Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d5aa71834ff6563f69d07e0002931d7eab3edc8fce6d05b7e869b6cd9c884e
+oid sha256:9e60e4b3769858cf0dd0a5843c31f89fdbf098d73cd2e4bc6510154c38ad4ec3
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e22f2f61f2be8916db372690b50b2539ee3db587719ead409c6b1089925b3af
+oid sha256:facc60c1910de044f5703c2543f518b2ba1a40ce035e295e527cce620613803c
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011774055867895094,
+  "epoch": 0.002354811173579019,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 46.0,
       "step": 9
+    },
+    {
+      "epoch": 0.001412886704147411,
+      "grad_norm": 0.00011067960440414026,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.001766108380184264,
+      "grad_norm": 0.0001415925653418526,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018838489388632149,
+      "eval_loss": 11.5,
+      "eval_runtime": 33.3057,
+      "eval_samples_per_second": 107.399,
+      "eval_steps_per_second": 53.714,
+      "step": 16
+    },
+    {
+      "epoch": 0.0021193300562211167,
+      "grad_norm": 0.00010048472177004442,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 398960885760.0,
+  "total_flos": 797921771520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null