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:c6f4c232be6894e79544bed14d06d54561f20e163938f1342136b6ca51324ee3
+oid sha256:ec6b2a01e1171274dd860b212c6e84810a93195cdb83f3a8a9c1fb457ce40482
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b76761f58ef61a9fdc7752ae0554c2e2ffb8bab2946554830ebb539e4c47859
+oid sha256:5f82ac14eb3e2b3dacaf91e323cb1ae5906d4dd7ef91fe36aa07b955cc08b288
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9817d49af1700b3b6a3a38925aea971c24d8ef3a7a83a7111d05a332400646
+oid sha256:9569a82096629a4752f43390cc4d687d8747d343bb173c2c0aa596b7a3fc989e
 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": 1.2993828058242798,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.2881134748458862,
+  "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": 4.1,
       "eval_steps_per_second": 0.514,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.0692,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.2881134748458862,
+      "eval_runtime": 470.2444,
+      "eval_samples_per_second": 4.104,
+      "eval_steps_per_second": 0.515,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9986706610323456.0,
+  "total_flos": 1.33237140701184e+16,
   "trial_name": null,
   "trial_params": null
 }