Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05aa022c54cc3af0df746afc7a430ec7202a1ad889fa763bfbf083dac63b6a81
+oid sha256:7e4033782c38746d2cfb86a6806fd9104a14271f43ec1cc2ae8850ebca3a72a4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dc5565906114330048a0088ffbb5bd8f8fce97f07e62ec2eafa6ff3e3a4fd0
+oid sha256:aa618e488300a30b81d9e0a901c38572cab13d028754949d3ce9e5ce8ac0ea27
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d13059a2d496303aa065549223e9500326c02d6d5046828f86e7c592e199d5
+oid sha256:311559792ec8fdab1dc40bdff8a028cd7746aae77c5ae9f277018ecf6bf02bc1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.567879319190979,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.5340639352798462,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 15.525,
       "eval_steps_per_second": 1.947,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.2977,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.5340639352798462,
+      "eval_runtime": 93.3831,
+      "eval_samples_per_second": 15.538,
+      "eval_steps_per_second": 1.949,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5840664718049280.0,
+  "total_flos": 1.169574007504896e+16,
   "trial_name": null,
   "trial_params": null
 }