End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.7825541496276855,
+    "eval_runtime": 51.9175,
+    "eval_samples_per_second": 220.272,
+    "eval_steps_per_second": 27.544,
+    "train_loss": 1.9890900429028717,
+    "train_runtime": 2263.9172,
+    "train_samples_per_second": 45.459,
+    "train_steps_per_second": 5.684
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.7825541496276855,
+    "eval_runtime": 51.9175,
+    "eval_samples_per_second": 220.272,
+    "eval_steps_per_second": 27.544
+}

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": 1.9890900429028717,
+    "train_runtime": 2263.9172,
+    "train_samples_per_second": 45.459,
+    "train_steps_per_second": 5.684
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12867,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.805704515427062e-05,
+      "loss": 2.0534,
+      "step": 500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.611409030854123e-05,
+      "loss": 2.0247,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.417113546281185e-05,
+      "loss": 2.0043,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.2228180617082464e-05,
+      "loss": 2.0058,
+      "step": 2000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0285225771353074e-05,
+      "loss": 1.975,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.834227092562369e-05,
+      "loss": 1.9893,
+      "step": 3000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.63993160798943e-05,
+      "loss": 1.9694,
+      "step": 3500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.445636123416492e-05,
+      "loss": 1.9835,
+      "step": 4000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.2513406388435536e-05,
+      "loss": 2.0311,
+      "step": 4500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.0570451542706146e-05,
+      "loss": 2.0796,
+      "step": 5000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8627496696976763e-05,
+      "loss": 2.0795,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.668454185124738e-05,
+      "loss": 2.0795,
+      "step": 6000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.4741587005517994e-05,
+      "loss": 2.0795,
+      "step": 6500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.2798632159788608e-05,
+      "loss": 2.0795,
+      "step": 7000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0855677314059222e-05,
+      "loss": 2.0794,
+      "step": 7500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.891272246832984e-05,
+      "loss": 2.0794,
+      "step": 8000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.6969767622600453e-05,
+      "loss": 2.0795,
+      "step": 8500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.5026812776871066e-05,
+      "loss": 2.0643,
+      "step": 9000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.308385793114168e-05,
+      "loss": 1.9871,
+      "step": 9500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1140903085412295e-05,
+      "loss": 1.9983,
+      "step": 10000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 9.19794823968291e-06,
+      "loss": 1.9287,
+      "step": 10500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.2549933939535245e-06,
+      "loss": 1.8553,
+      "step": 11000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.312038548224139e-06,
+      "loss": 1.8021,
+      "step": 11500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.369083702494754e-06,
+      "loss": 1.7824,
+      "step": 12000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.4261288567653689e-06,
+      "loss": 1.7905,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "step": 12867,
+      "total_flos": 1.37409308712e+16,
+      "train_loss": 1.9890900429028717,
+      "train_runtime": 2263.9172,
+      "train_samples_per_second": 45.459,
+      "train_steps_per_second": 5.684
+    }
+  ],
+  "max_steps": 12867,
+  "num_train_epochs": 3,
+  "total_flos": 1.37409308712e+16,
+  "trial_name": null,
+  "trial_params": null
+}