Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3029cc5bc111deb30744988063e62c23726710f8984b2ef55b7eb163e21412
+oid sha256:ce7e78d5c2bf703062bbf46f2120fd5ba6166b0fa77334349d148027020d2dca
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bb829ef9633f237bd9a661771f908827bc6ba89a79498cabb58d2490575848
+oid sha256:6c24af004aa7d60a813730e7955a5ade934491522a3b085bd2b3fced6318f7f5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
+oid sha256:12d5e215f21fbf0d0fadcba9d9404c63f2d389e7deeb200582435d8a294f7182
 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": 0.003551640858076431,
+  "epoch": 0.004735521144101909,
   "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": 1.3733,
       "step": 75
+    },
+    {
+      "epoch": 0.0035989960695174505,
+      "grad_norm": 5.541296482086182,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9249,
+      "step": 76
+    },
+    {
+      "epoch": 0.0036463512809584695,
+      "grad_norm": 5.917468070983887,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.8697,
+      "step": 77
+    },
+    {
+      "epoch": 0.0036937064923994885,
+      "grad_norm": 10.085787773132324,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8634,
+      "step": 78
+    },
+    {
+      "epoch": 0.0037410617038405075,
+      "grad_norm": 5.36349630355835,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.8555,
+      "step": 79
+    },
+    {
+      "epoch": 0.0037884169152815265,
+      "grad_norm": 7.90194845199585,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8127,
+      "step": 80
+    },
+    {
+      "epoch": 0.003835772126722546,
+      "grad_norm": 7.089127540588379,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1554,
+      "step": 81
+    },
+    {
+      "epoch": 0.003835772126722546,
+      "eval_loss": 1.8363431692123413,
+      "eval_runtime": 1963.8665,
+      "eval_samples_per_second": 9.055,
+      "eval_steps_per_second": 1.132,
+      "step": 81
+    },
+    {
+      "epoch": 0.003883127338163565,
+      "grad_norm": 6.435274600982666,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8305,
+      "step": 82
+    },
+    {
+      "epoch": 0.003930482549604584,
+      "grad_norm": 5.313261032104492,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.7793,
+      "step": 83
+    },
+    {
+      "epoch": 0.003977837761045603,
+      "grad_norm": 5.327849388122559,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.8134,
+      "step": 84
+    },
+    {
+      "epoch": 0.004025192972486622,
+      "grad_norm": 8.038222312927246,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.091,
+      "step": 85
+    },
+    {
+      "epoch": 0.004072548183927641,
+      "grad_norm": 6.482438564300537,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0731,
+      "step": 86
+    },
+    {
+      "epoch": 0.00411990339536866,
+      "grad_norm": 8.912972450256348,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1404,
+      "step": 87
+    },
+    {
+      "epoch": 0.00416725860680968,
+      "grad_norm": 6.126862049102783,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9181,
+      "step": 88
+    },
+    {
+      "epoch": 0.004214613818250699,
+      "grad_norm": 7.689204216003418,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.7556,
+      "step": 89
+    },
+    {
+      "epoch": 0.004261969029691718,
+      "grad_norm": 7.858786582946777,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.004261969029691718,
+      "eval_loss": 1.8280308246612549,
+      "eval_runtime": 1965.1163,
+      "eval_samples_per_second": 9.049,
+      "eval_steps_per_second": 1.131,
+      "step": 90
+    },
+    {
+      "epoch": 0.004309324241132737,
+      "grad_norm": 5.3724493980407715,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.8187,
+      "step": 91
+    },
+    {
+      "epoch": 0.004356679452573756,
+      "grad_norm": 10.32592487335205,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8049,
+      "step": 92
+    },
+    {
+      "epoch": 0.004404034664014775,
+      "grad_norm": 6.439472198486328,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6192,
+      "step": 93
+    },
+    {
+      "epoch": 0.004451389875455794,
+      "grad_norm": 9.626279830932617,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.053,
+      "step": 94
+    },
+    {
+      "epoch": 0.004498745086896813,
+      "grad_norm": 5.963990688323975,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.8517,
+      "step": 95
+    },
+    {
+      "epoch": 0.004546100298337832,
+      "grad_norm": 5.205244541168213,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0463,
+      "step": 96
+    },
+    {
+      "epoch": 0.004593455509778851,
+      "grad_norm": 5.28290319442749,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.7786,
+      "step": 97
+    },
+    {
+      "epoch": 0.00464081072121987,
+      "grad_norm": 5.157119274139404,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.855,
+      "step": 98
+    },
+    {
+      "epoch": 0.00468816593266089,
+      "grad_norm": 5.792222499847412,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.8657,
+      "step": 99
+    },
+    {
+      "epoch": 0.00468816593266089,
+      "eval_loss": 1.8215854167938232,
+      "eval_runtime": 1960.5219,
+      "eval_samples_per_second": 9.071,
+      "eval_steps_per_second": 1.134,
+      "step": 99
+    },
+    {
+      "epoch": 0.004735521144101909,
+      "grad_norm": 6.510435581207275,
+      "learning_rate": 0.0,
+      "loss": 1.9326,
+      "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