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:ca25e8d8ed72e3d3969b65198f8a313298bfeb54ad660790291d8ca454cb1583
+oid sha256:3e3d83116c9c9789806e4413ab28046a6e33d06f74b544208fcc5eca17f7d626
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4607eadcd03153fed57e9ca286157de311ebcd2de9c91691912f59c6e5ed8772
+oid sha256:9b5bff6d90d3f5872791b03932821e7933550198a6eb28aa6c8411db8f1e83ff
 size 295765866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ae7ca7c789f639bcad38d8a60a69ba45e8e51fec98d8d94a5ef0c64a0eb2a9
+oid sha256:ec1ae98d902bcbd9d814e43adbc63e512fa048d957f624e274404cda0f079d57
 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": 0.12775471095496646,
+  "epoch": 0.1916320664324497,
   "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": 23.378,
       "eval_steps_per_second": 11.689,
       "step": 50
+    },
+    {
+      "epoch": 0.1303098051740658,
+      "grad_norm": 1.1723414659500122,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0801,
+      "step": 51
+    },
+    {
+      "epoch": 0.13286489939316512,
+      "grad_norm": 0.8172379732131958,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.1024,
+      "step": 52
+    },
+    {
+      "epoch": 0.13541999361226445,
+      "grad_norm": 0.9060799479484558,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.1177,
+      "step": 53
+    },
+    {
+      "epoch": 0.13797508783136378,
+      "grad_norm": 0.5991807579994202,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0704,
+      "step": 54
+    },
+    {
+      "epoch": 0.1405301820504631,
+      "grad_norm": 0.703624427318573,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0954,
+      "step": 55
+    },
+    {
+      "epoch": 0.14308527626956244,
+      "grad_norm": 0.7881723642349243,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0788,
+      "step": 56
+    },
+    {
+      "epoch": 0.14564037048866177,
+      "grad_norm": 0.9600244164466858,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0974,
+      "step": 57
+    },
+    {
+      "epoch": 0.1481954647077611,
+      "grad_norm": 0.8376311659812927,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0588,
+      "step": 58
+    },
+    {
+      "epoch": 0.15075055892686043,
+      "grad_norm": 0.936733603477478,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1407,
+      "step": 59
+    },
+    {
+      "epoch": 0.15330565314595976,
+      "grad_norm": 0.8105266690254211,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0863,
+      "step": 60
+    },
+    {
+      "epoch": 0.1558607473650591,
+      "grad_norm": 0.4721161723136902,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0296,
+      "step": 61
+    },
+    {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 0.5724545121192932,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0688,
+      "step": 62
+    },
+    {
+      "epoch": 0.16097093580325775,
+      "grad_norm": 1.028909683227539,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0995,
+      "step": 63
+    },
+    {
+      "epoch": 0.16352603002235708,
+      "grad_norm": 0.7372393608093262,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0972,
+      "step": 64
+    },
+    {
+      "epoch": 0.1660811242414564,
+      "grad_norm": 1.3419673442840576,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.1088,
+      "step": 65
+    },
+    {
+      "epoch": 0.16863621846055574,
+      "grad_norm": 0.7063865661621094,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0701,
+      "step": 66
+    },
+    {
+      "epoch": 0.17119131267965507,
+      "grad_norm": 0.628400444984436,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0733,
+      "step": 67
+    },
+    {
+      "epoch": 0.1737464068987544,
+      "grad_norm": 1.4911381006240845,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.1276,
+      "step": 68
+    },
+    {
+      "epoch": 0.17630150111785373,
+      "grad_norm": 0.7579659223556519,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0869,
+      "step": 69
+    },
+    {
+      "epoch": 0.17885659533695306,
+      "grad_norm": 0.3117106258869171,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0235,
+      "step": 70
+    },
+    {
+      "epoch": 0.18141168955605239,
+      "grad_norm": 1.2181602716445923,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0903,
+      "step": 71
+    },
+    {
+      "epoch": 0.18396678377515172,
+      "grad_norm": 0.6046707034111023,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.03,
+      "step": 72
+    },
+    {
+      "epoch": 0.18652187799425105,
+      "grad_norm": 0.4396168291568756,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0308,
+      "step": 73
+    },
+    {
+      "epoch": 0.18907697221335037,
+      "grad_norm": 0.7448429465293884,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0689,
+      "step": 74
+    },
+    {
+      "epoch": 0.1916320664324497,
+      "grad_norm": 0.9112486839294434,
+      "learning_rate": 0.0,
+      "loss": 0.0907,
+      "step": 75
+    },
+    {
+      "epoch": 0.1916320664324497,
+      "eval_loss": 0.06476715207099915,
+      "eval_runtime": 14.1155,
+      "eval_samples_per_second": 23.379,
+      "eval_steps_per_second": 11.689,
+      "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": 1.32442044235776e+16,
+  "total_flos": 1.98663066353664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null