End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.17,
-    "eval_f1": 0.6419753086419753,
-    "eval_loss": 0.7558732032775879,
-    "eval_runtime": 75.417,
-    "eval_samples_per_second": 0.729,
-    "eval_steps_per_second": 0.186
+    "epoch": 3.25,
+    "eval_f1": 0.6470588235294118,
+    "eval_loss": 0.8799970746040344,
+    "eval_runtime": 126.6292,
+    "eval_samples_per_second": 0.908,
+    "eval_steps_per_second": 0.229
 }

runs/Nov16_12-11-16_eaf4bd5c128f/events.out.tfevents.1700137742.eaf4bd5c128f.114827.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be533950f701a1eeea1901e0c7b2a9feea33e123ed0c2a2c532d6612d355cbb
-size 399
+oid sha256:8d775b196b93ee679101b5977b6dad2706e7dddd1c184da845a83b827fa3abd7
+size 710

test_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.17,
-    "eval_f1": 0.6419753086419753,
-    "eval_loss": 0.7558732032775879,
-    "eval_runtime": 75.417,
-    "eval_samples_per_second": 0.729,
-    "eval_steps_per_second": 0.186
+    "epoch": 3.25,
+    "eval_f1": 0.6470588235294118,
+    "eval_loss": 0.8799970746040344,
+    "eval_runtime": 126.6292,
+    "eval_samples_per_second": 0.908,
+    "eval_steps_per_second": 0.229
 }

