Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610daa3a985b7936da98214445935aaebed6843797f1f7e3690a625f2a0a9bcb
+oid sha256:43d0502367e3523a054c70ca77722edce61b284c92f95edef86664ff36b613ba
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e39812ebdeb08e530e4d20862010a61f4da895dddf99324907b047f1892d00c
+oid sha256:858e07b54b6e048d0f39890d1a64fee6e3939117e523e736caee1c437a16da6f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bff83aa64785e622545a98dc743e577a347f7967e41f1b5f37a5363446796c3
+oid sha256:a82d5715858a6b453029f5e503f3f7b61d7408ce2719abf36d70ab6c90639243
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1178267002105713,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 1.9672131147540983,
+  "best_metric": 2.110224485397339,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 30.515,
       "eval_steps_per_second": 3.818,
       "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 2.064,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 2.110224485397339,
+      "eval_runtime": 206.36,
+      "eval_samples_per_second": 30.403,
+      "eval_steps_per_second": 3.804,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.88266658608128e+16,
+  "total_flos": 8.16793378136064e+16,
   "trial_name": null,
   "trial_params": null
 }