Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fea16fa22acdac770688389bec26076bc75e528d2aa241a468fdb94a7f72dc
+oid sha256:80d11f4b4d122c247ca30e8a484e4d5da7a0f312335b9ffafa8311b3d0c49342
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7f8294d829460a31e3a10f3bfc4790e3205c4a0280b9a90f620a38847a4506
+oid sha256:4161a268c431a2784049914d6488e4219157df4c0836f8f03cd16f49b9b58d46
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43457ee585de6d875538d2fea3b4d75cff27b3cf7a8fab622bf9466d2e04fc58
+oid sha256:e6bfd8deca4669c4d862688088e265172b55c9ed56fc54666385adead3bdb6c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032144005143040825,
+  "epoch": 0.006428801028608165,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 11.5557,
       "step": 9
+    },
+    {
+      "epoch": 0.003857280617164899,
+      "grad_norm": 3.8450965881347656,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.8073,
+      "step": 12
+    },
+    {
+      "epoch": 0.0048216007714561235,
+      "grad_norm": 4.419191360473633,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 9.5406,
+      "step": 15
+    },
+    {
+      "epoch": 0.005143040822886531,
+      "eval_loss": 2.2781641483306885,
+      "eval_runtime": 200.068,
+      "eval_samples_per_second": 6.548,
+      "eval_steps_per_second": 3.274,
+      "step": 16
+    },
+    {
+      "epoch": 0.0057859209257473485,
+      "grad_norm": 4.035886764526367,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 9.4144,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3466677952512000.0,
+  "total_flos": 6716688532992000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null