Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466fbce9975c9c05303ad2e9f3211bd116287df8f6b5fe724fff725117351d68
+oid sha256:3f256054f75ca529de3de3d31d968831168d96bd93b26db8cfb78737f117fa5f
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00654d0986b4c2807a076dcd6fb04da902863d7591267af0d0f07d64685e5591
+oid sha256:01e19a66b263f1d6b622f520ca1c19416aeecac18d947e4eebc62fbd930353fd
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91357e6edb760a8623172a8598e28f7bde5a301ce8f9e8873076c6ef6d8599e4
+oid sha256:a5247c071411b90e6abc28dfd3094729155dc46bfcf927ecdb927c420369d449
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1040574109853711,
+  "epoch": 1.380071763731714,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,41 @@
       "learning_rate": 9.561854333075736e-05,
       "loss": 0.3029,
       "step": 2000
+    },
+    {
+      "epoch": 1.1592602815346398,
+      "grad_norm": 1.305432915687561,
+      "learning_rate": 9.479575396130191e-05,
+      "loss": 0.2974,
+      "step": 2100
+    },
+    {
+      "epoch": 1.2144631520839084,
+      "grad_norm": 1.2165225744247437,
+      "learning_rate": 9.390639526418681e-05,
+      "loss": 0.2999,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2696660226331768,
+      "grad_norm": 1.5560479164123535,
+      "learning_rate": 9.295178888276614e-05,
+      "loss": 0.2957,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3248688931824455,
+      "grad_norm": 1.236303448677063,
+      "learning_rate": 9.193335342258558e-05,
+      "loss": 0.3,
+      "step": 2400
+    },
+    {
+      "epoch": 1.380071763731714,
+      "grad_norm": 1.3867113590240479,
+      "learning_rate": 9.08526023432446e-05,
+      "loss": 0.3113,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
@@ -166,7 +201,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0607056890750566e+18,
+  "total_flos": 1.3266286871642112e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null