End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # clip-finetuned
 
 This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5183
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.417513132095337,
-    "eval_runtime": 2.2084,
-    "eval_samples_per_second": 19.018,
-    "eval_steps_per_second": 0.906,
-    "test_loss": 3.6892688274383545,
-    "test_runtime": 0.9331,
-    "test_samples_per_second": 90.022,
-    "test_steps_per_second": 3.215,
-    "train_loss": 1.472021484375,
-    "train_runtime": 106.3445,
-    "train_samples_per_second": 31.878,
-    "train_steps_per_second": 1.034
+    "eval_loss": 3.5183489322662354,
+    "eval_runtime": 2.3671,
+    "eval_samples_per_second": 21.546,
+    "eval_steps_per_second": 0.845,
+    "test_loss": 3.517756462097168,
+    "test_runtime": 1.5745,
+    "test_samples_per_second": 64.781,
+    "test_steps_per_second": 2.54,
+    "train_loss": 1.2736186100886417,
+    "train_runtime": 133.9465,
+    "train_samples_per_second": 30.684,
+    "train_steps_per_second": 0.971
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.417513132095337,
-    "eval_runtime": 2.2084,
-    "eval_samples_per_second": 19.018,
-    "eval_steps_per_second": 0.906
+    "eval_loss": 3.5183489322662354,
+    "eval_runtime": 2.3671,
+    "eval_samples_per_second": 21.546,
+    "eval_steps_per_second": 0.845
 }

test_results.json

@@ -1,6 +1,6 @@
 {
-    "test_loss": 3.6892688274383545,
-    "test_runtime": 0.9331,
-    "test_samples_per_second": 90.022,
-    "test_steps_per_second": 3.215
+    "test_loss": 3.517756462097168,
+    "test_runtime": 1.5745,
+    "test_samples_per_second": 64.781,
+    "test_steps_per_second": 2.54
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 77,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 77
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 49407,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 49406,

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "train_loss": 1.472021484375,
-    "train_runtime": 106.3445,
-    "train_samples_per_second": 31.878,
-    "train_steps_per_second": 1.034
+    "train_loss": 1.2736186100886417,
+    "train_runtime": 133.9465,
+    "train_samples_per_second": 30.684,
+    "train_steps_per_second": 0.971
 }

trainer_state.json

@@ -3,27 +3,27 @@
   "best_model_checkpoint": null,
   "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 110,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 10.0,
-      "step": 110,
-      "total_flos": 197186123104740.0,
-      "train_loss": 1.472021484375,
-      "train_runtime": 106.3445,
-      "train_samples_per_second": 31.878,
-      "train_steps_per_second": 1.034
+      "step": 130,
+      "total_flos": 239066361640260.0,
+      "train_loss": 1.2736186100886417,
+      "train_runtime": 133.9465,
+      "train_samples_per_second": 30.684,
+      "train_steps_per_second": 0.971
     }
   ],
   "logging_steps": 500,
-  "max_steps": 110,
+  "max_steps": 130,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 197186123104740.0,
+  "total_flos": 239066361640260.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null