Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476f6bb78df6545178e3404b9f4a5e3500c6a6735edf82841944106a28df055c
+oid sha256:01bad594a40ef7269108cb506a905830433481939ed798053b94d87db4dd41e9
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e3e19b06d9a35e9745399b4c6fb27b12c3050fb2f0510a42e352e721f7845a
+oid sha256:c546f2c7429ed00d99c1c94109c22dc11de4520f807462cca0a7a3251a4310c1
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4326dc699bb7c5e9ead07d7b68eb66779dafd703b48be9f672949042930d6fd
+oid sha256:73fb1272c62b2beb85d7d81466ad83408fabe22e87ebba4c58518d4e33cd196b
 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": 1.4018691588785046,
+  "epoch": 1.8691588785046729,
   "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": 1.4424,
       "step": 75
+    },
+    {
+      "epoch": 1.4205607476635513,
+      "grad_norm": 4.1818928718566895,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3794,
+      "step": 76
+    },
+    {
+      "epoch": 1.439252336448598,
+      "grad_norm": 4.90915584564209,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6645,
+      "step": 77
+    },
+    {
+      "epoch": 1.4579439252336448,
+      "grad_norm": 4.465858459472656,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3885,
+      "step": 78
+    },
+    {
+      "epoch": 1.4766355140186915,
+      "grad_norm": 4.429285526275635,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4656,
+      "step": 79
+    },
+    {
+      "epoch": 1.4953271028037383,
+      "grad_norm": 4.444489002227783,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2159,
+      "step": 80
+    },
+    {
+      "epoch": 1.514018691588785,
+      "grad_norm": 5.05273962020874,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.5199,
+      "step": 81
+    },
+    {
+      "epoch": 1.514018691588785,
+      "eval_loss": 1.739353895187378,
+      "eval_runtime": 6.4079,
+      "eval_samples_per_second": 7.023,
+      "eval_steps_per_second": 0.936,
+      "step": 81
+    },
+    {
+      "epoch": 1.5327102803738317,
+      "grad_norm": 3.916069746017456,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8368,
+      "step": 82
+    },
+    {
+      "epoch": 1.5514018691588785,
+      "grad_norm": 5.19578218460083,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.6748,
+      "step": 83
+    },
+    {
+      "epoch": 1.5700934579439252,
+      "grad_norm": 4.349853515625,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3972,
+      "step": 84
+    },
+    {
+      "epoch": 1.588785046728972,
+      "grad_norm": 5.119319438934326,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5288,
+      "step": 85
+    },
+    {
+      "epoch": 1.6074766355140186,
+      "grad_norm": 4.669541358947754,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.2132,
+      "step": 86
+    },
+    {
+      "epoch": 1.6261682242990654,
+      "grad_norm": 4.935437202453613,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3261,
+      "step": 87
+    },
+    {
+      "epoch": 1.644859813084112,
+      "grad_norm": 4.904860019683838,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4705,
+      "step": 88
+    },
+    {
+      "epoch": 1.6635514018691588,
+      "grad_norm": 4.240081787109375,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.099,
+      "step": 89
+    },
+    {
+      "epoch": 1.6822429906542056,
+      "grad_norm": 4.541848182678223,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2773,
+      "step": 90
+    },
+    {
+      "epoch": 1.6822429906542056,
+      "eval_loss": 1.7255141735076904,
+      "eval_runtime": 6.4124,
+      "eval_samples_per_second": 7.018,
+      "eval_steps_per_second": 0.936,
+      "step": 90
+    },
+    {
+      "epoch": 1.7009345794392523,
+      "grad_norm": 4.372437953948975,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2509,
+      "step": 91
+    },
+    {
+      "epoch": 1.719626168224299,
+      "grad_norm": 4.487855911254883,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.26,
+      "step": 92
+    },
+    {
+      "epoch": 1.7383177570093458,
+      "grad_norm": 5.259077548980713,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.4056,
+      "step": 93
+    },
+    {
+      "epoch": 1.7570093457943925,
+      "grad_norm": 5.354936122894287,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4436,
+      "step": 94
+    },
+    {
+      "epoch": 1.7757009345794392,
+      "grad_norm": 4.266435146331787,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.2637,
+      "step": 95
+    },
+    {
+      "epoch": 1.794392523364486,
+      "grad_norm": 4.696818828582764,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3619,
+      "step": 96
+    },
+    {
+      "epoch": 1.8130841121495327,
+      "grad_norm": 3.7417712211608887,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.007,
+      "step": 97
+    },
+    {
+      "epoch": 1.8317757009345794,
+      "grad_norm": 4.609748363494873,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5455,
+      "step": 98
+    },
+    {
+      "epoch": 1.8504672897196262,
+      "grad_norm": 4.8934783935546875,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3418,
+      "step": 99
+    },
+    {
+      "epoch": 1.8504672897196262,
+      "eval_loss": 1.7031121253967285,
+      "eval_runtime": 6.4027,
+      "eval_samples_per_second": 7.028,
+      "eval_steps_per_second": 0.937,
+      "step": 99
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 5.0138468742370605,
+      "learning_rate": 0.0,
+      "loss": 1.4362,
+      "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": 5.742121532050637e+16,
+  "total_flos": 7.659357435907277e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null