Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7b38936076e5b11391ceccd250e1610af1e6bc87425413dd6f9433acbb5e7a
+oid sha256:c10cd879656c14f6c67706e5ef6a6ed5392b7455783b83226008557ab6c1c197
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6bb764c63ad42972788691621061a20dccf3a6ff14d4f48e016cc4376f18ad
+oid sha256:727c0144258ef51a1f515989e494415a1427822d9138284e64c8b3c60045bfff
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e654dc294f85bc7763a518d429cb3f8268e4e0d46f7022676840843e0297900
+oid sha256:cc78d73481e3ba72a3d6fb04344d343a7f6ed3f4dbca1980cc2dfd7e0b74a18a
 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": 0.008383861067445169,
+  "epoch": 0.00958155550565162,
   "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": 8.468,
       "eval_steps_per_second": 8.468,
       "step": 28
+    },
+    {
+      "epoch": 0.008683284676996781,
+      "grad_norm": 16.283584594726562,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 3.5697,
+      "step": 29
+    },
+    {
+      "epoch": 0.008982708286548395,
+      "grad_norm": 32.41582489013672,
+      "learning_rate": 0.0001,
+      "loss": 3.4125,
+      "step": 30
+    },
+    {
+      "epoch": 0.009282131896100007,
+      "grad_norm": 26.877944946289062,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 3.3671,
+      "step": 31
+    },
+    {
+      "epoch": 0.00958155550565162,
+      "grad_norm": 27.856897354125977,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.5875,
+      "step": 32
+    },
+    {
+      "epoch": 0.00958155550565162,
+      "eval_loss": 3.401846408843994,
+      "eval_runtime": 83.4215,
+      "eval_samples_per_second": 8.439,
+      "eval_steps_per_second": 8.439,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0386421969846272e+16,
+  "total_flos": 1.1870196536967168e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null