Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd49d25e55f37306375c7a1b28f0340b1324e3018bfd72063f01f3ae8ddd2bd6
+oid sha256:16bebfe14e75e775d06b7bd5d2995ebfce7a5b3e64ce3a76366069896e42911f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2864e4ad8f83b34c9e6a6fbbf0e187081e091f50037471755dae6ef5eaf888da
+oid sha256:01f27f1a647233d8e7c582a943c5830670bd399def7757ab8af213f70dbbda50
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4a7095e2c9a92fc4e9e7ec1485dbdbe05d9de13f2f18e978e6e1e728b72450
+oid sha256:a1c0adee3287ef4c2fba135caf85ea272d4eeb8f1e3e185eed18b80586c05641
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006070369592117859,
+  "epoch": 0.0012140739184235718,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 7.236,
       "eval_steps_per_second": 3.618,
       "step": 10
+    },
+    {
+      "epoch": 0.0007004272606289837,
+      "grad_norm": 3.883136749267578,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.4828,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009339030141719782,
+      "grad_norm": 5.323849678039551,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8697,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009339030141719782,
+      "eval_loss": 0.5890653729438782,
+      "eval_runtime": 1241.6779,
+      "eval_samples_per_second": 7.263,
+      "eval_steps_per_second": 3.631,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011673787677149727,
+      "grad_norm": 4.373797416687012,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.449,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null