Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10954919e25df70d17d47d08da3641147eb86f58bed58ae63b019a1a93108720
+oid sha256:be572d01e06dc0809fdf05dc4dadf6486cb6cef130f01bcf04aec299915bf67c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4308a7cd1cc9b3f277cc27fb3bdab37ec8a0ee103ea9425bca8fa06db8574099
+oid sha256:f971cdef64b419b534cad4bfc0b33dd168e350e37e546d9b31e05ff8dd205bf8
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c743e1bffaaa9e09888245c887191bdc321fd3a825e0b54e0754fb6d8a0f61
+oid sha256:1d804d42e1debb56a056bc554e869329ff39dff76880e80f5e9bddfe55fb7e54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41fe81b4cb3e7753621de49d816bff984b46a2120fc17d84d3662502b8a590a
+oid sha256:4ee902516bc4905777702eaeafbbca2e343e1851cdfce78d77cc031874f21056
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930bb06c7aac50b5c7b779e8e688eee40b177540cfffeeec9b6d5599d14d8338
+oid sha256:a42baad16ec6b017e9c5524c5a052bd535c0db7ac5d53c47bd7e21b36fd215c3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115011f931f8c895df84b559f917c9148825f6404fba1d054d029b7141d9da6e
+oid sha256:dbcd04f85644b238ac9efe30f361535bf49aa448a34dca7dc79ce32e36ef2304
 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": 0.44510385756676557,
+  "epoch": 0.5934718100890207,
   "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": 0.0305,
       "step": 75
+    },
+    {
+      "epoch": 0.45103857566765576,
+      "grad_norm": 0.32224422693252563,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0199,
+      "step": 76
+    },
+    {
+      "epoch": 0.456973293768546,
+      "grad_norm": 0.19896110892295837,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0438,
+      "step": 77
+    },
+    {
+      "epoch": 0.4629080118694362,
+      "grad_norm": 0.19278265535831451,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.02,
+      "step": 78
+    },
+    {
+      "epoch": 0.4688427299703264,
+      "grad_norm": 0.14536862075328827,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0158,
+      "step": 79
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 0.15426011383533478,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0292,
+      "step": 80
+    },
+    {
+      "epoch": 0.4807121661721068,
+      "grad_norm": 0.2467106133699417,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0245,
+      "step": 81
+    },
+    {
+      "epoch": 0.4807121661721068,
+      "eval_loss": 0.029930343851447105,
+      "eval_runtime": 8.8732,
+      "eval_samples_per_second": 64.013,
+      "eval_steps_per_second": 2.029,
+      "step": 81
+    },
+    {
+      "epoch": 0.486646884272997,
+      "grad_norm": 0.17040932178497314,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0207,
+      "step": 82
+    },
+    {
+      "epoch": 0.49258160237388726,
+      "grad_norm": 0.2426087111234665,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0383,
+      "step": 83
+    },
+    {
+      "epoch": 0.49851632047477745,
+      "grad_norm": 0.3300859034061432,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0313,
+      "step": 84
+    },
+    {
+      "epoch": 0.5044510385756676,
+      "grad_norm": 0.2978295087814331,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0439,
+      "step": 85
+    },
+    {
+      "epoch": 0.5103857566765578,
+      "grad_norm": 0.25744086503982544,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0309,
+      "step": 86
+    },
+    {
+      "epoch": 0.516320474777448,
+      "grad_norm": 0.1737741380929947,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0243,
+      "step": 87
+    },
+    {
+      "epoch": 0.5222551928783383,
+      "grad_norm": 0.17425476014614105,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0316,
+      "step": 88
+    },
+    {
+      "epoch": 0.5281899109792285,
+      "grad_norm": 0.1594141274690628,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.02,
+      "step": 89
+    },
+    {
+      "epoch": 0.5341246290801187,
+      "grad_norm": 0.12691667675971985,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0285,
+      "step": 90
+    },
+    {
+      "epoch": 0.5341246290801187,
+      "eval_loss": 0.029172684997320175,
+      "eval_runtime": 8.8893,
+      "eval_samples_per_second": 63.897,
+      "eval_steps_per_second": 2.025,
+      "step": 90
+    },
+    {
+      "epoch": 0.5400593471810089,
+      "grad_norm": 0.23202553391456604,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0204,
+      "step": 91
+    },
+    {
+      "epoch": 0.5459940652818991,
+      "grad_norm": 0.15419085323810577,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0278,
+      "step": 92
+    },
+    {
+      "epoch": 0.5519287833827893,
+      "grad_norm": 0.1561238318681717,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0296,
+      "step": 93
+    },
+    {
+      "epoch": 0.5578635014836796,
+      "grad_norm": 0.1936614066362381,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0277,
+      "step": 94
+    },
+    {
+      "epoch": 0.5637982195845698,
+      "grad_norm": 0.14458991587162018,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0276,
+      "step": 95
+    },
+    {
+      "epoch": 0.56973293768546,
+      "grad_norm": 0.1705336570739746,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0326,
+      "step": 96
+    },
+    {
+      "epoch": 0.5756676557863502,
+      "grad_norm": 0.16677498817443848,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0446,
+      "step": 97
+    },
+    {
+      "epoch": 0.5816023738872403,
+      "grad_norm": 0.16387122869491577,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0288,
+      "step": 98
+    },
+    {
+      "epoch": 0.5875370919881305,
+      "grad_norm": 0.18603426218032837,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0303,
+      "step": 99
+    },
+    {
+      "epoch": 0.5875370919881305,
+      "eval_loss": 0.0289829820394516,
+      "eval_runtime": 8.8826,
+      "eval_samples_per_second": 63.945,
+      "eval_steps_per_second": 2.026,
+      "step": 99
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "grad_norm": 0.20871266722679138,
+      "learning_rate": 0.0,
+      "loss": 0.0229,
+      "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": 2.255337347392471e+17,
+  "total_flos": 3.0120623793084826e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null