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:f8511e20117372f86c2e7cdc7673c0053c8e5ea834a35978653b3ab27bcdf093
+oid sha256:b179488b439d4857b47c213a9362a2a4538448a106316415aea1f4d6571558be
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6cb0064609579241a183e4b65e188c7b82f00dced64ade9b98134b5fa3a07a
+oid sha256:da866dd1ff954c8dacfa658c6986f5c19c45b8896a0ca000278c6bfb016b4088
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
+oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
 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": 0.00102880658436214,
+  "epoch": 0.0015432098765432098,
   "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": 92.214,
       "eval_steps_per_second": 46.107,
       "step": 6
+    },
+    {
+      "epoch": 0.0012002743484224967,
+      "grad_norm": 61.499454498291016,
+      "learning_rate": 0.00014,
+      "loss": 17.7969,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013717421124828531,
+      "grad_norm": 54.04728698730469,
+      "learning_rate": 0.00016,
+      "loss": 18.5754,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015432098765432098,
+      "grad_norm": 58.343406677246094,
+      "learning_rate": 0.00018,
+      "loss": 17.6067,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015432098765432098,
+      "eval_loss": 4.022153377532959,
+      "eval_runtime": 26.4858,
+      "eval_samples_per_second": 92.729,
+      "eval_steps_per_second": 46.365,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52637139468288.0,
+  "total_flos": 78955709202432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null