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:a834fd1483ad83f8c0c70d7d8bfa44d6776ea5e3ac71f875d6f945e872289c56
+oid sha256:2ce941deca9c36666bb0f1c546678ed47082c29ea526da8cb064f10003d7bb50
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c9acdc0f910469b351a806d676f16542285dfd13621121cd170bff9e2e9882
+oid sha256:d021a6d6a24125bf6c22d5c861593129874913ab65244f50dc3ca529679471fb
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea8b51e35881ab579a6293996173fcb614aaf154e1048c45664ea9d80e8998e
+oid sha256:86f6c38a2ef2447f68ed1ff203f4ba061cc240709cc4b0d15a640d65adf96104
 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": 0.01869741352446245,
+  "epoch": 0.02243689622935494,
   "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": 23.353,
       "eval_steps_per_second": 2.921,
       "step": 45
+    },
+    {
+      "epoch": 0.019943907759426612,
+      "grad_norm": 0.7918552160263062,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 1.2846,
+      "step": 48
+    },
+    {
+      "epoch": 0.021190401994390776,
+      "grad_norm": 0.7809180617332458,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 1.275,
+      "step": 51
+    },
+    {
+      "epoch": 0.02243689622935494,
+      "grad_norm": 0.6568572521209717,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 1.2913,
+      "step": 54
+    },
+    {
+      "epoch": 0.02243689622935494,
+      "eval_loss": 1.263215184211731,
+      "eval_runtime": 173.5147,
+      "eval_samples_per_second": 23.364,
+      "eval_steps_per_second": 2.922,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.809536922943488e+16,
+  "total_flos": 2.1714443075321856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null