Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871806b2dfe9f805fed9d8d8566b21a125d8fde7945d13658c1c717f0bb92ca5
+oid sha256:461dbbaeb5f65cb767c069783ec893610397babc197c6d923540b29ec58a6313
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5f9164b5168f63d6a7e6dcc936890297b53a2cfe54a3b6ed0bf3eb18763595
+oid sha256:7dee9d08462d4dce024de8abf0503cae23ebca74cbbaa8eaf7e994a72cf5b5fb
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
+oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
 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": 0.013437849944008958,
+  "epoch": 0.020156774916013438,
   "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": 20.952,
       "eval_steps_per_second": 10.476,
       "step": 6
+    },
+    {
+      "epoch": 0.015677491601343786,
+      "grad_norm": 1.2121307849884033,
+      "learning_rate": 0.00014,
+      "loss": 5.9106,
+      "step": 7
+    },
+    {
+      "epoch": 0.01791713325867861,
+      "grad_norm": 1.2964277267456055,
+      "learning_rate": 0.00016,
+      "loss": 5.8155,
+      "step": 8
+    },
+    {
+      "epoch": 0.020156774916013438,
+      "grad_norm": 1.2249387502670288,
+      "learning_rate": 0.00018,
+      "loss": 5.7872,
+      "step": 9
+    },
+    {
+      "epoch": 0.020156774916013438,
+      "eval_loss": 5.777248859405518,
+      "eval_runtime": 8.99,
+      "eval_samples_per_second": 20.912,
+      "eval_steps_per_second": 10.456,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1231436170395648.0,
+  "total_flos": 1847154255593472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null