Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792667d4b4e520ca0711b8b465670c9bb41b958608fa3cfa4f921b0637175a25
+oid sha256:8a10e8f2512f60e0dd15db52c5b307908d35af7e97d996ad1cbc66cbcfb2c3f2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46055f185f6c8858ec952088d8660b8a5a54408e58f3feccee4739a66e5213b
+oid sha256:327a714d70ddfd97f598cce2f38b6550bd5229a5cb1f63020da7a8319c244323
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6607cf26c854684035d4269af9de5c3a7874f3e74f4e3fbe7133e31c0efcece
+oid sha256:8615ddd7714345498ad71633a72be3fbc11f5ea097653dbf67dce8581e35aec4
 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": 0.007800920508620017,
+  "epoch": 0.011701380762930026,
   "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": 33.622,
       "eval_steps_per_second": 16.811,
       "step": 100
+    },
+    {
+      "epoch": 0.008581012559482019,
+      "grad_norm": 0.6181501746177673,
+      "learning_rate": 0.0002,
+      "loss": 0.8125,
+      "step": 110
+    },
+    {
+      "epoch": 0.00936110461034402,
+      "grad_norm": 0.9252316355705261,
+      "learning_rate": 0.0002,
+      "loss": 0.8039,
+      "step": 120
+    },
+    {
+      "epoch": 0.010141196661206022,
+      "grad_norm": 0.8269910216331482,
+      "learning_rate": 0.0002,
+      "loss": 0.8983,
+      "step": 130
+    },
+    {
+      "epoch": 0.010921288712068024,
+      "grad_norm": 0.7751689553260803,
+      "learning_rate": 0.0002,
+      "loss": 0.7934,
+      "step": 140
+    },
+    {
+      "epoch": 0.011701380762930026,
+      "grad_norm": 0.7328248620033264,
+      "learning_rate": 0.0002,
+      "loss": 0.7806,
+      "step": 150
+    },
+    {
+      "epoch": 0.011701380762930026,
+      "eval_loss": 0.7735591530799866,
+      "eval_runtime": 160.5021,
+      "eval_samples_per_second": 33.632,
+      "eval_steps_per_second": 16.816,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.660181595291648e+16,
+  "total_flos": 2.496451728900096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null