Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5b541bb702a004bd26e22a9b25613caa40ba226e1c32db33b163b11a283ee28
+oid sha256:29e8a26f3f57f3ca20fa5753a4b50a55eb51a1771ce64bd4d0897f6b4add7ecf
 size 3380768360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5abaa4082b22bd4a967f9c79a0482a15f529323f25a7e5d2a3e5d715794ca1
+oid sha256:f6678e377e56ff4352948db5780be2cab954115593707e8eae935e841cfb4995
 size 1757617777

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8568e47b8b6c26e0a7b5540da26be8f44a34e9279c25ee15a34f94896178a6b5
+oid sha256:7ccf6167c808ff7ae6fa6b87015b87701a77af18e7bc2a55dc01402d99d386a7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d25955d4e2674e5dd5eed0c89d1bc41de0292bbbb39829ac908ea95d7cec10
+oid sha256:0fcc312b60864d5ca59d7feaf623987674e51ded74157218540ec0457a67c222
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.627177700348432,
+  "epoch": 0.9407665505226481,
   "eval_steps": 30,
-  "global_step": 60,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 0.292,
       "eval_steps_per_second": 0.073,
       "step": 60
+    },
+    {
+      "epoch": 0.6794425087108014,
+      "grad_norm": 0.10611709207296371,
+      "learning_rate": 7.786622315612183e-05,
+      "loss": 0.3069,
+      "step": 65
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.093358114361763,
+      "learning_rate": 7.426509812655406e-05,
+      "loss": 0.3514,
+      "step": 70
+    },
+    {
+      "epoch": 0.7839721254355401,
+      "grad_norm": 0.0683087483048439,
+      "learning_rate": 7.049101623982937e-05,
+      "loss": 0.2057,
+      "step": 75
+    },
+    {
+      "epoch": 0.8362369337979094,
+      "grad_norm": 0.0792144313454628,
+      "learning_rate": 6.65708784109318e-05,
+      "loss": 0.2101,
+      "step": 80
+    },
+    {
+      "epoch": 0.8885017421602788,
+      "grad_norm": 0.09680237621068954,
+      "learning_rate": 6.253262661293604e-05,
+      "loss": 0.2638,
+      "step": 85
+    },
+    {
+      "epoch": 0.9407665505226481,
+      "grad_norm": 0.1257801651954651,
+      "learning_rate": 5.840504471210742e-05,
+      "loss": 0.3075,
+      "step": 90
+    },
+    {
+      "epoch": 0.9407665505226481,
+      "eval_loss": 0.2471843957901001,
+      "eval_runtime": 1748.4786,
+      "eval_samples_per_second": 0.292,
+      "eval_steps_per_second": 0.073,
+      "step": 90
     }
   ],
   "logging_steps": 5,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.066496537929974e+17,
+  "total_flos": 5.879999872679608e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null