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:be9bcd15d69a11514441b9a28179ee8268bda6cf39836bd197826e70d3c2e78f
+oid sha256:190f8523f43ffa57572340c5c85999d2b78025941853d510c8b2463766100827
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27797170f27ae4d267d28364b8334de9d90b83d21c688a7b582d73f87f668e49
+oid sha256:e20cff37a36426673722a8fe522d304a0cf28e4e19e78ef2d15b5b05d62f4822
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432b633e5dda27995d4289f9c9b4c7fc095ba96fbfd82e14d7f383c303196238
+oid sha256:7fc35b2465ed628ff7d1c151c6992ba75067041a43ade6dd7aea2af9126e5679
 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": 0.9727230072021484,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 0.9686517715454102,
+  "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": 5.262,
       "eval_steps_per_second": 0.66,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.8283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.9686517715454102,
+      "eval_runtime": 366.7742,
+      "eval_samples_per_second": 5.262,
+      "eval_steps_per_second": 0.66,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.3702940947828736e+17,
+  "total_flos": 5.652603258859438e+17,
   "trial_name": null,
   "trial_params": null
 }