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:e9dca553eb3c268bee2a407985d42a623f5b8aa411f1076f3e443c32a8849dee
+oid sha256:43c3535fdd33d88d1e147e8ab1c9f2e208594bacc30e68757fe0129e39b826d4
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ec37851d5febb47c290dc917f59223c31beaa5cd36133d1a4e1201246852db
+oid sha256:d0aa2b8b0c9087a3fa085f4406ca70f6d38632228c2dcdb31b9f5f9772671656
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8288cb8cb0b54526d97f2ff59da883c307360a17e99a5d7d1d6e7afb2436e03b
+oid sha256:cdf286495b2f9086f0435e305d486647eb1934cc509a3961a7bfe47275b3ca95
 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": 0.0014119058964720001,
+  "epoch": 0.0021178588447080004,
   "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": 9.1668,
       "step": 18
+    },
+    {
+      "epoch": 0.0014825011912956002,
+      "grad_norm": 1.2270914316177368,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.4758,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016942870757664001,
+      "grad_norm": 1.1084787845611572,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 9.4413,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016942870757664001,
+      "eval_loss": 2.3046886920928955,
+      "eval_runtime": 954.8324,
+      "eval_samples_per_second": 6.247,
+      "eval_steps_per_second": 3.124,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019060729602372003,
+      "grad_norm": 0.9991955161094666,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 8.9407,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021178588447080004,
+      "grad_norm": 1.0472006797790527,
+      "learning_rate": 0.0,
+      "loss": 9.2817,
+      "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": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null