792,
+      "step": 220
+    },
+    {
+      "epoch": 0.005257142857142857,
+      "grad_norm": 0.2460050880908966,
+      "learning_rate": 3.372727272727273e-05,
+      "loss": 3.6046,
+      "step": 230
+    },
+    {
+      "epoch": 0.005485714285714286,
+      "grad_norm": 0.3001673221588135,
+      "learning_rate": 3.281818181818182e-05,
+      "loss": 3.5625,
+      "step": 240
+    },
+    {
+      "epoch": 0.005714285714285714,
+      "grad_norm": 0.2713945209980011,
+      "learning_rate": 3.190909090909091e-05,
+      "loss": 3.6734,
+      "step": 250
+    },
+    {
+      "epoch": 0.005942857142857143,
+      "grad_norm": 0.30158859491348267,
+      "learning_rate": 3.1e-05,
+      "loss": 3.6523,
+      "step": 260
+    },
+    {
+      "epoch": 0.006171428571428572,
+      "grad_norm": 0.25476905703544617,
+      "learning_rate": 3.0090909090909093e-05,
+      "loss": 3.554,
+      "step": 270
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 0.247573122382164,
+      "learning_rate": 2.9181818181818182e-05,
+      "loss": 3.6185,
+      "step": 280
+    },
+    {
+      "epoch": 0.006628571428571429,
+      "grad_norm": 0.28666672110557556,
+      "learning_rate": 2.8272727272727274e-05,
+      "loss": 3.5647,
+      "step": 290
+    },
+    {
+      "epoch": 0.006857142857142857,
+      "grad_norm": 0.2672288417816162,
+      "learning_rate": 2.7363636363636362e-05,
+      "loss": 3.6464,
+      "step": 300
+    },
+    {
+      "epoch": 0.0070857142857142855,
+      "grad_norm": 0.27534735202789307,
+      "learning_rate": 2.6454545454545454e-05,
+      "loss": 3.5813,
+      "step": 310
+    },
+    {
+      "epoch": 0.007314285714285714,
+      "grad_norm": 0.24681590497493744,
+      "learning_rate": 2.5545454545454546e-05,
+      "loss": 3.6038,
+      "step": 320
+    },
+    {
+      "epoch": 0.007542857142857143,
+      "grad_norm": 0.2686510682106018,
+      "learning_rate": 2.4636363636363638e-05,
+      "loss": 3.5755,
+      "step": 330
+    },
+    {
+      "epoch": 0.0077714285714285715,
+      "grad_norm": 0.27035024762153625,
+      "learning_rate": 2.372727272727273e-05,
+      "loss": 3.5517,
+      "step": 340
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.28498750925064087,
+      "learning_rate": 2.281818181818182e-05,
+      "loss": 3.6397,
+      "step": 350
+    },
+    {
+      "epoch": 0.008228571428571429,
+      "grad_norm": 0.2775673568248749,
+      "learning_rate": 2.190909090909091e-05,
+      "loss": 3.6033,
+      "step": 360
+    },
+    {
+      "epoch": 0.008457142857142858,
+      "grad_norm": 0.29988932609558105,
+      "learning_rate": 2.1e-05,
+      "loss": 3.5917,
+      "step": 370
+    },
+    {
+      "epoch": 0.008685714285714286,
+      "grad_norm": 0.25248634815216064,
+      "learning_rate": 2.009090909090909e-05,
+      "loss": 3.6374,
+      "step": 380
+    },
+    {
+      "epoch": 0.008914285714285715,
+      "grad_norm": 0.2702570855617523,
+      "learning_rate": 1.9181818181818183e-05,
+      "loss": 3.5725,
+      "step": 390
+    },
+    {
+      "epoch": 0.009142857142857144,
+      "grad_norm": 0.29647764563560486,
+      "learning_rate": 1.8272727272727275e-05,
+      "loss": 3.5781,
+      "step": 400
+    },
+    {
+      "epoch": 0.009371428571428572,
+      "grad_norm": 0.2612384259700775,
+      "learning_rate": 1.7363636363636366e-05,
+      "loss": 3.5935,
+      "step": 410
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 0.24550645053386688,
