Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.6923076923076923,
     "eval_loss": 0.6873394846916199,
     "eval_runtime": 1.5094,
     "eval_samples_per_second": 17.226,
     "eval_steps_per_second": 0.663,
-    "total_flos": 7086826637549568.0,
-    "train_loss": 0.6862780253092448,
-    "train_runtime": 87.2572,
-    "train_samples_per_second": 8.045,
-    "train_steps_per_second": 0.069
+    "total_flos": 2.362275545849856e+16,
+    "train_loss": 0.6464766740798951,
+    "train_runtime": 277.8757,
+    "train_samples_per_second": 8.421,
+    "train_steps_per_second": 0.072
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./hfmodel",
+  "_name_or_path": "microsoft/resnet-18",
   "architectures": [
     "ResNetForImageClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca31df85fd98510c6b498db935abb6402a6f046c8da18b849612d1642e9497
+oid sha256:2ae71a5cee240902541c0d471dcce4708ef5ce660d3aff8a3b045f88a0a77a4f
 size 44764336

runs/May16_15-12-00_goku2/events.out.tfevents.1715872373.goku2.4604.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a81f55791fa6dc1bae91b76f5b8b8e1b072c86328cde87b470fb7e3ff49a9e
+size 5128

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 7086826637549568.0,
-    "train_loss": 0.6862780253092448,
-    "train_runtime": 87.2572,
-    "train_samples_per_second": 8.045,
-    "train_steps_per_second": 0.069
+    "epoch": 10.0,
+    "total_flos": 2.362275545849856e+16,
+    "train_loss": 0.6464766740798951,
+    "train_runtime": 277.8757,
+    "train_samples_per_second": 8.421,
+    "train_steps_per_second": 0.072
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6923076923076923,
   "best_model_checkpoint": "resnet-18-finetuned-fraud/checkpoint-2",
-  "epoch": 3.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 6,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,46 +11,123 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6873394846916199,
-      "eval_runtime": 1.7943,
-      "eval_samples_per_second": 14.49,
-      "eval_steps_per_second": 0.557,
+      "eval_loss": 0.6821401119232178,
+      "eval_runtime": 1.7618,
+      "eval_samples_per_second": 14.757,
+      "eval_steps_per_second": 0.568,
       "step": 2
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6751973032951355,
-      "eval_runtime": 1.6274,
-      "eval_samples_per_second": 15.976,
-      "eval_steps_per_second": 0.614,
+      "eval_loss": 0.6628227829933167,
+      "eval_runtime": 1.6027,
+      "eval_samples_per_second": 16.223,
+      "eval_steps_per_second": 0.624,
       "step": 4
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.6923076923076923,
-      "eval_loss": 0.6680338382720947,
-      "eval_runtime": 1.6065,
-      "eval_samples_per_second": 16.184,
-      "eval_steps_per_second": 0.622,
+      "eval_loss": 0.6421977281570435,
+      "eval_runtime": 1.6359,
+      "eval_samples_per_second": 15.894,
+      "eval_steps_per_second": 0.611,
       "step": 6
     },
     {
-      "epoch": 3.0,
-      "step": 6,
-      "total_flos": 7086826637549568.0,
-      "train_loss": 0.6862780253092448,
-      "train_runtime": 87.2572,
-      "train_samples_per_second": 8.045,
-      "train_steps_per_second": 0.069
+      "epoch": 4.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.6217892169952393,
+      "eval_runtime": 1.6129,
+      "eval_samples_per_second": 16.12,
+      "eval_steps_per_second": 0.62,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.009413242340088,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.6696,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.6059156656265259,
+      "eval_runtime": 1.6613,
+      "eval_samples_per_second": 15.65,
+      "eval_steps_per_second": 0.602,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.5922008752822876,
+      "eval_runtime": 1.4671,
+      "eval_samples_per_second": 17.723,
+      "eval_steps_per_second": 0.682,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.5782066583633423,
+      "eval_runtime": 1.5993,
+      "eval_samples_per_second": 16.257,
+      "eval_steps_per_second": 0.625,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.5681060552597046,
+      "eval_runtime": 1.508,
+      "eval_samples_per_second": 17.242,
+      "eval_steps_per_second": 0.663,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.5619844198226929,
+      "eval_runtime": 1.6504,
+      "eval_samples_per_second": 15.754,
+      "eval_steps_per_second": 0.606,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.1605825424194336,
+      "learning_rate": 0.0,
+      "loss": 0.6234,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.5624192357063293,
+      "eval_runtime": 1.4997,
+      "eval_samples_per_second": 17.337,
+      "eval_steps_per_second": 0.667,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "step": 20,
+      "total_flos": 2.362275545849856e+16,
+      "train_loss": 0.6464766740798951,
+      "train_runtime": 277.8757,
+      "train_samples_per_second": 8.421,
+      "train_steps_per_second": 0.072
     }
   ],
   "logging_steps": 10,
-  "max_steps": 6,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 7086826637549568.0,
+  "total_flos": 2.362275545849856e+16,
   "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:a1c9438ce0ead107b64ca22a0d18d49ec750844ddba5d3926b4c64f726172a98
+oid sha256:43bf2011d4389d0100877b2d1dc641cbbf8cc9cedc1dc9a974b1d23500c819da
 size 5048