Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cba37edda8ec089dc6e8c123f95120ff2f86a9ec0df1001107ad07c1d06193
+oid sha256:721849f9bdf743472f0a10f2087a30067665ff85385534c8af1c753ca4391b5e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42586373a4a6917cd301c2ed7558b055ab5dcd30e83351b3731fcb6f265eb53c
+oid sha256:6173d1adfdb2ad6474b9e162945362478d2c0792a577497c5edb6ddbaaee7644
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983c5c4c2002f613150a9ec518ceccd4866895ed9d8311633a539b15b7c4e719
+oid sha256:d3d170c8db509ef67a93e9ec03a7cb684f62e9573629664fc6b02b7f7348875f
 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": 0.1927710843373494,
+  "epoch": 0.21029572836801752,
   "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": 9.323,
       "eval_steps_per_second": 4.71,
       "step": 44
+    },
+    {
+      "epoch": 0.19715224534501644,
+      "grad_norm": 0.06332933157682419,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.008,
+      "step": 45
+    },
+    {
+      "epoch": 0.20153340635268346,
+      "grad_norm": 0.06510249525308609,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0065,
+      "step": 46
+    },
+    {
+      "epoch": 0.2059145673603505,
+      "grad_norm": 0.0478518009185791,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0045,
+      "step": 47
+    },
+    {
+      "epoch": 0.21029572836801752,
+      "grad_norm": 0.12734544277191162,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0174,
+      "step": 48
+    },
+    {
+      "epoch": 0.21029572836801752,
+      "eval_loss": 0.013411710038781166,
+      "eval_runtime": 10.3803,
+      "eval_samples_per_second": 9.345,
+      "eval_steps_per_second": 4.72,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.264304047665971e+16,
+  "total_flos": 3.5610589610901504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null