Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f14e47adf50843a1ed09972d0c4ffa2558defe162a98c0b13e4e120004c104
+oid sha256:d9a30df7dbb4fb934325aa704ee2ebbca9762b389740fed2808460125f67f61f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6289d5334e77e9e4d2882b0c97545752172bf9c150aca19de5e0f39d64cb60
+oid sha256:f7104e7c505f49abb9ad8d4e02e50cece657dcb1e3523a663fac62f131f36b77
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afb383c7427b2624c032eb9cec3a33da0380c9292fc9c147c59c840fa8dd709
+oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
 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": 0.0020451988955925964,
+  "epoch": 0.004090397791185193,
   "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": 2.1701,
       "step": 9
+    },
+    {
+      "epoch": 0.0024542386747111156,
+      "grad_norm": 3.2550463676452637,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.7727,
+      "step": 12
+    },
+    {
+      "epoch": 0.0030677983433888946,
+      "grad_norm": 1.5403249263763428,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.6086,
+      "step": 15
+    },
+    {
+      "epoch": 0.003272318232948154,
+      "eval_loss": 1.582494854927063,
+      "eval_runtime": 118.746,
+      "eval_samples_per_second": 17.34,
+      "eval_steps_per_second": 8.674,
+      "step": 16
+    },
+    {
+      "epoch": 0.0036813580120666736,
+      "grad_norm": 1.3476464748382568,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5991,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null