Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871feece1869ec94f4898ad14e5ff0c917acf15e1816eef7828c3465fd89210d
+oid sha256:d84907382e6743fa94ccae605274c46ca9a37968f360d7b61a36dc7c2504fc92
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9bd5dba385cef38cf4aaa4d08bfe388ca3157778768fb10f7fcc8f1530b1dee
+oid sha256:8d5706dbdc22e24884f1e7a50e570241e3498ac6179a4f1bcd0c5e7bafc5b93b
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359d0ddb346e1a051d153b9361e52227f5a93bfd11d7d59f8d34fe81bcaff9e5
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 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": 0.056607111268353084,
+  "epoch": 0.08491066690252963,
   "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": 75.595,
       "eval_steps_per_second": 37.861,
       "step": 10
+    },
+    {
+      "epoch": 0.062267822395188396,
+      "grad_norm": 0.24282322824001312,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.4583,
+      "step": 11
+    },
+    {
+      "epoch": 0.0679285335220237,
+      "grad_norm": 0.22543445229530334,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.416,
+      "step": 12
+    },
+    {
+      "epoch": 0.073589244648859,
+      "grad_norm": 0.2722141444683075,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.4259,
+      "step": 13
+    },
+    {
+      "epoch": 0.07924995577569433,
+      "grad_norm": 0.26514723896980286,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.4125,
+      "step": 14
+    },
+    {
+      "epoch": 0.08491066690252963,
+      "grad_norm": 0.23801234364509583,
+      "learning_rate": 5e-05,
+      "loss": 10.4257,
+      "step": 15
+    },
+    {
+      "epoch": 0.08491066690252963,
+      "eval_loss": 10.427189826965332,
+      "eval_runtime": 7.8704,
+      "eval_samples_per_second": 75.6,
+      "eval_steps_per_second": 37.863,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8368391454720.0,
+  "total_flos": 12552587182080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null