Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd4a2abb0e79d474a00b8479bcfe8e4c94b9be3184edd2cb382da313d280452
+oid sha256:f261465b4d23867a1c619e1e28ccaf6830a23c7bf76177c4e218a80a384afbd5
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d89f03fb33f6de6c1e53f0205ed8b0f0b7472f985ef1cb2ab5f6438eb024b2
+oid sha256:16bdfcc5899e5d96a4d9b26108ef6b0418f3fc5f423b34b5ca282c3aa0f431ee
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5535758ea04ad8843482933d69f64794466d07ff90e13c2204bdc84469ba4d4c
+oid sha256:645efebd8cd0508ea689d2f01abab724e0d823bfce8aee8b4645c3882ad93389
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
+oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.431217908859253,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 1.4048686027526855,
+  "best_model_checkpoint": "./outputs/checkpoint-2500",
+  "epoch": 1.8214936247723132,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,27 @@
       "eval_samples_per_second": 11.259,
       "eval_steps_per_second": 1.409,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 1.3827,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 1.4048686027526855,
+      "eval_runtime": 555.8745,
+      "eval_samples_per_second": 11.287,
+      "eval_steps_per_second": 1.412,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.254944630532506e+17,
+  "total_flos": 6.513063361819607e+17,
   "trial_name": null,
   "trial_params": null
 }