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:e02f7f2c79d04c58f52a0b65bcf12350a3e90c46c3e0636b3615f00bd8cbc626
+oid sha256:3a43dbde1d6e11da7b470680b9e6fd81caffe77be851a6224b3351b99f3abc28
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d653e0195b0782775a1563b2540fe62293cbeec57344bbe55531a8494915e2cd
+oid sha256:1b0460c1503dc185e164bbbe66afebc739e5d0d308985ced203d2b7f5b8ad76b
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2f907045898cbc3c448529b408f232677f39d97bc65c62fd0596be9e459b8f
+oid sha256:bd75cf3b809d1ad953986ea9c75f286af19a4850426c2af932b4978ec671eecb
 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": 0.0001183224829973057,
+  "epoch": 0.0002366449659946114,
   "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": 3.669,
       "eval_steps_per_second": 3.669,
       "step": 3
+    },
+    {
+      "epoch": 0.00015776331066307426,
+      "grad_norm": 2.0381834506988525,
+      "learning_rate": 8e-05,
+      "loss": 4.0984,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019720413832884282,
+      "grad_norm": 1.3214229345321655,
+      "learning_rate": 0.0001,
+      "loss": 3.4137,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002366449659946114,
+      "grad_norm": 2.0282857418060303,
+      "learning_rate": 0.00012,
+      "loss": 3.4421,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002366449659946114,
+      "eval_loss": 3.8443140983581543,
+      "eval_runtime": 5820.5712,
+      "eval_samples_per_second": 3.668,
+      "eval_steps_per_second": 3.668,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8388464319922176.0,
+  "total_flos": 1.6776928639844352e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null