Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6848ad7fe0ab9ebd010e4b53d428e9a2ecbf51eac7025ec3372d035f504cfda7
+oid sha256:1f6d32b846963fce3b0ce83bc9ac9a904e044e8fdc2b2aa11ee14ec67e67c82b
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9568be57a32d71e64a0a8a76e2f0252a12fca42f5ea09f44aeb7dc5a1241d96e
+oid sha256:1a63a7155896dcbc653500b72848d0bb43bb7c65fc786fdea9a10aad2c660d39
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c30a031a5dd4c570fd24101d516cbee229a4a54d7a97d450184c72ae0b9a52b
+oid sha256:1408ea0898f967d863a6906088863086fda9adc1a0df2c6b0f931de941d308d7
 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": 0.0008767123287671233,
+  "epoch": 0.001315068493150685,
   "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": 9.195,
       "eval_steps_per_second": 4.597,
       "step": 10
+    },
+    {
+      "epoch": 0.0009643835616438356,
+      "grad_norm": 9.178277969360352,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.2672,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010520547945205478,
+      "grad_norm": 6.568050861358643,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.0439,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011397260273972602,
+      "grad_norm": 4.214171409606934,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.3993,
+      "step": 13
+    },
+    {
+      "epoch": 0.0012273972602739726,
+      "grad_norm": 3.7734668254852295,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5691,
+      "step": 14
+    },
+    {
+      "epoch": 0.001315068493150685,
+      "grad_norm": 3.103121280670166,
+      "learning_rate": 5e-05,
+      "loss": 1.4274,
+      "step": 15
+    },
+    {
+      "epoch": 0.001315068493150685,
+      "eval_loss": 1.1212583780288696,
+      "eval_runtime": 4181.543,
+      "eval_samples_per_second": 9.188,
+      "eval_steps_per_second": 4.594,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5767634406604800.0,
+  "total_flos": 8651451609907200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null