Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da91b7851b8dfdcdeded4f515f77e72c2312c02fd2af42296c6cdc6667cf314
+oid sha256:fa209710d25f02d073c6e33d715ef603159e1541b3b288d7116272513424e2b2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11eebfdc529875deab7bfb83ca0321ba27c22b641cf3b403b00b4214a1edebe0
+oid sha256:cbc0bb2e06fb07887025cc073c02153a4eac2e336eb95b5d29d7603801e77f79
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
+oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011466372657111356,
+  "epoch": 0.02293274531422271,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 12.406,
       "eval_steps_per_second": 6.203,
       "step": 10
+    },
+    {
+      "epoch": 0.013230429988974642,
+      "grad_norm": 10.134819984436035,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.3156,
+      "step": 15
+    },
+    {
+      "epoch": 0.017640573318632856,
+      "grad_norm": 5.363346099853516,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.8045,
+      "step": 20
+    },
+    {
+      "epoch": 0.017640573318632856,
+      "eval_loss": 2.6722819805145264,
+      "eval_runtime": 38.5022,
+      "eval_samples_per_second": 12.415,
+      "eval_steps_per_second": 6.207,
+      "step": 20
+    },
+    {
+      "epoch": 0.022050716648291068,
+      "grad_norm": 6.477142810821533,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.4782,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null