Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.22972972972973,
-    "eval_accuracy": 0.5942028985507246,
-    "eval_loss": 0.7709811925888062,
-    "eval_runtime": 203.3655,
-    "eval_samples_per_second": 0.339,
-    "eval_steps_per_second": 0.089
+    "eval_accuracy": 0.6956521739130435,
+    "eval_loss": 0.6255780458450317,
+    "eval_runtime": 237.0624,
+    "eval_samples_per_second": 0.291,
+    "eval_steps_per_second": 0.076
 }

config.json

@@ -12,14 +12,14 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "carve-frontside",
+    "0": "cutback-frontside",
     "1": "roller"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "carve-frontside": 0,
+    "cutback-frontside": 0,
     "roller": 1
   },
   "layer_norm_eps": 1e-12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7518d6f5c6ab323ca814cc3a5df1affbf3f83a2b47d310e7fea987ecfaacc291
+oid sha256:8e740027589c2af09dc7b9a04424082467d598d1cf580ef053dd1e9ad9ad5080
 size 344937368

runs/May13_19-31-28_MSI/events.out.tfevents.1715627469.MSI.14116.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c48516203612434be6979e5dcbc952f402203093a8fcfb87b67c9a6967af98c
-size 411
+oid sha256:8505e70c366220741f4e09e37a5ec1829cf9384d811b366f408a66c035ad2c43
+size 1703

runs/May13_23-09-51_MSI/events.out.tfevents.1715634595.MSI.14116.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f0087eea08db8608341b5c755d19a485afbde807aecd6c2430edfc8358ffef
+size 4948

runs/May13_23-30-50_MSI/events.out.tfevents.1715635853.MSI.30180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75636ba592dbc97ac1b3a1bc51c9c71b84d62d6b87d7935c2ad8812e65c65ec
+size 4947

runs/May14_11-21-18_MSI/events.out.tfevents.1715678481.MSI.18796.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00be69255b6bcec18c4d6d38f50b94c70de23628605f7fe40ec33467de6df78
+size 4947

runs/May16_18-48-25_MSI/events.out.tfevents.1715878108.MSI.19764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa70203df4fa0c850965c9e5e1aed629e3d9dab7e497691a918736c315fce1e9
+size 4951

runs/May16_18-51-17_MSI/events.out.tfevents.1715878279.MSI.19764.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dccba6dc590aa794dc22c13dc73931497d3da95ce9afac67fca04446a8e58ee
+size 4951

runs/May16_18-59-46_MSI/events.out.tfevents.1715878788.MSI.22228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e511375ef359c8e8f9e80910bad2351425322a4deef23e4f5ae4a778cc05a35
+size 5887

