Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a0e2d10f0dd62311b44feb8661ac02b7086de6930935bdb07f0c4d1b27164c
+oid sha256:9261e9afe6e2ac3ff3bc24d7acd6a9740b6a9b6dcb72284361ab208baa24ca33
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f99872278e39dc9ede39530f7a44965b238d74c616da934dcd852cf34098be
+oid sha256:05997fea32f6d797649a89f934a1b13ee89d150eb4e2123a9af23c3cd6289e38
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18a282c73739e9e74b8d89cc984b5139d8c8f1ab50a76c135432616d97a98bd
+oid sha256:aae7470879e8f19f69edc3c78eb50abc11361e598294cc4a8c50a856c8142969
 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": 0.000215231194174409,
+  "epoch": 0.000430462388348818,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 13.954,
       "eval_steps_per_second": 6.978,
       "step": 3
+    },
+    {
+      "epoch": 0.00028697492556587867,
+      "grad_norm": 5.913466930389404,
+      "learning_rate": 8e-05,
+      "loss": 3.3287,
+      "step": 4
+    },
+    {
+      "epoch": 0.00035871865695734833,
+      "grad_norm": 4.9988694190979,
+      "learning_rate": 0.0001,
+      "loss": 2.7558,
+      "step": 5
+    },
+    {
+      "epoch": 0.000430462388348818,
+      "grad_norm": 5.8590779304504395,
+      "learning_rate": 0.00012,
+      "loss": 2.48,
+      "step": 6
+    },
+    {
+      "epoch": 0.000430462388348818,
+      "eval_loss": 0.5436943173408508,
+      "eval_runtime": 486.3101,
+      "eval_samples_per_second": 12.068,
+      "eval_steps_per_second": 6.035,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1052065728036864.0,
+  "total_flos": 2104131456073728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null