Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da33dc8f2bf75852820d1cc4f109fb8f63cc4b799a948019abe4f0797064d7e
+oid sha256:1421fe13e497491d66a2520bce89a66ff5a552a2e9f03313349eef8143554aee
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f3478c89bfe8a550267216ddb3299ed40dd899a395348c314c9731c79c11eb
+oid sha256:f3167ca23a2a197612ad72dc3600b0b9d6973f8f4b16ec12349963a693f8b595
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b5bfedd3fa6c6c17c6bd3f44d59680c9a0bce2372590a767e0a896aa476164
+oid sha256:9c0a3892426d471eda45de06c5d910a0dff8451e4b7f6aae0491711afd0a32a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015594541910331383,
+  "epoch": 0.031189083820662766,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 10.246,
       "eval_steps_per_second": 5.142,
       "step": 10
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 0.3255695104598999,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.3539,
+      "step": 12
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 0.2485169768333435,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3517,
+      "step": 15
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "eval_loss": 1.3882832527160645,
+      "eval_runtime": 26.4826,
+      "eval_samples_per_second": 10.233,
+      "eval_steps_per_second": 5.135,
+      "step": 15
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 0.3311094343662262,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.4781,
+      "step": 18
+    },
+    {
+      "epoch": 0.031189083820662766,
+      "eval_loss": 1.3644858598709106,
+      "eval_runtime": 26.4672,
+      "eval_samples_per_second": 10.239,
+      "eval_steps_per_second": 5.138,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6044488367603712.0,
+  "total_flos": 1.1680565359017984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null