Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbfc2bb74168e755fef28118545f891cdf186d2a944f9a29982293b5a92d6f5e
+oid sha256:3f55273b9efea6e083049f37ef6b83c5dad705296373082c3ef76bf9d2d3c779
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b91ec83db83c7de20f16763ab1a766b6d2da74c1ae636c907dd6823bd0dfe743
+oid sha256:687ae7a2a805d6884d673972681ee28e960c87d4fb965b2eac7932eed18537b6
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad9ad61d851362b016bc483f26fd031225443550ab3b51598f1b5b7efb51064
+oid sha256:35f1fb1094a75274c041ffed970d07172fea1185cb130b3e1c941999f2dc913c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010202780257620201,
+  "epoch": 0.015304170386430302,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.9326,
       "step": 18
+    },
+    {
+      "epoch": 0.010712919270501211,
+      "grad_norm": 0.37691137194633484,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9449,
+      "step": 21
+    },
+    {
+      "epoch": 0.012243336309144242,
+      "grad_norm": 0.45833703875541687,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.092,
+      "step": 24
+    },
+    {
+      "epoch": 0.012243336309144242,
+      "eval_loss": 1.0757582187652588,
+      "eval_runtime": 57.1584,
+      "eval_samples_per_second": 14.451,
+      "eval_steps_per_second": 7.226,
+      "step": 24
+    },
+    {
+      "epoch": 0.013773753347787273,
+      "grad_norm": 0.23235857486724854,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.0106,
+      "step": 27
+    },
+    {
+      "epoch": 0.015304170386430302,
+      "grad_norm": 0.26949524879455566,
+      "learning_rate": 0.0,
+      "loss": 0.9973,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7767855873392640.0,
+  "total_flos": 1.181705733931008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null