Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4574479d45d0d9e3baa490ede8f6114747e9d73cd2016d21a36c490f77723bbc
+oid sha256:cc2a600bda2ced945d986bd53a4d8d76302d637360e05095d4ec05041d67f70f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51de2d20386e82437e66ef8c217ae9eba54087b93e3c69195a0e9461d0ded72b
+oid sha256:2ca54928f760b404ef27f0a83f96306fa653c6c073cec1cdbb2f9f05111652e6
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb6c52509f6124e65ba9bebc18cf287604d7891c3901161e14bbc9ccc8a7d19
+oid sha256:50ce0581a1ebad30c1d498d23bd03a9574e22fa1027d16d465769bb3580632e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b92f6a8c8f69a383a7378c8526c34c47aacb6959ba4f705f8fb8753791be375
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010649837294152451,
+  "epoch": 0.011833152549058278,
   "eval_steps": 3,
-  "global_step": 27,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 7.675,
       "eval_steps_per_second": 3.837,
       "step": 27
+    },
+    {
+      "epoch": 0.011044275712454393,
+      "grad_norm": 0.6564432978630066,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9918,
+      "step": 28
+    },
+    {
+      "epoch": 0.011438714130756335,
+      "grad_norm": 0.5704507827758789,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.8769,
+      "step": 29
+    },
+    {
+      "epoch": 0.011833152549058278,
+      "grad_norm": 0.7271110415458679,
+      "learning_rate": 0.0,
+      "loss": 1.7657,
+      "step": 30
+    },
+    {
+      "epoch": 0.011833152549058278,
+      "eval_loss": 1.9052079916000366,
+      "eval_runtime": 138.7699,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 3.848,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -290,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0015478328066048e+16,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null