End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.5849734544754028,
+    "eval_runtime": 152.5492,
+    "eval_samples_per_second": 163.973,
+    "eval_steps_per_second": 0.642,
+    "train_loss": 0.3111796811702326,
+    "train_runtime": 14391.5786,
+    "train_samples_per_second": 123.354,
+    "train_steps_per_second": 0.482
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.5849734544754028,
+    "eval_runtime": 152.5492,
+    "eval_samples_per_second": 163.973,
+    "eval_steps_per_second": 0.642
+}

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
+  }
+}

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": 0.3111796811702326,
+    "train_runtime": 14391.5786,
+    "train_samples_per_second": 123.354,
+    "train_steps_per_second": 0.482
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6933,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.639405740660609e-05,
+      "loss": 0.8524,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.278811481321218e-05,
+      "loss": 0.5142,
+      "step": 1000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.9182172219818266e-05,
+      "loss": 0.433,
+      "step": 1500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.5576229626424354e-05,
+      "loss": 0.3839,
+      "step": 2000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.1970287033030435e-05,
+      "loss": 0.3263,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.836434443963652e-05,
+      "loss": 0.2745,
+      "step": 3000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.475840184624261e-05,
+      "loss": 0.2612,
+      "step": 3500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.11524592528487e-05,
+      "loss": 0.2418,
+      "step": 4000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7546516659454783e-05,
+      "loss": 0.2301,
+      "step": 4500
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.394057406606087e-05,
+      "loss": 0.1851,
+      "step": 5000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0334631472666955e-05,
+      "loss": 0.1674,
+      "step": 5500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.728688879273043e-06,
+      "loss": 0.1604,
+      "step": 6000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.122746285879129e-06,
+      "loss": 0.1545,
+      "step": 6500
+    },
+    {
+      "epoch": 3.0,
+      "step": 6933,
+      "total_flos": 2.3697287737344e+17,
+      "train_loss": 0.3111796811702326,
+      "train_runtime": 14391.5786,
+      "train_samples_per_second": 123.354,
+      "train_steps_per_second": 0.482
+    }
+  ],
+  "max_steps": 6933,
+  "num_train_epochs": 3,
+  "total_flos": 2.3697287737344e+17,
+  "trial_name": null,
+  "trial_params": null
+}