Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7eb37af6ff6a59d1061060fc9f40831c860b63da3e1ebcee8979a5bfc2d8ffd
+oid sha256:d9b1ebad499279a008042daa38f6ff7f7a8d6513c8e82e50cb241a67202718af
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe10651526d8c89532608e35d70bcc8fa59f317274dee170f19c15034889ea9
+oid sha256:d8ebd62b11d7245a118b71c791e0dbd06507a9be141f51be517598f2769c59ff
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bab3959305628610ea59050049ccf445cc768a7b69d4a2972396e289560e3b8
+oid sha256:1719fa6ec87d36176081793d1e7e5b701a50bca7359da17f151490755b222cce
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
+oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2403359413146973,
-  "best_model_checkpoint": "./outputs/checkpoint-2300",
-  "epoch": 1.6757741347905282,
+  "best_metric": 2.2235193252563477,
+  "best_model_checkpoint": "./outputs/checkpoint-2400",
+  "epoch": 1.748633879781421,
   "eval_steps": 100,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,13 +329,27 @@
       "eval_samples_per_second": 30.63,
       "eval_steps_per_second": 3.832,
       "step": 2300
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 2.2295,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 2.2235193252563477,
+      "eval_runtime": 204.6216,
+      "eval_samples_per_second": 30.661,
+      "eval_steps_per_second": 3.836,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.55823470611456e+16,
+  "total_flos": 6.841646122235904e+16,
   "trial_name": null,
   "trial_params": null
 }