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:f05e61f737ca411cd6da304860b6900fa467e41e5d4430949d46e31d0aa4f2c0
+oid sha256:03b6a24032a44491da9914c627f727b81cf5e7929121544dbf04e6e225758811
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622a7bd0d3c82eae740dd119a9ab44c90368a14f9bcf3bcf7b35ced9a8630a85
+oid sha256:791882984a8d1209ecb88f3cec928de149c81d078321f63393c45819ff0f63c4
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ab38f29dda544c1b38df51e18795bd51fd042e0475e338e0801f2540eb736d
+oid sha256:54b7a13534f277ad1a60bd0592a78bfdcb6c76a678021e64fa07d800a0abd80f
 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": 0.005103125664469487,
+  "epoch": 0.007654688496704231,
   "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": 26.801,
       "eval_steps_per_second": 13.428,
       "step": 6
+    },
+    {
+      "epoch": 0.005953646608547736,
+      "grad_norm": 4.330378532409668,
+      "learning_rate": 0.00014,
+      "loss": 8.4749,
+      "step": 7
+    },
+    {
+      "epoch": 0.006804167552625983,
+      "grad_norm": 4.18934440612793,
+      "learning_rate": 0.00016,
+      "loss": 8.491,
+      "step": 8
+    },
+    {
+      "epoch": 0.007654688496704231,
+      "grad_norm": 4.927352428436279,
+      "learning_rate": 0.00018,
+      "loss": 9.3576,
+      "step": 9
+    },
+    {
+      "epoch": 0.007654688496704231,
+      "eval_loss": 2.026862621307373,
+      "eval_runtime": 18.3928,
+      "eval_samples_per_second": 26.913,
+      "eval_steps_per_second": 13.484,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1017958209945600.0,
+  "total_flos": 1506578150719488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null