Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768f0b8494dbbcf1be7bddd66e8a45aba3a89ab318446e1c533ebcad4abea7de
+oid sha256:3b72650b34900e960d3b8e6d30ab11061eff5d72b62cfbe82ab01720d03b36ae
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd61636d4608e89896d8e81c483bbcceedf8964299c41d158ab15b3114ba3efa
+oid sha256:497a5525627977c98383368d11926918fabb1b93945858800fbd770cf9952fce
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915191ad61436a667d8d45034f27c7110941984405576e8ef009354f6c5821a4
+oid sha256:7b156be7230eb92a2c766e47652dc4dae9df7b1f8b521d4e9ecfbf2a31c902a2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0527396202087402,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.039888620376587,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 2.173,
       "eval_steps_per_second": 0.272,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.8697,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.039888620376587,
+      "eval_runtime": 883.1791,
+      "eval_samples_per_second": 2.185,
+      "eval_steps_per_second": 0.274,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.772891970699264e+16,
+  "total_flos": 1.03701644752896e+17,
   "trial_name": null,
   "trial_params": null
 }