End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4657968282699585,
+    "eval_runtime": 87.0777,
+    "eval_samples_per_second": 114.84,
+    "eval_steps_per_second": 3.594,
+    "train_loss": 1.4532607096354166,
+    "train_runtime": 6576.4517,
+    "train_samples_per_second": 45.617,
+    "train_steps_per_second": 1.426
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.4657968282699585,
+    "eval_runtime": 87.0777,
+    "eval_samples_per_second": 114.84,
+    "eval_steps_per_second": 3.594
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Aug03_12-50-11_cvrl-flynn-ws2/events.out.tfevents.1691088202.cvrl-flynn-ws2.6434.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5872c26b1ad4308fd31689ec51cd2b775f67f16c390974c9847cecf13d3bc6e7
+size 359

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.4532607096354166,
+    "train_runtime": 6576.4517,
+    "train_samples_per_second": 45.617,
+    "train_steps_per_second": 1.426
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7333333333333336e-05,
+      "loss": 2.8706,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 2.502,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.2e-05,
+      "loss": 2.3427,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 2.211,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 2.1047,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 2.0136,
+      "step": 3000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 1.5744,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 1.4265,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.4374,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.3846,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 1.3389,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8e-05,
+      "loss": 1.2897,
+      "step": 6000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.9945,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 0.7076,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 0.6831,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 0.6581,
+      "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.6292,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6242,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9375,
+      "total_flos": 3.01208373504e+16,
+      "train_loss": 1.4532607096354166,
+      "train_runtime": 6576.4517,
+      "train_samples_per_second": 45.617,
+      "train_steps_per_second": 1.426
+    }
+  ],
+  "max_steps": 9375,
+  "num_train_epochs": 3,
+  "total_flos": 3.01208373504e+16,
+  "trial_name": null,
+  "trial_params": null
+}