Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4943b1c479dffab184a5a31dec0d18399658116d07d244ed707d3a452549dc
+oid sha256:aca366a56c703290a1c9cc7a258adbcd9f098e144d663c5021d041779ed033a5
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2531a9695f2270c1a4141bac7551bd87cf8491440c9aa84b25ce46f25fe578
+oid sha256:f4a33145c1ffc5444221aaed451d1941570dbf557302782c177a892460d88074
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3768fac9e803470e1b5c69fa44328a4906557107a4842023795851adbb508d
+oid sha256:52688ab77e9b0d2e27658533044a9eecc35e94bdc2508083dd51bb81e56a27f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5113636363636364,
+  "epoch": 0.6136363636363636,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 8.682,
       "eval_steps_per_second": 1.115,
       "step": 45
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.4527229070663452,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 1.8334,
+      "step": 48
+    },
+    {
+      "epoch": 0.5795454545454546,
+      "grad_norm": 1.287550449371338,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 2.0519,
+      "step": 51
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "grad_norm": 1.421475887298584,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 2.0602,
+      "step": 54
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "eval_loss": 1.96761155128479,
+      "eval_runtime": 17.0648,
+      "eval_samples_per_second": 8.673,
+      "eval_steps_per_second": 1.113,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0450628465236378e+17,
+  "total_flos": 1.2687552283882291e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null