Training in progress, step 174, checkpoint

checkpoint-174/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: openai/clip-vit-base-patch32
+---
+
+# 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-174/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "CLIPDetails",
+    "parent_library": "clipdetails.models.clipdetails"
+  },
+  "base_model_name_or_path": "openai/clip-vit-base-patch32",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "loss_balance"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "fc1",
+    "v_proj",
+    "visual_projection",
+    "out_proj",
+    "k_proj",
+    "q_proj",
+    "text_projection"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-174/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ebd839aa50ba2c78fc4f0523aa4229bc692b0ef19f8d12739bc527159b0938
+size 8962304

checkpoint-174/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6651e47513e44f41b29f5df37d6e0b2d5bb45eceb3cfa8ec8e051519143c0fd
+size 18087162

checkpoint-174/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4874c4111c3be479675e2f2a153de2466133da1687977d0a6bdbcca469a2631
+size 14244

checkpoint-174/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b4c630bbf2933b7e8e30a4dea42c44841fd8bcfc0027918054366a82c263de
+size 1064

checkpoint-174/trainer_state.json

@@ -0,0 +1,269 @@
+{
+  "best_metric": 1.7821800708770752,
+  "best_model_checkpoint": "$../logs/03-08-2024T09-56-31-detailclip-b32/checkpoint-116",
+  "epoch": 1.5130434782608697,
+  "eval_steps": 58,
+  "global_step": 174,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05217391304347826,
+      "grad_norm": 3.0711264610290527,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8067,
+      "step": 6
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 3.019757032394409,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8037,
+      "step": 12
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 3.080796003341675,
+      "learning_rate": 3.6e-05,
+      "loss": 0.835,
+      "step": 18
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 2.9880104064941406,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6869,
+      "step": 24
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 2.5763087272644043,
+      "learning_rate": 6e-05,
+      "loss": 0.5712,
+      "step": 30
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 2.295846462249756,
+      "learning_rate": 7.2e-05,
+      "loss": 0.5537,
+      "step": 36
+    },
+    {
+      "epoch": 0.3652173913043478,
+      "grad_norm": 2.2098076343536377,
+      "learning_rate": 8.4e-05,
+      "loss": 0.481,
+      "step": 42
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 1.7029411792755127,
+      "learning_rate": 9.6e-05,
+      "loss": 0.3933,
+      "step": 48
+    },
+    {
+      "epoch": 0.46956521739130436,
+      "grad_norm": 2.0247466564178467,
+      "learning_rate": 9.999673735634258e-05,
+      "loss": 0.3398,
+      "step": 54
+    },
+    {
+      "epoch": 0.5043478260869565,
+      "eval_loss": 1.8895907402038574,
+      "eval_runtime": 362.9542,
+      "eval_samples_per_second": 6.155,
+      "eval_steps_per_second": 0.05,
+      "step": 58
+    },
+    {
+      "epoch": 0.5043478260869565,
+      "neg_increments": 0.3482297461360652,
+      "positive_increments": 0.5847584809616501,
+      "rate_increments": 0.6160316723977289,
+      "step": 58
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 1.6125733852386475,
+      "learning_rate": 9.997960964140947e-05,
+      "loss": 0.3224,
+      "step": 60
+    },
+    {
+      "epoch": 0.5739130434782609,
+      "grad_norm": 1.9766706228256226,
+      "learning_rate": 9.994780621691156e-05,
+      "loss": 0.2817,
+      "step": 66
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 1.4810394048690796,
+      "learning_rate": 9.990133642141359e-05,
+      "loss": 0.2746,
+      "step": 72
+    },
+    {
+      "epoch": 0.6782608695652174,
+      "grad_norm": 1.8605773448944092,
