Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40319307ffecbee59bfe6f9166aa64b6b410b39cf17749336c9a22115ebb5f36
+oid sha256:25f1f332ed296e6e7a749e61f61ac16592a2ba6fbb9f1b9f9b737da1547ef470
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee615c2d72be7caeb3e3bcf5a13bf0f47aca34ff19271a2809b1b7a950b69950
+oid sha256:95ec74b870ccf0ff0901d1cf4f0e1a02abd2eb601405d5cc9814a7fffc53412a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e10e7e084e9d9c969a8d9c919cc8f1ecdc23be93922140c6c36dc329b7d816c
+oid sha256:a02d055fd1532df55c5a8db423d165f840db8dc41c6f626c052a7498079b221a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021252103072699905,
+  "epoch": 0.0031878154609049853,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 14.044,
       "eval_steps_per_second": 7.028,
       "step": 6
+    },
+    {
+      "epoch": 0.002479412025148322,
+      "grad_norm": 1.0700939893722534,
+      "learning_rate": 0.00014,
+      "loss": 1.9569,
+      "step": 7
+    },
+    {
+      "epoch": 0.0028336137430266537,
+      "grad_norm": 0.8500562906265259,
+      "learning_rate": 0.00016,
+      "loss": 1.7184,
+      "step": 8
+    },
+    {
+      "epoch": 0.0031878154609049853,
+      "grad_norm": 1.1840053796768188,
+      "learning_rate": 0.00018,
+      "loss": 1.9608,
+      "step": 9
+    },
+    {
+      "epoch": 0.0031878154609049853,
+      "eval_loss": 2.069765329360962,
+      "eval_runtime": 83.9491,
+      "eval_samples_per_second": 14.163,
+      "eval_steps_per_second": 7.088,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1202216761294848.0,
+  "total_flos": 1757086035738624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null