Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824541f81053de4f7fa46a581977991ca6ad014805d1302e91117f1184f9dfaf
+oid sha256:0559b6be4577e6505c674c1d64a0fe28a81db911c8572cbf258123cc67c75a0c
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f60cec25d6eaa2e8cbc9f7bff1aa2d0772c44eac148fa6dacb94f10bfd434b
+oid sha256:d28568bba818770492fa3450bb4994fa67fff313f84f9eb844b1862d14dc1ef5
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5181b6b57805e794f8d032d74fb053f931ebb5d342b5d2ac6ca96c0a3cd5ef01
+oid sha256:f2b1cb1b881b2c5d20961baae5b2d3881fe6eec1e7679ede3e5223de0ac55407
 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": 0.008333333333333333,
+  "epoch": 0.0125,
   "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": 149.468,
       "eval_steps_per_second": 74.734,
       "step": 6
+    },
+    {
+      "epoch": 0.009722222222222222,
+      "grad_norm": 10.223564147949219,
+      "learning_rate": 0.00014,
+      "loss": 10.6506,
+      "step": 7
+    },
+    {
+      "epoch": 0.011111111111111112,
+      "grad_norm": 10.656414031982422,
+      "learning_rate": 0.00016,
+      "loss": 11.1384,
+      "step": 8
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 9.531949043273926,
+      "learning_rate": 0.00018,
+      "loss": 9.4213,
+      "step": 9
+    },
+    {
+      "epoch": 0.0125,
+      "eval_loss": 2.5223546028137207,
+      "eval_runtime": 2.0517,
+      "eval_samples_per_second": 148.167,
+      "eval_steps_per_second": 74.084,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12737706983424.0,
+  "total_flos": 19106560475136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null