Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e02854d3a9c1763ee9572a6370cdec912dcc7edf7e688ba1bb6f89d0ad5e0d
+oid sha256:1d42459043686e9cc6d4cb4d46883628c4b09651017690cf769606e49a3b03e0
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:521b4a0a3e1cf5e918ea7b9c5cf31eea037f01659a46bdfe91e36d8a4b20adfa
+oid sha256:6834519d61250957326a6586dfb694608b083e5511e576cf8fa4a271f22761fa
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
+oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
 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": 0.009184845005740528,
+  "epoch": 0.013777267508610792,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 38.69,
       "eval_steps_per_second": 19.415,
       "step": 6
+    },
+    {
+      "epoch": 0.010715652506697282,
+      "grad_norm": 0.038272857666015625,
+      "learning_rate": 0.00014,
+      "loss": 11.9285,
+      "step": 7
+    },
+    {
+      "epoch": 0.012246460007654038,
+      "grad_norm": 0.028404386714100838,
+      "learning_rate": 0.00016,
+      "loss": 11.9387,
+      "step": 8
+    },
+    {
+      "epoch": 0.013777267508610792,
+      "grad_norm": 0.04053066298365593,
+      "learning_rate": 0.00018,
+      "loss": 11.9364,
+      "step": 9
+    },
+    {
+      "epoch": 0.013777267508610792,
+      "eval_loss": 11.931608200073242,
+      "eval_runtime": 7.8922,
+      "eval_samples_per_second": 34.844,
+      "eval_steps_per_second": 17.486,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 708968448.0,
+  "total_flos": 1063452672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null