Best checkpoint (step 4176)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ff68740dbd51618e05d8e926e72bd32831e0cc00fa4d8693a1c4b6ccd39cc0
+oid sha256:f9a8fd5458b8d1577edb8a797dafb789dccb27c5daa17ed565b29753696bc342
 size 498673009

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 4638,
+  "epoch": 2.701164294954722,
+  "global_step": 4176,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1146,114 +1146,11 @@
       "eval_samples_per_second": 1517.169,
       "eval_steps_per_second": 11.869,
       "step": 4176
-    },
-    {
-      "epoch": 2.71,
-      "learning_rate": 5.498322951605176e-06,
-      "loss": 0.5301,
-      "step": 4183
-    },
-    {
-      "epoch": 2.74,
-      "learning_rate": 4.935313847628174e-06,
-      "loss": 0.5402,
-      "step": 4230
-    },
-    {
-      "epoch": 2.77,
-      "learning_rate": 4.372304743651174e-06,
-      "loss": 0.5167,
-      "step": 4277
-    },
-    {
-      "epoch": 2.8,
-      "learning_rate": 3.8092956396741735e-06,
-      "loss": 0.5004,
-      "step": 4324
-    },
-    {
-      "epoch": 2.83,
-      "learning_rate": 3.246286535697173e-06,
-      "loss": 0.5148,
-      "step": 4371
-    },
-    {
-      "epoch": 2.85,
-      "eval_accuracy": 0.7637243375237406,
-      "eval_b_acc": 0.6382943967754277,
-      "eval_f1": 0.7612453985473553,
-      "eval_f1_anger": 0.6462075848303392,
-      "eval_f1_disgust": 0.4666666666666667,
-      "eval_f1_fear": 0.6678592725104352,
-      "eval_f1_joy": 0.7563368765331154,
-      "eval_f1_neutral": 0.8485270885605427,
-      "eval_f1_sadness": 0.6918630502445532,
-      "eval_f1_surprise": 0.4760213143872114,
-      "eval_loss": 0.6637689471244812,
-      "eval_prec": 0.7597715932015663,
-      "eval_prec_anger": 0.6741280583029672,
-      "eval_prec_disgust": 0.5,
-      "eval_prec_fear": 0.681265206812652,
-      "eval_prec_joy": 0.7394084732214229,
-      "eval_prec_neutral": 0.8400183992640294,
-      "eval_prec_sadness": 0.6921708185053381,
-      "eval_prec_surprise": 0.5296442687747036,
-      "eval_recall": 0.7637243375237406,
-      "eval_recall_anger": 0.6205079060852899,
-      "eval_recall_disgust": 0.4375,
-      "eval_recall_fear": 0.6549707602339181,
-      "eval_recall_joy": 0.7740585774058577,
-      "eval_recall_neutral": 0.857209913631243,
-      "eval_recall_sadness": 0.6915555555555556,
-      "eval_recall_surprise": 0.432258064516129,
-      "eval_runtime": 14.5644,
-      "eval_samples_per_second": 1518.363,
-      "eval_steps_per_second": 11.878,
-      "step": 4408
-    },
-    {
-      "epoch": 2.86,
-      "learning_rate": 2.6832774317201726e-06,
-      "loss": 0.5231,
-      "step": 4418
-    },
-    {
-      "epoch": 2.89,
-      "learning_rate": 2.120268327743172e-06,
-      "loss": 0.5223,
-      "step": 4465
-    },
-    {
-      "epoch": 2.92,
-      "learning_rate": 1.5572592237661715e-06,
-      "loss": 0.525,
-      "step": 4512
-    },
-    {
-      "epoch": 2.95,
-      "learning_rate": 9.942501197891712e-07,
-      "loss": 0.5219,
-      "step": 4559
-    },
-    {
-      "epoch": 2.98,
-      "learning_rate": 4.312410158121706e-07,
-      "loss": 0.516,
-      "step": 4606
-    },
-    {
-      "epoch": 3.0,
-      "step": 4638,
-      "total_flos": 3.903427734912e+16,
-      "train_loss": 0.6570020180521673,
-      "train_runtime": 1377.6596,
-      "train_samples_per_second": 430.73,
-      "train_steps_per_second": 3.367
     }
   ],
   "max_steps": 4638,
   "num_train_epochs": 3,
-  "total_flos": 3.903427734912e+16,
+  "total_flos": 3.51500575835136e+16,
   "trial_name": null,
   "trial_params": null
 }