Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1e0bcc20cae484ab02a0fc1ef70fb2baafadfc6ac85adc17561883aff1f0be
+oid sha256:95ca9c630dfc30e0c9cec93290a2c85012608c5a6f2068ce3e1a075f96ce0506
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94cecc9c8b1d0347ab7146508f4894e902bff6a70e36f07ec08ca7640bee903
+oid sha256:1d4793d431b53f0bc62a40f4feeece05aa27ce44b1f14e5e11e18b07c82fa4e4
 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": 0.423728813559322,
+  "epoch": 0.5649717514124294,
   "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": 1.3581,
       "step": 75
+    },
+    {
+      "epoch": 0.4293785310734463,
+      "grad_norm": 0.41899287700653076,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.301,
+      "step": 76
+    },
+    {
+      "epoch": 0.4350282485875706,
+      "grad_norm": 0.486950159072876,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.379,
+      "step": 77
+    },
+    {
+      "epoch": 0.4406779661016949,
+      "grad_norm": 0.4415300786495209,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4033,
+      "step": 78
+    },
+    {
+      "epoch": 0.4463276836158192,
+      "grad_norm": 0.4912453889846802,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3361,
+      "step": 79
+    },
+    {
+      "epoch": 0.4519774011299435,
+      "grad_norm": 0.4673634171485901,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4221,
+      "step": 80
+    },
+    {
+      "epoch": 0.4576271186440678,
+      "grad_norm": 0.4738830029964447,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.3336,
+      "step": 81
+    },
+    {
+      "epoch": 0.4576271186440678,
+      "eval_loss": 1.3546689748764038,
+      "eval_runtime": 16.5231,
+      "eval_samples_per_second": 9.078,
+      "eval_steps_per_second": 1.15,
+      "step": 81
+    },
+    {
+      "epoch": 0.4632768361581921,
+      "grad_norm": 0.4595194458961487,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3226,
+      "step": 82
+    },
+    {
+      "epoch": 0.4689265536723164,
+      "grad_norm": 0.46952760219573975,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4328,
+      "step": 83
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 0.4681397080421448,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4563,
+      "step": 84
+    },
+    {
+      "epoch": 0.480225988700565,
+      "grad_norm": 0.49031302332878113,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3676,
+      "step": 85
+    },
+    {
+      "epoch": 0.4858757062146893,
+      "grad_norm": 0.5184950232505798,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3509,
+      "step": 86
+    },
+    {
+      "epoch": 0.4915254237288136,
+      "grad_norm": 0.4513101577758789,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3306,
+      "step": 87
+    },
+    {
+      "epoch": 0.4971751412429379,
+      "grad_norm": 0.5032865405082703,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.2823,
+      "step": 88
+    },
+    {
+      "epoch": 0.5028248587570622,
+      "grad_norm": 0.4926997125148773,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4277,
+      "step": 89
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "grad_norm": 0.4777621924877167,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.34,
+      "step": 90
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "eval_loss": 1.3536385297775269,
+      "eval_runtime": 16.5216,
+      "eval_samples_per_second": 9.079,
+      "eval_steps_per_second": 1.15,
+      "step": 90
+    },
+    {
+      "epoch": 0.5141242937853108,
+      "grad_norm": 0.4962153434753418,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3593,
+      "step": 91
+    },
+    {
+      "epoch": 0.519774011299435,
+      "grad_norm": 0.49940770864486694,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3884,
+      "step": 92
+    },
+    {
+      "epoch": 0.5254237288135594,
+      "grad_norm": 0.44710472226142883,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3047,
+      "step": 93
+    },
+    {
+      "epoch": 0.5310734463276836,
+      "grad_norm": 0.49211978912353516,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.3709,
+      "step": 94
+    },
+    {
+      "epoch": 0.536723163841808,
+      "grad_norm": 0.45334574580192566,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4069,
+      "step": 95
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.4448023736476898,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3452,
+      "step": 96
+    },
+    {
+      "epoch": 0.5480225988700564,
+      "grad_norm": 0.507058322429657,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.459,
+      "step": 97
+    },
+    {
+      "epoch": 0.5536723163841808,
+      "grad_norm": 0.43171530961990356,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.2972,
+      "step": 98
+    },
+    {
+      "epoch": 0.559322033898305,
+      "grad_norm": 0.5051499605178833,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4438,
+      "step": 99
+    },
+    {
+      "epoch": 0.559322033898305,
+      "eval_loss": 1.3532921075820923,
+      "eval_runtime": 16.5539,
+      "eval_samples_per_second": 9.061,
+      "eval_steps_per_second": 1.148,
+      "step": 99
+    },
+    {
+      "epoch": 0.5649717514124294,
+      "grad_norm": 0.49200373888015747,
+      "learning_rate": 0.0,
+      "loss": 1.4128,
+      "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