Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b489e7a8d9d0fa7628fbed15c1fc3077124bbdcea44d5a32220fdb9f614b7ab
+oid sha256:b30aab81a2c73ff179cf5cd5c7ef7a1fc2fc31593baa88ca724f3f56ec142ccd
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32f4f8da53e2d25785ba231f38161a4f4dffd0c2f47b8fc9c1e4ab604b1de1f
+oid sha256:d78c5948cc77970bfa90af60300a5aa1acbcbc4ac7f078590d1bfbbcde8fd1be
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edfda4456ffe1464fd3f2ab00db089363942d2f3ba0836f05c2b7e3e37ffea1
+oid sha256:b5422e431132fda45ce41e11245df931d4ae299f8b0106b13fe4320143a9aa79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15113350125944586,
+  "epoch": 0.20151133501259447,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 58.582,
       "eval_steps_per_second": 29.291,
       "step": 15
+    },
+    {
+      "epoch": 0.16120906801007556,
+      "grad_norm": 0.0886993408203125,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.7713,
+      "step": 16
+    },
+    {
+      "epoch": 0.1712846347607053,
+      "grad_norm": 0.12222450226545334,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.7706,
+      "step": 17
+    },
+    {
+      "epoch": 0.181360201511335,
+      "grad_norm": 0.1096186414361,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 11.7758,
+      "step": 18
+    },
+    {
+      "epoch": 0.181360201511335,
+      "eval_loss": 11.771020889282227,
+      "eval_runtime": 1.4359,
+      "eval_samples_per_second": 58.498,
+      "eval_steps_per_second": 29.249,
+      "step": 18
+    },
+    {
+      "epoch": 0.19143576826196473,
+      "grad_norm": 0.12593254446983337,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.7686,
+      "step": 19
+    },
+    {
+      "epoch": 0.20151133501259447,
+      "grad_norm": 0.12455257028341293,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.7715,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6111001313280.0,
+  "total_flos": 8148001751040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null