Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137e96b301913cb0e523d3d633f010f098915e7e046dfcbf10d79fed6be8ce76
+oid sha256:cd0fd5e8554cff4e67072da4803bd99ff15e625160dba045911ba4a02ba963e0
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86344e2450496f0ad06c3787a5f399c6bfe3e6013bf020efcb70d4105cae6b69
+oid sha256:a17cb1ef7a45ccc3dc9e6748f9d9e0c85de9cf915d16d5995b3bcf905f42ec11
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
+oid sha256:847e6adafbce1ce406fa778b8b6d2b9c0edf688a485355f7d2d7c87ce66c4fa0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011039050641644819,
+  "epoch": 0.013798813302056023,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 12.799,
       "eval_steps_per_second": 1.602,
       "step": 20
+    },
+    {
+      "epoch": 0.01159100317372706,
+      "grad_norm": 4.178547382354736,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.3626,
+      "step": 21
+    },
+    {
+      "epoch": 0.013246860769973782,
+      "grad_norm": 5.464514255523682,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.2085,
+      "step": 24
+    },
+    {
+      "epoch": 0.013798813302056023,
+      "eval_loss": 2.240475654602051,
+      "eval_runtime": 238.4465,
+      "eval_samples_per_second": 12.8,
+      "eval_steps_per_second": 1.602,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.017027157491712e+16,
+  "total_flos": 3.77128394686464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null