End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.2019567489624023,
+    "eval_runtime": 7.5069,
+    "eval_samples_per_second": 1.199,
+    "eval_steps_per_second": 0.133,
+    "train_loss": 3.6482365926106772,
+    "train_runtime": 206.699,
+    "train_samples_per_second": 0.479,
+    "train_steps_per_second": 0.015
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.2019567489624023,
+    "eval_runtime": 7.5069,
+    "eval_samples_per_second": 1.199,
+    "eval_steps_per_second": 0.133
+}

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/May29_04-52-32_f3d62a83e2fd/events.out.tfevents.1685336255.f3d62a83e2fd.117504.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f8d9a6789b981d730e1dbe408e135dc7240c8a2e5423e7b5c9098fd6fdbbd8
+size 354

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_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.6482365926106772,
+    "train_runtime": 206.699,
+    "train_samples_per_second": 0.479,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 3,
+      "total_flos": 13218210720000.0,
+      "train_loss": 3.6482365926106772,
+      "train_runtime": 206.699,
+      "train_samples_per_second": 0.479,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "max_steps": 3,
+  "num_train_epochs": 3,
+  "total_flos": 13218210720000.0,
+  "trial_name": null,
+  "trial_params": null
+}