Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e217275fbd9854b58925bbd8f01c037ecb0e0741cf647593eb75f89014b77bc
+oid sha256:67414f5495b0a4382078c58f56402529074f700e2e553647e096e23abda7d66b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d7129bc76f72c2d6b9ad04b1e4035945915c7c5a30702d8bf6d8a4d077b348
+oid sha256:28df018de140879056f85e2582aba09bb215d1d667a5dfcfc785367dfc5554d3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.410958904109589,
+  "epoch": 0.547945205479452,
   "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": 0.0568,
       "step": 75
+    },
+    {
+      "epoch": 0.41643835616438357,
+      "grad_norm": 0.6070038080215454,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1385,
+      "step": 76
+    },
+    {
+      "epoch": 0.42191780821917807,
+      "grad_norm": 0.40678951144218445,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0839,
+      "step": 77
+    },
+    {
+      "epoch": 0.4273972602739726,
+      "grad_norm": 0.5380614995956421,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1204,
+      "step": 78
+    },
+    {
+      "epoch": 0.4328767123287671,
+      "grad_norm": 0.47801193594932556,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0564,
+      "step": 79
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 0.36567771434783936,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0611,
+      "step": 80
+    },
+    {
+      "epoch": 0.4438356164383562,
+      "grad_norm": 0.556081235408783,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1175,
+      "step": 81
+    },
+    {
+      "epoch": 0.4438356164383562,
+      "eval_loss": 0.09113623946905136,
+      "eval_runtime": 16.8383,
+      "eval_samples_per_second": 9.146,
+      "eval_steps_per_second": 1.188,
+      "step": 81
+    },
+    {
+      "epoch": 0.44931506849315067,
+      "grad_norm": 0.43009400367736816,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0402,
+      "step": 82
+    },
+    {
+      "epoch": 0.4547945205479452,
+      "grad_norm": 0.38043421506881714,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0886,
+      "step": 83
+    },
+    {
+      "epoch": 0.4602739726027397,
+      "grad_norm": 0.5178118348121643,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1093,
+      "step": 84
+    },
+    {
+      "epoch": 0.4657534246575342,
+      "grad_norm": 0.33503755927085876,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0272,
+      "step": 85
+    },
+    {
+      "epoch": 0.4712328767123288,
+      "grad_norm": 0.32692286372184753,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0622,
+      "step": 86
+    },
+    {
+      "epoch": 0.4767123287671233,
+      "grad_norm": 0.5232061147689819,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1401,
+      "step": 87
+    },
+    {
+      "epoch": 0.4821917808219178,
+      "grad_norm": 0.658877968788147,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0988,
+      "step": 88
+    },
+    {
+      "epoch": 0.4876712328767123,
+      "grad_norm": 0.332600474357605,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0593,
+      "step": 89
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "grad_norm": 0.5183109641075134,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0841,
+      "step": 90
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "eval_loss": 0.09030048549175262,
+      "eval_runtime": 16.8374,
+      "eval_samples_per_second": 9.146,
+      "eval_steps_per_second": 1.188,
+      "step": 90
+    },
+    {
+      "epoch": 0.4986301369863014,
+      "grad_norm": 0.39023661613464355,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1157,
+      "step": 91
+    },
+    {
+      "epoch": 0.5041095890410959,
+      "grad_norm": 0.33333975076675415,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1145,
+      "step": 92
+    },
+    {
+      "epoch": 0.5095890410958904,
+      "grad_norm": 0.8736575245857239,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1166,
+      "step": 93
+    },
+    {
+      "epoch": 0.5150684931506849,
+      "grad_norm": 0.3711453378200531,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0474,
+      "step": 94
+    },
+    {
+      "epoch": 0.5205479452054794,
+      "grad_norm": 0.5244292616844177,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1088,
+      "step": 95
+    },
+    {
+      "epoch": 0.5260273972602739,
+      "grad_norm": 0.44030696153640747,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0721,
+      "step": 96
+    },
+    {
+      "epoch": 0.5315068493150685,
+      "grad_norm": 0.39572834968566895,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.086,
+      "step": 97
+    },
+    {
+      "epoch": 0.536986301369863,
+      "grad_norm": 0.5474194884300232,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.119,
+      "step": 98
+    },
+    {
+      "epoch": 0.5424657534246575,
+      "grad_norm": 0.5420786142349243,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0743,
+      "step": 99
+    },
+    {
+      "epoch": 0.5424657534246575,
+      "eval_loss": 0.09017093479633331,
+      "eval_runtime": 16.8401,
+      "eval_samples_per_second": 9.145,
+      "eval_steps_per_second": 1.188,
+      "step": 99
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.5939768552780151,
+      "learning_rate": 0.0,
+      "loss": 0.0951,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null