Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466cf69b50e909a6eb88657b2acb937b842c6f747015fec26905c133b42be024
+oid sha256:a082a58c07c33b34d9df10252ab8cfeeda84460644cee4441ede7924229611d8
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05a7133fa8eef64a28a22677a7916dd400c74fcab38af57d093f814c980747f
+oid sha256:6870c368db07817ea26669cdad467e37dc54db461e3d1a2fa7cb2d62c04af76b
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a3a2e7f87b24b5cd339ace17128f363e2805a5c9b3761ecc5ef97cd28ba615
+oid sha256:773be59c20afd641e7916cd56aeef99133cb59b4168ce3fcef9b62cf2c047e84
 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": 1.1869046688079834,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.1853452920913696,
+  "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": 3.97,
       "eval_steps_per_second": 0.498,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.9568,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.1853452920913696,
+      "eval_runtime": 469.1887,
+      "eval_samples_per_second": 4.113,
+      "eval_steps_per_second": 0.516,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.321054100743782e+16,
+  "total_flos": 6.653895699274138e+16,
   "trial_name": null,
   "trial_params": null
 }