Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ebe0169da0a9e91b80c2c3a8ece902998a2ba1f4784b2e89a518ed651b29a0
+oid sha256:f7af08bf38edc442cdd0dd11f9880fa53d98d85272f457e008eb5df69db493ac
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e4a3c9749ac8a9ed1e317b4ad11a0eb4816d1eb2d003d5d8a0a5102569f81f
+oid sha256:b57d616a64a25c3bd7c36467954f487c89539382a48deedeb5b9def6f934fd66
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd99a4658dfec332ee6968e96d372e722985cc6df641834de9b1d2be914dae4b
+oid sha256:b68d72e4453f3fb41267c49c417bbf1251e4c68afbf092a72f91cff4b3c02793
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010730477237975159,
+  "epoch": 0.016095715856962737,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 295.163,
       "eval_steps_per_second": 147.581,
       "step": 100
+    },
+    {
+      "epoch": 0.011803524961772675,
+      "grad_norm": 7551.27392578125,
+      "learning_rate": 0.0002,
+      "loss": 15.8545,
+      "step": 110
+    },
+    {
+      "epoch": 0.01287657268557019,
+      "grad_norm": 9171.0,
+      "learning_rate": 0.0002,
+      "loss": 14.3188,
+      "step": 120
+    },
+    {
+      "epoch": 0.013949620409367706,
+      "grad_norm": 8303.6533203125,
+      "learning_rate": 0.0002,
+      "loss": 13.6695,
+      "step": 130
+    },
+    {
+      "epoch": 0.015022668133165223,
+      "grad_norm": 7741.68896484375,
+      "learning_rate": 0.0002,
+      "loss": 13.0679,
+      "step": 140
+    },
+    {
+      "epoch": 0.016095715856962737,
+      "grad_norm": 9833.615234375,
+      "learning_rate": 0.0002,
+      "loss": 13.3664,
+      "step": 150
+    },
+    {
+      "epoch": 0.016095715856962737,
+      "eval_loss": 3.362622022628784,
+      "eval_runtime": 13.3642,
+      "eval_samples_per_second": 293.62,
+      "eval_steps_per_second": 146.81,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 18990130790400.0,
+  "total_flos": 28485196185600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null