Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee35ec5705f2b811f92a9e6d3e8abd9d7841a06e0b1cdb058d0636a938521326
+oid sha256:6ef73a291946fa1b7764cea2ecbc9fb77d4295b4d1578ccb60c70197fd1f94e0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92847cc760dd26eff17b8a1e591ef8a11654bbf43764bb1bd3c3d2398a270b4
+oid sha256:252696ba8ca13bef82ddb30f526624e5c4c347f19be2f1f8993e43be3ee58755
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffda2d0a868091a3ca3379a2e5ec9b477c1a5e302eb3cf2177106a9488251e8
+oid sha256:4ede67e859d756961386f4ff0eca77ffa5be243d151041e5152a2d4e13ba7209
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12050bdf0b8719c103ea937805d9f70f4d557382cbab2e264e9fd8308c1c5527
+oid sha256:a588f27f213b00969be40ec01aa5e05f45eda8ba0131c7afc4b942f061603955
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019335239589646724,
+  "epoch": 0.002082256571192724,
   "eval_steps": 2000,
-  "global_step": 2600,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -98,6 +98,13 @@
       "learning_rate": 1.9999992671458023e-05,
       "loss": 1.5586,
       "step": 2600
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.3063032627105713,
+      "learning_rate": 1.999999149640793e-05,
+      "loss": 1.6118,
+      "step": 2800
     }
   ],
   "logging_steps": 200,
@@ -105,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 3.3719238906126336e+16,
+  "total_flos": 3.630755793784013e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null