Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce3e4f4000fe65515edd679711ceaf4618a7862714e847409c3a6d4acc63b34
+oid sha256:585408afed0c99149015b8f4e970ee110db5eab0b30a8ba6d37a955fa7af9d73
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1549fcf1089d98f2a66e5805ea23ef4e3917700a6ac9b5946df793a4debc44
-size 50444613
+oid sha256:83eea3acd02a7890b16f2cfbf5766d7a864e65634c97350ac30eb913c01c709d
+size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f35b713645b2f6fb9d57649d0c8c63bb1e7812311062435203302e19fb74ba
+oid sha256:45ad477311de1f6b2e96cccdadfdec5df765b9531fbd21a05f460c15a1263a8a
 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": 1.05315363407135,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.0414820909500122,
+  "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": 5.471,
       "eval_steps_per_second": 0.686,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.9037,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.0414820909500122,
+      "eval_runtime": 353.1451,
+      "eval_samples_per_second": 5.465,
+      "eval_steps_per_second": 0.685,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.648480752523674e+16,
+  "total_flos": 8.485409566683955e+16,
   "trial_name": null,
   "trial_params": null
 }