trainer_state.json

@@ -1,178 +1,82 @@
 {
-  "best_metric": 0.7088607594936709,
+  "best_metric": 0.7108433734939759,
   "best_model_checkpoint": "videomae-base-SOCAL1-finetune/checkpoint-23",
-  "epoch": 5.166666666666667,
+  "epoch": 3.25,
   "eval_steps": 500,
-  "global_step": 138,
+  "global_step": 92,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.07,
-      "learning_rate": 3.571428571428572e-05,
-      "loss": 0.7246,
-      "step": 10
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.7580645161290326e-05,
-      "loss": 0.6991,
-      "step": 20
-    },
-    {
-      "epoch": 0.17,
-      "eval_f1": 0.7088607594936709,
-      "eval_loss": 0.7139360904693604,
-      "eval_runtime": 60.4444,
-      "eval_samples_per_second": 0.844,
-      "eval_steps_per_second": 0.215,
+      "epoch": 0.25,
+      "eval_f1": 0.7108433734939759,
+      "eval_loss": 0.8709341883659363,
+      "eval_runtime": 100.0415,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.27,
       "step": 23
     },
     {
-      "epoch": 1.05,
-      "learning_rate": 4.3548387096774194e-05,
-      "loss": 0.6108,
-      "step": 30
-    },
-    {
-      "epoch": 1.12,
-      "learning_rate": 3.951612903225806e-05,
-      "loss": 0.6361,
-      "step": 40
-    },
-    {
-      "epoch": 1.17,
-      "eval_f1": 0.7088607594936709,
-      "eval_loss": 0.7702756524085999,
-      "eval_runtime": 60.5668,
-      "eval_samples_per_second": 0.842,
-      "eval_steps_per_second": 0.215,
+      "epoch": 1.25,
+      "eval_f1": 0.7108433734939759,
+      "eval_loss": 0.8158706426620483,
+      "eval_runtime": 99.7202,
+      "eval_samples_per_second": 1.073,
+      "eval_steps_per_second": 0.271,
       "step": 46
     },
     {
-      "epoch": 2.03,
-      "learning_rate": 3.548387096774194e-05,
-      "loss": 0.6289,
-      "step": 50
-    },
-    {
-      "epoch": 2.1,
-      "learning_rate": 3.1451612903225806e-05,
-      "loss": 0.882,
-      "step": 60
-    },
-    {
-      "epoch": 2.17,
-      "eval_f1": 0.13333333333333333,
-      "eval_loss": 0.6996393203735352,
-      "eval_runtime": 60.2298,
-      "eval_samples_per_second": 0.847,
-      "eval_steps_per_second": 0.216,
+      "epoch": 2.25,
+      "eval_f1": 0.7108433734939759,
+      "eval_loss": 0.7319411635398865,
+      "eval_runtime": 101.0863,
+      "eval_samples_per_second": 1.059,
+      "eval_steps_per_second": 0.267,
       "step": 69
     },
     {
-      "epoch": 3.01,
-      "learning_rate": 2.7419354838709678e-05,
-      "loss": 0.7985,
-      "step": 70
-    },
-    {
-      "epoch": 3.08,
-      "learning_rate": 2.338709677419355e-05,
-      "loss": 0.6663,
-      "step": 80
-    },
-    {
-      "epoch": 3.15,
-      "learning_rate": 1.935483870967742e-05,
-      "loss": 0.657,
-      "step": 90
-    },
-    {
-      "epoch": 3.17,
-      "eval_f1": 0.7088607594936709,
-      "eval_loss": 0.732900083065033,
-      "eval_runtime": 60.0702,
-      "eval_samples_per_second": 0.849,
-      "eval_steps_per_second": 0.216,
+      "epoch": 3.25,
+      "eval_f1": 0.7108433734939759,
+      "eval_loss": 0.7353231310844421,
+      "eval_runtime": 103.0401,
+      "eval_samples_per_second": 1.038,
+      "eval_steps_per_second": 0.262,
       "step": 92
     },
     {
-      "epoch": 4.06,
-      "learning_rate": 1.5322580645161292e-05,
-      "loss": 0.5935,
-      "step": 100
-    },
-    {
-      "epoch": 4.13,
-      "learning_rate": 1.129032258064516e-05,
-      "loss": 0.64,
-      "step": 110
-    },
-    {
-      "epoch": 4.17,
-      "eval_f1": 0.7088607594936709,
-      "eval_loss": 0.7164726257324219,
-      "eval_runtime": 61.1419,
-      "eval_samples_per_second": 0.834,
-      "eval_steps_per_second": 0.213,
-      "step": 115
-    },
-    {
-      "epoch": 5.04,
-      "learning_rate": 7.258064516129033e-06,
-      "loss": 0.678,
-      "step": 120
+      "epoch": 3.25,
+      "step": 92,
+      "total_flos": 4.585517689256018e+17,
+      "train_loss": 0.6584867809129797,
+      "train_runtime": 903.9039,
+      "train_samples_per_second": 0.407,
+      "train_steps_per_second": 0.102
     },
     {
-      "epoch": 5.11,
-      "learning_rate": 3.225806451612903e-06,
-      "loss": 0.6312,
-      "step": 130
-    },
-    {
-      "epoch": 5.17,
-      "eval_f1": 0.7088607594936709,
-      "eval_loss": 0.6639404892921448,
-      "eval_runtime": 58.7006,
-      "eval_samples_per_second": 0.869,
-      "eval_steps_per_second": 0.221,
-      "step": 138
-    },
-    {
-      "epoch": 5.17,
-      "step": 138,
-      "total_flos": 6.878276533884027e+17,
-      "train_loss": 0.6765989255214083,
-      "train_runtime": 1244.4326,
-      "train_samples_per_second": 0.444,
-      "train_steps_per_second": 0.111
-    },
-    {
-      "epoch": 5.17,
-      "eval_f1": 0.6419753086419753,
-      "eval_loss": 0.7558730840682983,
-      "eval_runtime": 75.5334,
-      "eval_samples_per_second": 0.728,
-      "eval_steps_per_second": 0.185,
-      "step": 138
+      "epoch": 3.25,
+      "eval_f1": 0.6470588235294118,
+      "eval_loss": 0.879997193813324,
+      "eval_runtime": 129.7812,
+      "eval_samples_per_second": 0.886,
+      "eval_steps_per_second": 0.223,
+      "step": 92
     },
     {
-      "epoch": 5.17,
-      "eval_f1": 0.6419753086419753,
-      "eval_loss": 0.7558732032775879,
-      "eval_runtime": 75.417,
-      "eval_samples_per_second": 0.729,
-      "eval_steps_per_second": 0.186,
-      "step": 138
+      "epoch": 3.25,
+      "eval_f1": 0.6470588235294118,
+      "eval_loss": 0.8799970746040344,
+      "eval_runtime": 126.6292,
+      "eval_samples_per_second": 0.908,
+      "eval_steps_per_second": 0.229,
+      "step": 92
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 138,
+  "logging_steps": 100,
+  "max_steps": 92,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 500,
-  "total_flos": 6.878276533884027e+17,
+  "total_flos": 4.585517689256018e+17,
   "trial_name": null,
   "trial_params": null
 }