Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33326830ab01622491143c5e17cc86a6336d100f7451fd6b64f23d81566fb6d8
+oid sha256:a79ca9f8f3e9574cc290bc1a64bb65f09530779b2a90128b9c90cbb14274236c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4f1228e85e2a511c51e87733be5eed291dedc098d8a2465f2b32fd8ade38f2
+oid sha256:91780d9c2518ce43ba4d4684215b49fee7c5e44b4535d0a7decd7a0050148739
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afb383c7427b2624c032eb9cec3a33da0380c9292fc9c147c59c840fa8dd709
+oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
 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": 0.0005037719927960605,
+  "epoch": 0.001007543985592121,
   "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": 2.2233,
       "step": 9
+    },
+    {
+      "epoch": 0.0006045263913552726,
+      "grad_norm": 1.2511311769485474,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.8121,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007556579891940908,
+      "grad_norm": 1.166586995124817,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.6843,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008060351884736968,
+      "eval_loss": 1.806187391281128,
+      "eval_runtime": 477.6935,
+      "eval_samples_per_second": 17.497,
+      "eval_steps_per_second": 8.748,
+      "step": 16
+    },
+    {
+      "epoch": 0.0009067895870329089,
+      "grad_norm": 1.883200764656067,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.8519,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null