Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958573da2a65a00b7e42f13c00500b03fc51811b4a9428a3a58f47939578f28f
+oid sha256:5e714f551456cb321e14da4aa4bfa30082097a1ed6617aec5ebf7161bccfe05e
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04f1f1f53ee976262e68a5306205bcf159acf31b5084f41216ad241e653ece2
+oid sha256:3551db152725e0318800a915ea3d6f03339d8ee9f7b2bcd2b14f5d9016495321
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860872cca214687d6c1a8e76a17368b0a76c81370678fb757e73f62116383aac
+oid sha256:03e377c1380d240d43ba2d545f7f9a7f6e94581d4561c6de13cf0d3287942aef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011537352177675224,
+  "epoch": 0.02307470435535045,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.519,
       "step": 9
+    },
+    {
+      "epoch": 0.013844822613210269,
+      "grad_norm": 0.4261031150817871,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.4124,
+      "step": 12
+    },
+    {
+      "epoch": 0.017306028266512834,
+      "grad_norm": 0.2541234493255615,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.3079,
+      "step": 15
+    },
+    {
+      "epoch": 0.018459763484280356,
+      "eval_loss": 0.3048578202724457,
+      "eval_runtime": 76.5039,
+      "eval_samples_per_second": 4.771,
+      "eval_steps_per_second": 2.392,
+      "step": 16
+    },
+    {
+      "epoch": 0.020767233919815404,
+      "grad_norm": 0.2141341120004654,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.32,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8475499214929920.0,
+  "total_flos": 1.695099842985984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null