Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16de237da9e7e4ba6c9d3c22d0a3cc531d42dd3b4f30dfd95ac0675dfd8b1b16
+oid sha256:16faa071e37c443ce111aecbe6f79157e93076440e444ee37b97a97d9bf5b1aa
 size 125918320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b9e28c466a31c6b385d8fa1c9530b2275601ae36ed645ae5da61fc9cc73ecd
+oid sha256:3333806bb5de7491b94506bf313664883a33244b50719e491eeb35bdd3aa0627
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dac42d8984a6619e6eab6c4002ef7913983f3411914dd58a700599c18730a02
+oid sha256:94511bbc42184f8dae780daa982198c415e4b1d25cee4616831826d938f6008f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006824644549763033,
+  "epoch": 0.010236966824644549,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 7.857,
       "eval_steps_per_second": 0.983,
       "step": 18
+    },
+    {
+      "epoch": 0.007962085308056872,
+      "grad_norm": 5.295720100402832,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 2.5272,
+      "step": 21
+    },
+    {
+      "epoch": 0.009099526066350712,
+      "grad_norm": 4.090085983276367,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 2.3416,
+      "step": 24
+    },
+    {
+      "epoch": 0.010236966824644549,
+      "grad_norm": 4.162299156188965,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.010236966824644549,
+      "eval_loss": 0.562384307384491,
+      "eval_runtime": 565.6143,
+      "eval_samples_per_second": 7.853,
+      "eval_steps_per_second": 0.983,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.859990369737114e+16,
+  "total_flos": 7.368372496053043e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null