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:c56f81a19f2d7a89a5c39d51efa7df5b4faee2f8b3f08a9b5f67ccbe2186988d
+oid sha256:e1325624d0e1dbb456d5f62033f9fb91ce04f3e70382231dde2f140bef27b976
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ffc98cff462c6dc8e65046118fe70eee96408089cbc3da62ace8f123f907ec
+oid sha256:e4207d794e8622c76d053b201f92f1648323ec255d02cc966f776331300725ec
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c860416f4a35753c0891786622a3db7fb5c0f226f4b67e9e410abef8cbd1aca
+oid sha256:42766a51e1036e789e4e03b1f03717ae9276a3419af7bf466c98c83b6a063b78
 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": 0.0015798453857982433,
+  "epoch": 0.002106460514397658,
   "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": 10.3725,
       "step": 75
+    },
+    {
+      "epoch": 0.0016009099909422197,
+      "grad_norm": 0.08592105656862259,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.37,
+      "step": 76
+    },
+    {
+      "epoch": 0.0016219745960861964,
+      "grad_norm": 0.08493143320083618,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3702,
+      "step": 77
+    },
+    {
+      "epoch": 0.001643039201230173,
+      "grad_norm": 0.08430784940719604,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3686,
+      "step": 78
+    },
+    {
+      "epoch": 0.0016641038063741494,
+      "grad_norm": 0.07680730521678925,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3688,
+      "step": 79
+    },
+    {
+      "epoch": 0.0016851684115181261,
+      "grad_norm": 0.08067227154970169,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3713,
+      "step": 80
+    },
+    {
+      "epoch": 0.0017062330166621026,
+      "grad_norm": 0.08333154767751694,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3701,
+      "step": 81
+    },
+    {
+      "epoch": 0.0017062330166621026,
+      "eval_loss": 10.370133399963379,
+      "eval_runtime": 326.1701,
+      "eval_samples_per_second": 122.568,
+      "eval_steps_per_second": 15.323,
+      "step": 81
+    },
+    {
+      "epoch": 0.0017272976218060793,
+      "grad_norm": 0.0690532922744751,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3728,
+      "step": 82
+    },
+    {
+      "epoch": 0.0017483622269500558,
+      "grad_norm": 0.0802256315946579,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3694,
+      "step": 83
+    },
+    {
+      "epoch": 0.0017694268320940323,
+      "grad_norm": 0.08990988880395889,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3699,
+      "step": 84
+    },
+    {
+      "epoch": 0.001790491437238009,
+      "grad_norm": 0.0876426100730896,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3691,
+      "step": 85
+    },
+    {
+      "epoch": 0.0018115560423819855,
+      "grad_norm": 0.0830601155757904,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3695,
+      "step": 86
+    },
+    {
+      "epoch": 0.0018326206475259622,
+      "grad_norm": 0.08276013284921646,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3715,
+      "step": 87
+    },
+    {
+      "epoch": 0.0018536852526699387,
+      "grad_norm": 0.08257749676704407,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.368,
+      "step": 88
+    },
+    {
+      "epoch": 0.0018747498578139154,
+      "grad_norm": 0.08675715327262878,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3693,
+      "step": 89
+    },
+    {
+      "epoch": 0.0018958144629578919,
+      "grad_norm": 0.07969921082258224,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3689,
+      "step": 90
+    },
+    {
+      "epoch": 0.0018958144629578919,
+      "eval_loss": 10.369930267333984,
+      "eval_runtime": 326.3104,
+      "eval_samples_per_second": 122.515,
+      "eval_steps_per_second": 15.317,
+      "step": 90
+    },
+    {
+      "epoch": 0.0019168790681018684,
+      "grad_norm": 0.08067625761032104,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3702,
+      "step": 91
+    },
+    {
+      "epoch": 0.001937943673245845,
+      "grad_norm": 0.07955577224493027,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3701,
+      "step": 92
+    },
+    {
+      "epoch": 0.0019590082783898215,
+      "grad_norm": 0.08348768204450607,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3745,
+      "step": 93
+    },
+    {
+      "epoch": 0.001980072883533798,
+      "grad_norm": 0.08660487085580826,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3674,
+      "step": 94
+    },
+    {
+      "epoch": 0.002001137488677775,
+      "grad_norm": 0.0937645360827446,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3699,
+      "step": 95
+    },
+    {
+      "epoch": 0.0020222020938217514,
+      "grad_norm": 0.0810457393527031,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3703,
+      "step": 96
+    },
+    {
+      "epoch": 0.002043266698965728,
+      "grad_norm": 0.09225189685821533,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3692,
+      "step": 97
+    },
+    {
+      "epoch": 0.0020643313041097044,
+      "grad_norm": 0.07411503046751022,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3711,
+      "step": 98
+    },
+    {
+      "epoch": 0.002085395909253681,
+      "grad_norm": 0.07585640251636505,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.369,
+      "step": 99
+    },
+    {
+      "epoch": 0.002085395909253681,
+      "eval_loss": 10.369887351989746,
+      "eval_runtime": 326.4843,
+      "eval_samples_per_second": 122.45,
+      "eval_steps_per_second": 15.309,
+      "step": 99
+    },
+    {
+      "epoch": 0.002106460514397658,
+      "grad_norm": 0.08066422492265701,
+      "learning_rate": 0.0,
+      "loss": 10.3689,
+      "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": 4210346950656.0,
+  "total_flos": 5596361785344.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null