Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47998a8b750ea57dc68401817ab3cef5b8f611135711325dfa06022c1542df40
+oid sha256:8faeb0ff1806866e44086322934e79b60a40f902258e1bc10b99ae9e80d70695
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5132b712edc9d5803825782dc6245c8dc2edb90bfbf608092fcb77d8ce84321e
+oid sha256:f52f59802895eb570233fa63568becf54298340f80a4d3b09b8b91eebecd3aec
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2fdb38126bec91fa63804962e3448cc4fcaad4f83a5b93d7f41f106d1ea322
+oid sha256:8288cb8cb0b54526d97f2ff59da883c307360a17e99a5d7d1d6e7afb2436e03b
 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": 0.0005862609740726084,
+  "epoch": 0.0011725219481452168,
   "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": 3.6814,
       "step": 9
+    },
+    {
+      "epoch": 0.0007035131688871301,
+      "grad_norm": 3.7987024784088135,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.6162,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008793914611089126,
+      "grad_norm": 2.854783296585083,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.0406,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009380175585161735,
+      "eval_loss": 0.5670868754386902,
+      "eval_runtime": 1144.568,
+      "eval_samples_per_second": 6.275,
+      "eval_steps_per_second": 3.137,
+      "step": 16
+    },
+    {
+      "epoch": 0.001055269753330695,
+      "grad_norm": 2.479992628097534,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.3954,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.26956599246848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null