Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020c0fb13a58b5560f02c8bc234c279da102ee2eb7f298e1a83031fe8ed77a9d
+oid sha256:d8373c5e4c8ca9133fbe3ff268192eb46706f3a841ef92d81816a0577e1744f3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10233c45644298c18560fe20a01ae5677c0810ffb56603956549cd685a5b636e
+oid sha256:0a134857514fb9dfe5e2f59d16b28f578292d717fe3548b42257a0cb8f318fcf
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2ed7bb47263863992b4cee8254a6b09097065ba424f1725823e1454e5ac93b
+oid sha256:5607b27ad36e8b8b6a123386b38e0716be53aa03eb9581fdcae093ba333e0d68
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
+oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04306864064602961,
+  "epoch": 0.05383580080753701,
   "eval_steps": 4,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -159,6 +159,42 @@
       "eval_samples_per_second": 7.809,
       "eval_steps_per_second": 7.809,
       "step": 16
+    },
+    {
+      "epoch": 0.04576043068640646,
+      "grad_norm": 1.0929858684539795,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.2242,
+      "step": 17
+    },
+    {
+      "epoch": 0.04845222072678331,
+      "grad_norm": 1.4121438264846802,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2983,
+      "step": 18
+    },
+    {
+      "epoch": 0.05114401076716016,
+      "grad_norm": 0.9734262824058533,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 0.3084,
+      "step": 19
+    },
+    {
+      "epoch": 0.05383580080753701,
+      "grad_norm": 0.9649080038070679,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.2583,
+      "step": 20
+    },
+    {
+      "epoch": 0.05383580080753701,
+      "eval_loss": 0.28261926770210266,
+      "eval_runtime": 10.3045,
+      "eval_samples_per_second": 7.667,
+      "eval_steps_per_second": 7.667,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -178,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6584249641598976.0,
+  "total_flos": 8068024208719872.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null