End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.7853715419769287,
+    "eval_runtime": 235.5715,
+    "eval_samples_per_second": 84.9,
+    "eval_steps_per_second": 1.77,
+    "train_loss": 1.92795908203125,
+    "train_runtime": 4801.8714,
+    "train_samples_per_second": 37.485,
+    "train_steps_per_second": 0.781
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.7853715419769287,
+    "eval_runtime": 235.5715,
+    "eval_samples_per_second": 84.9,
+    "eval_steps_per_second": 1.77
+}

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/Jul30_13-30-55_cvrl-flynn-ws2/events.out.tfevents.1690743425.cvrl-flynn-ws2.25120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d70bdb512df0a8c81c1015fcbae2e88a91150613b1a697f5a3ca01d728022b
+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 +1,14 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.92795908203125,
+    "train_runtime": 4801.8714,
+    "train_samples_per_second": 37.485,
+    "train_steps_per_second": 0.781
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 3.4742,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 2.8398,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 2.238,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.8677,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.7004,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 1.0004,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9108,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "step": 3750,
+      "total_flos": 2.40331104e+16,
+      "train_loss": 1.92795908203125,
+      "train_runtime": 4801.8714,
+      "train_samples_per_second": 37.485,
+      "train_steps_per_second": 0.781
+    }
+  ],
+  "max_steps": 3750,
+  "num_train_epochs": 3,
+  "total_flos": 2.40331104e+16,
+  "trial_name": null,
+  "trial_params": null
+}