Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f233f915dfa0e48b4bc64f2ab1fb2486e14f3adae29f3c126b11bd29273ff01
+oid sha256:60b03b382389432264b36c03388bb267abcb745444e5e3ac19c662acd53bc3cc
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b200aab26602fda1995a1b7b35615500e5349445d817fc694cad3489da1e7e1
+oid sha256:0990efff57d9e2e12923df256c7a7dc58ebfbdec641874022761942c204a30ea
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:19a32067fb5f557237726e10d4e5248eee478b9f21bf82db1c657e481f64a127
 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": 0.00016842105263157895,
+  "epoch": 0.0002526315789473684,
   "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": 33.78,
       "eval_steps_per_second": 16.89,
       "step": 6
+    },
+    {
+      "epoch": 0.00019649122807017543,
+      "grad_norm": 0.5961188077926636,
+      "learning_rate": 0.00014,
+      "loss": 1.3514,
+      "step": 7
+    },
+    {
+      "epoch": 0.00022456140350877193,
+      "grad_norm": 0.5710781216621399,
+      "learning_rate": 0.00016,
+      "loss": 1.1787,
+      "step": 8
+    },
+    {
+      "epoch": 0.0002526315789473684,
+      "grad_norm": 0.5524436831474304,
+      "learning_rate": 0.00018,
+      "loss": 1.2798,
+      "step": 9
+    },
+    {
+      "epoch": 0.0002526315789473684,
+      "eval_loss": 1.2107768058776855,
+      "eval_runtime": 446.9412,
+      "eval_samples_per_second": 33.561,
+      "eval_steps_per_second": 16.781,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 106845796564992.0,
+  "total_flos": 160268694847488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null