Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f52bee8d2324e376c7e0c2d044b7ea137135b1b771ee8997e82e3c60612b05
+oid sha256:e941fcd88fb1e7f8e43908ba751f91989b3bc5637f65a093d59b5631639da89e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be372be3aada41e246a8530ab132a7a2674c31b52fb53d16730e47884756813
+oid sha256:1d637ee577ff0f1c23b1c99b6ca7356bee20c428b1836a3343424f63f4e58314
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca3297b5add8ca7ae84333ef2900e2f930e14cb9477b35d2309e18be9f92415
+oid sha256:2ba5397d9202659cf5d6e739d02427254832bce966d0fe014dc7f0134b413d65
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7d52dd34d2369da087bdc005cc930b95319a7d6a7635b74f5accf5ad3be6eb
+oid sha256:a81f51f65380e976bba69e80a76fc2fc52c05cb59496880696f10e3f632cd5eb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47dc4ae34f4d15a9c9f4b6570babb90739ec75e82321a633073d44233dde8c1
+oid sha256:b278e523f40cfd37b873b1379597f5c335b9e10604aa90507d83a5958f1e0dc8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565a7a95076128f49474df66b00b62546026b15fcbc933ddd70950815a6762f6
+oid sha256:7d326eca4282c474ac0b4e66db4d0e386629eaef28f387f6b1c39aa09df0ebef
 size 15024

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": 1.2096774193548387,
+  "epoch": 1.6129032258064515,
   "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": 0.1691,
       "step": 75
+    },
+    {
+      "epoch": 1.2258064516129032,
+      "grad_norm": 0.11228110641241074,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1465,
+      "step": 76
+    },
+    {
+      "epoch": 1.2419354838709677,
+      "grad_norm": 0.11053880304098129,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1654,
+      "step": 77
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.09700427949428558,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1462,
+      "step": 78
+    },
+    {
+      "epoch": 1.2741935483870968,
+      "grad_norm": 0.12035026401281357,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1642,
+      "step": 79
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.10824038088321686,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.161,
+      "step": 80
+    },
+    {
+      "epoch": 1.3064516129032258,
+      "grad_norm": 0.11326368898153305,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.171,
+      "step": 81
+    },
+    {
+      "epoch": 1.3064516129032258,
+      "eval_loss": 0.15154211223125458,
+      "eval_runtime": 5.137,
+      "eval_samples_per_second": 40.685,
+      "eval_steps_per_second": 1.363,
+      "step": 81
+    },
+    {
+      "epoch": 1.3225806451612903,
+      "grad_norm": 0.10717129707336426,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.139,
+      "step": 82
+    },
+    {
+      "epoch": 1.3387096774193548,
+      "grad_norm": 0.11026385426521301,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1504,
+      "step": 83
+    },
+    {
+      "epoch": 1.3548387096774195,
+      "grad_norm": 0.10799112915992737,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1473,
+      "step": 84
+    },
+    {
+      "epoch": 1.370967741935484,
+      "grad_norm": 0.10504213720560074,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1522,
+      "step": 85
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.1022191271185875,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1534,
+      "step": 86
+    },
+    {
+      "epoch": 1.403225806451613,
+      "grad_norm": 0.1087154969573021,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1371,
+      "step": 87
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 0.1028815284371376,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.139,
+      "step": 88
+    },
+    {
+      "epoch": 1.435483870967742,
+      "grad_norm": 0.11950594186782837,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1788,
+      "step": 89
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.1059289202094078,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1546,
+      "step": 90
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "eval_loss": 0.150466650724411,
+      "eval_runtime": 5.1364,
+      "eval_samples_per_second": 40.69,
+      "eval_steps_per_second": 1.363,
+      "step": 90
+    },
+    {
+      "epoch": 1.467741935483871,
+      "grad_norm": 0.10315851122140884,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1631,
+      "step": 91
+    },
+    {
+      "epoch": 1.4838709677419355,
+      "grad_norm": 0.10348256677389145,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1506,
+      "step": 92
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10390815138816833,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1533,
+      "step": 93
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.1149415373802185,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.147,
+      "step": 94
+    },
+    {
+      "epoch": 1.532258064516129,
+      "grad_norm": 0.10211697965860367,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1493,
+      "step": 95
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.1074586734175682,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1479,
+      "step": 96
+    },
+    {
+      "epoch": 1.564516129032258,
+      "grad_norm": 0.10077419877052307,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1455,
+      "step": 97
+    },
+    {
+      "epoch": 1.5806451612903225,
+      "grad_norm": 0.10627587139606476,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1566,
+      "step": 98
+    },
+    {
+      "epoch": 1.596774193548387,
+      "grad_norm": 0.10498929023742676,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1454,
+      "step": 99
+    },
+    {
+      "epoch": 1.596774193548387,
+      "eval_loss": 0.1502324491739273,
+      "eval_runtime": 5.124,
+      "eval_samples_per_second": 40.789,
+      "eval_steps_per_second": 1.366,
+      "step": 99
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.10515011101961136,
+      "learning_rate": 0.0,
+      "loss": 0.1451,
+      "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": 2.194832508321792e+17,
+  "total_flos": 2.9352579326541824e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null