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:d63c6e74c3470ac5c297d4bc4ba1d50016363410d6b8210719af24777011e492
+oid sha256:9f889b2884853eda4f55c9ec0fdfa641df4ee527f0bbdf528bf08000499da2ab
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12baf2d8e0a12b3cd86f93557d324042f1bb2038041d14ceacc84345cbe78cb5
+oid sha256:dc11dc4d7e4459b78a251da66c76cffac9e2b162b84fb7dca23a9c2405e64db3
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc47c3a1464826449c4b706b5a992ed4ba8b7c1085ff4feb0c933558ef732feb
+oid sha256:fd4269677e3d335673fbcee71e5b78f83433b7173960adf0a51d212c7727af18
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012869322751890182,
+  "epoch": 0.0019303984127835272,
   "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": 4.265,
       "eval_steps_per_second": 4.265,
       "step": 6
+    },
+    {
+      "epoch": 0.0015014209877205213,
+      "grad_norm": 40.18137741088867,
+      "learning_rate": 0.00012,
+      "loss": 1.7633,
+      "step": 7
+    },
+    {
+      "epoch": 0.0017159097002520242,
+      "grad_norm": 27.18015480041504,
+      "learning_rate": 0.00014,
+      "loss": 0.5389,
+      "step": 8
+    },
+    {
+      "epoch": 0.0019303984127835272,
+      "grad_norm": 59.13418197631836,
+      "learning_rate": 0.00016,
+      "loss": 2.1024,
+      "step": 9
+    },
+    {
+      "epoch": 0.0019303984127835272,
+      "eval_loss": 2.6004724502563477,
+      "eval_runtime": 230.3217,
+      "eval_samples_per_second": 4.264,
+      "eval_steps_per_second": 4.264,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4601366169255936.0,
+  "total_flos": 6902049253883904.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null