Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2e24d7f9e7b8fa39718c8a0b447f45ceb462e74a815912dbb2b3520897457c
+oid sha256:e647199bf95ee61d9fe9858f2dcda1f1245d807ddf6538274bf7cb73fe842cd4
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:178adc6b783290c57d0820c548006474b2bc4aed85bee44ae8d119262c589681
+oid sha256:863546bd77606ffcfbb0b238fee97fa9dc32bdcfedcc7825995f8faf77537f39
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19cc634d572060c7c54ed88334b3af6634a5781c94789f45d6e1b43c72a5b75
+oid sha256:40bfb7a2bb9e09979ca0850fe7db152528103f342b31a7d7161ea872baf3db7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032361935891005,
+  "epoch": 0.006472387178201,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 33.399,
       "eval_steps_per_second": 16.699,
       "step": 50
+    },
+    {
+      "epoch": 0.0038834323069206,
+      "grad_norm": 0.9267818927764893,
+      "learning_rate": 0.0002,
+      "loss": 1.1523,
+      "step": 60
+    },
+    {
+      "epoch": 0.0045306710247407,
+      "grad_norm": 1.0530893802642822,
+      "learning_rate": 0.0002,
+      "loss": 1.0864,
+      "step": 70
+    },
+    {
+      "epoch": 0.0051779097425608,
+      "grad_norm": 0.9379938244819641,
+      "learning_rate": 0.0002,
+      "loss": 1.0639,
+      "step": 80
+    },
+    {
+      "epoch": 0.0058251484603809,
+      "grad_norm": 0.6152510643005371,
+      "learning_rate": 0.0002,
+      "loss": 0.9727,
+      "step": 90
+    },
+    {
+      "epoch": 0.006472387178201,
+      "grad_norm": 1.0862324237823486,
+      "learning_rate": 0.0002,
+      "loss": 1.1407,
+      "step": 100
+    },
+    {
+      "epoch": 0.006472387178201,
+      "eval_loss": 1.0274646282196045,
+      "eval_runtime": 194.761,
+      "eval_samples_per_second": 33.405,
+      "eval_steps_per_second": 16.703,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9323102846582784.0,
+  "total_flos": 1.873333749547008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null