Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3645dbbec1be4cc33dbf9237e02ae36389451818310aa8b3ec124e5d0b223343
+oid sha256:2b8b4ffc45d18dc3fdecea9c8e570720100ad7dcef73e1123d900e4b29b3f96f
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6176ac2092aaf8ef73cb146871883e75309796c8e3e7c6b0722d60f538c4d6e4
+oid sha256:73e18d2cedd4162cbc27a8feb277d031f60713dda96fbed98ebf1944bf52125d
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
+oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
 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": 0.06315789473684211,
+  "epoch": 0.09473684210526316,
   "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": 53.063,
       "eval_steps_per_second": 26.531,
       "step": 6
+    },
+    {
+      "epoch": 0.07368421052631578,
+      "grad_norm": 5.213286876678467,
+      "learning_rate": 0.00014,
+      "loss": 4.6999,
+      "step": 7
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 5.555608749389648,
+      "learning_rate": 0.00016,
+      "loss": 4.5009,
+      "step": 8
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "grad_norm": 6.240391731262207,
+      "learning_rate": 0.00018,
+      "loss": 4.406,
+      "step": 9
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "eval_loss": 4.4296064376831055,
+      "eval_runtime": 0.7654,
+      "eval_samples_per_second": 52.259,
+      "eval_steps_per_second": 26.129,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null