Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d19857892cac4e77bb8b3dcd5ce6043403607651a641a3e2ac3a337bcf7c2bc
+oid sha256:b391ceeab4f6074a6fc33ed80f0a543a631a80616a02b08f2891f16eaea1a026
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548a4a8064e806916b801c055fd27a11de13400e99c1aecd4883e285bb954134
+oid sha256:7a6e96f20320a2db7d020eb241a63fa8064e16493c2282ef995876b23e7c45a8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d05e32f71f76f808bcb63b3ecdd7800763c40ca4882a0f0b21dcff1f9ed7b3
+oid sha256:8ab2e71098167d0332b198cc3f92b905079c7bc7230441e24ab53063e6ed4e90
 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": 1.0812042951583862,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.14204545454545456,
+  "best_metric": 1.0592867136001587,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.2840909090909091,
   "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": 11.703,
       "eval_steps_per_second": 1.467,
       "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 1.2145,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.0592867136001587,
+      "eval_runtime": 124.4418,
+      "eval_samples_per_second": 11.99,
+      "eval_steps_per_second": 1.503,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5593276624158720.0,
+  "total_flos": 1.11990315515904e+16,
   "trial_name": null,
   "trial_params": null
 }