Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c8d3bcb4a506c3b4d69955da8cc97d8ca04b6a5f30782bda412a242f24dcca
+oid sha256:399901c7526a722f66407e445b4340c947d1edddfaa803fa1b7fc0b17c6f8fe1
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8f97de1bc9eb3b7c106525db088a3eb547c76d28fcfc334af360cafd088efc
+oid sha256:fe8162f9b974da227883309c26b7c30c8f25bbb6de3bdc10616ac4d29c669546
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9374616f9d7997190ddd0b4f3acf4310b4b3aeb36a48ea977e0e4935e55dfae5
+oid sha256:d1a99c0eb9370d53a24cbd06e0e5be45a918d6a2d1b882c079da2c0baea22d9b
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9402989c561103fae8c846fc7cd8beee968bb6da9463171c6d6bc014ef3f06
+oid sha256:2739801862cebd8c0e0370b1333408f0c41bf735e0be595694a4a2011af68c74
 size 1064

last-checkpoint/trainer_state.json

@@ -1,52 +1,34 @@
 {
-  "best_metric": 0.7860793471336365,
-  "best_model_checkpoint": "./amazon-reviews-distilbert-base-sentiment/checkpoint-1000",
-  "epoch": 0.0851861316977596,
+  "best_metric": 0.8777859807014465,
+  "best_model_checkpoint": "./amazon-reviews-distilbert-base-sentiment/checkpoint-500",
+  "epoch": 0.08517887563884156,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.04,
-      "learning_rate": 1.9716046227674136e-05,
-      "loss": 0.0738,
-      "step": 500
-    },
-    {
-      "epoch": 0.04,
-      "eval_accuracy": 0.8679993653815643,
-      "eval_f1": 0.717381801052371,
-      "eval_loss": 0.9887846112251282,
-      "eval_precision": 0.6898909105252482,
-      "eval_recall": 0.76139346139969,
-      "eval_runtime": 97.95,
-      "eval_samples_per_second": 64.349,
-      "eval_steps_per_second": 8.045,
-      "step": 500
-    },
     {
       "epoch": 0.09,
-      "learning_rate": 1.943209245534827e-05,
-      "loss": 0.0983,
-      "step": 1000
+      "learning_rate": 1.943214082907439e-05,
+      "loss": 0.0657,
+      "step": 500
     },
     {
       "epoch": 0.09,
-      "eval_accuracy": 0.8837061716642869,
-      "eval_f1": 0.729170483604411,
-      "eval_loss": 0.7860793471336365,
-      "eval_precision": 0.7229190970608936,
-      "eval_recall": 0.7455918886412958,
-      "eval_runtime": 97.7735,
-      "eval_samples_per_second": 64.465,
-      "eval_steps_per_second": 8.059,
-      "step": 1000
+      "eval_accuracy": 0.8683166745993971,
+      "eval_f1": 0.7203595462721784,
+      "eval_loss": 0.8777859807014465,
+      "eval_precision": 0.7011145822442907,
+      "eval_recall": 0.7614722170387864,
+      "eval_runtime": 100.8555,
+      "eval_samples_per_second": 62.495,
+      "eval_steps_per_second": 3.907,
+      "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 35217,
+  "max_steps": 17610,
   "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 1059758088192000.0,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398a00b520c8b49d1718dad126b59723f2860bfaf262aff45310c69ba3d07d16
+oid sha256:2076442870c89c79fc879c9fd8da7da3c75ea6f104923ac55d3bbd77d6399e5a
 size 4600