Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485ed40dc60559bd022340f83a68d544d43141d5fffc14de56086ae46cbfab9f
+oid sha256:de979e6dd17d55b6f55570d71e791012ece6f58279bb0073d7d1ef5a0cad6222
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c87692fe4a5af057a5a1d2f9dec90887c42e097b6b389e806486c05f7fa80e
+oid sha256:dd6ee4f1baab4952bf525b122c7864a3f22d3c9e8480788cd9a5d315d98347b3
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7c63649bbfbc654c9320d13fb127a9fc70ebb76dcfd99ba788425a385a575e
+oid sha256:1e7080bcf59da0b32506b7a5a2d8d25e1abeb09c4e8d9d3f76e7b7d3df2f68de
 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": 0.010346611484738748,
+  "epoch": 0.015519917227108122,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 13.779,
       "eval_steps_per_second": 6.89,
       "step": 20
+    },
+    {
+      "epoch": 0.010863942058975685,
+      "grad_norm": 4.095158576965332,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.4083,
+      "step": 21
+    },
+    {
+      "epoch": 0.012415933781686497,
+      "grad_norm": 3.549262046813965,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.8976,
+      "step": 24
+    },
+    {
+      "epoch": 0.012933264355923435,
+      "eval_loss": 1.8360580205917358,
+      "eval_runtime": 59.1053,
+      "eval_samples_per_second": 13.772,
+      "eval_steps_per_second": 6.886,
+      "step": 25
+    },
+    {
+      "epoch": 0.01396792550439731,
+      "grad_norm": 4.930000305175781,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.178,
+      "step": 27
+    },
+    {
+      "epoch": 0.015519917227108122,
+      "grad_norm": 4.502659797668457,
+      "learning_rate": 0.0,
+      "loss": 7.1827,
+      "step": 30
+    },
+    {
+      "epoch": 0.015519917227108122,
+      "eval_loss": 1.8303591012954712,
+      "eval_runtime": 59.1323,
+      "eval_samples_per_second": 13.766,
+      "eval_steps_per_second": 6.883,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null