Training in progress, step 100, checkpoint

checkpoint-100/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7346ec1ae7c9b8c42ee468ae13423be6aa1c8975467ce0e77a27b489c7fe012
+oid sha256:82badac31c39aef875e8457adefd9fd641ee6da84e3f503212042d11a47d703c
 size 14244

checkpoint-100/trainer_state.json

@@ -23,10 +23,14 @@
     {
       "epoch": 0.06,
       "eval_accuracy": 0.44479243019924036,
+      "eval_combined_score": 0.3403229798934559,
+      "eval_f1": 0.2738667532127967,
       "eval_loss": 1.065091609954834,
-      "eval_runtime": 50.348,
-      "eval_samples_per_second": 596.131,
-      "eval_steps_per_second": 1.172,
+      "eval_precision": 0.19784030596254612,
+      "eval_recall": 0.44479243019924036,
+      "eval_runtime": 49.6621,
+      "eval_samples_per_second": 604.364,
+      "eval_steps_per_second": 1.188,
       "step": 20
     },
     {
@@ -44,10 +48,14 @@
     {
       "epoch": 0.12,
       "eval_accuracy": 0.5033650962883988,
+      "eval_combined_score": 0.4633375988688383,
+      "eval_f1": 0.4137746858205889,
       "eval_loss": 1.0188277959823608,
-      "eval_runtime": 49.614,
-      "eval_samples_per_second": 604.95,
-      "eval_steps_per_second": 1.189,
+      "eval_precision": 0.43284551707796665,
+      "eval_recall": 0.5033650962883988,
+      "eval_runtime": 49.1985,
+      "eval_samples_per_second": 610.06,
+      "eval_steps_per_second": 1.199,
       "step": 40
     },
     {
@@ -65,10 +73,14 @@
     {
       "epoch": 0.18,
       "eval_accuracy": 0.5279203038581995,
+      "eval_combined_score": 0.48433586826626607,
+      "eval_f1": 0.4596383010419703,
       "eval_loss": 0.9871189594268799,
-      "eval_runtime": 49.5201,
-      "eval_samples_per_second": 606.098,
-      "eval_steps_per_second": 1.191,
+      "eval_precision": 0.421864564306695,
+      "eval_recall": 0.5279203038581995,
+      "eval_runtime": 49.0237,
+      "eval_samples_per_second": 612.235,
+      "eval_steps_per_second": 1.204,
       "step": 60
     },
     {
@@ -86,10 +98,14 @@
     {
       "epoch": 0.24,
       "eval_accuracy": 0.5308189511561271,
+      "eval_combined_score": 0.4866197693698143,
+      "eval_f1": 0.46528335920671143,
       "eval_loss": 0.9888613224029541,
-      "eval_runtime": 49.4469,
-      "eval_samples_per_second": 606.994,
-      "eval_steps_per_second": 1.193,
+      "eval_precision": 0.4195578159602916,
+      "eval_recall": 0.5308189511561271,
+      "eval_runtime": 49.518,
+      "eval_samples_per_second": 606.124,
+      "eval_steps_per_second": 1.191,
       "step": 80
     },
     {
@@ -107,18 +123,22 @@
     {
       "epoch": 0.3,
       "eval_accuracy": 0.5307856333710935,
+      "eval_combined_score": 0.48644275806230897,
+      "eval_f1": 0.4666072639999521,
       "eval_loss": 0.9762536883354187,
-      "eval_runtime": 49.4804,
-      "eval_samples_per_second": 606.583,
-      "eval_steps_per_second": 1.192,
+      "eval_precision": 0.4175925015070968,
+      "eval_recall": 0.5307856333710935,
+      "eval_runtime": 49.4629,
+      "eval_samples_per_second": 606.798,
+      "eval_steps_per_second": 1.193,
       "step": 100
     }
   ],
   "logging_steps": 10,
-  "max_steps": 996,
-  "num_train_epochs": 3,
+  "max_steps": 1660,
+  "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 1.34714065158144e+16,
+  "total_flos": 1.34714069876736e+16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1be80ebe52f6e43af0b8aa087e72fad77310d5998b6e0b8f66a6a1d53be7b7
+oid sha256:ae98e7de1b05a570517ae68653e3c31b639a52c739d05197601f467f38b01c66
 size 4536