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:d9a2ece78f7c018cd3609726177852da9fb11d6e37d1d7f46ba824ea6db36032
+oid sha256:bbfc2bb74168e755fef28118545f891cdf186d2a944f9a29982293b5a92d6f5e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7315564211c17d286e9795a3e5361ec7009dd43a094a592bd42a2de8caa9c486
+oid sha256:b91ec83db83c7de20f16763ab1a766b6d2da74c1ae636c907dd6823bd0dfe743
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc64f0a0e842d32619638e3558fd3b7737be8eec0d62b0251e76c36775a60ada
+oid sha256:dad9ad61d851362b016bc483f26fd031225443550ab3b51598f1b5b7efb51064
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0051013901288101005,
+  "epoch": 0.010202780257620201,
   "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": 0.00018,
       "loss": 1.2362,
       "step": 9
+    },
+    {
+      "epoch": 0.006121668154572121,
+      "grad_norm": 0.3734286427497864,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.1759,
+      "step": 12
+    },
+    {
+      "epoch": 0.007652085193215151,
+      "grad_norm": 0.31507617235183716,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.1013,
+      "step": 15
+    },
+    {
+      "epoch": 0.008162224206096162,
+      "eval_loss": 1.0907156467437744,
+      "eval_runtime": 57.1,
+      "eval_samples_per_second": 14.466,
+      "eval_steps_per_second": 7.233,
+      "step": 16
+    },
+    {
+      "epoch": 0.00918250223185818,
+      "grad_norm": 0.2881808876991272,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9326,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3718654407475200.0,
+  "total_flos": 7767855873392640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null