Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984110147188a1f6ee8591aab864463010a00ba240c00c00dd51c80985667741
+oid sha256:a0445650b673f6acf4b81accd31266f2c4637fc19aa77cc6e396eaa4975a1eab
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec0ba721da412ffc1f7465918fac4e09155be321984860a0ace335e108aea67
+oid sha256:286fd08dd930b8bfdfaa5d84780012e0686a79b98621af42af734f8c4f1c5e8d
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f05d96ec1d3414d8a43b755006d0bfaacb7e09fc9f8c12126cc859dd6ce3e83
+oid sha256:330a75bddc9a21e822cfc3670609e9a673a0ce82e6de4caea030d25bd7d00980
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2529035806655884,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 1.221109390258789,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.5500910746812386,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,41 @@
       "eval_samples_per_second": 11.289,
       "eval_steps_per_second": 1.412,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.1648,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 1.2390271425247192,
+      "eval_runtime": 555.5992,
+      "eval_samples_per_second": 11.292,
+      "eval_steps_per_second": 1.413,
+      "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.1497,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.221109390258789,
+      "eval_runtime": 555.5623,
+      "eval_samples_per_second": 11.293,
+      "eval_steps_per_second": 1.413,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.592632013251543e+17,
+  "total_flos": 9.112777792001802e+17,
   "trial_name": null,
   "trial_params": null
 }