Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328e6219a84a1c5d014d73882c90e59b775009ebde96f422efd9a96131f10d74
+oid sha256:fec2536c5cc3f6066e23a7f2da7de15348c7b7d8801388a7a4b27222eec59555
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3493323eb6c6109718f564ec556625834692da58d518284df1e2fcb38c0d9b2f
+oid sha256:d7da0063208795cf88527b4db364a79f1e4214d461125cbeff58288b5cd915c7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c809f327643e2371174055edbcb9fb814f0c6bc7665957ef69286f7e20857b
+oid sha256:00af49bc877fc3774ed92bad30a4b1fb8f6d2fe6758836d66c5826cf252f1b79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45323741007194246,
+  "epoch": 0.5179856115107914,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 12.083,
       "eval_steps_per_second": 1.549,
       "step": 63
+    },
+    {
+      "epoch": 0.4748201438848921,
+      "grad_norm": 2.1625380516052246,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 4.3836,
+      "step": 66
+    },
+    {
+      "epoch": 0.49640287769784175,
+      "grad_norm": 2.1454732418060303,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 4.2899,
+      "step": 69
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 2.406993865966797,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 3.9958,
+      "step": 72
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "eval_loss": 1.0135488510131836,
+      "eval_runtime": 19.3546,
+      "eval_samples_per_second": 12.09,
+      "eval_steps_per_second": 1.55,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.079303780475863e+17,
+  "total_flos": 1.230476622692352e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null