Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c145c57781431c7ea3ab34d9ece0d9db7741f412082d016f3b05e990f012324
+oid sha256:0d7ee63af715935c41050ccdf151429f4e5e64b7073519970602809547a4925d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288f5747825c1c9f6a40aae2c568a2cad6e2b3b2285c2da2321bf1db84163476
+oid sha256:d7c42940bebff7bcd3d27748123ed192ad8cee0020a4ef7880757289f571c8d2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a2ceac8780befc0683f9bef6e870ca84bd737e8a83c0f5eee58e03df31124f
+oid sha256:6c3432e9eeea181767d829c92d87624b64dfb1a86ab756b798de464f214a41df
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9676258563995361,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.840909090909091,
+  "best_metric": 1.9613432884216309,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.9829545454545454,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 28.65,
       "eval_steps_per_second": 3.591,
       "step": 2000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002,
+      "loss": 2.081,
+      "step": 2100
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 1.9613432884216309,
+      "eval_runtime": 52.027,
+      "eval_samples_per_second": 28.677,
+      "eval_steps_per_second": 3.594,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.804658999724032e+16,
+  "total_flos": 6.092531163629568e+16,
   "trial_name": null,
   "trial_params": null
 }