+      "learning_rate": 9.984021390002458e-05,
+      "loss": 0.2948,
+      "step": 78
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 1.2394453287124634,
+      "learning_rate": 9.976445660039118e-05,
+      "loss": 0.2688,
+      "step": 84
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.2431163787841797,
+      "learning_rate": 9.967408676742751e-05,
+      "loss": 0.2639,
+      "step": 90
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 1.2484493255615234,
+      "learning_rate": 9.956913093678348e-05,
+      "loss": 0.2358,
+      "step": 96
+    },
+    {
+      "epoch": 0.8869565217391304,
+      "grad_norm": 1.6284162998199463,
+      "learning_rate": 9.944961992705288e-05,
+      "loss": 0.2598,
+      "step": 102
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 1.6559319496154785,
+      "learning_rate": 9.931558883072403e-05,
+      "loss": 0.2436,
+      "step": 108
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 1.544296383857727,
+      "learning_rate": 9.916707700387547e-05,
+      "loss": 0.2499,
+      "step": 114
+    },
+    {
+      "epoch": 1.008695652173913,
+      "eval_loss": 1.7821800708770752,
+      "eval_runtime": 369.7296,
+      "eval_samples_per_second": 6.042,
+      "eval_steps_per_second": 0.049,
+      "step": 116
+    },
+    {
+      "epoch": 1.008695652173913,
+      "neg_increments": 0.3239222537704994,
+      "positive_increments": 0.5982375050866754,
+      "rate_increments": 0.6459971370030191,
+      "step": 116
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 1.2527427673339844,
+      "learning_rate": 9.900412805461967e-05,
+      "loss": 0.2314,
+      "step": 120
+    },
+    {
+      "epoch": 1.0956521739130434,
+      "grad_norm": 1.442431092262268,
+      "learning_rate": 9.882678983029819e-05,
+      "loss": 0.2154,
+      "step": 126
+    },
+    {
+      "epoch": 1.1478260869565218,
+      "grad_norm": 1.1382640600204468,
+      "learning_rate": 9.863511440343206e-05,
+      "loss": 0.2099,
+      "step": 132
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.301225185394287,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 0.2129,
+      "step": 138
+    },
+    {
+      "epoch": 1.2521739130434781,
+      "grad_norm": 1.6986100673675537,
+      "learning_rate": 9.820898126506979e-05,
+      "loss": 0.2136,
+      "step": 144
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 1.7194011211395264,
+      "learning_rate": 9.797464868072488e-05,
+      "loss": 0.2284,
+      "step": 150
+    },
+    {
+      "epoch": 1.3565217391304347,
+      "grad_norm": 1.5837785005569458,
+      "learning_rate": 9.772622911139622e-05,
+      "loss": 0.2175,
+      "step": 156
+    },
+    {
+      "epoch": 1.4086956521739131,
+      "grad_norm": 1.3046813011169434,
+      "learning_rate": 9.746379550150009e-05,
+      "loss": 0.2399,
+      "step": 162
+    },
+    {
+      "epoch": 1.4608695652173913,
+      "grad_norm": 1.3825078010559082,
+      "learning_rate": 9.71874249104506e-05,
+      "loss": 0.1966,
+      "step": 168
+    },
+    {
+      "epoch": 1.5130434782608697,
+      "grad_norm": 1.2827361822128296,
+      "learning_rate": 9.68971984900326e-05,
+      "loss": 0.1898,
+      "step": 174
+    },
+    {
+      "epoch": 1.5130434782608697,
+      "eval_loss": 1.842968225479126,
+      "eval_runtime": 360.8646,
+      "eval_samples_per_second": 6.191,
+      "eval_steps_per_second": 0.05,
+      "step": 174
+    },
+    {
+      "epoch": 1.5130434782608697,
+      "neg_increments": 0.3106953354534828,
+      "positive_increments": 0.6017424889735749,
+      "rate_increments": 0.6599375188611972,
+      "step": 174
+    }
+  ],
+  "logging_steps": 6,
+  "max_steps": 1150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 58,
+  "total_flos": 3942368157607110.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-174/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28caa9c21f1b2004942db77da588c4d31446af433a9325540f1e9797f62993ef
+size 5112