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:d2dd66d0b8c7a186e9008078ca3d6fe21f2891b5161a36901aca7a385fb017ac
+oid sha256:2be3066b271f9511745ed840a43f7d59fd46ec5624c110f6193e56318cf2c248
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3dec126f4ec0b2b6a8ea60ad3d2edc5ef2b550a3751bbede769ea8b4b6f8f95
+oid sha256:b816a58d1448bfb46b626d377bb5b997f02ae53eed060b604f73907bb5366cfc
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7dce7e0170aa34175b5269717b961d1ffe522fb28bfeef670f097012d24db8
+oid sha256:55fe7c60145aa0c3bd8024fe4dfc785bce4490b593d58e915a6976a1164c5f91
 size 14960

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": 0.4322766570605187,
+  "epoch": 0.5763688760806917,
   "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": 3.1457,
       "step": 75
+    },
+    {
+      "epoch": 0.43804034582132567,
+      "grad_norm": 1.0064634084701538,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.2492,
+      "step": 76
+    },
+    {
+      "epoch": 0.4438040345821326,
+      "grad_norm": 0.993618905544281,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 3.2248,
+      "step": 77
+    },
+    {
+      "epoch": 0.4495677233429395,
+      "grad_norm": 0.9184038639068604,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.3028,
+      "step": 78
+    },
+    {
+      "epoch": 0.4553314121037464,
+      "grad_norm": 1.4929434061050415,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 3.08,
+      "step": 79
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.8565345406532288,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.0604,
+      "step": 80
+    },
+    {
+      "epoch": 0.4668587896253602,
+      "grad_norm": 1.0060956478118896,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.2126,
+      "step": 81
+    },
+    {
+      "epoch": 0.4668587896253602,
+      "eval_loss": 3.25429105758667,
+      "eval_runtime": 0.8563,
+      "eval_samples_per_second": 680.804,
+      "eval_steps_per_second": 22.187,
+      "step": 81
+    },
+    {
+      "epoch": 0.47262247838616717,
+      "grad_norm": 1.0326199531555176,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.1554,
+      "step": 82
+    },
+    {
+      "epoch": 0.4783861671469741,
+      "grad_norm": 1.0476312637329102,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.0711,
+      "step": 83
+    },
+    {
+      "epoch": 0.484149855907781,
+      "grad_norm": 0.9754363298416138,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.0958,
+      "step": 84
+    },
+    {
+      "epoch": 0.4899135446685879,
+      "grad_norm": 0.9376251697540283,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.1599,
+      "step": 85
+    },
+    {
+      "epoch": 0.4956772334293948,
+      "grad_norm": 1.141634464263916,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.3735,
+      "step": 86
+    },
+    {
+      "epoch": 0.5014409221902018,
+      "grad_norm": 1.1722526550292969,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 3.2415,
+      "step": 87
+    },
+    {
+      "epoch": 0.5072046109510087,
+      "grad_norm": 1.0881351232528687,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.1117,
+      "step": 88
+    },
+    {
+      "epoch": 0.5129682997118156,
+      "grad_norm": 0.9429522752761841,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 3.2167,
+      "step": 89
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "grad_norm": 0.940540075302124,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.1963,
+      "step": 90
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "eval_loss": 3.24446439743042,
+      "eval_runtime": 0.8414,
+      "eval_samples_per_second": 692.9,
+      "eval_steps_per_second": 22.582,
+      "step": 90
+    },
+    {
+      "epoch": 0.5244956772334294,
+      "grad_norm": 0.9718915820121765,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.1742,
+      "step": 91
+    },
+    {
+      "epoch": 0.5302593659942363,
+      "grad_norm": 1.0493394136428833,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.3019,
+      "step": 92
+    },
+    {
+      "epoch": 0.5360230547550432,
+      "grad_norm": 0.9497436285018921,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.1389,
+      "step": 93
+    },
+    {
+      "epoch": 0.5417867435158501,
+      "grad_norm": 0.9836515188217163,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.2025,
+      "step": 94
+    },
+    {
+      "epoch": 0.547550432276657,
+      "grad_norm": 0.8586398959159851,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.1825,
+      "step": 95
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.9107511043548584,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.1041,
+      "step": 96
+    },
+    {
+      "epoch": 0.5590778097982709,
+      "grad_norm": 1.0116721391677856,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 3.2034,
+      "step": 97
+    },
+    {
+      "epoch": 0.5648414985590778,
+      "grad_norm": 1.0893186330795288,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.1851,
+      "step": 98
+    },
+    {
+      "epoch": 0.5706051873198847,
+      "grad_norm": 1.1509395837783813,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 3.0855,
+      "step": 99
+    },
+    {
+      "epoch": 0.5706051873198847,
+      "eval_loss": 3.242032051086426,
+      "eval_runtime": 0.8412,
+      "eval_samples_per_second": 693.07,
+      "eval_steps_per_second": 22.587,
+      "step": 99
+    },
+    {
+      "epoch": 0.5763688760806917,
+      "grad_norm": 0.9414284229278564,
+      "learning_rate": 0.0,
+      "loss": 3.0767,
+      "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