Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b25093c2ddcfc392d555be93b382a35b05845daad2edfe7e7ddcf5bd8c58d4
+oid sha256:cddf9d5112c733ae89391773f35c6a07ff3b7afff1a25408d640ec320b216023
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f987a0e8ca33db7f01839de2164ccf4db663a66e6f7689a9ed004b586e621276
+oid sha256:97be81b5e88c4af1748f8211c030ce7ac2bbf575e7c0c27b3bb9474c9a8b7b8f
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c88366e4cedd829c09c5fe7059b8e2e98aca6c5ecd80e83fa5290e51d4813d6
+oid sha256:b1eda10e338bda450401b94e9d71edd0e8030fa85df4e15faff7fc1927b372d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37fdc46c9ceacc4f09fb079980eedde483f3261a807a717ac38bb84282cfbc0
+oid sha256:b79cde9ee58bdae8d5bf70ac16895e4e2030aa3fdbfeffaeba15804803784fd2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dd44bba8ec82bdc5a999dd503ca41e696d9d7a9a02f9a40556aba1f7d284e1
+oid sha256:f6d9acef45e6155e320d4a78b12d869ff81c303ca98bc7eb367be40086458cfa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9f53c748ab56977e5d0b2dabfb603fcb816a36a8711e81b4f65d5a8fb7d27c
+oid sha256:610c9f310ffd54fd8cf1375ce3733a85b79590ac8039610a2dbe77dd26d9688b
 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": 0.44642857142857145,
+  "epoch": 0.5952380952380952,
   "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": 0.1972,
       "step": 75
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 0.4646625518798828,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2428,
+      "step": 76
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.43261802196502686,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1961,
+      "step": 77
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.4902274012565613,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1893,
+      "step": 78
+    },
+    {
+      "epoch": 0.47023809523809523,
+      "grad_norm": 0.36820879578590393,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1857,
+      "step": 79
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.40407320857048035,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1762,
+      "step": 80
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 0.42008960247039795,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2245,
+      "step": 81
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "eval_loss": 0.2156299650669098,
+      "eval_runtime": 0.731,
+      "eval_samples_per_second": 772.964,
+      "eval_steps_per_second": 24.625,
+      "step": 81
+    },
+    {
+      "epoch": 0.4880952380952381,
+      "grad_norm": 0.5599027872085571,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2199,
+      "step": 82
+    },
+    {
+      "epoch": 0.49404761904761907,
+      "grad_norm": 0.49288442730903625,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2179,
+      "step": 83
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.385234534740448,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1945,
+      "step": 84
+    },
+    {
+      "epoch": 0.5059523809523809,
+      "grad_norm": 0.5592166185379028,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2251,
+      "step": 85
+    },
+    {
+      "epoch": 0.5119047619047619,
+      "grad_norm": 0.39405468106269836,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2158,
+      "step": 86
+    },
+    {
+      "epoch": 0.5178571428571429,
+      "grad_norm": 0.5080683827400208,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2302,
+      "step": 87
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.45728829503059387,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1862,
+      "step": 88
+    },
+    {
+      "epoch": 0.5297619047619048,
+      "grad_norm": 0.3771636188030243,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2153,
+      "step": 89
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.43016037344932556,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.266,
+      "step": 90
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "eval_loss": 0.21077343821525574,
+      "eval_runtime": 0.7276,
+      "eval_samples_per_second": 776.507,
+      "eval_steps_per_second": 24.738,
+      "step": 90
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.5915383100509644,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2349,
+      "step": 91
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 0.37992358207702637,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1927,
+      "step": 92
+    },
+    {
+      "epoch": 0.5535714285714286,
+      "grad_norm": 0.4356793463230133,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2227,
+      "step": 93
+    },
+    {
+      "epoch": 0.5595238095238095,
+      "grad_norm": 0.5157723426818848,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2807,
+      "step": 94
+    },
+    {
+      "epoch": 0.5654761904761905,
+      "grad_norm": 0.4171281158924103,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1941,
+      "step": 95
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.44283267855644226,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2501,
+      "step": 96
+    },
+    {
+      "epoch": 0.5773809523809523,
+      "grad_norm": 0.3836650252342224,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1853,
+      "step": 97
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.40736451745033264,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1831,
+      "step": 98
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 0.40472492575645447,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1468,
+      "step": 99
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "eval_loss": 0.20941224694252014,
+      "eval_runtime": 0.7248,
+      "eval_samples_per_second": 779.517,
+      "eval_steps_per_second": 24.834,
+      "step": 99
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 0.3667122721672058,
+      "learning_rate": 0.0,
+      "loss": 0.1555,
+      "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": 4165127582515200.0,
+  "total_flos": 5553503443353600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null