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:ba70748dd59c881c6918db0d4d2048ce549d2bd938d9e691456748855fd7a439
+oid sha256:5a9de7d7c68a45cade2a29fd998ad1a6e104d8f52b40fd663f0b6be1a50a7f5d
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88ddebd2a88cf51e08f0bfd4e520e7c9d815362d3ebebc1bddeb07aab417aca
+oid sha256:eea618614d87612ea0ed6341239d9eca5f8cf84af2fda427054ec143198fc0ff
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84cacbdbb0b72a95fd5620124a96c0ed5a18674aa4e52f454d365e2e6e3e2d1e
+oid sha256:239daa8b2bb1f4927cbcf5416bf2579c1aa0907f9332deb7dbba8d04d1fd1184
 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": 0.12974375608173858,
+  "epoch": 0.19461563412260785,
   "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": 1.354,
       "eval_steps_per_second": 0.679,
       "step": 50
+    },
+    {
+      "epoch": 0.13233863120337333,
+      "grad_norm": 31.205846786499023,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.3168,
+      "step": 51
+    },
+    {
+      "epoch": 0.1349335063250081,
+      "grad_norm": 14.114444732666016,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.809,
+      "step": 52
+    },
+    {
+      "epoch": 0.13752838144664287,
+      "grad_norm": 8.728169441223145,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0702,
+      "step": 53
+    },
+    {
+      "epoch": 0.14012325656827765,
+      "grad_norm": 33.120567321777344,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9649,
+      "step": 54
+    },
+    {
+      "epoch": 0.14271813168991243,
+      "grad_norm": 16.788246154785156,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.8312,
+      "step": 55
+    },
+    {
+      "epoch": 0.14531300681154719,
+      "grad_norm": 14.110865592956543,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.5348,
+      "step": 56
+    },
+    {
+      "epoch": 0.14790788193318197,
+      "grad_norm": 21.55290412902832,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8498,
+      "step": 57
+    },
+    {
+      "epoch": 0.15050275705481675,
+      "grad_norm": 24.52911949157715,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.9744,
+      "step": 58
+    },
+    {
+      "epoch": 0.1530976321764515,
+      "grad_norm": 22.370573043823242,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7237,
+      "step": 59
+    },
+    {
+      "epoch": 0.15569250729808629,
+      "grad_norm": 15.488335609436035,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4487,
+      "step": 60
+    },
+    {
+      "epoch": 0.15828738241972104,
+      "grad_norm": 13.158798217773438,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.3464,
+      "step": 61
+    },
+    {
+      "epoch": 0.16088225754135582,
+      "grad_norm": 1.3022491931915283,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0314,
+      "step": 62
+    },
+    {
+      "epoch": 0.1634771326629906,
+      "grad_norm": 5.222805023193359,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.119,
+      "step": 63
+    },
+    {
+      "epoch": 0.16607200778462536,
+      "grad_norm": 6.309266090393066,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.1355,
+      "step": 64
+    },
+    {
+      "epoch": 0.16866688290626014,
+      "grad_norm": 19.3297119140625,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.0106,
+      "step": 65
+    },
+    {
+      "epoch": 0.1712617580278949,
+      "grad_norm": 58.562843322753906,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.6547,
+      "step": 66
+    },
+    {
+      "epoch": 0.17385663314952968,
+      "grad_norm": 88.08123016357422,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2678,
+      "step": 67
+    },
+    {
+      "epoch": 0.17645150827116446,
+      "grad_norm": 8.794583320617676,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.2489,
+      "step": 68
+    },
+    {
+      "epoch": 0.1790463833927992,
+      "grad_norm": 46.94881057739258,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4205,
+      "step": 69
+    },
+    {
+      "epoch": 0.181641258514434,
+      "grad_norm": 3.1083903312683105,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0701,
+      "step": 70
+    },
+    {
+      "epoch": 0.18423613363606878,
+      "grad_norm": 12.472285270690918,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2219,
+      "step": 71
+    },
+    {
+      "epoch": 0.18683100875770353,
+      "grad_norm": 32.516963958740234,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5728,
+      "step": 72
+    },
+    {
+      "epoch": 0.1894258838793383,
+      "grad_norm": 50.7675666809082,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 4.1427,
+      "step": 73
+    },
+    {
+      "epoch": 0.19202075900097307,
+      "grad_norm": 43.09784698486328,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.7928,
+      "step": 74
+    },
+    {
+      "epoch": 0.19461563412260785,
+      "grad_norm": 45.91943359375,
+      "learning_rate": 0.0,
+      "loss": 2.4261,
+      "step": 75
+    },
+    {
+      "epoch": 0.19461563412260785,
+      "eval_loss": 0.1303597092628479,
+      "eval_runtime": 240.3643,
+      "eval_samples_per_second": 1.352,
+      "eval_steps_per_second": 0.678,
+      "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": 6.57394539429888e+16,
+  "total_flos": 9.86091809144832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null