Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23450359fdb07ebcd0caa0b3b757cc7ebb632d49851262494267f85df9b75f9
+oid sha256:da90fa0e16e41fdfe764b4234dbea16e19ff591391333eb9adcdc7f6278266c7
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968db29b6bed2f48495b5e4b3842813ade8836d75e6e318a78f20b3c4b192404
+oid sha256:dbe28944b0e69e5f100787ef18ce315e0ecd9f75ff6d8c81f53c778898769765
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f5fe99d81e7517b5957d450f6702d8ebbd0807e19095a89194ae9f341f65dc
+oid sha256:6653bc060345fb346135d580a2bf3cff0c36f2c54b348b5459115515481320b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0053839423918164075,
+  "epoch": 0.006460730870179689,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,42 @@
       "eval_samples_per_second": 8.369,
       "eval_steps_per_second": 4.187,
       "step": 20
+    },
+    {
+      "epoch": 0.005653139511407228,
+      "grad_norm": 2.7933688163757324,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 3.8037,
+      "step": 21
+    },
+    {
+      "epoch": 0.005922336630998048,
+      "grad_norm": 2.6206228733062744,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 4.1224,
+      "step": 22
+    },
+    {
+      "epoch": 0.006191533750588869,
+      "grad_norm": 2.956394910812378,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 3.8059,
+      "step": 23
+    },
+    {
+      "epoch": 0.006460730870179689,
+      "grad_norm": 2.445277690887451,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 3.8613,
+      "step": 24
+    },
+    {
+      "epoch": 0.006460730870179689,
+      "eval_loss": 3.9950814247131348,
+      "eval_runtime": 186.8191,
+      "eval_samples_per_second": 8.377,
+      "eval_steps_per_second": 4.191,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -214,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.533788723085312e+16,
+  "total_flos": 1.8405464677023744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null