Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9fbac71c01cba7e8118b8c9fab28a8d81e85098d1de0924653bd43c32e500cc
+oid sha256:12e1d9f715d8862ca28cdde688e126d78f1f4354e5309c185dbdacb55b25c59c
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80fcc843a3281e0dadf6911b688c69eab2e4b01e06a04cd7cfcd3e066e45ba1
+oid sha256:3f6f57255ef4085436c9ed5e7aa6c26ea2928ff049f9e8b1172ee063b3caf91b
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268b907a92307342b44ca97f05d9955310c3f825328fc98573f8ff3422c6bc0a
+oid sha256:c459a2c8cc316df8cc4f80f04b42cf96413340513e5446d85ab7d7620edec535
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1677733659744263,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.4051001821493623,
+  "best_metric": 1.1566288471221924,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477959927140255,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 18.152,
       "eval_steps_per_second": 2.271,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.1252,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 1.1566288471221924,
+      "eval_runtime": 339.7257,
+      "eval_samples_per_second": 18.468,
+      "eval_steps_per_second": 2.311,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.070057571942399e+18,
+  "total_flos": 1.1024547940327404e+18,
   "trial_name": null,
   "trial_params": null
 }