Training in progress, step 100, checkpoint

checkpoint-100/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e54a571980ef134298a554aac722af4da89b170eca1f61bc565ab07edd2e0cc
+oid sha256:3b1d0c548c3d756009acc070d474575be1f7e4c75e1600d04dbb7dcf0f91a3be
 size 19690328

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db9b7bb8d83065acd43107b3a28a3c47cda014c84cc04a1e2e58f347c455e066
+oid sha256:47619c6beea50c01a29357e91c3df111c8cbf60d0d93f5562a7d88a1c6967672
 size 38087098

checkpoint-100/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6246d9c400e96b7758f74d80fdfcf27ca4bb2331c3eddc08048e54128097ec2
+oid sha256:4d82e6f097badc4ed1f3a723b703da5a6a435d0d1cc3afcce8e0bc55816f6b12
 size 14244

checkpoint-100/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07ad19a040c410b88518a62aabd6f98c60b9d523db55f3a636e7312ec6a15d7
+oid sha256:7e847ef2ab3d229924a0ef679327445195238f1d0893ee7f18c5152cb57a98ec
 size 1064

checkpoint-100/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.49520450830459595,
-  "best_model_checkpoint": "output/checkpoint-100",
-  "epoch": 0.08211023298778611,
+  "best_metric": 0.4239814877510071,
+  "best_model_checkpoint": "output/checkpoint-50",
+  "epoch": 1.444043321299639,
   "eval_steps": 50,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,47 +9,47 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0,
+      "epoch": 0.01,
       "learning_rate": 0.0,
-      "loss": 0.8903,
+      "loss": 0.3991,
       "step": 1
     },
     {
-      "epoch": 0.04,
-      "learning_rate": 1.2222222222222224e-05,
-      "loss": 0.7189,
+      "epoch": 0.72,
+      "learning_rate": 1.8902439024390243e-05,
+      "loss": 0.3172,
       "step": 50
     },
     {
-      "epoch": 0.04,
-      "eval_accuracy": 0.8228571428571428,
-      "eval_loss": 0.5415178537368774,
-      "eval_runtime": 28.5756,
-      "eval_samples_per_second": 6.124,
-      "eval_steps_per_second": 1.54,
+      "epoch": 0.72,
+      "eval_accuracy": 0.84,
+      "eval_loss": 0.4239814877510071,
+      "eval_runtime": 28.6347,
+      "eval_samples_per_second": 6.111,
+      "eval_steps_per_second": 1.537,
       "step": 50
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 1.8658536585365855e-05,
-      "loss": 0.5723,
+      "epoch": 1.44,
+      "learning_rate": 1.2804878048780488e-05,
+      "loss": 0.1954,
       "step": 100
     },
     {
-      "epoch": 0.08,
-      "eval_accuracy": 0.8,
-      "eval_loss": 0.49520450830459595,
-      "eval_runtime": 28.516,
-      "eval_samples_per_second": 6.137,
-      "eval_steps_per_second": 1.543,
+      "epoch": 1.44,
+      "eval_accuracy": 0.8514285714285714,
+      "eval_loss": 0.5004297494888306,
+      "eval_runtime": 28.6111,
+      "eval_samples_per_second": 6.117,
+      "eval_steps_per_second": 1.538,
       "step": 100
     }
   ],
   "logging_steps": 50,
-  "max_steps": 400,
-  "num_train_epochs": 1,
+  "max_steps": 200,
+  "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 3.712987376369664e+16,
+  "total_flos": 3.815256140660736e+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 sha256:090099aa07c672025c60437897a7a19f63d8d7bd4284af2562fc632695431956
+oid sha256:d6e1226be91d4f2bcdcde81b49645b5882b397e67c3f85a88d2c0a49245bf8c5
 size 4600