Model save

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- ydshieh/coco_dataset_script
+- coco_dataset_script
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -13,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5877
+This model was trained from scratch on the coco_dataset_script dataset.
 
 ## Model description
 
@@ -44,7 +42,7 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 1
 
 ### Training results
 
@@ -54,5 +52,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.38.0.dev0
 - Pytorch 2.0.1+gita61a294
-- Datasets 2.17.0
+- Datasets 2.17.1
 - Tokenizers 0.15.2

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 5.0,
-    "eval_loss": 1.587681531906128,
-    "eval_runtime": 22.6452,
-    "eval_samples_per_second": 1104.605,
-    "eval_steps_per_second": 2.164,
-    "train_loss": 0.24804650540995352,
-    "train_runtime": 4511.4291,
-    "train_samples_per_second": 655.838,
-    "train_steps_per_second": 1.281
+    "epoch": 1.0,
+    "eval_loss": 4.245348930358887,
+    "eval_runtime": 23.2323,
+    "eval_samples_per_second": 1076.693,
+    "eval_steps_per_second": 2.109,
+    "train_loss": 4.222018241882324,
+    "train_runtime": 2.6838,
+    "train_samples_per_second": 37.261,
+    "train_steps_per_second": 0.373
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 5.0,
-    "eval_loss": 1.587681531906128,
-    "eval_runtime": 22.6452,
-    "eval_samples_per_second": 1104.605,
-    "eval_steps_per_second": 2.164
+    "epoch": 1.0,
+    "eval_loss": 4.245348930358887,
+    "eval_runtime": 23.2323,
+    "eval_samples_per_second": 1076.693,
+    "eval_steps_per_second": 2.109
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647327dd1e7ab36b8309aef5689b6c55d0ee312364ebb486faaae029e6b7ce77
+oid sha256:585e472774472feb8b26fc756ac99bf8c6adabec9f1333f3026e66d6752ad93b
 size 851603588

runs/Feb20_01-55-59_b2d203f0f1d0/events.out.tfevents.1708394230.b2d203f0f1d0.4134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25954e7e6ea72fcdfc2f0557426e440f5160b0a8ef2fa801aef0660fbc4f49ab
+size 8516

runs/Feb20_02-04-16_b2d203f0f1d0/events.out.tfevents.1708394669.b2d203f0f1d0.4412.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551cb63bf724c3ed85e9d85e50183fb3927fc067b964db71e2be5040e035c56e
+size 8516

runs/Feb20_04-04-22_b2d203f0f1d0/events.out.tfevents.1708401867.b2d203f0f1d0.5056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54be8f1ccbc2917726e0a85ae071329e5387733b6f70438dcd825b831007365
+size 8503

runs/Feb20_04-35-08_b2d203f0f1d0/events.out.tfevents.1708403713.b2d203f0f1d0.5278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e28a02bbd4caf67604a600a69b236189c30b6aae7f49c310a4427b92f362eb
+size 8502

runs/Feb20_04-38-45_b2d203f0f1d0/events.out.tfevents.1708403930.b2d203f0f1d0.5381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc8d14de0e9dda35f028c2bddb8acfe3776a57f3967b6cc2e17134aec81f5fe
+size 8503

runs/Feb20_04-39-27_b2d203f0f1d0/events.out.tfevents.1708403972.b2d203f0f1d0.5474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07b50d5ac0977ed794507ef8bbc0369a8576084ce51e359584614f8026423d5
+size 8503

runs/Feb20_04-40-22_b2d203f0f1d0/events.out.tfevents.1708404027.b2d203f0f1d0.5563.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5b6780a44417e226f0aa2eb23c5221c4c242e6e41793aaa4db888da197ff3a
+size 9558

runs/Feb20_05-23-50_35c5cc03ccf3/events.out.tfevents.1708406724.35c5cc03ccf3.1893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e16abe3f452600e3b53c349c985e7b2d95bd958790fd18fa8b731d64e467c3
+size 8727

