Training in progress, step 419, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d81ad20d6a6c4fe379bacb4c8d4a808360e99a6c66a1dc7f53e2b6139b8d2ab
+oid sha256:ad25bfffaddacce85d110ce29d3d66035bbdaf582630fd0bdc4eac047ebfa5cc
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa96847b6f54bdff6418d7a390c990b585b9a48dc362b81f36244df43abcdc59
+oid sha256:24c8c66ebb1f0121a0f8862fb9f74f96028d215f428a7984980c64491acaf981
 size 99241221

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852572ec0a5139abf7706cbd44b245b4d47b4ea48568f8acba9d5eb3a1ceceea
+oid sha256:13bed7301669ccb097d17c85fa97336ba58eceed5812de578fb239d94f52a2e7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc95c37cee1aebca09c18497d4c5a88aa069c3ace91dfd78d825324dd82fe2f
+oid sha256:f82c9e405f2f212635f9ba951d44193363d960dccb8756713af9916ef936e913
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9528063123418192,
+  "epoch": 0.9980646121780556,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 419,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,13 @@
       "learning_rate": 5.394019045729448e-07,
       "loss": 1.016,
       "step": 400
+    },
+    {
+      "epoch": 0.9766264701503647,
+      "grad_norm": 0.11270304024219513,
+      "learning_rate": 1.2119848050025085e-07,
+      "loss": 0.9987,
+      "step": 410
     }
   ],
   "logging_steps": 10,
@@ -301,12 +308,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.382493306683392e+17,
+  "total_flos": 3.543161738750853e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null