Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8d6417890764b0b8d0e22fa8c18470b0dc59d45519298306ded6a41e5dacb1
+oid sha256:a9d4a4a496b5af04e04416d63e2101ea643afbdacd673dd6e1ba4ff65978ae4d
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0067188a5413405d3850314b19a624e224ba875cda204ce1339112cc7852e0
+oid sha256:60afefeedc65a49c5987d0e5980d27a9201472f2405cfaf3be6874f1ed4773dc
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8586512a4566a393800b83e344d6730e6751cb11be4ad93fd9de02ed9e47b01f
+oid sha256:fbe38599c452d9ae6dc34f6e1fc26d8c070f9321d6d7b5ad8731beaf1827578f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008126227398930047,
+  "epoch": 0.0016252454797860093,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 58.125,
       "eval_steps_per_second": 29.081,
       "step": 3
+    },
+    {
+      "epoch": 0.0010834969865240061,
+      "grad_norm": 6.078212738037109,
+      "learning_rate": 8e-05,
+      "loss": 44.5714,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013543712331550077,
+      "grad_norm": 5.919520378112793,
+      "learning_rate": 0.0001,
+      "loss": 44.3545,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016252454797860093,
+      "grad_norm": 7.104866981506348,
+      "learning_rate": 0.00012,
+      "loss": 44.5365,
+      "step": 6
+    },
+    {
+      "epoch": 0.0016252454797860093,
+      "eval_loss": 11.10763168334961,
+      "eval_runtime": 26.4786,
+      "eval_samples_per_second": 58.727,
+      "eval_steps_per_second": 29.382,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 249594642432.0,
+  "total_flos": 499189284864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null