Training in progress, epoch 0

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1.575666934345728e+17,
+    "epoch": 4.680851063829787,
+    "eval_accuracy": 0.4889937106918239,
+    "eval_loss": NaN,
+    "eval_runtime": 8.3571,
+    "eval_samples_per_second": 76.103,
+    "eval_steps_per_second": 2.393,
+    "total_flos": 1.477984078577664e+17,
     "train_loss": 0.0,
-    "train_runtime": 166.8151,
-    "train_samples_per_second": 44.48,
-    "train_steps_per_second": 1.409
+    "train_runtime": 167.7096,
+    "train_samples_per_second": 44.243,
+    "train_steps_per_second": 0.328
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.680851063829787,
+    "eval_accuracy": 0.4889937106918239,
+    "eval_loss": NaN,
+    "eval_runtime": 8.3571,
+    "eval_samples_per_second": 76.103,
+    "eval_steps_per_second": 2.393
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780eabfb1ede8e9e88f021a6b3eb3e36687167bee7cd7ec380ba2499c1df5c17
+oid sha256:83218fc677ef895342b4874306a47dd0b316a563b91ba4c24f45fc17c74d9e8e
 size 94302952

runs/May04_07-56-14_4f22111e1b44/events.out.tfevents.1714809564.4f22111e1b44.9006.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d76245d32abc3c7bbea1fb89684cfdb56a8834c299c3bb8418d8dffbc0355a5
+size 405

runs/May04_08-00-17_4f22111e1b44/events.out.tfevents.1714809630.4f22111e1b44.9006.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1768cdd459268561b5738d0910350fcb5d2d6bcf6ecbbd89b6176f367f723268
+size 5370

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1.575666934345728e+17,
+    "epoch": 4.680851063829787,
+    "total_flos": 1.477984078577664e+17,
     "train_loss": 0.0,
-    "train_runtime": 166.8151,
-    "train_samples_per_second": 44.48,
-    "train_steps_per_second": 1.409
+    "train_runtime": 167.7096,
+    "train_samples_per_second": 44.243,
+    "train_steps_per_second": 0.328
 }

