Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba3724ae64fc51e2227c8c68ab46cbb74a20d751048c6e396cbbb8422bbd041
+oid sha256:7d3b07bd310c2c77bf281dbf16a61be566959ba79626d5bb4239b5ccbd82a979
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab4ec4667a0ffa22e69096e1081261fc578141e6e2e5ce253173f2ac2385c92
+oid sha256:6ae1ad81131d86ae05701f2915f8702dd6e795ee3ea134033f8ce212b8642cca
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfb429fe11bbb7b4706ac3ef71d598ecdc0cdf7b9afab8efadb0c323e9f3463
+oid sha256:7508b824c8dad473e22c31032ece242e15353e035fff9b2306e9e0fda5e83d7a
 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": 0.020835744877879384,
+  "epoch": 0.02500289385345526,
   "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": 24.824,
       "eval_steps_per_second": 3.105,
       "step": 45
+    },
+    {
+      "epoch": 0.022224794536404677,
+      "grad_norm": 0.5362297892570496,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 1.6418,
+      "step": 48
+    },
+    {
+      "epoch": 0.02361384419492997,
+      "grad_norm": 0.4934613108634949,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 1.6214,
+      "step": 51
+    },
+    {
+      "epoch": 0.02500289385345526,
+      "grad_norm": 0.4781782627105713,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 1.635,
+      "step": 54
+    },
+    {
+      "epoch": 0.02500289385345526,
+      "eval_loss": 1.6491777896881104,
+      "eval_runtime": 146.6097,
+      "eval_samples_per_second": 24.814,
+      "eval_steps_per_second": 3.103,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.515358636310528e+16,
+  "total_flos": 3.0184303635726336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null