Model save

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,12 +13,13 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/aeroberts4444/huggingface/runs/120mmtvn)
 # vit-base-beans-2
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1144
-- Accuracy: 0.375
+- Accuracy: 0.0
+- Loss: 1.1626
 
 ## Model description
 
@@ -45,22 +44,19 @@ The following hyperparameters were used during training:
 - seed: 1337
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5.0
+- num_epochs: 2.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 2    | 1.1243          | 0.4375   |
-| No log        | 2.0   | 4    | 1.1204          | 0.375    |
-| No log        | 3.0   | 6    | 1.1172          | 0.375    |
-| No log        | 4.0   | 8    | 1.1152          | 0.375    |
-| 0.9751        | 5.0   | 10   | 1.1144          | 0.375    |
+| Training Loss | Epoch | Step | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| No log        | 1.0   | 1    | 0.125    | 1.1599          |
+| No log        | 2.0   | 2    | 0.0      | 1.1626          |
 
 
 ### Framework versions
 
-- Transformers 4.37.0.dev0
-- Pytorch 2.1.1
+- Transformers 4.41.0.dev0
+- Pytorch 2.3.0
 - Datasets 2.15.1.dev0
-- Tokenizers 0.15.0
+- Tokenizers 0.19.1

all_results.json

@@ -1,12 +1,13 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.375,
-    "eval_loss": 1.114396333694458,
-    "eval_runtime": 0.2995,
-    "eval_samples_per_second": 53.415,
-    "eval_steps_per_second": 6.677,
-    "train_loss": 0.9750574111938477,
-    "train_runtime": 26.3663,
-    "train_samples_per_second": 3.034,
-    "train_steps_per_second": 0.379
+    "epoch": 2.0,
+    "eval_accuracy": 0.125,
+    "eval_loss": 1.1599400043487549,
+    "eval_runtime": 0.178,
+    "eval_samples_per_second": 44.956,
+    "eval_steps_per_second": 5.619,
+    "total_flos": 1239882946412544.0,
+    "train_loss": 0.96820068359375,
+    "train_runtime": 21.5994,
+    "train_samples_per_second": 0.741,
+    "train_steps_per_second": 0.093
 }

config.json

@@ -28,8 +28,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
-  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.0.dev0"
+  "transformers_version": "4.41.0.dev0"
 }

emissions.csv

@@ -1,2 +1,3 @@
-timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
-2024-01-02T17:11:45,92bc4d12-1cf1-4cbf-920f-219cbb6a8760,codecarbon,21.716214895248413,0.00014833485723264947,0.00022070057817033512,United Kingdom,GBR,england,N,,
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2024-05-16T18:15:35,20844103-22f2-4177-99d7-f25724b28b42,codecarbon,14.596347332000732,5.807478962366664e-05,0.0001367804705449295,France,FRA,île-de-france,N,,
+2024-05-16T18:16:51,680aa9f6-f24e-4f00-a2b6-63d5cb1fbe86,codecarbon,1.1446659564971924,6.779186780091144e-07,1.5966658918639545e-06,France,FRA,île-de-france,N,,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.375,
-    "eval_loss": 1.114396333694458,
-    "eval_runtime": 0.2995,
-    "eval_samples_per_second": 53.415,
-    "eval_steps_per_second": 6.677
+    "epoch": 2.0,
+    "eval_accuracy": 0.125,
+    "eval_loss": 1.1599400043487549,
+    "eval_runtime": 0.178,
+    "eval_samples_per_second": 44.956,
+    "eval_steps_per_second": 5.619
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9187bf81e3cee0d7531c2e1dc7966085f6f8744d089fc3ea745fddc7daa1a6a3
+oid sha256:7ad556d12bfff5046ea12ab16737cbe9cb793e83b103cea0a8de2afaa32bd309
 size 343227052

preprocessor_config.json

@@ -1,4 +1,18 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,

runs/May16_18-14-57_amys-mbp-2.taildb5d.ts.net/events.out.tfevents.1715879710.amys-mbp-2.taildb5d.ts.net

