Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ea2ceae1e1612375d36c5d9c3801dc8b8835f84585ccc46428284a3aa3b45
+oid sha256:764ead2b37dc2690d73d14a2a881560975263a601238845ad5ffc76c096be848
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b3d30a0fa9db66eb32d2138c86e81afe558b2f5ec2cfa6587c2c8e1b660f81
+oid sha256:0956d13262f0159196fbd064db832faa1a6939cafc99264d69cf4bd24a2e0540
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58b155e5123c7f1976665fc15d0993b62f2994fac0848287641211bae5ae5bc
+oid sha256:d665228d5c674a5322354b2cbabcdb77447213d0273363aa47e9189b164a4bf9
 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": 0.1595744680851064,
+  "epoch": 0.2127659574468085,
   "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": 0.0403,
       "step": 75
+    },
+    {
+      "epoch": 0.16170212765957448,
+      "grad_norm": 0.2003021091222763,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0533,
+      "step": 76
+    },
+    {
+      "epoch": 0.16382978723404254,
+      "grad_norm": 0.12371911853551865,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0258,
+      "step": 77
+    },
+    {
+      "epoch": 0.16595744680851063,
+      "grad_norm": 0.17193201184272766,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.03,
+      "step": 78
+    },
+    {
+      "epoch": 0.16808510638297872,
+      "grad_norm": 0.2122802734375,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0446,
+      "step": 79
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.17824585735797882,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0516,
+      "step": 80
+    },
+    {
+      "epoch": 0.1723404255319149,
+      "grad_norm": 0.10696157068014145,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0105,
+      "step": 81
+    },
+    {
+      "epoch": 0.1723404255319149,
+      "eval_loss": 0.016418613493442535,
+      "eval_runtime": 137.3662,
+      "eval_samples_per_second": 2.883,
+      "eval_steps_per_second": 0.364,
+      "step": 81
+    },
+    {
+      "epoch": 0.17446808510638298,
+      "grad_norm": 0.19411924481391907,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0412,
+      "step": 82
+    },
+    {
+      "epoch": 0.17659574468085107,
+      "grad_norm": 0.15288114547729492,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0347,
+      "step": 83
+    },
+    {
+      "epoch": 0.17872340425531916,
+      "grad_norm": 0.13765448331832886,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0298,
+      "step": 84
+    },
+    {
+      "epoch": 0.18085106382978725,
+      "grad_norm": 0.2824060320854187,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0797,
+      "step": 85
+    },
+    {
+      "epoch": 0.1829787234042553,
+      "grad_norm": 0.15786072611808777,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0406,
+      "step": 86
+    },
+    {
+      "epoch": 0.1851063829787234,
+      "grad_norm": 0.12804144620895386,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0286,
+      "step": 87
+    },
+    {
+      "epoch": 0.18723404255319148,
+      "grad_norm": 0.16002494096755981,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0166,
+      "step": 88
+    },
+    {
+      "epoch": 0.18936170212765957,
+      "grad_norm": 0.17278890311717987,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0615,
+      "step": 89
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 0.12740778923034668,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0259,
+      "step": 90
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "eval_loss": 0.015345096588134766,
+      "eval_runtime": 137.224,
+      "eval_samples_per_second": 2.886,
+      "eval_steps_per_second": 0.364,
+      "step": 90
+    },
+    {
+      "epoch": 0.19361702127659575,
+      "grad_norm": 0.10843079537153244,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0235,
+      "step": 91
+    },
+    {
+      "epoch": 0.19574468085106383,
+      "grad_norm": 0.11718861013650894,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0224,
+      "step": 92
+    },
+    {
+      "epoch": 0.19787234042553192,
+      "grad_norm": 0.19033397734165192,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0543,
+      "step": 93
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.17855358123779297,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0734,
+      "step": 94
+    },
+    {
+      "epoch": 0.20212765957446807,
+      "grad_norm": 0.16578811407089233,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0443,
+      "step": 95
+    },
+    {
+      "epoch": 0.20425531914893616,
+      "grad_norm": 0.10047528892755508,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0116,
+      "step": 96
+    },
+    {
+      "epoch": 0.20638297872340425,
+      "grad_norm": 0.1590314358472824,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.031,
+      "step": 97
+    },
+    {
+      "epoch": 0.20851063829787234,
+      "grad_norm": 0.12019843608140945,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0363,
+      "step": 98
+    },
+    {
+      "epoch": 0.21063829787234042,
+      "grad_norm": 0.19698375463485718,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0541,
+      "step": 99
+    },
+    {
+      "epoch": 0.21063829787234042,
+      "eval_loss": 0.01515384390950203,
+      "eval_runtime": 137.3473,
+      "eval_samples_per_second": 2.883,
+      "eval_steps_per_second": 0.364,
+      "step": 99
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.09224493056535721,
+      "learning_rate": 0.0,
+      "loss": 0.007,
+      "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": 9.80196966531072e+16,
+  "total_flos": 1.306929288708096e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null