Training in progress, step 21, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617ec71bb6d7be5013a8eda3a5d4b1f2d765e8add4661c52038bda965224e570
+oid sha256:df55ebbc253d796f893d39cf7e21a9647b86adb544e967a9d5180715b837a154
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2558efb4866a7aa1d374ac514913e1378a6b4bb8b2c76d9944afb73b4dc140
+oid sha256:308b70daea68247765fd18ef395af74c9684014fc606192ef97250d88f568564
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf31c512ec60fac585dc956675d6fafb69f46281c9d5097dd31e373ec167adb
+oid sha256:f3d485376269cb08d5dd5b0246e2a05cf77b55914063aeb7d69eed728d074503
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f940c5d1e031c7c504060a0d45fdef14952a5ed87024c0d526910b242ec67bba
+oid sha256:023bdd8ed5f79026a3d2962328197e68e515f50915f88388642e8ab363ec2e23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5714285714285714,
+  "epoch": 0.8571428571428571,
   "eval_steps": 7,
-  "global_step": 14,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -129,6 +129,63 @@
       "eval_samples_per_second": 248.484,
       "eval_steps_per_second": 124.242,
       "step": 14
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.06866129487752914,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3797,
+      "step": 15
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.05690615996718407,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3774,
+      "step": 16
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 0.05999697744846344,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3833,
+      "step": 17
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.0649491399526596,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3827,
+      "step": 18
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 0.06522160768508911,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3783,
+      "step": 19
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.06119329482316971,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3785,
+      "step": 20
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.05723724141716957,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3765,
+      "step": 21
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "eval_loss": 10.37861442565918,
+      "eval_runtime": 0.1725,
+      "eval_samples_per_second": 243.487,
+      "eval_steps_per_second": 121.743,
+      "step": 21
     }
   ],
   "logging_steps": 1,
@@ -148,7 +205,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5857874018304.0,
+  "total_flos": 8786811027456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null