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:f5426063e43ebc812755f2333138461b28d31a45e84812f13d83de889f82ab99
+oid sha256:974ee799f54854bf1072a69159bc1af530dbfaa8509e7c531f5f7937a921ba43
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a330e893a6cf2d9ad8569eea605517adf30370516ffcfcb66ad971d384e173c7
+oid sha256:0c7c1ec18afab6f1494a4b94fe67094018e384030e9b987849443c65756ed8d8
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb3140e11f0d5833c00e9f4928bfeb27b734066b93311a0b98886e275b02212
+oid sha256:8fd9a273afce6245b47c12202ac7b282edb77ae2a41fe12118524eef3d6863ae
 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": 8.899535370090886e-05,
+  "epoch": 0.0001334930305513633,
   "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": 18.407,
       "eval_steps_per_second": 9.204,
       "step": 6
+    },
+    {
+      "epoch": 0.00010382791265106034,
+      "grad_norm": 1553.6900634765625,
+      "learning_rate": 0.00014,
+      "loss": 92.2466,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011866047160121182,
+      "grad_norm": 963.3795166015625,
+      "learning_rate": 0.00016,
+      "loss": 92.4837,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "grad_norm": 1251.0181884765625,
+      "learning_rate": 0.00018,
+      "loss": 94.2449,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "eval_loss": 23.44436264038086,
+      "eval_runtime": 1621.1736,
+      "eval_samples_per_second": 17.51,
+      "eval_steps_per_second": 8.755,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53623740432384.0,
+  "total_flos": 80435610648576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null