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:af07823c4cb973ebb13b823c3908906ca269080618838a9dc34fd997679144c5
+oid sha256:737176acb2f58e64d05846a53ccea8d22dd661d6de333d8c74a086012a666c81
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4598f58d62c9238984653abbeca3c4d0269ad2d55ce3340238ce20bb46bd26e9
+oid sha256:a7cf92d0327a57c268d425c2358353c613f0c40b583c22a0baec4b4c0481e2ab
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57caf8339a7ba861d2b2a967b4505f18f8c7d34af6b764b7f5c429ba7fe4fa7
+oid sha256:20c3d5cbeb8cdb702c7af2051ef34525b3edb220b994d650ce737f871f3d07c8
 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": 0.004921259842519685,
+  "epoch": 0.00984251968503937,
   "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": 4.9321,
       "step": 9
+    },
+    {
+      "epoch": 0.005905511811023622,
+      "grad_norm": 2.2096595764160156,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.3159,
+      "step": 12
+    },
+    {
+      "epoch": 0.0073818897637795275,
+      "grad_norm": 2.601541519165039,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.5939,
+      "step": 15
+    },
+    {
+      "epoch": 0.007874015748031496,
+      "eval_loss": 1.2247308492660522,
+      "eval_runtime": 12.5266,
+      "eval_samples_per_second": 68.335,
+      "eval_steps_per_second": 34.167,
+      "step": 16
+    },
+    {
+      "epoch": 0.008858267716535433,
+      "grad_norm": 1.7524709701538086,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.542,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 495876053139456.0,
+  "total_flos": 1048101657772032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null