Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3316d61ed090605d37d1decc00cd742353d5837d056dcf72461ba5373b82a0c2
+oid sha256:a190b10ceee5fe048c381c2608a742d6a57e83f27313b86b4215f601fa46f060
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc43b170c2e62a2bc717a4c56ffe8e8a0f0c7ff1be8c1c03a4dc008179cc7c2
+oid sha256:5702dd5adf435229e5955857c6d53b75cbd418ba54a6172c4ece8c93a88ca9d5
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.00015167793718005436,
+  "epoch": 0.00030335587436010873,
   "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": 160.373,
       "eval_steps_per_second": 80.187,
       "step": 3
+    },
+    {
+      "epoch": 0.0002022372495734058,
+      "grad_norm": 5.731997225666419e-05,
+      "learning_rate": 8e-05,
+      "loss": 46.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00025279656196675726,
+      "grad_norm": 9.691962986835279e-06,
+      "learning_rate": 0.0001,
+      "loss": 46.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030335587436010873,
+      "grad_norm": 1.898708796943538e-05,
+      "learning_rate": 0.00012,
+      "loss": 46.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00030335587436010873,
+      "eval_loss": 11.5,
+      "eval_runtime": 53.6365,
+      "eval_samples_per_second": 155.267,
+      "eval_steps_per_second": 77.634,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 109575831552.0,
+  "total_flos": 219151663104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null