Training in progress, step 51, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef352b3755cd2c3514a70e0f1913121f3c90f77b381ac85eeb778430e7a0492f
+oid sha256:7509a38f253530a371c4f75f1b5dcbea50b136a890c57a3ee3bc66254766e63f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255220845625b8a532eac68bcefb4bfe60d87d73a6ff5f76ef1a4f52d1f270d8
+oid sha256:943bc6dada57397735ca818193ed0b16c7c4f3889837989d8dfbb6097b4a594f
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624617eb67c5ae66a26f74399b042214fe4beaf1a0d11ffcede0e4228de76c62
+oid sha256:c543948a535496f0dde46e00d90041e4b64736cb4a715d793f78a309b0450ac5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af27ed5b5e5c3013f1da7a97e494138e751399ceff1f8e7486b6e269bc7092f
+oid sha256:a9fa892ecd236e652150058649b13d9161331d85e374c4bec1d60ad6a556c3a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00872633942893808,
+  "epoch": 0.013089509143407122,
   "eval_steps": 17,
-  "global_step": 34,
+  "global_step": 51,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -108,6 +108,56 @@
       "eval_samples_per_second": 13.292,
       "eval_steps_per_second": 1.663,
       "step": 34
+    },
+    {
+      "epoch": 0.009239653512993263,
+      "grad_norm": 0.3209523558616638,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 2.4035,
+      "step": 36
+    },
+    {
+      "epoch": 0.010009624639076035,
+      "grad_norm": 0.33573678135871887,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": 2.3783,
+      "step": 39
+    },
+    {
+      "epoch": 0.010779595765158807,
+      "grad_norm": 0.3218136131763458,
+      "learning_rate": 9.316282404787871e-05,
+      "loss": 2.4247,
+      "step": 42
+    },
+    {
+      "epoch": 0.011549566891241578,
+      "grad_norm": 0.30115804076194763,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 2.3915,
+      "step": 45
+    },
+    {
+      "epoch": 0.01231953801732435,
+      "grad_norm": 0.34325042366981506,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.3639,
+      "step": 48
+    },
+    {
+      "epoch": 0.013089509143407122,
+      "grad_norm": 0.3467099666595459,
+      "learning_rate": 8.894386393810563e-05,
+      "loss": 2.3171,
+      "step": 51
+    },
+    {
+      "epoch": 0.013089509143407122,
+      "eval_loss": 2.341045379638672,
+      "eval_runtime": 494.2874,
+      "eval_samples_per_second": 13.278,
+      "eval_steps_per_second": 1.661,
+      "step": 51
     }
   ],
   "logging_steps": 3,
@@ -127,7 +177,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.977191316514406e+16,
+  "total_flos": 7.41634467692544e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null