End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # pt
 
 This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0905
 
 ## Model description
 

all_results.json

@@ -1,8 +1,12 @@
 {
     "epoch": 30.0,
+    "eval_loss": 0.0905422493815422,
+    "eval_runtime": 0.5259,
+    "eval_samples_per_second": 115.992,
+    "eval_steps_per_second": 7.606,
     "total_flos": 1305922815073800.0,
-    "train_loss": 1.2748958587646484,
-    "train_runtime": 114.0949,
-    "train_samples_per_second": 63.631,
-    "train_steps_per_second": 1.052
+    "train_loss": 1.105910873413086,
+    "train_runtime": 168.9398,
+    "train_samples_per_second": 42.974,
+    "train_steps_per_second": 1.421
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 0.0905422493815422,
+    "eval_runtime": 0.5259,
+    "eval_samples_per_second": 115.992,
+    "eval_steps_per_second": 7.606
+}

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

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
     "total_flos": 1305922815073800.0,
-    "train_loss": 1.2748958587646484,
-    "train_runtime": 114.0949,
-    "train_samples_per_second": 63.631,
-    "train_steps_per_second": 1.052
+    "train_loss": 1.105910873413086,
+    "train_runtime": 168.9398,
+    "train_samples_per_second": 42.974,
+    "train_steps_per_second": 1.421
 }

trainer_state.json

@@ -3,23 +3,23 @@
   "best_model_checkpoint": null,
   "epoch": 30.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 30.0,
-      "step": 120,
+      "step": 240,
       "total_flos": 1305922815073800.0,
-      "train_loss": 1.2748958587646484,
-      "train_runtime": 114.0949,
-      "train_samples_per_second": 63.631,
-      "train_steps_per_second": 1.052
+      "train_loss": 1.105910873413086,
+      "train_runtime": 168.9398,
+      "train_samples_per_second": 42.974,
+      "train_steps_per_second": 1.421
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
+  "max_steps": 240,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 500,
@@ -36,7 +36,7 @@
     }
   },
   "total_flos": 1305922815073800.0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }