Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.88,
-    "total_flos": 5.789887959505306e+16,
-    "train_loss": 1.4178554217020671,
-    "train_runtime": 455.1681,
-    "train_samples_per_second": 5.273,
-    "train_steps_per_second": 0.04
+    "total_flos": 1.1579775919010611e+17,
+    "train_loss": 1.2937633593877156,
+    "train_runtime": 628.6336,
+    "train_samples_per_second": 7.636,
+    "train_steps_per_second": 0.057
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2188532756fdce4ae398a2f9595dd39c5a2fa7cc7cdffaa384cd5047a550262
+oid sha256:f62ecc5f8341c0e3e82750d58146915ee8f55de895f9035ca523f4fca990a2a2
 size 111317164

runs/Aug19_11-15-29_6801bce4c4b3/events.out.tfevents.1724066883.6801bce4c4b3.1808.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01219911e81cc12c95825ef21b9e8001f2611093602e8e16b671f4ff4eab71e
+size 404

runs/Aug19_11-29-30_6801bce4c4b3/events.out.tfevents.1724066979.6801bce4c4b3.1808.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c15727453ff8039df0fcc57f7d1c298858c4b3c2204337c2d998a6ab88ef8e
+size 6047

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.88,
-    "total_flos": 5.789887959505306e+16,
-    "train_loss": 1.4178554217020671,
-    "train_runtime": 455.1681,
-    "train_samples_per_second": 5.273,
-    "train_steps_per_second": 0.04
+    "total_flos": 1.1579775919010611e+17,
+    "train_loss": 1.2937633593877156,
+    "train_runtime": 628.6336,
+    "train_samples_per_second": 7.636,
+    "train_steps_per_second": 0.057
 }

trainer_state.json

@@ -1,68 +1,82 @@
 {
-  "best_metric": 1.3130167722702026,
-  "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-18",
+  "best_metric": 1.1360527276992798,
+  "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-36",
   "epoch": 2.88,
   "eval_steps": 500,
-  "global_step": 18,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.1323318481445312,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 1.5112,
+      "step": 10
+    },
     {
       "epoch": 0.96,
       "eval_accuracy": {
-        "accuracy": 0.42
+        "accuracy": 0.4525
       },
-      "eval_logLoss": 1.4662960767745972,
-      "eval_loss": 1.4662964344024658,
-      "eval_runtime": 71.93,
-      "eval_samples_per_second": 2.78,
-      "eval_steps_per_second": 0.097,
-      "step": 6
+      "eval_logLoss": 1.3027347326278687,
+      "eval_loss": 1.3027344942092896,
+      "eval_runtime": 97.0576,
+      "eval_samples_per_second": 4.121,
+      "eval_steps_per_second": 0.134,
+      "step": 12
     },
     {
       "epoch": 1.6,
-      "grad_norm": 2.0363504886627197,
+      "grad_norm": 1.6718777418136597,
       "learning_rate": 2.5e-05,
-      "loss": 1.4937,
-      "step": 10
+      "loss": 1.278,
+      "step": 20
     },
     {
-      "epoch": 1.92,
+      "epoch": 2.0,
       "eval_accuracy": {
-        "accuracy": 0.445
+        "accuracy": 0.51
       },
-      "eval_logLoss": 1.3507485389709473,
-      "eval_loss": 1.3507485389709473,
-      "eval_runtime": 4.9957,
-      "eval_samples_per_second": 40.034,
-      "eval_steps_per_second": 1.401,
-      "step": 12
+      "eval_logLoss": 1.161118984222412,
+      "eval_loss": 1.161118984222412,
+      "eval_runtime": 9.8941,
+      "eval_samples_per_second": 40.428,
+      "eval_steps_per_second": 1.314,
+      "step": 25
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.342809796333313,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.18,
+      "step": 30
     },
     {
       "epoch": 2.88,
       "eval_accuracy": {
-        "accuracy": 0.43
+        "accuracy": 0.52
       },
-      "eval_logLoss": 1.3130167722702026,
-      "eval_loss": 1.3130167722702026,
-      "eval_runtime": 6.5823,
-      "eval_samples_per_second": 30.385,
-      "eval_steps_per_second": 1.063,
-      "step": 18
+      "eval_logLoss": 1.1360526084899902,
+      "eval_loss": 1.1360527276992798,
+      "eval_runtime": 11.1011,
+      "eval_samples_per_second": 36.033,
+      "eval_steps_per_second": 1.171,
+      "step": 36
     },
     {
       "epoch": 2.88,
-      "step": 18,
-      "total_flos": 5.789887959505306e+16,
-      "train_loss": 1.4178554217020671,
-      "train_runtime": 455.1681,
-      "train_samples_per_second": 5.273,
-      "train_steps_per_second": 0.04
+      "step": 36,
+      "total_flos": 1.1579775919010611e+17,
+      "train_loss": 1.2937633593877156,
+      "train_runtime": 628.6336,
+      "train_samples_per_second": 7.636,
+      "train_steps_per_second": 0.057
     }
   ],
   "logging_steps": 10,
-  "max_steps": 18,
+  "max_steps": 36,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -78,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.789887959505306e+16,
+  "total_flos": 1.1579775919010611e+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:b21473a72cb2c10232c58d5d4dfd554255cb3e73168fb1ed2a381bd5ac0fd6b5
+oid sha256:3ebabc1689913ed01c06d9f70c768efb64b111b87c4d7cf605d87a2d50ecf3e5
 size 5176