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.22972972972973,
-    "eval_accuracy": 0.5942028985507246,
-    "eval_loss": 0.7709811925888062,
-    "eval_runtime": 203.3655,
-    "eval_samples_per_second": 0.339,
-    "eval_steps_per_second": 0.089
+    "eval_accuracy": 0.6956521739130435,
+    "eval_loss": 0.6255780458450317,
+    "eval_runtime": 237.0624,
+    "eval_samples_per_second": 0.291,
+    "eval_steps_per_second": 0.076
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6181818181818182,
-  "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-76",
+  "best_metric": 0.6727272727272727,
+  "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-114",
   "epoch": 3.22972972972973,
   "eval_steps": 500,
   "global_step": 148,
@@ -10,163 +10,163 @@
   "log_history": [
     {
       "epoch": 0.06756756756756757,
-      "grad_norm": 16.52984046936035,
+      "grad_norm": 10.621135711669922,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 4.2404,
+      "loss": 0.7046,
       "step": 10
     },
     {
       "epoch": 0.13513513513513514,
-      "grad_norm": 10.275276184082031,
+      "grad_norm": 15.56004524230957,
       "learning_rate": 4.81203007518797e-05,
-      "loss": 2.1932,
+      "loss": 0.6959,
       "step": 20
     },
     {
       "epoch": 0.20270270270270271,
-      "grad_norm": 6.553492069244385,
+      "grad_norm": 12.019503593444824,
       "learning_rate": 4.43609022556391e-05,
-      "loss": 1.0024,
+      "loss": 0.6924,
       "step": 30
     },
     {
       "epoch": 0.25675675675675674,
-      "eval_accuracy": 0.6,
-      "eval_loss": 0.8335393667221069,
-      "eval_runtime": 202.228,
-      "eval_samples_per_second": 0.272,
-      "eval_steps_per_second": 0.069,
+      "eval_accuracy": 0.5454545454545454,
+      "eval_loss": 0.6671423316001892,
+      "eval_runtime": 167.6467,
+      "eval_samples_per_second": 0.328,
+      "eval_steps_per_second": 0.084,
       "step": 38
     },
     {
       "epoch": 1.0135135135135136,
-      "grad_norm": 5.992822170257568,
+      "grad_norm": 5.8651123046875,
       "learning_rate": 4.0601503759398494e-05,
-      "loss": 0.9484,
+      "loss": 0.7766,
       "step": 40
     },
     {
       "epoch": 1.0810810810810811,
-      "grad_norm": 4.172947406768799,
+      "grad_norm": 4.48609733581543,
       "learning_rate": 3.6842105263157895e-05,
-      "loss": 0.8423,
+      "loss": 0.7431,
       "step": 50
     },
     {
       "epoch": 1.1486486486486487,
-      "grad_norm": 8.419867515563965,
+      "grad_norm": 17.070894241333008,
       "learning_rate": 3.3082706766917295e-05,
-      "loss": 0.7835,
+      "loss": 0.7388,
       "step": 60
     },
     {
       "epoch": 1.2162162162162162,
-      "grad_norm": 6.0131940841674805,
+      "grad_norm": 5.109278678894043,
       "learning_rate": 2.9323308270676693e-05,
-      "loss": 0.733,
+      "loss": 0.6664,
       "step": 70
     },
     {
       "epoch": 1.2567567567567568,
       "eval_accuracy": 0.6181818181818182,
-      "eval_loss": 0.7877511978149414,
-      "eval_runtime": 181.8111,
-      "eval_samples_per_second": 0.303,
-      "eval_steps_per_second": 0.077,
+      "eval_loss": 0.6748194694519043,
+      "eval_runtime": 170.038,
+      "eval_samples_per_second": 0.323,
+      "eval_steps_per_second": 0.082,
       "step": 76
     },
     {
       "epoch": 2.027027027027027,
-      "grad_norm": 11.416802406311035,
+      "grad_norm": 8.704899787902832,
       "learning_rate": 2.556390977443609e-05,
-      "loss": 0.8287,
+      "loss": 0.7082,
       "step": 80
     },
     {
       "epoch": 2.0945945945945947,
-      "grad_norm": 8.970609664916992,
+      "grad_norm": 7.929505825042725,
       "learning_rate": 2.1804511278195487e-05,
-      "loss": 0.6822,
+      "loss": 0.6429,
       "step": 90
     },
     {
       "epoch": 2.1621621621621623,
-      "grad_norm": 20.559356689453125,
+      "grad_norm": 17.118267059326172,
       "learning_rate": 1.8045112781954888e-05,
-      "loss": 0.8237,
+      "loss": 0.8039,
       "step": 100
     },
     {
       "epoch": 2.22972972972973,
-      "grad_norm": 9.306185722351074,
+      "grad_norm": 7.988255500793457,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.704,
+      "loss": 0.5947,
       "step": 110
     },
     {
       "epoch": 2.2567567567567566,
-      "eval_accuracy": 0.6181818181818182,
-      "eval_loss": 0.8107306957244873,
-      "eval_runtime": 178.6821,
-      "eval_samples_per_second": 0.308,
-      "eval_steps_per_second": 0.078,
+      "eval_accuracy": 0.6727272727272727,
+      "eval_loss": 0.6094833612442017,
+      "eval_runtime": 168.4773,
+      "eval_samples_per_second": 0.326,
+      "eval_steps_per_second": 0.083,
       "step": 114
     },
     {
       "epoch": 3.0405405405405403,
-      "grad_norm": 10.595173835754395,
+      "grad_norm": 7.859794616699219,
       "learning_rate": 1.0526315789473684e-05,
-      "loss": 0.8146,
+      "loss": 0.5892,
       "step": 120
     },
     {
       "epoch": 3.108108108108108,
-      "grad_norm": 13.952937126159668,
+      "grad_norm": 12.87205982208252,
       "learning_rate": 6.766917293233083e-06,
-      "loss": 0.6075,
+      "loss": 0.5001,
       "step": 130
     },
     {
       "epoch": 3.175675675675676,
-      "grad_norm": 14.456306457519531,
+      "grad_norm": 13.842416763305664,
       "learning_rate": 3.007518796992481e-06,
-      "loss": 0.5661,
+      "loss": 0.5049,
       "step": 140
     },
     {
       "epoch": 3.22972972972973,
       "eval_accuracy": 0.6181818181818182,
-      "eval_loss": 0.7859958410263062,
-      "eval_runtime": 168.8621,
-      "eval_samples_per_second": 0.326,
-      "eval_steps_per_second": 0.083,
+      "eval_loss": 0.6914771199226379,
+      "eval_runtime": 166.1396,
+      "eval_samples_per_second": 0.331,
+      "eval_steps_per_second": 0.084,
       "step": 148
     },
     {
       "epoch": 3.22972972972973,
       "step": 148,
-      "total_flos": 7.270063395179397e+17,
-      "train_loss": 1.1026684142447807,
-      "train_runtime": 5645.231,
-      "train_samples_per_second": 0.105,
-      "train_steps_per_second": 0.026
+      "total_flos": 7.264556556620268e+17,
+      "train_loss": 0.6650454998016357,
+      "train_runtime": 4992.096,
+      "train_samples_per_second": 0.119,
+      "train_steps_per_second": 0.03
     },
     {
       "epoch": 3.22972972972973,
-      "eval_accuracy": 0.5942028985507246,
-      "eval_loss": 0.7709812521934509,
-      "eval_runtime": 248.4709,
-      "eval_samples_per_second": 0.278,
-      "eval_steps_per_second": 0.072,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.6255781054496765,
+      "eval_runtime": 189.5334,
+      "eval_samples_per_second": 0.364,
+      "eval_steps_per_second": 0.095,
       "step": 148
     },
     {
       "epoch": 3.22972972972973,
-      "eval_accuracy": 0.5942028985507246,
-      "eval_loss": 0.7709811925888062,
-      "eval_runtime": 203.3655,
-      "eval_samples_per_second": 0.339,
-      "eval_steps_per_second": 0.089,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.6255780458450317,
+      "eval_runtime": 237.0624,
+      "eval_samples_per_second": 0.291,
+      "eval_steps_per_second": 0.076,
       "step": 148
     }
   ],
@@ -175,7 +175,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 500,
-  "total_flos": 7.270063395179397e+17,
+  "total_flos": 7.264556556620268e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43654f961aef1e5dd1068a7d3b8fa50ac16eb42e41c0e7feac21eb0f47247ad3
+oid sha256:498bb098c9e8befc320966c8d6858e42030b47f82ab4d7282188f2c749102de0
 size 4984