End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.8674657344818115,
+    "eval_runtime": 268.6011,
+    "eval_samples_per_second": 74.46,
+    "eval_steps_per_second": 2.327,
+    "train_loss": 2.2601124869791667,
+    "train_runtime": 7762.5186,
+    "train_samples_per_second": 38.647,
+    "train_steps_per_second": 1.208
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.8674657344818115,
+    "eval_runtime": 268.6011,
+    "eval_samples_per_second": 74.46,
+    "eval_steps_per_second": 2.327
+}

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/Aug15_17-11-13_cvrl-flynn-ws2/events.out.tfevents.1692142027.cvrl-flynn-ws2.14211.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3477ea8ba06a037dc77f94a1a9ea669038eab40191105d8f06880a3bbcf4d2
+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 +1,18 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "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": 2.2601124869791667,
+    "train_runtime": 7762.5186,
+    "train_samples_per_second": 38.647,
+    "train_steps_per_second": 1.208
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 2.8674657344818115,
+  "best_model_checkpoint": "clip-br-100k/checkpoint-6250",
+  "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": 3.364,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 3.1853,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.2e-05,
+      "loss": 3.0724,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 2.9594,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 2.8763,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 2.7977,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0236034393310547,
+      "eval_runtime": 269.4873,
+      "eval_samples_per_second": 74.215,
+      "eval_steps_per_second": 2.319,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 2.4752,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 2.3537,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.3224,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 2.2794,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 2.2444,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2202,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.8674657344818115,
+      "eval_runtime": 269.0568,
+      "eval_samples_per_second": 74.334,
+      "eval_steps_per_second": 2.323,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 1.8795,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 1.501,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 1.4826,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 1.4807,
+      "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 1.446,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4086,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.140260934829712,
+      "eval_runtime": 269.6762,
+      "eval_samples_per_second": 74.163,
+      "eval_steps_per_second": 2.318,
+      "step": 9375
+    },
+    {
+      "epoch": 3.0,
+      "step": 9375,
+      "total_flos": 3.01208373504e+16,
+      "train_loss": 2.2601124869791667,
+      "train_runtime": 7762.5186,
+      "train_samples_per_second": 38.647,
+      "train_steps_per_second": 1.208
+    }
+  ],
+  "max_steps": 9375,
+  "num_train_epochs": 3,
+  "total_flos": 3.01208373504e+16,
+  "trial_name": null,
+  "trial_params": null
+}