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:b934d244f2cf57e180e2dbb0f98966a6f451e8111c6e562d0a4d8312cfac48cc
+oid sha256:6ff6f7c7d919c4aa3aa022ca5e0c197de5faf259ecb32201d97797235ac1c753
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f342f0f1399139c30e9b55f3ad8c710e44ab265a693b531892c4bcfa4d386c
+oid sha256:c1f04fc892e014b6bc265869739aa884e033b443850ea42ed2c7a274b3d943b4
 size 41119636

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": 0.008732671105774479,
+  "epoch": 0.013099006658661719,
   "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": 22.986,
       "eval_steps_per_second": 11.499,
       "step": 10
+    },
+    {
+      "epoch": 0.009605938216351927,
+      "grad_norm": 1.8270329236984253,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 14.8922,
+      "step": 11
+    },
+    {
+      "epoch": 0.010479205326929374,
+      "grad_norm": 1.498534917831421,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 12.4,
+      "step": 12
+    },
+    {
+      "epoch": 0.011352472437506823,
+      "grad_norm": 1.495392084121704,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 13.5343,
+      "step": 13
+    },
+    {
+      "epoch": 0.01222573954808427,
+      "grad_norm": 1.452784538269043,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 14.3007,
+      "step": 14
+    },
+    {
+      "epoch": 0.013099006658661719,
+      "grad_norm": 1.3574515581130981,
+      "learning_rate": 5e-05,
+      "loss": 13.6316,
+      "step": 15
+    },
+    {
+      "epoch": 0.013099006658661719,
+      "eval_loss": NaN,
+      "eval_runtime": 84.1591,
+      "eval_samples_per_second": 22.921,
+      "eval_steps_per_second": 11.466,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2989275205271552e+16,
+  "total_flos": 1.9463553442381824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null