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:b81e41d86f078e30c8170dd6d94cae205eb3e983fd1779313e5ede17d26ee475
+oid sha256:1ed3f2a232dd3c98c60436e1ccab867b7fd8c2c983e933ecce05ecec4e11ad3a
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99db5ad55e9170f7e0bf0e9a106d2e779df88f69fbfc20ee00f8577cdca8b74e
+oid sha256:a7519740c8981260c2deec53d12a7eec2a587c23ab026ba6a074e8f9bfd21f39
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7593e318f7dbb96e75637425ecb665ac7b53bc2560542c64546f1cc95e5b92c4
+oid sha256:adb542cc4f512564db8b7905da56d4b58a7fc616efd174c3b729697ebe2ff0bf
 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": 0.0017516049079969523,
+  "epoch": 0.0026274073619954284,
   "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": 6.246,
       "eval_steps_per_second": 3.123,
       "step": 50
+    },
+    {
+      "epoch": 0.0017866370061568912,
+      "grad_norm": 11.697985649108887,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.0276,
+      "step": 51
+    },
+    {
+      "epoch": 0.0018216691043168303,
+      "grad_norm": 13.977499961853027,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 12.4535,
+      "step": 52
+    },
+    {
+      "epoch": 0.0018567012024767694,
+      "grad_norm": 14.096190452575684,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 12.3367,
+      "step": 53
+    },
+    {
+      "epoch": 0.0018917333006367083,
+      "grad_norm": 13.248291969299316,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.8346,
+      "step": 54
+    },
+    {
+      "epoch": 0.0019267653987966474,
+      "grad_norm": 16.24111557006836,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 12.1668,
+      "step": 55
+    },
+    {
+      "epoch": 0.0019617974969565865,
+      "grad_norm": 16.580856323242188,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 11.8119,
+      "step": 56
+    },
+    {
+      "epoch": 0.0019968295951165254,
+      "grad_norm": 11.197458267211914,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7317,
+      "step": 57
+    },
+    {
+      "epoch": 0.0020318616932764647,
+      "grad_norm": 12.0034761428833,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 15.88,
+      "step": 58
+    },
+    {
+      "epoch": 0.0020668937914364036,
+      "grad_norm": 11.464460372924805,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 14.5566,
+      "step": 59
+    },
+    {
+      "epoch": 0.0021019258895963425,
+      "grad_norm": 9.426189422607422,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9118,
+      "step": 60
+    },
+    {
+      "epoch": 0.002136957987756282,
+      "grad_norm": 11.631290435791016,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 13.0088,
+      "step": 61
+    },
+    {
+      "epoch": 0.0021719900859162207,
+      "grad_norm": 9.637537956237793,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 12.759,
+      "step": 62
+    },
+    {
+      "epoch": 0.0022070221840761596,
+      "grad_norm": 11.821331024169922,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 13.3715,
+      "step": 63
+    },
+    {
+      "epoch": 0.002242054282236099,
+      "grad_norm": 12.932907104492188,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 16.1093,
+      "step": 64
+    },
+    {
+      "epoch": 0.002277086380396038,
+      "grad_norm": 9.686279296875,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 12.3969,
+      "step": 65
+    },
+    {
+      "epoch": 0.002312118478555977,
+      "grad_norm": 11.873120307922363,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.2338,
+      "step": 66
+    },
+    {
+      "epoch": 0.002347150576715916,
+      "grad_norm": 10.407732009887695,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 14.9716,
+      "step": 67
+    },
+    {
+      "epoch": 0.002382182674875855,
+      "grad_norm": 12.169331550598145,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 14.9951,
+      "step": 68
+    },
+    {
+      "epoch": 0.0024172147730357942,
+      "grad_norm": 14.04606819152832,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 15.8657,
+      "step": 69
+    },
+    {
+      "epoch": 0.002452246871195733,
+      "grad_norm": 9.512072563171387,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 13.8743,
+      "step": 70
+    },
+    {
+      "epoch": 0.002487278969355672,
+      "grad_norm": 10.393471717834473,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 12.4094,
+      "step": 71
+    },
+    {
+      "epoch": 0.0025223110675156113,
+      "grad_norm": 10.671348571777344,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.0238,
+      "step": 72
+    },
+    {
+      "epoch": 0.0025573431656755502,
+      "grad_norm": 11.587846755981445,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 13.5365,
+      "step": 73
+    },
+    {
+      "epoch": 0.002592375263835489,
+      "grad_norm": 9.723920822143555,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 12.6632,
+      "step": 74
+    },
+    {
+      "epoch": 0.0026274073619954284,
+      "grad_norm": 10.614508628845215,
+      "learning_rate": 0.0,
+      "loss": 11.4377,
+      "step": 75
+    },
+    {
+      "epoch": 0.0026274073619954284,
+      "eval_loss": 1.660986304283142,
+      "eval_runtime": 3847.2283,
+      "eval_samples_per_second": 6.248,
+      "eval_steps_per_second": 3.124,
+      "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": 1.27571048005632e+17,
+  "total_flos": 1.91356572008448e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null