Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d710004dff6649495c18a033179d7f322584f9279fa0ac641251cb7d6ceda2
+oid sha256:a79b7b05d5d224c7efccaa8cb908ad2d6010c4820253b6e8396617ab427642b4
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc1569ded0f43e8da58f5e396181c7c63e4cfb71ae9d5f0b3b7458f94f282f0
+oid sha256:3005149bfd96cef6b9b3e4adf2861a90c2906c33029bd78c0c34c92a29bac2fd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e843a368393e1b5efd15ce155ddf7a1314fb792347aecbb8e7a205b664e6218d
+oid sha256:178f8909923e6640d4f0c616b2d412013f1968cd9ff6dd0b71136a5f01ae62f9
 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": 0.00270947639368692,
+  "epoch": 0.00406421459053038,
   "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": 7.2584,
       "step": 18
+    },
+    {
+      "epoch": 0.002844950213371266,
+      "grad_norm": 6.8131208419799805,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.6355,
+      "step": 21
+    },
+    {
+      "epoch": 0.003251371672424304,
+      "grad_norm": 4.061794281005859,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.7912,
+      "step": 24
+    },
+    {
+      "epoch": 0.003251371672424304,
+      "eval_loss": 1.8718359470367432,
+      "eval_runtime": 279.9161,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 5.552,
+      "step": 24
+    },
+    {
+      "epoch": 0.003657793131477342,
+      "grad_norm": 4.054107189178467,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.9789,
+      "step": 27
+    },
+    {
+      "epoch": 0.00406421459053038,
+      "grad_norm": 11.858595848083496,
+      "learning_rate": 0.0,
+      "loss": 7.398,
+      "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": 1.285435567374336e+16,
+  "total_flos": 1.920218563608576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null