+      "learning_rate": 1.6454545454545455e-05,
+      "loss": 3.5511,
+      "step": 420
+    },
+    {
+      "epoch": 0.009828571428571428,
+      "grad_norm": 0.3067398965358734,
+      "learning_rate": 1.5545454545454547e-05,
+      "loss": 3.6077,
+      "step": 430
+    },
+    {
+      "epoch": 0.010057142857142857,
+      "grad_norm": 0.2859310507774353,
+      "learning_rate": 1.4636363636363637e-05,
+      "loss": 3.5567,
+      "step": 440
+    },
+    {
+      "epoch": 0.010285714285714285,
+      "grad_norm": 0.34277746081352234,
+      "learning_rate": 1.3727272727272727e-05,
+      "loss": 3.5546,
+      "step": 450
+    },
+    {
+      "epoch": 0.010514285714285714,
+      "grad_norm": 0.31543368101119995,
+      "learning_rate": 1.2818181818181818e-05,
+      "loss": 3.5976,
+      "step": 460
+    },
+    {
+      "epoch": 0.010742857142857143,
+      "grad_norm": 0.2583160698413849,
+      "learning_rate": 1.190909090909091e-05,
+      "loss": 3.566,
+      "step": 470
+    },
+    {
+      "epoch": 0.010971428571428571,
+      "grad_norm": 0.2528459131717682,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 3.667,
+      "step": 480
+    },
+    {
+      "epoch": 0.0112,
+      "grad_norm": 0.26343825459480286,
+      "learning_rate": 1.0090909090909092e-05,
+      "loss": 3.5792,
+      "step": 490
+    },
+    {
+      "epoch": 0.011428571428571429,
+      "grad_norm": 0.26427048444747925,
+      "learning_rate": 9.181818181818182e-06,
+      "loss": 3.5028,
+      "step": 500
+    },
+    {
+      "epoch": 0.011657142857142857,
+      "grad_norm": 0.3029393255710602,
+      "learning_rate": 8.272727272727274e-06,
+      "loss": 3.6024,
+      "step": 510
+    },
+    {
+      "epoch": 0.011885714285714286,
+      "grad_norm": 0.2847612500190735,
+      "learning_rate": 7.363636363636364e-06,
+      "loss": 3.5887,
+      "step": 520
+    },
+    {
+      "epoch": 0.012114285714285715,
+      "grad_norm": 0.2795548439025879,
+      "learning_rate": 6.454545454545455e-06,
+      "loss": 3.5564,
+      "step": 530
+    },
+    {
+      "epoch": 0.012342857142857143,
+      "grad_norm": 0.2452515810728073,
+      "learning_rate": 5.545454545454546e-06,
+      "loss": 3.5679,
+      "step": 540
+    },
+    {
+      "epoch": 0.012571428571428572,
+      "grad_norm": 0.27698689699172974,
+      "learning_rate": 4.636363636363636e-06,
+      "loss": 3.6436,
+      "step": 550
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 0.286603718996048,
+      "learning_rate": 3.727272727272727e-06,
+      "loss": 3.5336,
+      "step": 560
+    },
+    {
+      "epoch": 0.01302857142857143,
+      "grad_norm": 0.2752152681350708,
+      "learning_rate": 2.8181818181818185e-06,
+      "loss": 3.5525,
+      "step": 570
+    },
+    {
+      "epoch": 0.013257142857142858,
+      "grad_norm": 0.28077051043510437,
+      "learning_rate": 1.9090909090909095e-06,
+      "loss": 3.6844,
+      "step": 580
+    },
+    {
+      "epoch": 0.013485714285714285,
+      "grad_norm": 0.31142348051071167,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.557,
+      "step": 590
+    },
+    {
+      "epoch": 0.013714285714285714,
+      "grad_norm": 0.29399439692497253,
+      "learning_rate": 9.090909090909091e-08,
+      "loss": 3.5452,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 2571449548492800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f764764cbbf6f04efada30eef8f82170094fa59ad2c6f7979bc7524e6a36ea44
+size 6033