Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81834b3b8ce8a84668f373441f0d50637fb84cd037399793dbd007eae58e5f5
+oid sha256:a040ca27d0100839ba68aba6cc909fdd3515a2433ff8cd90ae13518c16f34257
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c1215701e6b6e5b69da3135df5870e6f8747aed9e256a4eb58e36b25200add
+oid sha256:5c5a00274b22bb01ac96efb28d93c2dabad352f408b1e4aaf907704acc7a6f46
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4661af03204b37126651ed054d902327a755c23a1b8ab409aa9200fc8c97a842
+oid sha256:f751eb29a40a1e2576d3c8b90d6adc7af4c98308e5e6c6759b5d1087ce3eb13a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
+oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9069462418556213,
-  "best_model_checkpoint": "./outputs/checkpoint-2900",
-  "epoch": 3.8666666666666667,
+  "best_metric": 0.9039433002471924,
+  "best_model_checkpoint": "./outputs/checkpoint-3000",
+  "epoch": 4.0,
   "eval_steps": 100,
-  "global_step": 2900,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,6 +413,20 @@
       "eval_samples_per_second": 2.478,
       "eval_steps_per_second": 0.311,
       "step": 2900
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 0.7253,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9039433002471924,
+      "eval_runtime": 773.591,
+      "eval_samples_per_second": 2.495,
+      "eval_steps_per_second": 0.313,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -420,7 +434,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 7.511437778626253e+17,
+  "total_flos": 7.769908955437056e+17,
   "trial_name": null,
   "trial_params": null
 }