Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfb0681cf264d0d6828df272d9cfd1dbd06f5e0bc775c0d17ff8a5b3706ce03
+oid sha256:4a79b2566d502ee5d9ff730f9ff544dfddf2a91cd38ac3ab709cd11b24883647
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f46414575b6d899f6936e64c869f64493ad98aeec78f3bdb0211772ed0f522
+oid sha256:357915395628135521d48151776409a9d887a7a5f350014406789becf852338f
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43800b050359a981bd6e05898b883373851a14e947762809d83209bbb5d177c2
+oid sha256:51bb995af00e6337b13ecac026841c2cddb804d8479cb07e79a791a1d862346f
 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": 0.0063590982798639156,
+  "epoch": 0.009538647419795872,
   "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": 6.507,
       "eval_steps_per_second": 3.254,
       "step": 50
+    },
+    {
+      "epoch": 0.0064862802454611936,
+      "grad_norm": 2.5585479736328125,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6511,
+      "step": 51
+    },
+    {
+      "epoch": 0.0066134622110584716,
+      "grad_norm": 3.03650164604187,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 1.465,
+      "step": 52
+    },
+    {
+      "epoch": 0.00674064417665575,
+      "grad_norm": 2.079188108444214,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 1.5449,
+      "step": 53
+    },
+    {
+      "epoch": 0.006867826142253028,
+      "grad_norm": 2.6188244819641113,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5621,
+      "step": 54
+    },
+    {
+      "epoch": 0.006995008107850306,
+      "grad_norm": 2.1260628700256348,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.5848,
+      "step": 55
+    },
+    {
+      "epoch": 0.007122190073447585,
+      "grad_norm": 1.6332706212997437,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.5695,
+      "step": 56
+    },
+    {
+      "epoch": 0.007249372039044863,
+      "grad_norm": 2.4522626399993896,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6052,
+      "step": 57
+    },
+    {
+      "epoch": 0.007376554004642142,
+      "grad_norm": 2.603383779525757,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 1.6324,
+      "step": 58
+    },
+    {
+      "epoch": 0.00750373597023942,
+      "grad_norm": 2.176748752593994,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.3584,
+      "step": 59
+    },
+    {
+      "epoch": 0.007630917935836698,
+      "grad_norm": 2.0545296669006348,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5658,
+      "step": 60
+    },
+    {
+      "epoch": 0.007758099901433977,
+      "grad_norm": 2.176485061645508,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.5229,
+      "step": 61
+    },
+    {
+      "epoch": 0.007885281867031255,
+      "grad_norm": 2.3088207244873047,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.4633,
+      "step": 62
+    },
+    {
+      "epoch": 0.008012463832628533,
+      "grad_norm": 3.608034372329712,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6021,
+      "step": 63
+    },
+    {
+      "epoch": 0.008139645798225811,
+      "grad_norm": 1.7870920896530151,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.5331,
+      "step": 64
+    },
+    {
+      "epoch": 0.00826682776382309,
+      "grad_norm": 2.5201566219329834,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.5798,
+      "step": 65
+    },
+    {
+      "epoch": 0.008394009729420369,
+      "grad_norm": 3.3685851097106934,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6904,
+      "step": 66
+    },
+    {
+      "epoch": 0.008521191695017647,
+      "grad_norm": 4.109929084777832,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6286,
+      "step": 67
+    },
+    {
+      "epoch": 0.008648373660614925,
+      "grad_norm": 3.135014533996582,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.5616,
+      "step": 68
+    },
+    {
+      "epoch": 0.008775555626212203,
+      "grad_norm": 2.6625030040740967,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5772,
+      "step": 69
+    },
+    {
+      "epoch": 0.00890273759180948,
+      "grad_norm": 2.5769317150115967,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 1.4481,
+      "step": 70
+    },
+    {
+      "epoch": 0.00902991955740676,
+      "grad_norm": 2.8375887870788574,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.6209,
+      "step": 71
+    },
+    {
+      "epoch": 0.009157101523004038,
+      "grad_norm": 2.410177707672119,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6444,
+      "step": 72
+    },
+    {
+      "epoch": 0.009284283488601316,
+      "grad_norm": 2.377715826034546,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.5977,
+      "step": 73
+    },
+    {
+      "epoch": 0.009411465454198594,
+      "grad_norm": 2.3886666297912598,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 1.6901,
+      "step": 74
+    },
+    {
+      "epoch": 0.009538647419795872,
+      "grad_norm": 2.8022537231445312,
+      "learning_rate": 0.0,
+      "loss": 1.3744,
+      "step": 75
+    },
+    {
+      "epoch": 0.009538647419795872,
+      "eval_loss": 1.5396223068237305,
+      "eval_runtime": 1016.8842,
+      "eval_samples_per_second": 6.512,
+      "eval_steps_per_second": 3.256,
+      "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