Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3bf2795c4458c9a52b54cfdfe5196e5e554d93584208235dc49c60da9967a06
+oid sha256:9f8d7c1f0f792d5521f2984c7e83f1d753f2b7fccf175ea14ee5502a380be231
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78ed199da906e6cfad93b300cc97a9056b9165f8b3915ce1c3986ffbbf0a32d
+oid sha256:7f2fcf57821bb6e00f537c7469cb857ddebe2e6370221ac15e02d8ef19e7dc14
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1425980134b756e495fed364df5798074a840daaa9dbf4ae0b7169122270e9b
+oid sha256:494c8c60ef0549be376f24afcc76568f7deec252f4421bd32e533c506e648827
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001006233617258919,
+  "epoch": 0.002012467234517838,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 24.364,
       "eval_steps_per_second": 12.182,
       "step": 50
+    },
+    {
+      "epoch": 0.0012074803407107028,
+      "grad_norm": 0.7305423021316528,
+      "learning_rate": 0.0002,
+      "loss": 1.2205,
+      "step": 60
+    },
+    {
+      "epoch": 0.0014087270641624865,
+      "grad_norm": 1.4533841609954834,
+      "learning_rate": 0.0002,
+      "loss": 1.2138,
+      "step": 70
+    },
+    {
+      "epoch": 0.0016099737876142705,
+      "grad_norm": 1.0131192207336426,
+      "learning_rate": 0.0002,
+      "loss": 1.3712,
+      "step": 80
+    },
+    {
+      "epoch": 0.0018112205110660542,
+      "grad_norm": 0.9000447988510132,
+      "learning_rate": 0.0002,
+      "loss": 1.1396,
+      "step": 90
+    },
+    {
+      "epoch": 0.002012467234517838,
+      "grad_norm": 1.9898265600204468,
+      "learning_rate": 0.0002,
+      "loss": 1.229,
+      "step": 100
+    },
+    {
+      "epoch": 0.002012467234517838,
+      "eval_loss": 1.4349274635314941,
+      "eval_runtime": 858.4486,
+      "eval_samples_per_second": 24.373,
+      "eval_steps_per_second": 12.187,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.180098949545984e+16,
+  "total_flos": 2.331531527847936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null