Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ad590876bbdfcea56000cc76d58d45d8288554cb6049dd9fb20159f276b328
+oid sha256:0a2d246ad869cae2daea9d05f2cf2ea3cfe8ea8b25e02492fd5ff1783f16013f
 size 125918320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781a5f6905f1abb59a0dac36ffbc1d85a1cd0af42d242b192b01d3f7358926a6
+oid sha256:577bf305eb4012e7592b20e3998de4a0ee8f83a1866b53b830da0ef9cbd90ac8
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74f0fa67ad2ea453853ea9c83fafb9413743a4d7deb09428e0f1e45b1df8364
+oid sha256:3c8f3d1a3b6d477a03acbf7dd0224c1db8e20da3ef49010019bfb5ec701f8f08
 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": 0.0006191471248355391,
+  "epoch": 0.0009287206872533086,
   "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": 12.926,
       "eval_steps_per_second": 6.465,
       "step": 6
+    },
+    {
+      "epoch": 0.0007223383123081289,
+      "grad_norm": 4.424726486206055,
+      "learning_rate": 0.00014,
+      "loss": 2.0521,
+      "step": 7
+    },
+    {
+      "epoch": 0.0008255294997807187,
+      "grad_norm": 2.7366762161254883,
+      "learning_rate": 0.00016,
+      "loss": 1.3545,
+      "step": 8
+    },
+    {
+      "epoch": 0.0009287206872533086,
+      "grad_norm": 2.943781852722168,
+      "learning_rate": 0.00018,
+      "loss": 1.9685,
+      "step": 9
+    },
+    {
+      "epoch": 0.0009287206872533086,
+      "eval_loss": NaN,
+      "eval_runtime": 316.0129,
+      "eval_samples_per_second": 12.914,
+      "eval_steps_per_second": 6.459,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135477657894912.0,
+  "total_flos": 4703216486842368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null