Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888a5fe9316a9d4295a9ade1229344248e69fce6c01039ac2a132a091084b00b
+oid sha256:bea9de72b37c9143800882af9583cdc2eb1f575c1b89ca52aaacd30da7f4d3f3
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02cbd0cf0559cfbb4d0b57072239e76c7864e5e54fec3c6af26d273326eac6a
+oid sha256:76f6222bbd989611bd7bd8dc6c32fa053f38c49257aa636758392a1b75a53d22
 size 162868

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": 0.0004669937568772127,
+  "epoch": 0.0007004906353158192,
   "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": 585.598,
       "eval_steps_per_second": 292.807,
       "step": 10
+    },
+    {
+      "epoch": 0.000513693132564934,
+      "grad_norm": 4.010018825531006,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 177.6875,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005603925082526553,
+      "grad_norm": 3.2741129398345947,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 177.6875,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006070918839403765,
+      "grad_norm": 3.3117642402648926,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 177.875,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006537912596280978,
+      "grad_norm": 3.361257791519165,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 177.75,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007004906353158192,
+      "grad_norm": 4.330252647399902,
+      "learning_rate": 5e-05,
+      "loss": 177.375,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007004906353158192,
+      "eval_loss": 11.09012508392334,
+      "eval_runtime": 61.4037,
+      "eval_samples_per_second": 587.342,
+      "eval_steps_per_second": 293.679,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 629323333632.0,
+  "total_flos": 957246603264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null