Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b067116c0d67eb4ec54e8dfe0a8fe79341a335f28d6e7899b54c6647300d6f1
+oid sha256:89094a0860c201bfa7b510e2952b4209c91c85be98ace53acb59731d712c5c5a
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820f2077c0d20daa13a67b46fb1f151e100fca8283d411fd8c9ecef445040500
+oid sha256:a6f68fcb63914119b6518be9306360134d6406f2834dd8275b0d0d307839c102
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85d4d74a92d9100cfbb70681d5fdf5283462de79b77166854c267737fd306c9
+oid sha256:3a07c66a8bbda035c71637231362589b93f6d10c6d5ad4f8f3c1facfda53ac13
 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": 0.0005141828777101723,
+  "epoch": 0.0010283657554203446,
   "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": 15.358,
       "eval_steps_per_second": 7.682,
       "step": 3
+    },
+    {
+      "epoch": 0.0006855771702802296,
+      "grad_norm": 0.5108266472816467,
+      "learning_rate": 8e-05,
+      "loss": 4.2006,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008569714628502871,
+      "grad_norm": 0.9380823373794556,
+      "learning_rate": 0.0001,
+      "loss": 4.482,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010283657554203446,
+      "grad_norm": 0.6530066728591919,
+      "learning_rate": 0.00012,
+      "loss": 4.6658,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010283657554203446,
+      "eval_loss": 1.2455629110336304,
+      "eval_runtime": 160.3867,
+      "eval_samples_per_second": 15.319,
+      "eval_steps_per_second": 7.663,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1274012762112000.0,
+  "total_flos": 2632959708364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null