Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b934623644b2cad72bce18be279967285a692175ebd40ccea73ffe3ed34434f
+oid sha256:681b2d24ea28ee82e6aae8302d1382a0f77801f9e454db5217e47a9a66bc37bf
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc16809c7607f921c1b36704dd4b322eed592cf003c38877592000a5dfcef12e
+oid sha256:def6fc0dd6afafd9683b85026dd4b02c505c3ac9637eb824f80b7e3df0b7d2b7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a82d713e666f36b9ace8a6054cfde823b8feae9a07812ff4e3a4e51f579dbc1
+oid sha256:4b8270fb5b98b86da8550d75dc7fb5d84906b144754ea3444bb49fbaae1ee321
 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": 1.8645176887512207,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.6988636363636362,
+  "best_metric": 1.8587623834609985,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.840909090909091,
   "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": 18.99,
       "eval_steps_per_second": 2.38,
       "step": 1900
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 1.981,
+      "step": 2000
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.8587623834609985,
+      "eval_runtime": 78.4761,
+      "eval_samples_per_second": 19.012,
+      "eval_steps_per_second": 2.383,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.78668418399232e+16,
+  "total_flos": 6.090842007484416e+16,
   "trial_name": null,
   "trial_params": null
 }