Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca13da1b343d62e3b74c214f51e917a4e6ad518a7969479aaa992359b799a9a
+oid sha256:f82f0245db55d96d9f94a2988999618fae7f5b8bb3d01b5a7bb84f9f9f4f7e4b
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94522e13bf2cbe4d5b7499d255ada3e1412948f6c02f61e4370fce76178e488
+oid sha256:f2ebd6e52e935accca36f0cb4a0d2115b2e403c0ed0d724aebe77f5358f17bcb
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016112140497865142,
+  "epoch": 0.002416821074679771,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 140.272,
       "eval_steps_per_second": 70.136,
       "step": 10
+    },
+    {
+      "epoch": 0.0017723354547651655,
+      "grad_norm": 1.0180318355560303,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.3632,
+      "step": 11
+    },
+    {
+      "epoch": 0.001933456859743817,
+      "grad_norm": 0.8413439989089966,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2812,
+      "step": 12
+    },
+    {
+      "epoch": 0.0020945782647224685,
+      "grad_norm": 0.7293118238449097,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.1871,
+      "step": 13
+    },
+    {
+      "epoch": 0.00225569966970112,
+      "grad_norm": 0.953554630279541,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.2257,
+      "step": 14
+    },
+    {
+      "epoch": 0.002416821074679771,
+      "grad_norm": 0.8305586576461792,
+      "learning_rate": 5e-05,
+      "loss": 0.1871,
+      "step": 15
+    },
+    {
+      "epoch": 0.002416821074679771,
+      "eval_loss": 0.16657570004463196,
+      "eval_runtime": 74.6167,
+      "eval_samples_per_second": 140.103,
+      "eval_steps_per_second": 70.051,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 962182061752320.0,
+  "total_flos": 1443273092628480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null