Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35c482ffad1f129952aa59730ba0f0979755112b0db9b4de08a4a5293a50fdd
+oid sha256:dadce3bfe987462a5cafc68fc08131a37caea2ef0560e67e36a44a07b1fa7943
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb33c3053e61392c0db977a157e4d76cc38dbc497cdc7a3936e3510409a0f68
+oid sha256:9613635f59f1a0e4273673e708f901ab92fcdf7bca8c76daa6c91152293ab567
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380e80b9e6582470b4911900358ab1de16010eecb7f83d5455453e38ae615ecb
+oid sha256:148ea586316f8f5aa1bd86e07b936f021b6002c24ba7c39e3d88ebc3b263f688
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003989391844413718,
+  "epoch": 0.004352063830269511,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 8.228,
       "eval_steps_per_second": 8.228,
       "step": 44
+    },
+    {
+      "epoch": 0.004080059840877667,
+      "grad_norm": 0.4004136025905609,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.1641,
+      "step": 45
+    },
+    {
+      "epoch": 0.004170727837341614,
+      "grad_norm": 0.4379856586456299,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.1492,
+      "step": 46
+    },
+    {
+      "epoch": 0.004261395833805562,
+      "grad_norm": 0.32673540711402893,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.1826,
+      "step": 47
+    },
+    {
+      "epoch": 0.004352063830269511,
+      "grad_norm": 0.2924938499927521,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.1529,
+      "step": 48
+    },
+    {
+      "epoch": 0.004352063830269511,
+      "eval_loss": 0.20006079971790314,
+      "eval_runtime": 281.9182,
+      "eval_samples_per_second": 8.236,
+      "eval_steps_per_second": 8.236,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6600016269344768e+16,
+  "total_flos": 1.808381660626944e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null