Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.4,
-    "total_flos": 9649813265842176.0,
-    "train_loss": 1.6085638999938965,
-    "train_runtime": 113.3217,
-    "train_samples_per_second": 4.236,
-    "train_steps_per_second": 0.026
+    "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bb98de4cec6cd4aa3f885b76b9cadf19cb0218f513f377cf426db773408dc5
+oid sha256:048012c5b6a8b66f7d7027c16a6f24ee4454f3b978d3aef92627434b43e4cb6c
 size 111317164

runs/Aug19_11-03-24_6801bce4c4b3/events.out.tfevents.1724065922.6801bce4c4b3.1808.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c9ba3cc9acfadf9acfe1444ebacd17185191680347698c3966823ebceb5866
+size 404

runs/Aug19_11-15-29_6801bce4c4b3/events.out.tfevents.1724066134.6801bce4c4b3.1808.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6d8b741a4436e396a6094598612da293ceb3cbbfb13edbcef2dc5afc4d0a64
+size 5633

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.4,
-    "total_flos": 9649813265842176.0,
-    "train_loss": 1.6085638999938965,
-    "train_runtime": 113.3217,
-    "train_samples_per_second": 4.236,
-    "train_steps_per_second": 0.026
+    "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
 }

trainer_state.json

@@ -1,61 +1,68 @@
 {
-  "best_metric": 1.578920841217041,
-  "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-3",
-  "epoch": 2.4,
+  "best_metric": 1.3130167722702026,
+  "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-18",
+  "epoch": 2.88,
   "eval_steps": 500,
-  "global_step": 3,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
+      "epoch": 0.96,
       "eval_accuracy": {
-        "accuracy": 0.225
+        "accuracy": 0.42
       },
-      "eval_logLoss": 1.6326653957366943,
-      "eval_loss": 1.6326653957366943,
-      "eval_runtime": 17.9685,
-      "eval_samples_per_second": 2.226,
-      "eval_steps_per_second": 0.111,
-      "step": 1
+      "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
     },
     {
       "epoch": 1.6,
+      "grad_norm": 2.0363504886627197,
+      "learning_rate": 2.5e-05,
+      "loss": 1.4937,
+      "step": 10
+    },
+    {
+      "epoch": 1.92,
       "eval_accuracy": {
-        "accuracy": 0.275
+        "accuracy": 0.445
       },
-      "eval_logLoss": 1.5965577363967896,
-      "eval_loss": 1.5965576171875,
-      "eval_runtime": 2.0506,
-      "eval_samples_per_second": 19.507,
-      "eval_steps_per_second": 0.975,
-      "step": 2
+      "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
     },
     {
-      "epoch": 2.4,
+      "epoch": 2.88,
       "eval_accuracy": {
-        "accuracy": 0.275
+        "accuracy": 0.43
       },
-      "eval_logLoss": 1.578920841217041,
-      "eval_loss": 1.578920841217041,
-      "eval_runtime": 1.5145,
-      "eval_samples_per_second": 26.412,
-      "eval_steps_per_second": 1.321,
-      "step": 3
+      "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
     },
     {
-      "epoch": 2.4,
-      "step": 3,
-      "total_flos": 9649813265842176.0,
-      "train_loss": 1.6085638999938965,
-      "train_runtime": 113.3217,
-      "train_samples_per_second": 4.236,
-      "train_steps_per_second": 0.026
+      "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
     }
   ],
   "logging_steps": 10,
-  "max_steps": 3,
+  "max_steps": 18,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -71,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9649813265842176.0,
+  "total_flos": 5.789887959505306e+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 sha256:67d359248c1d8c44f15ba7eff5b68a2f13ac146bde4db9e23d55dc7362bb3d16
+oid sha256:b21473a72cb2c10232c58d5d4dfd554255cb3e73168fb1ed2a381bd5ac0fd6b5
 size 5176