Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b9a1c4cd6756b5549e27bb4c33e545c74ea63303f4c123ac209fc94f01bbd2
+oid sha256:ad7550b4ac768735d3cb2f1af7f9f89a08f17e2ad4fe3fb85d572fa49931f6e1
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b06070df479a1e3ca72d0f9153843f60d3be358ae455d6aec2f13b16b15475b
+oid sha256:232d24f3fd5d4a84a12d2ce17c80fd077ea45da58c11da8ff99c9ee803c8b18f
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7451c710a641502bbbb3acf0d586e7814a0639e75a133cc0aca111133274a4d0
+oid sha256:2adb3ffb83a5ba4b6a22e94c65400c3667f11f3eb4aa97bd766f7f0dc3e44e88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0944733112895607,
+  "epoch": 0.14170996693434104,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 6.436,
       "eval_steps_per_second": 3.218,
       "step": 50
+    },
+    {
+      "epoch": 0.09636277751535191,
+      "grad_norm": 3.2441093921661377,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.2623,
+      "step": 51
+    },
+    {
+      "epoch": 0.09825224374114312,
+      "grad_norm": 2.6940605640411377,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 3.9519,
+      "step": 52
+    },
+    {
+      "epoch": 0.10014170996693435,
+      "grad_norm": 3.0306456089019775,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 4.5108,
+      "step": 53
+    },
+    {
+      "epoch": 0.10203117619272556,
+      "grad_norm": 3.2167880535125732,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.8739,
+      "step": 54
+    },
+    {
+      "epoch": 0.10392064241851677,
+      "grad_norm": 3.2988834381103516,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.5123,
+      "step": 55
+    },
+    {
+      "epoch": 0.10581010864430798,
+      "grad_norm": 3.672719717025757,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 4.1436,
+      "step": 56
+    },
+    {
+      "epoch": 0.1076995748700992,
+      "grad_norm": 2.936258554458618,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.9928,
+      "step": 57
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "grad_norm": 13.814180374145508,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 4.8073,
+      "step": 58
+    },
+    {
+      "epoch": 0.11147850732168163,
+      "grad_norm": 3.6494219303131104,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.6496,
+      "step": 59
+    },
+    {
+      "epoch": 0.11336797354747284,
+      "grad_norm": 2.834043025970459,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.8589,
+      "step": 60
+    },
+    {
+      "epoch": 0.11525743977326405,
+      "grad_norm": 3.1567180156707764,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 4.2451,
+      "step": 61
+    },
+    {
+      "epoch": 0.11714690599905526,
+      "grad_norm": 3.726329803466797,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 4.367,
+      "step": 62
+    },
+    {
+      "epoch": 0.11903637222484648,
+      "grad_norm": 3.2015750408172607,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.1579,
+      "step": 63
+    },
+    {
+      "epoch": 0.1209258384506377,
+      "grad_norm": 3.231867790222168,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 4.1819,
+      "step": 64
+    },
+    {
+      "epoch": 0.12281530467642891,
+      "grad_norm": 3.6476991176605225,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 4.4892,
+      "step": 65
+    },
+    {
+      "epoch": 0.12470477090222012,
+      "grad_norm": 3.3844738006591797,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.6449,
+      "step": 66
+    },
+    {
+      "epoch": 0.12659423712801135,
+      "grad_norm": 3.922344207763672,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.7279,
+      "step": 67
+    },
+    {
+      "epoch": 0.12848370335380255,
+      "grad_norm": 3.484113931655884,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 3.4314,
+      "step": 68
+    },
+    {
+      "epoch": 0.13037316957959377,
+      "grad_norm": 3.8980712890625,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.1555,
+      "step": 69
+    },
+    {
+      "epoch": 0.13226263580538497,
+      "grad_norm": 3.5929458141326904,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 4.7111,
+      "step": 70
+    },
+    {
+      "epoch": 0.1341521020311762,
+      "grad_norm": 3.9087624549865723,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.0477,
+      "step": 71
+    },
+    {
+      "epoch": 0.1360415682569674,
+      "grad_norm": 3.5490529537200928,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.0776,
+      "step": 72
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 3.6930553913116455,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 4.2169,
+      "step": 73
+    },
+    {
+      "epoch": 0.13982050070854984,
+      "grad_norm": 3.2639620304107666,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 4.129,
+      "step": 74
+    },
+    {
+      "epoch": 0.14170996693434104,
+      "grad_norm": 3.8900978565216064,
+      "learning_rate": 0.0,
+      "loss": 4.0938,
+      "step": 75
+    },
+    {
+      "epoch": 0.14170996693434104,
+      "eval_loss": 0.5526300072669983,
+      "eval_runtime": 69.1915,
+      "eval_samples_per_second": 6.446,
+      "eval_steps_per_second": 3.223,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.27571853312e+17,
+  "total_flos": 1.91357779968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null