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:f0270ff8db942b1801ffbb10e83049b1704386820363694d832ede35adfd9c49
+oid sha256:69f128ca614fd03dc503a8cb30927e19ea2ca90d875a0e30085dcdc383616716
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae618b18d221d6d15e6ece8d0a925be5128a4f60297ef93aa6c00355cebd16cc
+oid sha256:3f454819a881385019618f2ff391f82c29eb8d96dab9decaeba8c29d6bdbe472
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096dd8906fa13c0263c4485732569b7394e280028b16a12c791d30f7b6a33cb1
+oid sha256:0465759d94b23e403a8125785111894d4a6dc2776a010cdcfd480fcf7cd58060
 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": 0.1437125748502994,
+  "epoch": 0.2155688622754491,
   "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": 81.784,
       "eval_steps_per_second": 40.892,
       "step": 6
+    },
+    {
+      "epoch": 0.16766467065868262,
+      "grad_norm": 14934.6083984375,
+      "learning_rate": 0.00014,
+      "loss": 18.3235,
+      "step": 7
+    },
+    {
+      "epoch": 0.19161676646706588,
+      "grad_norm": 26373.935546875,
+      "learning_rate": 0.00016,
+      "loss": 17.102,
+      "step": 8
+    },
+    {
+      "epoch": 0.2155688622754491,
+      "grad_norm": 14985.6845703125,
+      "learning_rate": 0.00018,
+      "loss": 17.8228,
+      "step": 9
+    },
+    {
+      "epoch": 0.2155688622754491,
+      "eval_loss": 4.397857666015625,
+      "eval_runtime": 0.2368,
+      "eval_samples_per_second": 76.008,
+      "eval_steps_per_second": 38.004,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1139407847424.0,
+  "total_flos": 1709111771136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null