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:c44f204f00ebed2311a6d97215df243a4fe2e5ed8fd2528fafb89894c13b13a2
+oid sha256:8b282b6ab82685a92f2f68f6c454a9b4fe8a2f5c2c14b7310bea46a672022f72
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b932c45c8a8e76713b9623419f69d551f1005a9f9ac8a310d5b2978bbba1fb60
+oid sha256:d41749b7400a1599ca029b03bf6fd99d989faabe9a2808a99e8d24e6fa813a33
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f705c082d332de54cfe79c27f867d94dab71248684de742861b0dc66c012a86
+oid sha256:a065a72e547f070b8d65170742d85eb0fdead04d69f3080b7f5cac37b1c906d9
 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": 0.00282585658777817,
+  "epoch": 0.00565171317555634,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 3.3809,
       "step": 9
+    },
+    {
+      "epoch": 0.0033910279053338045,
+      "grad_norm": 4.092407703399658,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.8404,
+      "step": 12
+    },
+    {
+      "epoch": 0.0042387848816672555,
+      "grad_norm": 2.0768399238586426,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.5214,
+      "step": 15
+    },
+    {
+      "epoch": 0.004521370540445073,
+      "eval_loss": 0.639369010925293,
+      "eval_runtime": 370.4721,
+      "eval_samples_per_second": 4.022,
+      "eval_steps_per_second": 2.011,
+      "step": 16
+    },
+    {
+      "epoch": 0.005086541858000706,
+      "grad_norm": 1.9335154294967651,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.5936,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7031303039877120.0,
+  "total_flos": 1.406260607975424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null