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:ffece9bc80de0559ec793dc414be18d052f1c36c4b4a5f59b0b1427a596b4ded
+oid sha256:df1ccbeda8b6431919012c1dae62923ff4c1df868ef64abfc9f7bd2379ebc6c7
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49855e54587beaff1cbec791c4a25aa8f4ce0613ab14d49d5c9c98251c1c441
+oid sha256:81fbd54dddcae94ab6fd15d2b28ba0a8cdf2a66415380f8767b934359fdc743d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28716e0201d453dfccb8481130df36b8957e6f8e6d3cb2e37ebe0b0b0a6ffeb
+oid sha256:46e435e3959c91f5bacc73de4513b83a4662b6a759ef3a86638c445ea68b5d25
 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": 0.0325874429719748,
+  "epoch": 0.043449923962633065,
   "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": 0.9906,
       "step": 75
+    },
+    {
+      "epoch": 0.03302194221160113,
+      "grad_norm": 0.7703763842582703,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9075,
+      "step": 76
+    },
+    {
+      "epoch": 0.03345644145122746,
+      "grad_norm": 0.7331583499908447,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.9032,
+      "step": 77
+    },
+    {
+      "epoch": 0.03389094069085379,
+      "grad_norm": 0.8618801832199097,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9932,
+      "step": 78
+    },
+    {
+      "epoch": 0.03432543993048012,
+      "grad_norm": 0.7720716595649719,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.7723,
+      "step": 79
+    },
+    {
+      "epoch": 0.03475993917010645,
+      "grad_norm": 0.7049722075462341,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.004,
+      "step": 80
+    },
+    {
+      "epoch": 0.035194438409732784,
+      "grad_norm": 0.7694608569145203,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.001,
+      "step": 81
+    },
+    {
+      "epoch": 0.035194438409732784,
+      "eval_loss": 0.42849254608154297,
+      "eval_runtime": 937.4186,
+      "eval_samples_per_second": 2.068,
+      "eval_steps_per_second": 0.259,
+      "step": 81
+    },
+    {
+      "epoch": 0.035628937649359115,
+      "grad_norm": 0.7914429903030396,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8019,
+      "step": 82
+    },
+    {
+      "epoch": 0.036063436888985445,
+      "grad_norm": 0.7216392159461975,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.7337,
+      "step": 83
+    },
+    {
+      "epoch": 0.036497936128611776,
+      "grad_norm": 0.7539612054824829,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.7445,
+      "step": 84
+    },
+    {
+      "epoch": 0.036932435368238106,
+      "grad_norm": 0.7819778323173523,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.759,
+      "step": 85
+    },
+    {
+      "epoch": 0.03736693460786444,
+      "grad_norm": 0.8650638461112976,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.903,
+      "step": 86
+    },
+    {
+      "epoch": 0.03780143384749077,
+      "grad_norm": 0.7645513415336609,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.8763,
+      "step": 87
+    },
+    {
+      "epoch": 0.0382359330871171,
+      "grad_norm": 0.7570232152938843,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9802,
+      "step": 88
+    },
+    {
+      "epoch": 0.03867043232674343,
+      "grad_norm": 0.6940462589263916,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.8409,
+      "step": 89
+    },
+    {
+      "epoch": 0.03910493156636976,
+      "grad_norm": 0.7175998687744141,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8271,
+      "step": 90
+    },
+    {
+      "epoch": 0.03910493156636976,
+      "eval_loss": 0.42518991231918335,
+      "eval_runtime": 937.2878,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.259,
+      "step": 90
+    },
+    {
+      "epoch": 0.03953943080599609,
+      "grad_norm": 0.7848137021064758,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7753,
+      "step": 91
+    },
+    {
+      "epoch": 0.03997393004562242,
+      "grad_norm": 0.8303205370903015,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9935,
+      "step": 92
+    },
+    {
+      "epoch": 0.04040842928524875,
+      "grad_norm": 0.7627360820770264,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.8909,
+      "step": 93
+    },
+    {
+      "epoch": 0.04084292852487508,
+      "grad_norm": 0.7823213934898376,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7864,
+      "step": 94
+    },
+    {
+      "epoch": 0.04127742776450141,
+      "grad_norm": 0.7386431694030762,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.8293,
+      "step": 95
+    },
+    {
+      "epoch": 0.04171192700412774,
+      "grad_norm": 0.7980239987373352,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8131,
+      "step": 96
+    },
+    {
+      "epoch": 0.04214642624375407,
+      "grad_norm": 0.6765995621681213,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.7674,
+      "step": 97
+    },
+    {
+      "epoch": 0.042580925483380404,
+      "grad_norm": 0.8706260919570923,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8537,
+      "step": 98
+    },
+    {
+      "epoch": 0.043015424723006734,
+      "grad_norm": 0.7013819217681885,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.8367,
+      "step": 99
+    },
+    {
+      "epoch": 0.043015424723006734,
+      "eval_loss": 0.4246019124984741,
+      "eval_runtime": 937.3227,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.259,
+      "step": 99
+    },
+    {
+      "epoch": 0.043449923962633065,
+      "grad_norm": 0.7123420834541321,
+      "learning_rate": 0.0,
+      "loss": 0.9134,
+      "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": 1.8281750291546112e+17,
+  "total_flos": 2.443914535501824e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null