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:c17e36c580ec55b7a0ff935294df3fe68f8c9ffc689792f3aff4cb9471ba456f
+oid sha256:d31f48285c8ae869354663d9d9212410b3165056bcfc7a13d9310fb5bb350f13
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf43bcf58ab6c923744dc9f5ccfa3d49ad33b1f4749d4ee9918213545432704
+oid sha256:4f594a1741c1280b22b9282963847c14d0b95d6291e07e46368e9c12db2b6544
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399f12128758c20f45f058a67599e1b9a2d9cd495e1ccd71687a907821c8d121
+oid sha256:49593839f9d1f47c098855c411ae242b6ae0da44eb823919bbad1cbb6de79de6
 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": 0.00020941860160728776,
+  "epoch": 0.00031412790241093166,
   "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": 420.819,
       "eval_steps_per_second": 210.41,
       "step": 6
+    },
+    {
+      "epoch": 0.0002443217018751691,
+      "grad_norm": 0.5813419222831726,
+      "learning_rate": 0.00014,
+      "loss": 6.9556,
+      "step": 7
+    },
+    {
+      "epoch": 0.00027922480214305034,
+      "grad_norm": 0.6712679266929626,
+      "learning_rate": 0.00016,
+      "loss": 6.9495,
+      "step": 8
+    },
+    {
+      "epoch": 0.00031412790241093166,
+      "grad_norm": 0.5434843897819519,
+      "learning_rate": 0.00018,
+      "loss": 6.9555,
+      "step": 9
+    },
+    {
+      "epoch": 0.00031412790241093166,
+      "eval_loss": 6.940571308135986,
+      "eval_runtime": 28.3785,
+      "eval_samples_per_second": 425.111,
+      "eval_steps_per_second": 212.555,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9887477760.0,
+  "total_flos": 15160799232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null