Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85278223068f24a7826dddfe02c46fa23438be0e3775f31b84ddd366e563018
+oid sha256:14c9f3275cdbfeadc16f587e2a007afd85c91b7eed91f0e3d102da7efa083839
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a8b8128e99daafc325a8e18bf8870ce648686c729d4fe2740e32ce8db4de2c
+oid sha256:657d034203185a031d9e2ac689d7370db0942eea2b2039c0f784901f9c9775e5
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003370502485745583,
+  "epoch": 0.0005055753728618375,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 301.583,
       "eval_steps_per_second": 150.791,
       "step": 6
+    },
+    {
+      "epoch": 0.0003932252900036514,
+      "grad_norm": 0.4972425699234009,
+      "learning_rate": 0.00014,
+      "loss": 44.3123,
+      "step": 7
+    },
+    {
+      "epoch": 0.00044940033143274445,
+      "grad_norm": 0.5303033590316772,
+      "learning_rate": 0.00016,
+      "loss": 44.3085,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005055753728618375,
+      "grad_norm": 0.5744194984436035,
+      "learning_rate": 0.00018,
+      "loss": 44.3066,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005055753728618375,
+      "eval_loss": 11.080731391906738,
+      "eval_runtime": 24.3255,
+      "eval_samples_per_second": 308.155,
+      "eval_steps_per_second": 154.077,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8965324800.0,
+  "total_flos": 13447987200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null