Training in progress, step 434, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fd31fb9f62306330a62d03ac774b78f6f28c2f740c1c11d27cc0b459d180f7
+oid sha256:6f29bece7f5d3a6d7983929b36fdd27d718d95657f793d9d5e6f3cfa88297f85
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32e133fd2812edc1c5dce1be27b5a46fee4bd8f173f66ca7b3afda005973393
+oid sha256:afc3e3ee70cf903c1796f57d4e5235a441242375ef1f9a858eae3e8d05f28343
 size 50675604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4d88d6aa0cf77e00d03223bf672dc6270466833d08ef64560b03a03290bd1e
+oid sha256:4088348bc24d9e4ac19382802a5af616a59820aa6b3e226460dd20d33eb18c94
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6253310199981736,
+  "epoch": 0.6340973427084284,
   "eval_steps": 500,
-  "global_step": 428,
+  "global_step": 434,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3003,6 +3003,48 @@
       "learning_rate": 8.767123287671233e-06,
       "loss": 1.1644,
       "step": 428
+    },
+    {
+      "epoch": 0.6267920737832161,
+      "grad_norm": 0.11811359971761703,
+      "learning_rate": 8.732876712328769e-06,
+      "loss": 1.1466,
+      "step": 429
+    },
+    {
+      "epoch": 0.6282531275682586,
+      "grad_norm": 0.11676699668169022,
+      "learning_rate": 8.698630136986302e-06,
+      "loss": 1.1889,
+      "step": 430
+    },
+    {
+      "epoch": 0.629714181353301,
+      "grad_norm": 0.10928516089916229,
+      "learning_rate": 8.664383561643837e-06,
+      "loss": 1.1603,
+      "step": 431
+    },
+    {
+      "epoch": 0.6311752351383435,
+      "grad_norm": 0.13088025152683258,
+      "learning_rate": 8.63013698630137e-06,
+      "loss": 1.0952,
+      "step": 432
+    },
+    {
+      "epoch": 0.632636288923386,
+      "grad_norm": 0.11683713644742966,
+      "learning_rate": 8.595890410958905e-06,
+      "loss": 1.2762,
+      "step": 433
+    },
+    {
+      "epoch": 0.6340973427084284,
+      "grad_norm": 0.10292809456586838,
+      "learning_rate": 8.56164383561644e-06,
+      "loss": 1.1743,
+      "step": 434
     }
   ],
   "logging_steps": 1,
@@ -3022,7 +3064,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.8293970753705984e+17,
+  "total_flos": 4.8957186703303066e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null