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae468d96c3bd9404accce866775e9db1e9f519fac814df422060b1c2a01c0b6f
+size 5934

runs/May16_18-14-57_amys-mbp-2.taildb5d.ts.net/events.out.tfevents.1715879753.amys-mbp-2.taildb5d.ts.net

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50810ea5b36f9d4e5180e469e19fbf807653e2aae47c2af290c0d00d7a57a583
+size 357

runs/May16_18-16-28_amys-mbp-2.taildb5d.ts.net/events.out.tfevents.1715879800.amys-mbp-2.taildb5d.ts.net

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9dc8fc31dfce16f34d087e725004c7d67fb1c74fd9dcd5758f7434c460b03b
+size 5300

train_results.json

@@ -1,7 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 0.9750574111938477,
-    "train_runtime": 26.3663,
-    "train_samples_per_second": 3.034,
-    "train_steps_per_second": 0.379
+    "epoch": 2.0,
+    "total_flos": 1239882946412544.0,
+    "train_loss": 0.96820068359375,
+    "train_runtime": 21.5994,
+    "train_samples_per_second": 0.741,
+    "train_steps_per_second": 0.093
 }

trainer_state.json

@@ -1,80 +1,59 @@
 {
-  "best_metric": 1.114396333694458,
-  "best_model_checkpoint": "./beans_outputs/checkpoint-10",
-  "epoch": 5.0,
+  "best_metric": 1.1599400043487549,
+  "best_model_checkpoint": "./beans_outputs/checkpoint-1",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 10,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4375,
-      "eval_loss": 1.1243417263031006,
-      "eval_runtime": 0.3336,
-      "eval_samples_per_second": 47.962,
-      "eval_steps_per_second": 5.995,
-      "step": 2
+      "eval_accuracy": 0.125,
+      "eval_loss": 1.1599400043487549,
+      "eval_runtime": 0.2079,
+      "eval_samples_per_second": 38.483,
+      "eval_steps_per_second": 4.81,
+      "step": 1
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.375,
-      "eval_loss": 1.1203868389129639,
-      "eval_runtime": 0.2032,
-      "eval_samples_per_second": 78.744,
-      "eval_steps_per_second": 9.843,
-      "step": 4
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.375,
-      "eval_loss": 1.1172332763671875,
-      "eval_runtime": 0.1981,
-      "eval_samples_per_second": 80.755,
-      "eval_steps_per_second": 10.094,
-      "step": 6
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.375,
-      "eval_loss": 1.1152395009994507,
-      "eval_runtime": 0.1941,
-      "eval_samples_per_second": 82.414,
-      "eval_steps_per_second": 10.302,
-      "step": 8
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 0.0,
-      "loss": 0.9751,
-      "step": 10
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.375,
-      "eval_loss": 1.114396333694458,
-      "eval_runtime": 0.189,
-      "eval_samples_per_second": 84.659,
-      "eval_steps_per_second": 10.582,
-      "step": 10
+      "eval_accuracy": 0.0,
+      "eval_loss": 1.1626136302947998,
+      "eval_runtime": 0.1072,
+      "eval_samples_per_second": 74.595,
+      "eval_steps_per_second": 9.324,
+      "step": 2
     },
     {
-      "epoch": 5.0,
-      "step": 10,
-      "total_flos": 6199414732062720.0,
-      "train_loss": 0.9750574111938477,
-      "train_runtime": 26.3663,
-      "train_samples_per_second": 3.034,
-      "train_steps_per_second": 0.379
+      "epoch": 2.0,
+      "step": 2,
+      "total_flos": 1239882946412544.0,
+      "train_loss": 0.96820068359375,
+      "train_runtime": 21.5994,
+      "train_samples_per_second": 0.741,
+      "train_steps_per_second": 0.093
     }
   ],
   "logging_steps": 10,
-  "max_steps": 10,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 6199414732062720.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1239882946412544.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a69cbc0bf26905ca43fed1884c56974369c9d37371214839f7b1bf3079f6663
-size 4792
+oid sha256:dfb4cad7bc41b207d5115ed761ba29bdbeeae8035ae57be2dc1893cf198dda2e
+size 5176