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:a05a3d227c596c939c0c34997d71b34a609bb16763e3cccdeee3dc480bf39d65
+oid sha256:4ee3af761a767f3c400a8d8ca69c07513e09c57e4c999828c9d07a3fa9e4b714
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7e162a392617319676602207f588dad49ec6eafcfe9759f5ae518b1c07eb06
+oid sha256:419a8c99a5f17d5d4184541873ecfaf5c3ec9c9e8a4640411f9561707a7c600a
 size 19859140

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": 0.03083445750626325,
+  "epoch": 0.046251686259394874,
   "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": 80.371,
       "eval_steps_per_second": 40.259,
       "step": 10
+    },
+    {
+      "epoch": 0.03391790325688957,
+      "grad_norm": 0.22862684726715088,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.8543,
+      "step": 11
+    },
+    {
+      "epoch": 0.0370013490075159,
+      "grad_norm": 0.24351704120635986,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.7939,
+      "step": 12
+    },
+    {
+      "epoch": 0.04008479475814222,
+      "grad_norm": 0.24571087956428528,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.7667,
+      "step": 13
+    },
+    {
+      "epoch": 0.04316824050876855,
+      "grad_norm": 0.28732648491859436,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.8403,
+      "step": 14
+    },
+    {
+      "epoch": 0.046251686259394874,
+      "grad_norm": 0.2647162675857544,
+      "learning_rate": 5e-05,
+      "loss": 1.7692,
+      "step": 15
+    },
+    {
+      "epoch": 0.046251686259394874,
+      "eval_loss": 1.8046153783798218,
+      "eval_runtime": 6.903,
+      "eval_samples_per_second": 79.241,
+      "eval_steps_per_second": 39.693,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1475557076238336.0,
+  "total_flos": 2237657983746048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null