Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84065167cdbab97397049fccb675d4dd3c283e011d081cfe984d4f952ad93130
+oid sha256:75f2b5c2f7a9755022d863a7c41f68f2dd9f5867b0b5610eddda63f3046b6004
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b410eaea722510661410805be903ff0bbbcb65c3815e8e943f7e1d093f4d2ca9
+oid sha256:7b8ee06bde015a0a38e7ee3505acffa880fa879e9ae23b8c11b12dc2384c6095
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b35bc5f4703bfdc2408995ce3360c64d9c850a91b68abfc8d67041fbf297720
+oid sha256:8b0c49424925dca105bc84a20e264635988c0059b5e731fb70356897e19c825e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019917673615721682,
+  "epoch": 0.02655689815429558,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.0193,
       "step": 75
+    },
+    {
+      "epoch": 0.02018324259726464,
+      "grad_norm": 4.517977714538574,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2632,
+      "step": 76
+    },
+    {
+      "epoch": 0.020448811578807596,
+      "grad_norm": 1.7417783737182617,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0566,
+      "step": 77
+    },
+    {
+      "epoch": 0.02071438056035055,
+      "grad_norm": 0.07233806699514389,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0025,
+      "step": 78
+    },
+    {
+      "epoch": 0.020979949541893507,
+      "grad_norm": 3.043607234954834,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0618,
+      "step": 79
+    },
+    {
+      "epoch": 0.021245518523436462,
+      "grad_norm": 1.1216740608215332,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0171,
+      "step": 80
+    },
+    {
+      "epoch": 0.021511087504979418,
+      "grad_norm": 0.18935361504554749,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0035,
+      "step": 81
+    },
+    {
+      "epoch": 0.021511087504979418,
+      "eval_loss": 0.030739974230527878,
+      "eval_runtime": 559.8399,
+      "eval_samples_per_second": 5.664,
+      "eval_steps_per_second": 0.709,
+      "step": 81
+    },
+    {
+      "epoch": 0.021776656486522373,
+      "grad_norm": 4.249741554260254,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3826,
+      "step": 82
+    },
+    {
+      "epoch": 0.02204222546806533,
+      "grad_norm": 1.0712897777557373,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0169,
+      "step": 83
+    },
+    {
+      "epoch": 0.022307794449608287,
+      "grad_norm": 0.07341117411851883,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0022,
+      "step": 84
+    },
+    {
+      "epoch": 0.022573363431151242,
+      "grad_norm": 0.10707651823759079,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0047,
+      "step": 85
+    },
+    {
+      "epoch": 0.022838932412694198,
+      "grad_norm": 0.08516495674848557,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0034,
+      "step": 86
+    },
+    {
+      "epoch": 0.023104501394237153,
+      "grad_norm": 1.109482765197754,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0298,
+      "step": 87
+    },
+    {
+      "epoch": 0.023370070375780108,
+      "grad_norm": 4.274382591247559,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1633,
+      "step": 88
+    },
+    {
+      "epoch": 0.023635639357323063,
+      "grad_norm": 4.241298198699951,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1244,
+      "step": 89
+    },
+    {
+      "epoch": 0.02390120833886602,
+      "grad_norm": 0.4226183593273163,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0099,
+      "step": 90
+    },
+    {
+      "epoch": 0.02390120833886602,
+      "eval_loss": 0.030956266447901726,
+      "eval_runtime": 559.9924,
+      "eval_samples_per_second": 5.663,
+      "eval_steps_per_second": 0.709,
+      "step": 90
+    },
+    {
+      "epoch": 0.024166777320408978,
+      "grad_norm": 0.1662449985742569,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0056,
+      "step": 91
+    },
+    {
+      "epoch": 0.024432346301951933,
+      "grad_norm": 0.1186576634645462,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0044,
+      "step": 92
+    },
+    {
+      "epoch": 0.024697915283494888,
+      "grad_norm": 0.24360933899879456,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0076,
+      "step": 93
+    },
+    {
+      "epoch": 0.024963484265037843,
+      "grad_norm": 0.07054503262042999,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0021,
+      "step": 94
+    },
+    {
+      "epoch": 0.0252290532465808,
+      "grad_norm": 0.06228477507829666,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0017,
+      "step": 95
+    },
+    {
+      "epoch": 0.025494622228123754,
+      "grad_norm": 6.644521713256836,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.492,
+      "step": 96
+    },
+    {
+      "epoch": 0.02576019120966671,
+      "grad_norm": 3.683866262435913,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0485,
+      "step": 97
+    },
+    {
+      "epoch": 0.026025760191209668,
+      "grad_norm": 0.042617376893758774,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.002,
+      "step": 98
+    },
+    {
+      "epoch": 0.026291329172752623,
+      "grad_norm": 0.17293287813663483,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0065,
+      "step": 99
+    },
+    {
+      "epoch": 0.026291329172752623,
+      "eval_loss": 0.030459770932793617,
+      "eval_runtime": 559.7954,
+      "eval_samples_per_second": 5.665,
+      "eval_steps_per_second": 0.709,
+      "step": 99
+    },
+    {
+      "epoch": 0.02655689815429558,
+      "grad_norm": 0.04684700816869736,
+      "learning_rate": 0.0,
+      "loss": 0.0018,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.703854298261094e+16,
+  "total_flos": 1.293847239768146e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null