Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cdb48e0a4ecafd9feb0b91c31888b5615560dc7661640a8f664458feb28c88
+oid sha256:963490951e41a6b298a2a45c0b12b8fc868d4a1d813dea2d1a70e2059efef1c5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfc8343814c91c194d54f5f7d921a7df81ff0fa18a719650d61daf0ecd94c61
+oid sha256:a96a9b13d7fdf85a74ba640636bfd4ed8b20fcf5a6c1175be5764b29e567a57d
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767bc8a6f0ce209c5888baa62e92fcbb0825f5a364f7b7c5405d1d6cadb028c8
+oid sha256:11654361354869c625ade8e3cd35ca4b4e58bd76e4982e4f6b61c5dae495485f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07543611504007544,
+  "epoch": 0.08486562942008487,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 12.973,
       "eval_steps_per_second": 1.627,
       "step": 40
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 0.2324731945991516,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2811,
+      "step": 42
+    },
+    {
+      "epoch": 0.08486562942008487,
+      "grad_norm": 0.2373012900352478,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2594,
+      "step": 45
+    },
+    {
+      "epoch": 0.08486562942008487,
+      "eval_loss": 1.2852133512496948,
+      "eval_runtime": 68.8227,
+      "eval_samples_per_second": 12.975,
+      "eval_steps_per_second": 1.627,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.86529082703872e+16,
+  "total_flos": 6.647329603977216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null