Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cca2af601992adcda95b08dc762ca731050e4a186832f91b50e950235f85d90
+oid sha256:16fc8e3d1db654c9e2e4572b150cb7b1e23944fa0774ee76e37f9e75a8f5d87f
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be7dc276a1bb7b12ea054e25bfcd31dd7e1ff910d81088314884e223ccb756d
+oid sha256:e9be36c1d691914526051a456bc55a32162e247ee7db53d7813d5e437520a88b
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44b4c2939ff17bcfa7216556067440798f6d3d905dfa73c6ecaa290f650fdf5
+oid sha256:2524d0bbcba4740cd7bcb7b38bf3a617d1bce7003e9fd41727db5747210a9ac1
 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": 0.3367003367003367,
+  "epoch": 0.5050505050505051,
   "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": 24.585,
       "eval_steps_per_second": 12.391,
       "step": 100
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 3.9325928810285404e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 3.4849592339014634e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 3.0408471502596512e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 2.9038872526143678e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 2.3728689484414645e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "eval_loss": 9.585951374901924e-07,
+      "eval_runtime": 5.0581,
+      "eval_samples_per_second": 24.713,
+      "eval_steps_per_second": 12.455,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1121827078144e+16,
+  "total_flos": 3.1682740617216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null