Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0397837f94674d6ca330b258adeceb005dd33aa4e380ec2714489734a744617
+oid sha256:c5d6afdfb7abda138ac5a7e8230ad6fe13cf712320b186a9f10cfdab7837a510
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2163ff937a0070b508e6383b00d530d64138551809c2972cfc07595be90113c0
+oid sha256:2d7409ade6160d4f15bda95bf0a963969fad8a81fe51367c42f302f751df51ca
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a793a4bb6d7ad0c9ab597d723f0209456c5c120d347f8afa1ae7dbad7c5d74
+oid sha256:6a5616fda15e72a8c8ee348cad1a2bd9180fd92294398094aba03a3b73af356e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2020516395568848,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.1988099813461304,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 4.135,
       "eval_steps_per_second": 0.519,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 0.9724,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.1988099813461304,
+      "eval_runtime": 469.2999,
+      "eval_samples_per_second": 4.113,
+      "eval_steps_per_second": 0.516,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.32352337813504e+16,
+  "total_flos": 5.656486774308864e+16,
   "trial_name": null,
   "trial_params": null
 }