Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589d93e1644290e1763ee903924287395b8711bcc462c358790f2bd476968213
+oid sha256:bc0a2c4f5804bc833543977a5610b19ecf809ed3e1c030f43ee00839a70ff92f
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6672bfe400a9d4d5706252e9cd899264f30591c191b7f2dc6bc0ae9cca496f7
+oid sha256:79a7ca2ef6a2d13030630527be80ee345db1102a3327f9d64c73b1ea3b3437b9
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3fde9edff067179eaac97e25ed4311ccba425a548976dedf75ffc08ca49cb4
+oid sha256:923c546d72e202dad57c207c925fd1b276eaac8a8b8d2e0e6daee9cfc60c92c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6813880126182965,
+  "epoch": 0.7949526813880127,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 59.772,
       "eval_steps_per_second": 7.583,
       "step": 54
+    },
+    {
+      "epoch": 0.7192429022082019,
+      "grad_norm": 0.7091464400291443,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.7363,
+      "step": 57
+    },
+    {
+      "epoch": 0.7570977917981072,
+      "grad_norm": 0.7677245140075684,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4822,
+      "step": 60
+    },
+    {
+      "epoch": 0.7949526813880127,
+      "grad_norm": 0.6542797088623047,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.5378,
+      "step": 63
+    },
+    {
+      "epoch": 0.7949526813880127,
+      "eval_loss": 1.6406694650650024,
+      "eval_runtime": 2.2416,
+      "eval_samples_per_second": 59.778,
+      "eval_steps_per_second": 7.584,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4307701947432960.0,
+  "total_flos": 4992608533217280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null