Training in progress, epoch 0

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 1.0,
-    "eval_accuracy": 0.5833333333333334,
-    "eval_f1": 0.45324283559577677,
-    "eval_loss": 0.9569942951202393,
-    "eval_runtime": 1.7976,
-    "eval_samples_per_second": 20.027,
-    "eval_steps_per_second": 2.782,
-    "train_loss": 1.2908155653211806,
-    "train_runtime": 58.4515,
-    "train_samples_per_second": 4.91,
-    "train_steps_per_second": 0.154
+    "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
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "eval_accuracy": 0.5833333333333334,
-    "eval_f1": 0.45324283559577677,
-    "eval_loss": 0.9569942951202393,
-    "eval_runtime": 1.7976,
-    "eval_samples_per_second": 20.027,
-    "eval_steps_per_second": 2.782
+    "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
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b684e8c0256167df6b112ec69fb12a8006bd05a7d3cc88836e5e98cc8a742ce5
+oid sha256:6349acdf0bba46f03c55f21cfd4c29e4575e0a75bf40fff07104816411aa8bb1
 size 111356130

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 1.0,
-    "train_loss": 1.2908155653211806,
-    "train_runtime": 58.4515,
-    "train_samples_per_second": 4.91,
-    "train_steps_per_second": 0.154
+    "epoch": 0.96,
+    "train_loss": 3.5844920873641968,
+    "train_runtime": 75.7789,
+    "train_samples_per_second": 5.239,
+    "train_steps_per_second": 0.158
 }

trainer_state.json

@@ -1,35 +1,41 @@
 {
-  "best_metric": 0.5277777777777778,
-  "best_model_checkpoint": "convnext/checkpoint-9",
-  "epoch": 1.0,
+  "best_metric": 0.76,
+  "best_model_checkpoint": "convnext/checkpoint-12",
+  "epoch": 0.96,
   "eval_steps": 500,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5277777777777778,
-      "eval_f1": 0.37425404944586527,
-      "eval_loss": 0.9641907215118408,
-      "eval_runtime": 2.5647,
-      "eval_samples_per_second": 14.037,
-      "eval_steps_per_second": 1.95,
-      "step": 9
+      "epoch": 0.8,
+      "learning_rate": 0.0001,
+      "loss": 3.6602,
+      "step": 10
     },
     {
-      "epoch": 1.0,
-      "step": 9,
+      "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,
       "total_flos": 0.0,
-      "train_loss": 1.2908155653211806,
-      "train_runtime": 58.4515,
-      "train_samples_per_second": 4.91,
-      "train_steps_per_second": 0.154
+      "train_loss": 3.5844920873641968,
+      "train_runtime": 75.7789,
+      "train_samples_per_second": 5.239,
+      "train_steps_per_second": 0.158
     }
   ],
   "logging_steps": 10,
-  "max_steps": 9,
+  "max_steps": 12,
   "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 sha256:4fd595d05c9dac4710bc4d0b45e2caf4f19065e5f83f5d9aa3d5c11cb48b9cb4
+oid sha256:908a060e4bf217c1550fa07c16f5e2213522a75fa50b925e0edcbb5f8e9c81ef
 size 4472