End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- coco_dataset_script
+- ydshieh/coco_dataset_script
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model was trained from scratch on the coco_dataset_script dataset.
+This model was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5655
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.5824697017669678,
-    "eval_runtime": 43.6193,
-    "eval_samples_per_second": 573.462,
-    "eval_steps_per_second": 2.247,
-    "train_loss": 0.3156686747637862,
-    "train_runtime": 5245.2618,
-    "train_samples_per_second": 338.45,
-    "train_steps_per_second": 1.322
+    "eval_loss": 1.5654611587524414,
+    "eval_runtime": 22.7529,
+    "eval_samples_per_second": 1099.377,
+    "eval_steps_per_second": 2.154,
+    "train_loss": 0.31381386621600615,
+    "train_runtime": 2692.8552,
+    "train_samples_per_second": 659.248,
+    "train_steps_per_second": 1.288
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.5824697017669678,
-    "eval_runtime": 43.6193,
-    "eval_samples_per_second": 573.462,
-    "eval_steps_per_second": 2.247
+    "eval_loss": 1.5654611587524414,
+    "eval_runtime": 22.7529,
+    "eval_samples_per_second": 1099.377,
+    "eval_steps_per_second": 2.154
 }

runs/Feb12_18-25-46_28fc6ffbaa77/events.out.tfevents.1707765211.28fc6ffbaa77.4275.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e3771d04fd0a366483fcde57ee02e6f32df88f6fd84078ca4acf3abcd48b9f
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.3156686747637862,
-    "train_runtime": 5245.2618,
-    "train_samples_per_second": 338.45,
-    "train_steps_per_second": 1.322
+    "train_loss": 0.31381386621600615,
+    "train_runtime": 2692.8552,
+    "train_samples_per_second": 659.248,
+    "train_steps_per_second": 1.288
 }

trainer_state.json

@@ -3,101 +3,59 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 6936,
+  "global_step": 3468,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.22,
-      "learning_rate": 4.639561707035756e-05,
-      "loss": 0.9035,
-      "step": 500
-    },
     {
       "epoch": 0.43,
       "learning_rate": 4.2791234140715114e-05,
-      "loss": 0.5166,
-      "step": 1000
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 3.9186851211072664e-05,
-      "loss": 0.4342,
-      "step": 1500
+      "loss": 0.725,
+      "step": 500
     },
     {
       "epoch": 0.87,
       "learning_rate": 3.558246828143022e-05,
-      "loss": 0.3862,
-      "step": 2000
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 3.1978085351787776e-05,
-      "loss": 0.3272,
-      "step": 2500
+      "loss": 0.3879,
+      "step": 1000
     },
     {
       "epoch": 1.3,
       "learning_rate": 2.8373702422145332e-05,
-      "loss": 0.2757,
-      "step": 3000
-    },
-    {
-      "epoch": 1.51,
-      "learning_rate": 2.4769319492502884e-05,
-      "loss": 0.2623,
-      "step": 3500
+      "loss": 0.2897,
+      "step": 1500
     },
     {
       "epoch": 1.73,
       "learning_rate": 2.116493656286044e-05,
-      "loss": 0.2416,
-      "step": 4000
-    },
-    {
-      "epoch": 1.95,
-      "learning_rate": 1.7560553633217993e-05,
-      "loss": 0.2301,
-      "step": 4500
+      "loss": 0.2463,
+      "step": 2000
     },
     {
       "epoch": 2.16,
       "learning_rate": 1.395617070357555e-05,
-      "loss": 0.1858,
-      "step": 5000
-    },
-    {
-      "epoch": 2.38,
-      "learning_rate": 1.0351787773933102e-05,
-      "loss": 0.1698,
-      "step": 5500
+      "loss": 0.2074,
+      "step": 2500
     },
     {
       "epoch": 2.6,
       "learning_rate": 6.747404844290659e-06,
-      "loss": 0.1611,
-      "step": 6000
-    },
-    {
-      "epoch": 2.81,
-      "learning_rate": 3.143021914648212e-06,
-      "loss": 0.1545,
-      "step": 6500
+      "loss": 0.1688,
+      "step": 3000
     },
     {
       "epoch": 3.0,
-      "step": 6936,
+      "step": 3468,
       "total_flos": 2.370754172808069e+17,
-      "train_loss": 0.3156686747637862,
-      "train_runtime": 5245.2618,
-      "train_samples_per_second": 338.45,
-      "train_steps_per_second": 1.322
+      "train_loss": 0.31381386621600615,
+      "train_runtime": 2692.8552,
+      "train_samples_per_second": 659.248,
+      "train_steps_per_second": 1.288
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6936,
+  "max_steps": 3468,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,