Training in progress, epoch 0

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 0.96,
-    "eval_accuracy": 0.78,
-    "eval_f1": 0.7285479916951179,
-    "eval_loss": 3.062906503677368,
-    "eval_runtime": 1.551,
-    "eval_samples_per_second": 32.237,
-    "eval_steps_per_second": 4.513,
-    "train_loss": 3.5844920873641968,
-    "train_runtime": 75.7789,
-    "train_samples_per_second": 5.239,
-    "train_steps_per_second": 0.158
+    "epoch": 0.92,
+    "eval_accuracy": 0.6923076923076923,
+    "eval_f1": 0.40909090909090906,
+    "eval_loss": 2.1946330070495605,
+    "eval_runtime": 1.6106,
+    "eval_samples_per_second": 16.143,
+    "eval_steps_per_second": 2.484,
+    "train_loss": 3.3007516860961914,
+    "train_runtime": 38.8385,
+    "train_samples_per_second": 5.201,
+    "train_steps_per_second": 0.154
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "eval_accuracy": 0.78,
-    "eval_f1": 0.7285479916951179,
-    "eval_loss": 3.062906503677368,
-    "eval_runtime": 1.551,
-    "eval_samples_per_second": 32.237,
-    "eval_steps_per_second": 4.513
+    "eval_accuracy": 0.6923076923076923,
+    "eval_f1": 0.40909090909090906,
+    "eval_loss": 2.1946330070495605,
+    "eval_runtime": 1.6106,
+    "eval_samples_per_second": 16.143,
+    "eval_steps_per_second": 2.484
 }

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 0.96,
-    "train_loss": 3.5844920873641968,
-    "train_runtime": 75.7789,
-    "train_samples_per_second": 5.239,
-    "train_steps_per_second": 0.158
+    "epoch": 0.92,
+    "train_loss": 3.3007516860961914,
+    "train_runtime": 38.8385,
+    "train_samples_per_second": 5.201,
+    "train_steps_per_second": 0.154
 }

trainer_state.json

@@ -1,41 +1,35 @@
 {
-  "best_metric": 0.76,
-  "best_model_checkpoint": "convnext/checkpoint-12",
-  "epoch": 0.96,
+  "best_metric": 0.68,
+  "best_model_checkpoint": "convnext/checkpoint-6",
+  "epoch": 0.9230769230769231,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
-      "learning_rate": 0.0001,
-      "loss": 3.6602,
-      "step": 10
+      "epoch": 0.92,
+      "eval_accuracy": 0.68,
+      "eval_f1": 0.40476190476190477,
+      "eval_loss": 2.135345935821533,
+      "eval_runtime": 3.511,
+      "eval_samples_per_second": 7.12,
+      "eval_steps_per_second": 1.139,
+      "step": 6
     },
     {
-      "epoch": 0.96,
-      "eval_accuracy": 0.76,
-      "eval_f1": 0.7543106131341425,
-      "eval_loss": 3.08089017868042,
-      "eval_runtime": 2.178,
-      "eval_samples_per_second": 22.957,
-      "eval_steps_per_second": 3.214,
-      "step": 12
-    },
-    {
-      "epoch": 0.96,
-      "step": 12,
+      "epoch": 0.92,
+      "step": 6,
       "total_flos": 0.0,
-      "train_loss": 3.5844920873641968,
-      "train_runtime": 75.7789,
-      "train_samples_per_second": 5.239,
-      "train_steps_per_second": 0.158
+      "train_loss": 3.3007516860961914,
+      "train_runtime": 38.8385,
+      "train_samples_per_second": 5.201,
+      "train_steps_per_second": 0.154
     }
   ],
   "logging_steps": 10,
-  "max_steps": 12,
+  "max_steps": 6,
   "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908a060e4bf217c1550fa07c16f5e2213522a75fa50b925e0edcbb5f8e9c81ef
+oid sha256:646e4e2b8a299f0c95adb8e59dc44753490bfc893f30471602f43c2a5305dcdc
 size 4472