End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.327958106994629,
+    "eval_runtime": 127.0788,
+    "eval_samples_per_second": 78.691,
+    "eval_steps_per_second": 2.463,
+    "train_loss": 3.383876552723975,
+    "train_runtime": 1383.4982,
+    "train_samples_per_second": 21.684,
+    "train_steps_per_second": 0.679
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.327958106994629,
+    "eval_runtime": 127.0788,
+    "eval_samples_per_second": 78.691,
+    "eval_steps_per_second": 2.463
+}

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/Aug10_13-46-15_cvrl-flynn-ws2/events.out.tfevents.1691691156.cvrl-flynn-ws2.4174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5368561400b6a6eb1e8a4582922586c09b273cba77b95f9eb44a78859e12be9
+size 359

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c08c80d1df11b82ada2fd707562f86a9ebd5b7de04f51ebd2b49f2cd5906d00
+size 17082925

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.383876552723975,
+    "train_runtime": 1383.4982,
+    "train_samples_per_second": 21.684,
+    "train_steps_per_second": 0.679
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 3.327958106994629,
+  "best_model_checkpoint": "clip-roberta-10k/checkpoint-939",
+  "epoch": 3.0,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.4277737140655518,
+      "eval_runtime": 117.2709,
+      "eval_samples_per_second": 85.273,
+      "eval_steps_per_second": 2.669,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3375931842385517e-05,
+      "loss": 3.4415,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.3748862743377686,
+      "eval_runtime": 131.3188,
+      "eval_samples_per_second": 76.151,
+      "eval_steps_per_second": 2.384,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.327958106994629,
+      "eval_runtime": 131.0009,
+      "eval_samples_per_second": 76.335,
+      "eval_steps_per_second": 2.389,
+      "step": 939
+    },
+    {
+      "epoch": 3.0,
+      "step": 939,
+      "total_flos": 4005518400000000.0,
+      "train_loss": 3.383876552723975,
+      "train_runtime": 1383.4982,
+      "train_samples_per_second": 21.684,
+      "train_steps_per_second": 0.679
+    }
+  ],
+  "max_steps": 939,
+  "num_train_epochs": 3,
+  "total_flos": 4005518400000000.0,
+  "trial_name": null,
+  "trial_params": null
+}