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:c0ed64d3cea59ac5dd157ce8f220b0138df0d16923ba3f16b7e135578ffe10e7
+oid sha256:4da71344aa1ff97eea0246faca6940d1fb746f997d77b368665852028a6c73a3
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e669def968155ebe4432144f9b3dd3cfff4812be0387c1571be7a8ada287cad6
+oid sha256:9c79322c66fa7684df4904cef6074168257778a516aa21813594de4e09a524a6
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538cff3c10661ea76e600773cc0d09c07a766b0c0a55c1bc0ac438e2a723a38d
+oid sha256:a3874d81c68d237eff7165dcf48e6973ab7998fdec16147e742b36a46a13a76c
 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": 0.0006843455945252353,
+  "epoch": 0.0013686911890504706,
   "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": 52.017,
       "eval_steps_per_second": 26.013,
       "step": 10
+    },
+    {
+      "epoch": 0.0008212147134302823,
+      "grad_norm": 4.1342692375183105,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 12.3301,
+      "step": 12
+    },
+    {
+      "epoch": 0.001026518391787853,
+      "grad_norm": 4.67058801651001,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 13.0502,
+      "step": 15
+    },
+    {
+      "epoch": 0.001026518391787853,
+      "eval_loss": 3.1648316383361816,
+      "eval_runtime": 118.209,
+      "eval_samples_per_second": 52.052,
+      "eval_steps_per_second": 26.03,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012318220701454234,
+      "grad_norm": 6.681149482727051,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 14.0048,
+      "step": 18
+    },
+    {
+      "epoch": 0.0013686911890504706,
+      "eval_loss": 3.0710721015930176,
+      "eval_runtime": 118.1932,
+      "eval_samples_per_second": 52.059,
+      "eval_steps_per_second": 26.034,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 151685494210560.0,
+  "total_flos": 303370988421120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null