Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265d587ab2a61e7762d1b025336332d6531fac909a5f37e1aad282dcfea605a9
+oid sha256:8f1ca1c258dd45f5aa5ee9dae99cc03b4ec4ac7333c0d28325dd8d6828307fb6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb851879a6198c3d5b5de21bfe7b6a5a0d7dcb9a2d155d9a36cbd999c08889b
+oid sha256:7c20328aa00928ffc90d66614c46178cc27e00f1af3c9d65cda69c9f76af0d55
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7617ba3cf9e8ddb856448f9dbc39430954823c370dbeabbecf9999c7ef8bb520
+oid sha256:18c6ae539a28ac0bad077c10a0f07de54484b6eb719e0fc0b8cac0f33ac261a3
 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": 0.0003900517306107723,
+  "epoch": 0.0005850775959161584,
   "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": 10.7891,
       "step": 18
+    },
+    {
+      "epoch": 0.00040955431714131084,
+      "grad_norm": 16.250656127929688,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.661,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "grad_norm": 14.20734691619873,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.2675,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "eval_loss": 2.685302257537842,
+      "eval_runtime": 2119.1554,
+      "eval_samples_per_second": 10.188,
+      "eval_steps_per_second": 5.094,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005265698363245426,
+      "grad_norm": 16.34672737121582,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.9929,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005850775959161584,
+      "grad_norm": 13.728306770324707,
+      "learning_rate": 0.0,
+      "loss": 11.1346,
+      "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": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null