Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5848482a10ef394945764aa3111dd4cdd643cfa6b9e8bd685f8ba014d544c1f6
+oid sha256:5c16c471efc6ec0a122a1e816c4cb866431cf46c0719a4be7eff885225dd2438
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c14903002dfb46f90d437c64b638d17434f2d6f5c9d24f228bba36f89cff15a
+oid sha256:2964a56551efc77b571b3e58ab4fb5e8c1e4cdf2be4068c1c3d2546b80c20c66
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d1fb7896c431fe529191f15ca9034e305b6676bcd2db3bd244d556edf97e74
+oid sha256:bf25c1186f011dc9a52116a8f2240ae21b29ddd5e2e91eaeccdf9ff94ea3c8ba
 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": 0.01444616995918957,
+  "epoch": 0.021669254938784355,
   "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": 2.926,
       "eval_steps_per_second": 1.464,
       "step": 50
+    },
+    {
+      "epoch": 0.014735093358373362,
+      "grad_norm": 26.76323699951172,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.3221,
+      "step": 51
+    },
+    {
+      "epoch": 0.015024016757557152,
+      "grad_norm": 40.71314239501953,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 7.0028,
+      "step": 52
+    },
+    {
+      "epoch": 0.015312940156740944,
+      "grad_norm": 18.181428909301758,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 5.6947,
+      "step": 53
+    },
+    {
+      "epoch": 0.015601863555924736,
+      "grad_norm": 23.002670288085938,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.155,
+      "step": 54
+    },
+    {
+      "epoch": 0.015890786955108527,
+      "grad_norm": 18.26033592224121,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 5.6797,
+      "step": 55
+    },
+    {
+      "epoch": 0.016179710354292318,
+      "grad_norm": 14.501717567443848,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 4.742,
+      "step": 56
+    },
+    {
+      "epoch": 0.01646863375347611,
+      "grad_norm": 17.230289459228516,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.2838,
+      "step": 57
+    },
+    {
+      "epoch": 0.0167575571526599,
+      "grad_norm": 14.124578475952148,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 5.8269,
+      "step": 58
+    },
+    {
+      "epoch": 0.01704648055184369,
+      "grad_norm": 20.78701400756836,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.3414,
+      "step": 59
+    },
+    {
+      "epoch": 0.017335403951027485,
+      "grad_norm": 13.879270553588867,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.1704,
+      "step": 60
+    },
+    {
+      "epoch": 0.017624327350211275,
+      "grad_norm": 13.16641902923584,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 4.4702,
+      "step": 61
+    },
+    {
+      "epoch": 0.017913250749395065,
+      "grad_norm": 12.741442680358887,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 4.0511,
+      "step": 62
+    },
+    {
+      "epoch": 0.01820217414857886,
+      "grad_norm": 12.697881698608398,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.0318,
+      "step": 63
+    },
+    {
+      "epoch": 0.01849109754776265,
+      "grad_norm": 19.755266189575195,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 3.4955,
+      "step": 64
+    },
+    {
+      "epoch": 0.01878002094694644,
+      "grad_norm": 17.082738876342773,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 5.3582,
+      "step": 65
+    },
+    {
+      "epoch": 0.019068944346130233,
+      "grad_norm": 15.043936729431152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.0782,
+      "step": 66
+    },
+    {
+      "epoch": 0.019357867745314023,
+      "grad_norm": 24.604942321777344,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.5255,
+      "step": 67
+    },
+    {
+      "epoch": 0.019646791144497817,
+      "grad_norm": 13.922004699707031,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 4.1978,
+      "step": 68
+    },
+    {
+      "epoch": 0.019935714543681607,
+      "grad_norm": 13.740044593811035,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.8924,
+      "step": 69
+    },
+    {
+      "epoch": 0.020224637942865397,
+      "grad_norm": 12.760802268981934,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 4.1786,
+      "step": 70
+    },
+    {
+      "epoch": 0.02051356134204919,
+      "grad_norm": 13.630950927734375,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.6798,
+      "step": 71
+    },
+    {
+      "epoch": 0.02080248474123298,
+      "grad_norm": 15.914883613586426,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.1266,
+      "step": 72
+    },
+    {
+      "epoch": 0.02109140814041677,
+      "grad_norm": 21.27867889404297,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 3.6778,
+      "step": 73
+    },
+    {
+      "epoch": 0.021380331539600565,
+      "grad_norm": 16.753841400146484,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 5.9576,
+      "step": 74
+    },
+    {
+      "epoch": 0.021669254938784355,
+      "grad_norm": 15.862313270568848,
+      "learning_rate": 0.0,
+      "loss": 3.6563,
+      "step": 75
+    },
+    {
+      "epoch": 0.021669254938784355,
+      "eval_loss": 0.6312903761863708,
+      "eval_runtime": 995.9618,
+      "eval_samples_per_second": 2.927,
+      "eval_steps_per_second": 1.464,
+      "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