Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a040ca27d0100839ba68aba6cc909fdd3515a2433ff8cd90ae13518c16f34257
+oid sha256:085a2ebfd04a3809d12b0e3db225b58bc970a83b1089d0a63600fcfc200ecdba
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c5a00274b22bb01ac96efb28d93c2dabad352f408b1e4aaf907704acc7a6f46
+oid sha256:3bdab217ef76511669f78840feecc999ecc4aaa34ffbda530e89db33f056d9c5
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f751eb29a40a1e2576d3c8b90d6adc7af4c98308e5e6c6759b5d1087ce3eb13a
+oid sha256:b02564141f65d6796fc22bd626e526e8aed02bce0651ca616957fae586fbe037
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9039433002471924,
   "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 4.0,
+  "epoch": 4.133333333333334,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,20 @@
       "eval_samples_per_second": 2.495,
       "eval_steps_per_second": 0.313,
       "step": 3000
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 0.0002,
+      "loss": 0.6845,
+      "step": 3100
+    },
+    {
+      "epoch": 4.13,
+      "eval_loss": 0.906529426574707,
+      "eval_runtime": 784.1515,
+      "eval_samples_per_second": 2.461,
+      "eval_steps_per_second": 0.309,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
@@ -434,7 +448,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 7.769908955437056e+17,
+  "total_flos": 8.029294478933606e+17,
   "trial_name": null,
   "trial_params": null
 }