Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3534087f41de4279371254e1a272ab967c8f965b14c6fbd94a1510292d08a2
+oid sha256:c6f4c232be6894e79544bed14d06d54561f20e163938f1342136b6ca51324ee3
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd8f1e867b5651b6f9d92b34a59ca3ba7533fed54d960314c79b5b2e33d85a39
-size 12611081
+oid sha256:2b76761f58ef61a9fdc7752ae0554c2e2ffb8bab2946554830ebb539e4c47859
+size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914d66e5e379e4cfd8e3c151fb439a74f39ae2645cf3cf7ec31a3328442be621
+oid sha256:dc9817d49af1700b3b6a3a38925aea971c24d8ef3a7a83a7111d05a332400646
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3190627098083496,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.2993828058242798,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 4.136,
       "eval_steps_per_second": 0.519,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.2993828058242798,
+      "eval_runtime": 470.7014,
+      "eval_samples_per_second": 4.1,
+      "eval_steps_per_second": 0.514,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6647423649644544.0,
+  "total_flos": 9986706610323456.0,
   "trial_name": null,
   "trial_params": null
 }