Training in progress, epoch 0

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 2.77,
-    "eval_accuracy": 0.6666666666666666,
-    "eval_loss": 1.2180020809173584,
-    "eval_runtime": 1.2421,
-    "eval_samples_per_second": 70.045,
-    "eval_steps_per_second": 2.415,
-    "total_flos": 1.6971202035873792e+17,
-    "train_loss": 0.5219763120015463,
-    "train_runtime": 81.1004,
-    "train_samples_per_second": 28.668,
-    "train_steps_per_second": 0.111
+    "epoch": 4.8,
+    "total_flos": 2.898278338546483e+17,
+    "train_loss": 0.46080586115519206,
+    "train_runtime": 138.2316,
+    "train_samples_per_second": 28.033,
+    "train_steps_per_second": 0.217
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db231dcc11a001a85fddfc20f6b61369bf79f2c0c483938182d13ce192ca4861
+oid sha256:64d1ab0b5ef8761f03bab6b582212cdb697d40d360d7aa1c8037a78837f97c30
 size 343233204

runs/Mar13_07-36-15_be0be0d60671/events.out.tfevents.1710315394.be0be0d60671.34.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e9d2bafeacd1dfb37b6558115a19ae9dde9c2462422617b13acb4aced85de7
+size 5235

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.77,
-    "total_flos": 1.6971202035873792e+17,
-    "train_loss": 0.5219763120015463,
-    "train_runtime": 81.1004,
-    "train_samples_per_second": 28.668,
-    "train_steps_per_second": 0.111
+    "epoch": 4.8,
+    "total_flos": 2.898278338546483e+17,
+    "train_loss": 0.46080586115519206,
+    "train_runtime": 138.2316,
+    "train_samples_per_second": 28.033,
+    "train_steps_per_second": 0.217
 }

trainer_state.json

@@ -1,57 +1,96 @@
 {
-  "best_metric": 0.6666666666666666,
-  "best_model_checkpoint": "vit-base-patch16-224-in21k-finetunedmangodisease/checkpoint-9",
-  "epoch": 2.769230769230769,
+  "best_metric": 0.6436781609195402,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-finetunedmangodisease/checkpoint-6",
+  "epoch": 4.8,
   "eval_steps": 500,
-  "global_step": 9,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.92,
-      "eval_accuracy": 0.6091954022988506,
-      "eval_loss": 1.2354542016983032,
-      "eval_runtime": 0.8662,
-      "eval_samples_per_second": 100.435,
-      "eval_steps_per_second": 2.309,
-      "step": 3
-    },
-    {
-      "epoch": 1.85,
-      "eval_accuracy": 0.6551724137931034,
-      "eval_loss": 1.2132805585861206,
-      "eval_runtime": 0.8407,
-      "eval_samples_per_second": 103.485,
-      "eval_steps_per_second": 2.379,
+      "epoch": 0.96,
+      "eval_accuracy": 0.6436781609195402,
+      "eval_loss": 1.2097221612930298,
+      "eval_runtime": 0.8815,
+      "eval_samples_per_second": 98.69,
+      "eval_steps_per_second": 3.403,
       "step": 6
     },
     {
-      "epoch": 2.77,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_loss": 1.2124366760253906,
-      "eval_runtime": 0.8725,
-      "eval_samples_per_second": 99.71,
-      "eval_steps_per_second": 2.292,
-      "step": 9
+      "epoch": 1.6,
+      "grad_norm": 3.50262713432312,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.4195,
+      "step": 10
     },
     {
-      "epoch": 2.77,
-      "step": 9,
-      "total_flos": 1.6971202035873792e+17,
-      "train_loss": 0.5219763120015463,
-      "train_runtime": 81.1004,
-      "train_samples_per_second": 28.668,
-      "train_steps_per_second": 0.111
+      "epoch": 1.92,
+      "eval_accuracy": 0.632183908045977,
+      "eval_loss": 1.1981477737426758,
+      "eval_runtime": 0.8644,
+      "eval_samples_per_second": 100.653,
+      "eval_steps_per_second": 3.471,
+      "step": 12
+    },
+    {
+      "epoch": 2.88,
+      "eval_accuracy": 0.6436781609195402,
+      "eval_loss": 1.180879831314087,
+      "eval_runtime": 0.8615,
+      "eval_samples_per_second": 100.981,
+      "eval_steps_per_second": 3.482,
+      "step": 18
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.852848529815674,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 0.5111,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6206896551724138,
+      "eval_loss": 1.2068603038787842,
+      "eval_runtime": 0.8925,
+      "eval_samples_per_second": 97.474,
+      "eval_steps_per_second": 3.361,
+      "step": 25
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 2.1081032752990723,
+      "learning_rate": 0.0,
+      "loss": 0.4519,
+      "step": 30
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.6206896551724138,
+      "eval_loss": 1.2022522687911987,
+      "eval_runtime": 0.8651,
+      "eval_samples_per_second": 100.567,
+      "eval_steps_per_second": 3.468,
+      "step": 30
+    },
+    {
+      "epoch": 4.8,
+      "step": 30,
+      "total_flos": 2.898278338546483e+17,
+      "train_loss": 0.46080586115519206,
+      "train_runtime": 138.2316,
+      "train_samples_per_second": 28.033,
+      "train_steps_per_second": 0.217
     }
   ],
   "logging_steps": 10,
-  "max_steps": 9,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.6971202035873792e+17,
-  "train_batch_size": 64,
+  "total_flos": 2.898278338546483e+17,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb99fc52ef1a4ecbcb147d2efb413199f6e50a79192a682a76570060fc2d21e1
+oid sha256:e5786851aee98ed291dc6a39ddf072c13ab69b25debc2f02ec1409bc720947f6
 size 4984