Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a03415e1e333fc0d06955d3256c6e95fbec7c159c59ab14b7f74649dcffdd9
+oid sha256:9636b7d32b959a9726577531792e283bbb4d7d5763a0c2104215ab04c1358185
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e0752f22ac93ef420fd51c8fd46aadd3851241850548c1046b2bdf2c1d86f1
+oid sha256:9dfc80329425eed4fd0acfb3b9abb353340a811266f6d9eae7b76eacd29a8f32
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc35b2465ed628ff7d1c151c6992ba75067041a43ade6dd7aea2af9126e5679
+oid sha256:7f905070f344ff5757d2e5f48fcda24ded17f953888429aa8e5791b2828fc54a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9697631597518921,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 0.967492401599884,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 5.299,
       "eval_steps_per_second": 0.664,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 0.8311,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.967492401599884,
+      "eval_runtime": 364.003,
+      "eval_samples_per_second": 5.302,
+      "eval_steps_per_second": 0.665,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.652603258859438e+17,
+  "total_flos": 5.936315915975148e+17,
   "trial_name": null,
   "trial_params": null
 }