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:a30fd0b534d9416ee56886f3afc1bbf2c0f549e2d50fd08f9804c5f954e3fe81
+oid sha256:b3c1fb2860924b2c14f52c057ed5ae1fa0efbb35597f8334e46ca74537f61a76
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdd10a6d65af39824c06061c13bbff8d36d845811ff5c8bf7ea44e04f5fb7c9
+oid sha256:67f889c472e533cea2f43aebece05794d0d6d6f1f718b5d8aa5f5a1f5b121066
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d290bfb7997bdc285eee08b3d84d53e851d63b356269dcb61cba8ecbf64733
+oid sha256:6e613b0245eaa439b6105a22a865a5694d38452efce7b6b7387d2ca69d455114
 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": 0.004569235338466108,
+  "epoch": 0.006853853007699162,
   "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": 8.834,
       "eval_steps_per_second": 4.418,
       "step": 50
+    },
+    {
+      "epoch": 0.00466062004523543,
+      "grad_norm": 5.613043308258057,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1746,
+      "step": 51
+    },
+    {
+      "epoch": 0.004752004752004752,
+      "grad_norm": 6.032951831817627,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 1.348,
+      "step": 52
+    },
+    {
+      "epoch": 0.004843389458774074,
+      "grad_norm": 4.618442058563232,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.808,
+      "step": 53
+    },
+    {
+      "epoch": 0.004934774165543396,
+      "grad_norm": 4.89528226852417,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1702,
+      "step": 54
+    },
+    {
+      "epoch": 0.005026158872312719,
+      "grad_norm": 5.89093017578125,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.1912,
+      "step": 55
+    },
+    {
+      "epoch": 0.005117543579082041,
+      "grad_norm": 4.801693439483643,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.0937,
+      "step": 56
+    },
+    {
+      "epoch": 0.005208928285851362,
+      "grad_norm": 6.408935070037842,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3091,
+      "step": 57
+    },
+    {
+      "epoch": 0.005300312992620685,
+      "grad_norm": 5.189580917358398,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.8866,
+      "step": 58
+    },
+    {
+      "epoch": 0.005391697699390007,
+      "grad_norm": 5.219249248504639,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0799,
+      "step": 59
+    },
+    {
+      "epoch": 0.0054830824061593295,
+      "grad_norm": 5.454803466796875,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0661,
+      "step": 60
+    },
+    {
+      "epoch": 0.005574467112928651,
+      "grad_norm": 4.765921592712402,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.7579,
+      "step": 61
+    },
+    {
+      "epoch": 0.005665851819697974,
+      "grad_norm": 5.725944519042969,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.0852,
+      "step": 62
+    },
+    {
+      "epoch": 0.005757236526467296,
+      "grad_norm": 4.559783935546875,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9034,
+      "step": 63
+    },
+    {
+      "epoch": 0.0058486212332366175,
+      "grad_norm": 5.786202430725098,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.0369,
+      "step": 64
+    },
+    {
+      "epoch": 0.00594000594000594,
+      "grad_norm": 4.688554286956787,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.0344,
+      "step": 65
+    },
+    {
+      "epoch": 0.006031390646775262,
+      "grad_norm": 5.780782699584961,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9494,
+      "step": 66
+    },
+    {
+      "epoch": 0.006122775353544585,
+      "grad_norm": 5.427234649658203,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9841,
+      "step": 67
+    },
+    {
+      "epoch": 0.0062141600603139065,
+      "grad_norm": 5.6869215965271,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.0319,
+      "step": 68
+    },
+    {
+      "epoch": 0.006305544767083228,
+      "grad_norm": 5.268839359283447,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0643,
+      "step": 69
+    },
+    {
+      "epoch": 0.006396929473852551,
+      "grad_norm": 5.248642921447754,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 1.174,
+      "step": 70
+    },
+    {
+      "epoch": 0.006488314180621873,
+      "grad_norm": 6.898940086364746,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.2062,
+      "step": 71
+    },
+    {
+      "epoch": 0.006579698887391195,
+      "grad_norm": 5.899970531463623,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9557,
+      "step": 72
+    },
+    {
+      "epoch": 0.006671083594160517,
+      "grad_norm": 5.415920734405518,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.3895,
+      "step": 73
+    },
+    {
+      "epoch": 0.006762468300929839,
+      "grad_norm": 5.120940685272217,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.8528,
+      "step": 74
+    },
+    {
+      "epoch": 0.006853853007699162,
+      "grad_norm": 5.29119873046875,
+      "learning_rate": 0.0,
+      "loss": 1.0819,
+      "step": 75
+    },
+    {
+      "epoch": 0.006853853007699162,
+      "eval_loss": 1.0691897869110107,
+      "eval_runtime": 1043.1267,
+      "eval_samples_per_second": 8.834,
+      "eval_steps_per_second": 4.417,
+      "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": 2.01059658104832e+16,
+  "total_flos": 3.01589487157248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null