Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399e747c9d6a3c849653897719c3f0f4e34f789f6921bf7292699b7df7680911
+oid sha256:dc55ec36e7b40b236fa29b3a07ef4bbfc22651c465bb8c5aa65a46e475ba31ab
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e91c47de2fa455733b42ab22604cecc1b6185ce8d7eeaaa1c82046313f67ca5
+oid sha256:9fe30e3a36d3aadc8a6fce11ee0ba29ea56602fc131e1f101109207efd76c5c6
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171c39a51d67c5fd26a97228c49c329b7ef38a53ea4a56f315f2a2274edd0e31
+oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
 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": 0.004551661356395084,
+  "epoch": 0.009103322712790168,
   "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": 2.0455,
       "step": 9
+    },
+    {
+      "epoch": 0.005461993627674101,
+      "grad_norm": 0.9622390866279602,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.4306,
+      "step": 12
+    },
+    {
+      "epoch": 0.006827492034592627,
+      "grad_norm": 0.6104026436805725,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.1061,
+      "step": 15
+    },
+    {
+      "epoch": 0.007282658170232135,
+      "eval_loss": 0.945639431476593,
+      "eval_runtime": 86.1537,
+      "eval_samples_per_second": 10.737,
+      "eval_steps_per_second": 5.374,
+      "step": 16
+    },
+    {
+      "epoch": 0.008192990441511151,
+      "grad_norm": 0.513958752155304,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9718,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347792213606400.0,
+  "total_flos": 1.26955844272128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null