runs/Feb20_05-37-26_35c5cc03ccf3/events.out.tfevents.1708407454.35c5cc03ccf3.10573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88947bc353eb7b0bc168961de051d21eec229ca8afa2e0b92425eb788ff00564
+size 8864

runs/Feb20_05-37-26_35c5cc03ccf3/events.out.tfevents.1708407490.35c5cc03ccf3.10573.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52eacb8dc598230538a39fe07f94ad80ddbe4d3f5cd4f05a5ca21fa8cbd62310
+size 354

runs/Feb20_05-48-07_35c5cc03ccf3/events.out.tfevents.1708408093.35c5cc03ccf3.12717.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca6249e9d415ab8e4f265d60ec3a3e6002c3e89ddd9687044d552761c8f2775
+size 8863

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 5.0,
-    "train_loss": 0.24804650540995352,
-    "train_runtime": 4511.4291,
-    "train_samples_per_second": 655.838,
-    "train_steps_per_second": 1.281
+    "epoch": 1.0,
+    "train_loss": 4.222018241882324,
+    "train_runtime": 2.6838,
+    "train_samples_per_second": 37.261,
+    "train_steps_per_second": 0.373
 }

trainer_state.json

@@ -1,95 +1,29 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 5780,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.43,
-      "learning_rate": 4.567474048442907e-05,
-      "loss": 0.7182,
-      "step": 500
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 4.134948096885813e-05,
-      "loss": 0.393,
-      "step": 1000
-    },
-    {
-      "epoch": 1.3,
-      "learning_rate": 3.70242214532872e-05,
-      "loss": 0.3001,
-      "step": 1500
-    },
-    {
-      "epoch": 1.73,
-      "learning_rate": 3.269896193771627e-05,
-      "loss": 0.2633,
-      "step": 2000
-    },
-    {
-      "epoch": 2.16,
-      "learning_rate": 2.8373702422145332e-05,
-      "loss": 0.2275,
-      "step": 2500
-    },
-    {
-      "epoch": 2.6,
-      "learning_rate": 2.4048442906574396e-05,
-      "loss": 0.1934,
-      "step": 3000
-    },
-    {
-      "epoch": 3.03,
-      "learning_rate": 1.972318339100346e-05,
-      "loss": 0.1841,
-      "step": 3500
-    },
-    {
-      "epoch": 3.46,
-      "learning_rate": 1.5397923875432525e-05,
-      "loss": 0.1484,
-      "step": 4000
-    },
-    {
-      "epoch": 3.89,
-      "learning_rate": 1.1072664359861593e-05,
-      "loss": 0.1445,
-      "step": 4500
-    },
-    {
-      "epoch": 4.33,
-      "learning_rate": 6.747404844290659e-06,
-      "loss": 0.1217,
-      "step": 5000
-    },
-    {
-      "epoch": 4.76,
-      "learning_rate": 2.4221453287197232e-06,
-      "loss": 0.113,
-      "step": 5500
-    },
-    {
-      "epoch": 5.0,
-      "step": 5780,
-      "total_flos": 3.951256954680115e+17,
-      "train_loss": 0.24804650540995352,
-      "train_runtime": 4511.4291,
-      "train_samples_per_second": 655.838,
-      "train_steps_per_second": 1.281
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 68360846966784.0,
+      "train_loss": 4.222018241882324,
+      "train_runtime": 2.6838,
+      "train_samples_per_second": 37.261,
+      "train_steps_per_second": 0.373
     }
   ],
   "logging_steps": 500,
-  "max_steps": 5780,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3.951256954680115e+17,
+  "total_flos": 68360846966784.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6623b37b1d356473764e5afe1b5235846f11dc42692c18f5476bc94b805ebe3
+oid sha256:a6cc5992e14fa461b474d0c2e6d76ae8e94ba01f52f2d524fae1e8e45c488fa7
 size 4475