Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eec38dce14a32a5ed84521f25138ae3e6ec5cce02fbae614b6ef91d8b24b709
+oid sha256:e056f7dd2c77c0151716a31e53acd300bee4e94886f70dd9208fb031749cd6f6
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929f4145d54e0893227aa2a2fee8fa07eabe9f53d71d14ceee2d2461c987bdd5
+oid sha256:ac0d1a2e96cc70f48ed65f89dfa42246a1311e146f5e84bdfcce7af295ab06d7
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d78b57bfd8822f6d4dd569ab218b373d27ca759dfddb18577b520307cf2027
+oid sha256:85501daaab0c301949fa550583a1d6090576f079356806ca962c6e2db60935a0
 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": 0.010596026490066225,
+  "epoch": 0.015894039735099338,
   "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": 151.401,
       "eval_steps_per_second": 76.017,
       "step": 6
+    },
+    {
+      "epoch": 0.012362030905077263,
+      "grad_norm": 22.77167320251465,
+      "learning_rate": 0.00014,
+      "loss": 12.8872,
+      "step": 7
+    },
+    {
+      "epoch": 0.0141280353200883,
+      "grad_norm": 18.597755432128906,
+      "learning_rate": 0.00016,
+      "loss": 13.1089,
+      "step": 8
+    },
+    {
+      "epoch": 0.015894039735099338,
+      "grad_norm": 18.6827449798584,
+      "learning_rate": 0.00018,
+      "loss": 13.8305,
+      "step": 9
+    },
+    {
+      "epoch": 0.015894039735099338,
+      "eval_loss": 2.8598744869232178,
+      "eval_runtime": 1.552,
+      "eval_samples_per_second": 153.992,
+      "eval_steps_per_second": 77.318,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14329920356352.0,
+  "total_flos": 22821725011968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null