Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795d9bc010f9024cfc519a932bbf5d9f224c5305587a440075604f0e93b50adf
+oid sha256:a2a3673ac6ecfcf9fbd4e8a74b81927275b26bd0684e838caa39b7caf422cf88
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e3fea581a136135d89bf36c83792eff24f24efbc1064d189e71138ec095b3f
+oid sha256:a6817fbbcd33480f164784483673185908595dff99afaaa869a566aa99376d9a
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c838b63f3004ffa4c11a6eaefac6d22bf6e2f78bfb1531b43e7aa35aacfbd1
+oid sha256:9f07b4f2bcc3f569f306e9b6554b0fe04785f073abde4e0109bc3d3d5eb765c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
+oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.968392737054472,
+  "epoch": 1.1620712844653664,
   "eval_steps": 50,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -330,6 +330,77 @@
       "learning_rate": 0.00011666776747647015,
       "loss": 32.9791,
       "step": 45
+    },
+    {
+      "epoch": 0.9899125756556826,
+      "grad_norm": 22.867385864257812,
+      "learning_rate": 0.00011418739235369615,
+      "loss": 23.7823,
+      "step": 46
+    },
+    {
+      "epoch": 1.0114324142568931,
+      "grad_norm": 18.280826568603516,
+      "learning_rate": 0.00011164659311227163,
+      "loss": 32.527,
+      "step": 47
+    },
+    {
+      "epoch": 1.0329522528581037,
+      "grad_norm": 19.427658081054688,
+      "learning_rate": 0.00010904928748046599,
+      "loss": 27.8595,
+      "step": 48
+    },
+    {
+      "epoch": 1.054472091459314,
+      "grad_norm": 19.467891693115234,
+      "learning_rate": 0.0001063994803153071,
+      "loss": 26.26,
+      "step": 49
+    },
+    {
+      "epoch": 1.0759919300605245,
+      "grad_norm": 16.39354705810547,
+      "learning_rate": 0.00010370125742738173,
+      "loss": 24.7449,
+      "step": 50
+    },
+    {
+      "epoch": 1.0759919300605245,
+      "eval_loss": 0.8254633545875549,
+      "eval_runtime": 26.532,
+      "eval_samples_per_second": 5.917,
+      "eval_steps_per_second": 2.978,
+      "step": 50
+    },
+    {
+      "epoch": 1.097511768661735,
+      "grad_norm": 27.119155883789062,
+      "learning_rate": 0.00010095877928081196,
+      "loss": 25.2238,
+      "step": 51
+    },
+    {
+      "epoch": 1.1190316072629456,
+      "grad_norm": 21.737436294555664,
+      "learning_rate": 9.817627457812105e-05,
+      "loss": 24.4688,
+      "step": 52
+    },
+    {
+      "epoch": 1.1405514458641561,
+      "grad_norm": 18.230609893798828,
+      "learning_rate": 9.535803373988056e-05,
+      "loss": 19.7777,
+      "step": 53
+    },
+    {
+      "epoch": 1.1620712844653664,
+      "grad_norm": 17.096773147583008,
+      "learning_rate": 9.25084022891929e-05,
+      "loss": 26.5253,
+      "step": 54
     }
   ],
   "logging_steps": 1,
@@ -349,7 +420,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3666203419475968e+17,
+  "total_flos": 2.839944410337116e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null