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:d365c6280c8e4e83271d6da15ba847e305ade635513bd707a1feb8fc143efa39
+oid sha256:595d34e656d698dd6181f306cbf54bbc4b9644ae4479ec2e886dda96304cb534
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7027ded9aa14d01271c4d002e790da95fccd98c71340d635b8a4775d0872c804
+oid sha256:f23dd7c84fc49141af6c78c8e4f8ca06e8f849bf2aa62159d1dbe81a3d04ecde
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7d0343bb4a4510d1b39011ff93bf12d532b23ca006000ab6087a87acc566ab
+oid sha256:9241ae5f100d41489fe612e8d118c9904146ca360764e8f0fb387d527abb6207
 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": 0.010640561821664184,
+  "epoch": 0.014187415762218911,
   "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": 0.8064,
       "step": 75
+    },
+    {
+      "epoch": 0.010782435979286372,
+      "grad_norm": 5.031896591186523,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8174,
+      "step": 76
+    },
+    {
+      "epoch": 0.010924310136908562,
+      "grad_norm": 3.872175455093384,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6007,
+      "step": 77
+    },
+    {
+      "epoch": 0.011066184294530752,
+      "grad_norm": 4.109659671783447,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.5097,
+      "step": 78
+    },
+    {
+      "epoch": 0.01120805845215294,
+      "grad_norm": 6.500185489654541,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.8836,
+      "step": 79
+    },
+    {
+      "epoch": 0.01134993260977513,
+      "grad_norm": 8.053261756896973,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6566,
+      "step": 80
+    },
+    {
+      "epoch": 0.011491806767397318,
+      "grad_norm": 4.231142044067383,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.7664,
+      "step": 81
+    },
+    {
+      "epoch": 0.011491806767397318,
+      "eval_loss": 0.3777725398540497,
+      "eval_runtime": 540.9366,
+      "eval_samples_per_second": 10.974,
+      "eval_steps_per_second": 1.372,
+      "step": 81
+    },
+    {
+      "epoch": 0.011633680925019508,
+      "grad_norm": 5.413785934448242,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7267,
+      "step": 82
+    },
+    {
+      "epoch": 0.011775555082641697,
+      "grad_norm": 5.458988189697266,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.8067,
+      "step": 83
+    },
+    {
+      "epoch": 0.011917429240263885,
+      "grad_norm": 3.969133138656616,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5833,
+      "step": 84
+    },
+    {
+      "epoch": 0.012059303397886075,
+      "grad_norm": 4.596381187438965,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8829,
+      "step": 85
+    },
+    {
+      "epoch": 0.012201177555508265,
+      "grad_norm": 6.600720405578613,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9084,
+      "step": 86
+    },
+    {
+      "epoch": 0.012343051713130453,
+      "grad_norm": 8.138842582702637,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.6855,
+      "step": 87
+    },
+    {
+      "epoch": 0.012484925870752643,
+      "grad_norm": 4.982905387878418,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5768,
+      "step": 88
+    },
+    {
+      "epoch": 0.01262680002837483,
+      "grad_norm": 4.94661283493042,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.7711,
+      "step": 89
+    },
+    {
+      "epoch": 0.01276867418599702,
+      "grad_norm": 5.5673136711120605,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.601,
+      "step": 90
+    },
+    {
+      "epoch": 0.01276867418599702,
+      "eval_loss": 0.36759427189826965,
+      "eval_runtime": 541.9128,
+      "eval_samples_per_second": 10.954,
+      "eval_steps_per_second": 1.369,
+      "step": 90
+    },
+    {
+      "epoch": 0.01291054834361921,
+      "grad_norm": 4.802902698516846,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6431,
+      "step": 91
+    },
+    {
+      "epoch": 0.013052422501241398,
+      "grad_norm": 4.773902416229248,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.7515,
+      "step": 92
+    },
+    {
+      "epoch": 0.013194296658863588,
+      "grad_norm": 3.6889700889587402,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5724,
+      "step": 93
+    },
+    {
+      "epoch": 0.013336170816485778,
+      "grad_norm": 5.018240451812744,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7002,
+      "step": 94
+    },
+    {
+      "epoch": 0.013478044974107966,
+      "grad_norm": 3.2519288063049316,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5406,
+      "step": 95
+    },
+    {
+      "epoch": 0.013619919131730156,
+      "grad_norm": 4.466538906097412,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7291,
+      "step": 96
+    },
+    {
+      "epoch": 0.013761793289352344,
+      "grad_norm": 4.562383651733398,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.4869,
+      "step": 97
+    },
+    {
+      "epoch": 0.013903667446974534,
+      "grad_norm": 3.9905810356140137,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.639,
+      "step": 98
+    },
+    {
+      "epoch": 0.014045541604596723,
+      "grad_norm": 5.33958625793457,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.7274,
+      "step": 99
+    },
+    {
+      "epoch": 0.014045541604596723,
+      "eval_loss": 0.36495569348335266,
+      "eval_runtime": 541.0666,
+      "eval_samples_per_second": 10.971,
+      "eval_steps_per_second": 1.371,
+      "step": 99
+    },
+    {
+      "epoch": 0.014187415762218911,
+      "grad_norm": 6.187318325042725,
+      "learning_rate": 0.0,
+      "loss": 1.056,
+      "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": 4.90093651427328e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null