Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714e6464882a12977f9161b0725f0f293b62727654edea6c7cd1304a993dfac9
+oid sha256:ee35ec5705f2b811f92a9e6d3e8abd9d7841a06e0b1cdb058d0636a938521326
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a8ffb4f5658e0682ef76e7152bbe595d7237d7f6021f8772ee7e472eef8d29
+oid sha256:a92847cc760dd26eff17b8a1e591ef8a11654bbf43764bb1bd3c3d2398a270b4
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f378a879622820d825a4a635bf9928d84f866b9daa73fe1f9fc42587e2508c66
+oid sha256:7ffda2d0a868091a3ca3379a2e5ec9b477c1a5e302eb3cf2177106a9488251e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fd41f1ab3b29e88abab4e0f95a7542016a4426d0de6a4edad353ac7f02e3e5
+oid sha256:12050bdf0b8719c103ea937805d9f70f4d557382cbab2e264e9fd8308c1c5527
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017847913467366205,
+  "epoch": 0.0019335239589646724,
   "eval_steps": 2000,
-  "global_step": 2400,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,13 @@
       "learning_rate": 1.9999993759176304e-05,
       "loss": 1.564,
       "step": 2400
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.8213422298431396,
+      "learning_rate": 1.9999992671458023e-05,
+      "loss": 1.5586,
+      "step": 2600
     }
   ],
   "logging_steps": 200,
@@ -98,7 +105,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 3.125489981718528e+16,
+  "total_flos": 3.3719238906126336e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null