Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c267a52b7c3ddbc2c04d0e2e917acedd383d3ef93d530d1f48565bde020aca4
+oid sha256:629252e9c62969d00b9a31b0f56f1f7ffd153fac8b357e58bb2a436413169fca
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c779d2ba83c384b14484bdc0422ea56e28bcb9b3094ff9dd3a2f054b239ff4e1
+oid sha256:eb20e18f09a2a6cd50a6f41d5d3502d0d994ef1ec443fe9a16c0b3571a422333
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.010373030121683623,
+  "epoch": 0.020746060243367247,
   "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": 14.711,
       "eval_steps_per_second": 7.355,
       "step": 10
+    },
+    {
+      "epoch": 0.011968880909634948,
+      "grad_norm": 3.546405076980591,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.7101,
+      "step": 15
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "grad_norm": 3.569300651550293,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.9901,
+      "step": 20
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "eval_loss": 1.8978782892227173,
+      "eval_runtime": 35.9973,
+      "eval_samples_per_second": 14.668,
+      "eval_steps_per_second": 7.334,
+      "step": 20
+    },
+    {
+      "epoch": 0.01994813484939158,
+      "grad_norm": 2.9264533519744873,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.8919,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null