Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2ef53c596bc85be4326782aaee1bd1832f3f12ad68b89f713ee571afc5a867
+oid sha256:6dbea9d99327f08b5e2f4c41f3c505dd3407a2016da7ac4bb1f7c468202a0443
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a719d122e46781e039718c6690e78a21e5ce6a4d3432c983b3080710d813515
+oid sha256:d6ca561cedc2b983dbdc1d6be07f1ac8544bb7f315a0e8463d7e2e8309743384
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fe4992c6c19e6bb7168c5f362cac0252bc422b1e6e626dc30177dfd901e744
+oid sha256:119e0e6feea8782c2d5cfd3117e6d646e92bd2a074259490f6554f07264c2392
 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": 0.9128983020782471,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 3.6,
+  "best_metric": 0.9102813601493835,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 3.7333333333333334,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,6 +385,20 @@
       "eval_samples_per_second": 2.485,
       "eval_steps_per_second": 0.312,
       "step": 2700
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.0002,
+      "loss": 0.7224,
+      "step": 2800
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 0.9102813601493835,
+      "eval_runtime": 777.5262,
+      "eval_samples_per_second": 2.482,
+      "eval_steps_per_second": 0.311,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
@@ -392,7 +406,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 6.994348686765773e+17,
+  "total_flos": 7.253666659583693e+17,
   "trial_name": null,
   "trial_params": null
 }