Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e29563e2f8eb05b785163d7eaee94e5587b6eb06dfd3affb61bbfde7975c970
+oid sha256:e4c75a3dc66f39eaa7aff82866128bfeb194b246e9ca3734ca521914e5d5cca0
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c2246296da887f4e28b7cbb8baa664d5ce66f43aa032d3aabbc9ab0cefba01
+oid sha256:3e264b1b998cd99b172e11b97d69e14db9f5fa1d5349e80dab38049b8579262a
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
+oid sha256:01ae0673394c6d0448d87a05b8dce85b58d04fafa4d6c418a5ee6c92aeaab53d
 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": 0.00024071492332226714,
+  "epoch": 0.0003610723849834007,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 1.599,
       "eval_steps_per_second": 0.799,
       "step": 6
+    },
+    {
+      "epoch": 0.00028083407720931163,
+      "grad_norm": 44.111427307128906,
+      "learning_rate": 0.00014,
+      "loss": 6.7464,
+      "step": 7
+    },
+    {
+      "epoch": 0.00032095323109635615,
+      "grad_norm": 43.45552062988281,
+      "learning_rate": 0.00016,
+      "loss": 5.3264,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003610723849834007,
+      "grad_norm": 42.62737274169922,
+      "learning_rate": 0.00018,
+      "loss": 3.9528,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003610723849834007,
+      "eval_loss": 1.397772192955017,
+      "eval_runtime": 2166.8639,
+      "eval_samples_per_second": 4.843,
+      "eval_steps_per_second": 2.422,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 432572580495360.0,
+  "total_flos": 648858870743040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null