Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca94817db72d0e01e355a165a8b4e1af9fbe59e283c7d7f5c77cedf571ab407
+oid sha256:599d9f1c9b039546505a4690f92c0ca34439708128873aeefdf3c298d02a38e8
 size 5687360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4055879a8af4ed670e5ae958567a5cf0cf868bbcf34153b2b96e9a8c3015f7f1
+oid sha256:a8ca44b66cda373206a7924cdfb22cf24b665f8aa42f8ff176882de5d0eb0462
 size 154536948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b726c873ee1e0285a31b2d6e8aa7348232298bcb52b3df38302b4af9c97f2172
+oid sha256:805b952d6ed276148c3b93345e8330ad707ed6e8acffefe39b19d4e93e713656
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c9a89756eab4cc469f92a3efb736bac5da229eda0a7d5c4d203923562b5961
+oid sha256:bf87d2f6e922b4fc58db5e9445c0aa14b6455c6deeb769b4ec03d2f176f13118
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.961672473867596,
   "eval_steps": 500,
-  "global_step": 72,
+  "global_step": 213,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,48 @@
       "learning_rate": 0.0004400347115466442,
       "loss": 1.5577,
       "step": 66
+    },
+    {
+      "epoch": 1.2229965156794425,
+      "grad_norm": 0.605900228023529,
+      "learning_rate": 0.00037022215582942734,
+      "loss": 1.5324,
+      "step": 88
+    },
+    {
+      "epoch": 1.529616724738676,
+      "grad_norm": 0.5823822021484375,
+      "learning_rate": 0.00028483851926153393,
+      "loss": 1.4878,
+      "step": 110
+    },
+    {
+      "epoch": 1.8362369337979094,
+      "grad_norm": 1.2892831563949585,
+      "learning_rate": 0.0001949426245628773,
+      "loss": 1.5933,
+      "step": 132
+    },
+    {
+      "epoch": 2.1393728222996518,
+      "grad_norm": 0.6070840954780579,
+      "learning_rate": 0.00011217771864447396,
+      "loss": 1.3866,
+      "step": 154
+    },
+    {
+      "epoch": 2.445993031358885,
+      "grad_norm": 0.5739336609840393,
+      "learning_rate": 4.7263448253322574e-05,
+      "loss": 1.4519,
+      "step": 176
+    },
+    {
+      "epoch": 2.7526132404181185,
+      "grad_norm": 0.5276680588722229,
+      "learning_rate": 8.607459597809564e-06,
+      "loss": 1.4926,
+      "step": 198
     }
   ],
   "logging_steps": 22,
@@ -43,12 +85,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2646681266880512e+16,
+  "total_flos": 3.746593107659981e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null