Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bb1216267849bbda2fadfca822890ef69a755bc752607051aafb05cea2fc18
+oid sha256:d735c4b89414520c131ac73a795192c84d95eef0de212348b2b51afb34f9ec4d
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da9e351bb454392c3c404ceba21c42ea7fc8c69f110c366bc7dcb705eb0f2f4
+oid sha256:3b2ff0d4bcb6ad0b53412b2963deda9c76e73a842858859bc80e648836078da4
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9721883eeb5dfd58d4927218422ce48028e14bf282115382a00d7498ac3281ed
+oid sha256:a93ac6f173601e9cf9cc746893f2796266cbc5ea513d76e893442659b6b60649
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2401798963546753,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.2377259731292725,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 15.245,
       "eval_steps_per_second": 1.912,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 1.0715,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.2377259731292725,
+      "eval_runtime": 126.6342,
+      "eval_samples_per_second": 15.241,
+      "eval_steps_per_second": 1.911,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.736067175819264e+16,
+  "total_flos": 7.090695034659226e+16,
   "trial_name": null,
   "trial_params": null
 }