Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039105e4bc1329bda11f23ca86a182bedf4a41503364ff688327fa65e8796d2c
+oid sha256:9bfdbbeb03a1db2758472cfb857daa41a125167dfa53ef7aaf6d7b3c92f32f4b
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef46fa9fc6efda5501ce0771cdb8ef66d024f20ad8522ab933385ea9d7e412b
+oid sha256:041fb1f033cda3794f210027c924e2f461e4ece9c45529aa812f03aef36b55eb
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56b73ba5f2d662c92296e87599e4454df3aa952447ac02ee3c950d1f55780e2
+oid sha256:ece86352a70a0ae1b0a79f1e827d2f763027b67df8f5936a8a181a5c0188fa66
 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": 0.00857449088960343,
+  "epoch": 0.012861736334405145,
   "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": 2.1609,
       "step": 18
+    },
+    {
+      "epoch": 0.0090032154340836,
+      "grad_norm": 1.5848770141601562,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2663,
+      "step": 21
+    },
+    {
+      "epoch": 0.010289389067524116,
+      "grad_norm": 1.5910948514938354,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.163,
+      "step": 24
+    },
+    {
+      "epoch": 0.010289389067524116,
+      "eval_loss": 2.192744016647339,
+      "eval_runtime": 195.2457,
+      "eval_samples_per_second": 5.035,
+      "eval_steps_per_second": 2.52,
+      "step": 24
+    },
+    {
+      "epoch": 0.01157556270096463,
+      "grad_norm": 1.6390970945358276,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.2368,
+      "step": 27
+    },
+    {
+      "epoch": 0.012861736334405145,
+      "grad_norm": 1.5747755765914917,
+      "learning_rate": 0.0,
+      "loss": 2.1479,
+      "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": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null