Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7215f9f15c094cf3cdeb1e5537709a89bef70adc369dc292e35882f21cc46725
+oid sha256:128525095c9c4aa2360441c5622c7962547ed143337bfac52c83e3c618dc4e84
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed5fd588ee748ab7c105ed8409ef61fdb4fcfc08394d7fd879127026767aac6
+oid sha256:dfbc3e8f45768fc4da85d1bfec94316cf2bc55ecb2cfaf6f30ff35e6567ace72
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e18c671f1c508102bc524438e5e499b73e4276946e8f3dfc5062547fd2a74b0
+oid sha256:fd8ec78ff15268c9da253ecb4b146058c0df0371aefad94e4b756060686ce26d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
+oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07537012113055182,
+  "epoch": 0.08613728129205922,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,42 @@
       "eval_samples_per_second": 7.82,
       "eval_steps_per_second": 7.82,
       "step": 28
+    },
+    {
+      "epoch": 0.07806191117092867,
+      "grad_norm": 0.8260064721107483,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.2503,
+      "step": 29
+    },
+    {
+      "epoch": 0.08075370121130551,
+      "grad_norm": 1.2920253276824951,
+      "learning_rate": 0.0001,
+      "loss": 0.3839,
+      "step": 30
+    },
+    {
+      "epoch": 0.08344549125168237,
+      "grad_norm": 1.1818400621414185,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.2586,
+      "step": 31
+    },
+    {
+      "epoch": 0.08613728129205922,
+      "grad_norm": 1.3729400634765625,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.4248,
+      "step": 32
+    },
+    {
+      "epoch": 0.08613728129205922,
+      "eval_loss": 0.27306219935417175,
+      "eval_runtime": 10.1319,
+      "eval_samples_per_second": 7.797,
+      "eval_steps_per_second": 7.797,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591988805632e+16,
+  "total_flos": 1.3168499283197952e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null