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:f4e2645d435ec11b52672f578a93062d56850691d5993a0d398e5c6a97ce686c
+oid sha256:3b5870a74dfa590ef5b5198b051bcea3fe500652e07c13b62d4b099d77270b52
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a215d955803918d4290809c654a1e0824c52373da03612aec5c61fbb7e3d79
-size 151034437
+oid sha256:5bc64d20b94e879e2f33431f461509dc9cb2172d28d7988f0fda31c3671e9e86
+size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4844b248bb8bc6625514d53ad7de0c9c14b2aad47aacb389b6b1780e4e27aac
+oid sha256:2fe3b9d7263291620430092f11a7ea7a0681167058a88f3663f7172adf47f039
 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": 1.5872766971588135,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 1.556390643119812,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 14.979,
       "eval_steps_per_second": 1.874,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 1.5756,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 1.556390643119812,
+      "eval_runtime": 418.8265,
+      "eval_samples_per_second": 14.98,
+      "eval_steps_per_second": 1.874,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.481310369453568e+16,
+  "total_flos": 9.729006729706906e+16,
   "trial_name": null,
   "trial_params": null
 }