Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed986a30c89a035286fcde611da36e9564116f693293ca4f7c507c62928ddaf
+oid sha256:320fcaa4881a085e08afecc439e34ab02fb9b08efb7234483ae7b7879b113f01
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7389276df18e251c25a156be77e8b803cf65ffdac4a4785d223acc1767a0ad8a
+oid sha256:ed961bcbe143c3a1b8c5c2afd53aa8d6ea3586ad407056e24c2504caefa331cf
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e1d9e3c6fddcf57fc2aabd22296e90ae548cdb72410388a1385f5736629c4e
+oid sha256:37d52c1bc6ea42c69efec50a9fdb93109c150d0f5358a667cf5ce03d6e6f892e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.214716911315918,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 1.4571948998178508,
+  "best_metric": 2.201956272125244,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 1.530054644808743,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,13 +287,27 @@
       "eval_samples_per_second": 30.233,
       "eval_steps_per_second": 3.783,
       "step": 2000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002,
+      "loss": 2.178,
+      "step": 2100
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 2.201956272125244,
+      "eval_runtime": 207.8863,
+      "eval_samples_per_second": 30.18,
+      "eval_steps_per_second": 3.776,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.844081922689024e+16,
+  "total_flos": 6.134610229364736e+16,
   "trial_name": null,
   "trial_params": null
 }