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": 3.464627265930176,
+    "eval_runtime": 110.4261,
+    "eval_samples_per_second": 90.558,
+    "eval_steps_per_second": 2.834,
+    "train_loss": 3.465808619791667,
+    "train_runtime": 8159.563,
+    "train_samples_per_second": 36.767,
+    "train_steps_per_second": 1.149
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.464627265930176,
+    "eval_runtime": 110.4261,
+    "eval_samples_per_second": 90.558,
+    "eval_steps_per_second": 2.834
+}

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_15-29-46_cvrl-flynn-ws2/events.out.tfevents.1691704222.cvrl-flynn-ws2.9661.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04aacae39b18534db0983968e94f49e7d9f92d25f585ad8b0380bf18f2fde03c
+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": 3.465808619791667,
+    "train_runtime": 8159.563,
+    "train_samples_per_second": 36.767,
+    "train_steps_per_second": 1.149
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 3.464627265930176,
+  "best_model_checkpoint": "clip-roberta-100k/checkpoint-3125",
+  "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": 3.467,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 3.4658,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.2e-05,
+      "loss": 3.4658,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 3.4657,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 3.4657,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 3.4657,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.464627265930176,
+      "eval_runtime": 112.6897,
+      "eval_samples_per_second": 88.739,
+      "eval_steps_per_second": 2.778,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 3.4657,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 3.4657,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 3.4657,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 3.4658,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 3.4657,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.8e-05,
+      "loss": 3.4658,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.464627265930176,
+      "eval_runtime": 112.4973,
+      "eval_samples_per_second": 88.891,
+      "eval_steps_per_second": 2.782,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 3.4657,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 3.4657,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 3.4657,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 3.4657,
+      "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 3.4657,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.4657,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.464627265930176,
+      "eval_runtime": 112.9817,
+      "eval_samples_per_second": 88.51,
+      "eval_steps_per_second": 2.77,
+      "step": 9375
+    },
+    {
+      "epoch": 3.0,
+      "step": 9375,
+      "total_flos": 4.0055184e+16,
+      "train_loss": 3.465808619791667,
+      "train_runtime": 8159.563,
+      "train_samples_per_second": 36.767,
+      "train_steps_per_second": 1.149
+    }
+  ],
+  "max_steps": 9375,
+  "num_train_epochs": 3,
+  "total_flos": 4.0055184e+16,
+  "trial_name": null,
+  "trial_params": null
+}