Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3356e0dcb295fc68a038b4193109f01aa6af480c55d4449910331f6b42ad4059
+oid sha256:5e40d05ca3aa346739540d9f75f554cf54fb3471d922e454cb10e10948e5e7c2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d6b9b1528d5be01b613da0eceb5ab6fe94959eff9f875850ddeeeedaee293c
+oid sha256:e452fbb1a0ea417280992ef329845d8786d08f410e0fea8eca1e8dc4154563ab
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36b079fde0d50a71846e4012b55dbfb2dd9d8c0de22b0a59c006da6f057b01b
+oid sha256:bc05cd3a98949633cd0945d642fde31aa27434b462cc4feb8ff105332385519f
 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": 0.013753581661891117,
+  "epoch": 0.020630372492836675,
   "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": 17.742,
       "eval_steps_per_second": 8.871,
       "step": 6
+    },
+    {
+      "epoch": 0.016045845272206302,
+      "grad_norm": 6.4106974601745605,
+      "learning_rate": 0.00014,
+      "loss": 2.1572,
+      "step": 7
+    },
+    {
+      "epoch": 0.01833810888252149,
+      "grad_norm": 4.761960983276367,
+      "learning_rate": 0.00016,
+      "loss": 1.9368,
+      "step": 8
+    },
+    {
+      "epoch": 0.020630372492836675,
+      "grad_norm": 5.439733982086182,
+      "learning_rate": 0.00018,
+      "loss": 2.0602,
+      "step": 9
+    },
+    {
+      "epoch": 0.020630372492836675,
+      "eval_loss": 0.49143391847610474,
+      "eval_runtime": 10.3623,
+      "eval_samples_per_second": 17.757,
+      "eval_steps_per_second": 8.878,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2103206159056896.0,
+  "total_flos": 3154809238585344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null