trainer_state.json

@@ -1,235 +1,109 @@
 {
   "best_metric": 0.4889937106918239,
-  "best_model_checkpoint": "resnet-50-finetuned-student_kaggle/checkpoint-47",
-  "epoch": 5.0,
+  "best_model_checkpoint": "resnet-50-finetuned-student_kaggle/checkpoint-11",
+  "epoch": 4.680851063829787,
   "eval_steps": 500,
-  "global_step": 235,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.2127659574468085,
-      "grad_norm": NaN,
-      "learning_rate": 2.0833333333333336e-05,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.425531914893617,
-      "grad_norm": NaN,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.6382978723404256,
-      "grad_norm": NaN,
-      "learning_rate": 4.857819905213271e-05,
-      "loss": 0.0,
-      "step": 30
-    },
     {
       "epoch": 0.851063829787234,
       "grad_norm": NaN,
-      "learning_rate": 4.620853080568721e-05,
+      "learning_rate": 4.591836734693878e-05,
       "loss": 0.0,
-      "step": 40
+      "step": 10
     },
     {
-      "epoch": 1.0,
+      "epoch": 0.9361702127659575,
       "eval_accuracy": 0.4889937106918239,
       "eval_loss": NaN,
-      "eval_runtime": 8.1507,
-      "eval_samples_per_second": 78.03,
-      "eval_steps_per_second": 2.454,
-      "step": 47
-    },
-    {
-      "epoch": 1.0638297872340425,
-      "grad_norm": NaN,
-      "learning_rate": 4.383886255924171e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 1.2765957446808511,
-      "grad_norm": NaN,
-      "learning_rate": 4.146919431279621e-05,
-      "loss": 0.0,
-      "step": 60
-    },
-    {
-      "epoch": 1.4893617021276595,
-      "grad_norm": NaN,
-      "learning_rate": 3.909952606635071e-05,
-      "loss": 0.0,
-      "step": 70
+      "eval_runtime": 8.3443,
+      "eval_samples_per_second": 76.22,
+      "eval_steps_per_second": 2.397,
+      "step": 11
     },
     {
       "epoch": 1.702127659574468,
       "grad_norm": NaN,
-      "learning_rate": 3.672985781990522e-05,
+      "learning_rate": 3.571428571428572e-05,
       "loss": 0.0,
-      "step": 80
-    },
-    {
-      "epoch": 1.9148936170212765,
-      "grad_norm": NaN,
-      "learning_rate": 3.4360189573459716e-05,
-      "loss": 0.0,
-      "step": 90
+      "step": 20
     },
     {
-      "epoch": 2.0,
+      "epoch": 1.9574468085106385,
       "eval_accuracy": 0.4889937106918239,
       "eval_loss": NaN,
-      "eval_runtime": 8.3873,
-      "eval_samples_per_second": 75.829,
-      "eval_steps_per_second": 2.385,
-      "step": 94
-    },
-    {
-      "epoch": 2.127659574468085,
-      "grad_norm": NaN,
-      "learning_rate": 3.1990521327014215e-05,
-      "loss": 0.0,
-      "step": 100
-    },
-    {
-      "epoch": 2.3404255319148937,
-      "grad_norm": NaN,
-      "learning_rate": 2.962085308056872e-05,
-      "loss": 0.0,
-      "step": 110
+      "eval_runtime": 7.5463,
+      "eval_samples_per_second": 84.28,
+      "eval_steps_per_second": 2.65,
+      "step": 23
     },
     {
       "epoch": 2.5531914893617023,
       "grad_norm": NaN,
-      "learning_rate": 2.7251184834123224e-05,
-      "loss": 0.0,
-      "step": 120
-    },
-    {
-      "epoch": 2.7659574468085104,
-      "grad_norm": NaN,
-      "learning_rate": 2.4881516587677726e-05,
+      "learning_rate": 2.5510204081632654e-05,
       "loss": 0.0,
-      "step": 130
+      "step": 30
     },
     {
       "epoch": 2.978723404255319,
-      "grad_norm": NaN,
-      "learning_rate": 2.251184834123223e-05,
-      "loss": 0.0,
-      "step": 140
-    },
-    {
-      "epoch": 3.0,
       "eval_accuracy": 0.4889937106918239,
       "eval_loss": NaN,
-      "eval_runtime": 7.8854,
-      "eval_samples_per_second": 80.655,
-      "eval_steps_per_second": 2.536,
-      "step": 141
-    },
-    {
-      "epoch": 3.1914893617021276,
-      "grad_norm": NaN,
-      "learning_rate": 2.014218009478673e-05,
-      "loss": 0.0,
-      "step": 150
+      "eval_runtime": 8.3005,
+      "eval_samples_per_second": 76.621,
+      "eval_steps_per_second": 2.409,
+      "step": 35
     },
     {
       "epoch": 3.404255319148936,
       "grad_norm": NaN,
-      "learning_rate": 1.7772511848341233e-05,
-      "loss": 0.0,
-      "step": 160
-    },
-    {
-      "epoch": 3.617021276595745,
-      "grad_norm": NaN,
-      "learning_rate": 1.5402843601895736e-05,
-      "loss": 0.0,
-      "step": 170
-    },
-    {
-      "epoch": 3.829787234042553,
-      "grad_norm": NaN,
-      "learning_rate": 1.3033175355450238e-05,
+      "learning_rate": 1.5306122448979594e-05,
       "loss": 0.0,
-      "step": 180
+      "step": 40
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.4889937106918239,
       "eval_loss": NaN,
-      "eval_runtime": 8.0232,
-      "eval_samples_per_second": 79.27,
-      "eval_steps_per_second": 2.493,
-      "step": 188
-    },
-    {
-      "epoch": 4.042553191489362,
-      "grad_norm": NaN,
-      "learning_rate": 1.066350710900474e-05,
-      "loss": 0.0,
-      "step": 190
+      "eval_runtime": 14.6795,
+      "eval_samples_per_second": 43.326,
+      "eval_steps_per_second": 1.362,
+      "step": 47
     },
     {
       "epoch": 4.25531914893617,
       "grad_norm": NaN,
-      "learning_rate": 8.293838862559241e-06,
-      "loss": 0.0,
-      "step": 200
-    },
-    {
-      "epoch": 4.468085106382979,
-      "grad_norm": NaN,
-      "learning_rate": 5.924170616113745e-06,
+      "learning_rate": 5.102040816326531e-06,
       "loss": 0.0,
-      "step": 210
+      "step": 50
     },
     {
       "epoch": 4.680851063829787,
-      "grad_norm": NaN,
-      "learning_rate": 3.5545023696682464e-06,
-      "loss": 0.0,
-      "step": 220
-    },
-    {
-      "epoch": 4.8936170212765955,
-      "grad_norm": NaN,
-      "learning_rate": 1.1848341232227488e-06,
-      "loss": 0.0,
-      "step": 230
-    },
-    {
-      "epoch": 5.0,
       "eval_accuracy": 0.4889937106918239,
       "eval_loss": NaN,
-      "eval_runtime": 8.3163,
-      "eval_samples_per_second": 76.476,
-      "eval_steps_per_second": 2.405,
-      "step": 235
+      "eval_runtime": 7.5742,
+      "eval_samples_per_second": 83.969,
+      "eval_steps_per_second": 2.641,
+      "step": 55
     },
     {
-      "epoch": 5.0,
-      "step": 235,
-      "total_flos": 1.575666934345728e+17,
+      "epoch": 4.680851063829787,
+      "step": 55,
+      "total_flos": 1.477984078577664e+17,
       "train_loss": 0.0,
-      "train_runtime": 166.8151,
-      "train_samples_per_second": 44.48,
-      "train_steps_per_second": 1.409
+      "train_runtime": 167.7096,
+      "train_samples_per_second": 44.243,
+      "train_steps_per_second": 0.328
     }
   ],
   "logging_steps": 10,
-  "max_steps": 235,
+  "max_steps": 55,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.575666934345728e+17,
+  "total_flos": 1.477984078577664e+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:d8121ae27cdcd1b7b5c4adc8363f0af01cc99f2b977ff73e68a871ff6fbd7636
+oid sha256:d2f07845e5a4f177d4d37279be2bdadd143d53be652dea45ac33053323beb4cc
 size 5048