Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616674be1bb8e871070e6f95e2d66f199e37b5c177e71ad2559d21b408b27140
+oid sha256:673d9608924b7a71a3f40dc32ae5c22c2125b6c5fa3a77b704bbfe0de2770651
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f6148b3bb203d879d795ef2408dd61a0c3f99503646ff2e4a5f0f1f35b41f1
+oid sha256:3d17511b2beb3a2f4f5e2b2124f742f4c23db764b5fdf4118f35d581a85f3585
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cacb2b95777e76d9a0e2379d4f68472c2353f0b8d8da4ae69678334b46e61e30
+oid sha256:2008a75cb5dd5d8e6402990beb1748d1bf46fc447f0eaeb2c4cf2f7794d1897e
 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": 0.9410523176193237,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 0.9364854693412781,
+  "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": 2.333,
       "eval_steps_per_second": 0.293,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.7577,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.9364854693412781,
+      "eval_runtime": 777.3543,
+      "eval_samples_per_second": 2.483,
+      "eval_steps_per_second": 0.311,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.921400718048461e+17,
+  "total_flos": 5.1806097015361536e+17,
   "trial_name": null,
   "trial_params": null
 }