Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5236324e3a7a622b3d3a8c3b4c5e490c95e2b6e344054539dc8e628cd01a41df
+oid sha256:25c4471d4c9cb64d09a6a7b30ac9acaaee7bcb2ad736e42b5cae06ec31ff4d3a
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1139378ee5687e8f880b32c1381b49cc84b4e697788cbff25b2ff8b3d92428
+oid sha256:ce7a8feea41db270f56d340882d0d3416c58bd18cc1b291769b71a91d463cd0f
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010506f5183effa53d7aa8d46a25684a39261fcc416c599950a69030c9f3e88c
+oid sha256:63f4f0d73cfa12954b18866e2bc71834d7bd1e65711fb8787e02fc9fa799dbae
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1022e527da06cbaf638e84a3ed40784692ff247255b0b6df21fb38828d3c2cd9
+oid sha256:b20095ae7e248e019efdc0c5bbc6d09f2da8b05d1a427b4f2fe08d3ff1ff17a2
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19818961410195332,
+  "epoch": 0.39637922820390664,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 39.24,
       "eval_steps_per_second": 9.854,
       "step": 13
+    },
+    {
+      "epoch": 0.2134349690328728,
+      "grad_norm": 0.2040378302335739,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0044,
+      "step": 14
+    },
+    {
+      "epoch": 0.2286803239637923,
+      "grad_norm": 0.2001662701368332,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.9819,
+      "step": 15
+    },
+    {
+      "epoch": 0.24392567889471176,
+      "grad_norm": 0.19261719286441803,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.9881,
+      "step": 16
+    },
+    {
+      "epoch": 0.2591710338256313,
+      "grad_norm": 0.17622911930084229,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.9625,
+      "step": 17
+    },
+    {
+      "epoch": 0.2744163887565507,
+      "grad_norm": 0.15968532860279083,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9984,
+      "step": 18
+    },
+    {
+      "epoch": 0.2896617436874702,
+      "grad_norm": 0.1644553393125534,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.9865,
+      "step": 19
+    },
+    {
+      "epoch": 0.3049070986183897,
+      "grad_norm": 0.1669108122587204,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9395,
+      "step": 20
+    },
+    {
+      "epoch": 0.3201524535493092,
+      "grad_norm": 0.17810705304145813,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.9736,
+      "step": 21
+    },
+    {
+      "epoch": 0.33539780848022865,
+      "grad_norm": 0.17343126237392426,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.9803,
+      "step": 22
+    },
+    {
+      "epoch": 0.35064316341114815,
+      "grad_norm": 0.1609954833984375,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.9451,
+      "step": 23
+    },
+    {
+      "epoch": 0.36588851834206765,
+      "grad_norm": 0.15459877252578735,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.9486,
+      "step": 24
+    },
+    {
+      "epoch": 0.38113387327298714,
+      "grad_norm": 0.21900911629199982,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.9981,
+      "step": 25
+    },
+    {
+      "epoch": 0.39637922820390664,
+      "grad_norm": 0.15433238446712494,
+      "learning_rate": 5e-05,
+      "loss": 0.9631,
+      "step": 26
+    },
+    {
+      "epoch": 0.39637922820390664,
+      "eval_loss": 0.9836097359657288,
+      "eval_runtime": 11.2612,
+      "eval_samples_per_second": 39.25,
+      "eval_steps_per_second": 9.857,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.28217409166377e+16,
+  "total_flos": 8.56434818332754e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null