Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0eac459dad6fc60d68fc7d1c04c4afb3b4e53f67c9e1061528635d2cccbf551
+oid sha256:1f52197f08ac97bce789589be026a6552fa357a40982aaf726e97861587d3fb4
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa73aa0689efbffc29ce161405e62b844c323a4999df892b3bc4741e0c513f83
+oid sha256:aee98f50f61c85daaf59201011827a23c014e12e6fa98809c0893fd188daf5fe
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105f96f979368944b59d27d1e74fc1fa8227279f7d5146ad57761b7d32f1a2d9
+oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007425756934090606,
+  "epoch": 0.0014851513868181212,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,70 @@
       "eval_samples_per_second": 157.763,
       "eval_steps_per_second": 78.886,
       "step": 8
+    },
+    {
+      "epoch": 0.0008353976550851931,
+      "grad_norm": 0.012540486641228199,
+      "learning_rate": 9e-05,
+      "loss": 11.9294,
+      "step": 9
+    },
+    {
+      "epoch": 0.0009282196167613257,
+      "grad_norm": 0.016163840889930725,
+      "learning_rate": 0.0001,
+      "loss": 11.9286,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010210415784374584,
+      "grad_norm": 0.018371539190411568,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 11.9273,
+      "step": 11
+    },
+    {
+      "epoch": 0.0011138635401135909,
+      "grad_norm": 0.016105543822050095,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9294,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012066855017897234,
+      "grad_norm": 0.012495412491261959,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 11.929,
+      "step": 13
+    },
+    {
+      "epoch": 0.001299507463465856,
+      "grad_norm": 0.014130703173577785,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9288,
+      "step": 14
+    },
+    {
+      "epoch": 0.0013923294251419885,
+      "grad_norm": 0.011071882210671902,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9295,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014851513868181212,
+      "grad_norm": 0.015319784171879292,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.93,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014851513868181212,
+      "eval_loss": 11.928154945373535,
+      "eval_runtime": 115.181,
+      "eval_samples_per_second": 157.535,
+      "eval_steps_per_second": 78.772,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 49839734784.0,
+  "total_flos": 98555265024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null