Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b45eaa815e65a967e3d8aea054b99da0c3d714b373973f12e9d63dec447c360
+oid sha256:d0106617ceb27e2d43b901da7eb0adaed17851e200dc2848025020d0bf17793a
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc739ccd3077420eb23aa0cecc6e9d9bdedda5f986a663abd768e50065a4e79
+oid sha256:25c017378aa13c2f326fbfa5636e011ba2eeddef7eebb16047ca7fca53b1819d
 size 27231226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea700645d5d847c0004a54d122e57717513cffc5f5cad95acb6fbff114711511
+oid sha256:6ef73aa36afabdfbf7be74c4769cba6429bbaaf8e4ecdfa5b7e9a2a21434f561
 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": 0.024052916416115455,
+  "epoch": 0.04810583283223091,
   "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": 3.1571,
       "step": 9
+    },
+    {
+      "epoch": 0.028863499699338546,
+      "grad_norm": 0.5767693519592285,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.8209,
+      "step": 12
+    },
+    {
+      "epoch": 0.03607937462417318,
+      "grad_norm": 1.131788969039917,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.978,
+      "step": 15
+    },
+    {
+      "epoch": 0.03848466626578473,
+      "eval_loss": 2.703683614730835,
+      "eval_runtime": 2.6207,
+      "eval_samples_per_second": 66.776,
+      "eval_steps_per_second": 33.579,
+      "step": 16
+    },
+    {
+      "epoch": 0.04329524954900782,
+      "grad_norm": 0.47926196455955505,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8346,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69418793041920.0,
+  "total_flos": 138837586083840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null