Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41115913310f8b89c33f34282f67b4cced696e7432684b96bf1ed8e009f61aca
+oid sha256:10c6a9a7d44b04a2205bddab3e8d178652fe29a5e4b0e6a0e826da584652e897
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e103f82b3a7d88eddeb08b797efdb4baf3b0ba426b79f47f7cf0c0903ab5bcc9
+oid sha256:37e1f0caa593493f00a4eb74da7166de28da8b64253dc3f04f6b47201f5c1b24
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.00453953938807009,
+  "epoch": 0.006052719184093454,
   "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": 11.7317,
       "step": 75
+    },
+    {
+      "epoch": 0.004600066579911025,
+      "grad_norm": 0.20901891589164734,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.7242,
+      "step": 76
+    },
+    {
+      "epoch": 0.004660593771751959,
+      "grad_norm": 0.27064740657806396,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 11.7254,
+      "step": 77
+    },
+    {
+      "epoch": 0.004721120963592894,
+      "grad_norm": 0.19310081005096436,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.7343,
+      "step": 78
+    },
+    {
+      "epoch": 0.0047816481554338285,
+      "grad_norm": 0.20806212723255157,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 11.7366,
+      "step": 79
+    },
+    {
+      "epoch": 0.004842175347274763,
+      "grad_norm": 0.21633297204971313,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.7296,
+      "step": 80
+    },
+    {
+      "epoch": 0.0049027025391156975,
+      "grad_norm": 0.20946356654167175,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 11.7218,
+      "step": 81
+    },
+    {
+      "epoch": 0.0049027025391156975,
+      "eval_loss": 11.726729393005371,
+      "eval_runtime": 336.8313,
+      "eval_samples_per_second": 41.306,
+      "eval_steps_per_second": 5.166,
+      "step": 81
+    },
+    {
+      "epoch": 0.0049632297309566325,
+      "grad_norm": 0.1784806102514267,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7253,
+      "step": 82
+    },
+    {
+      "epoch": 0.0050237569227975665,
+      "grad_norm": 0.2104777693748474,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 11.7201,
+      "step": 83
+    },
+    {
+      "epoch": 0.0050842841146385015,
+      "grad_norm": 0.19271083176136017,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.7222,
+      "step": 84
+    },
+    {
+      "epoch": 0.005144811306479436,
+      "grad_norm": 0.20797564089298248,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7252,
+      "step": 85
+    },
+    {
+      "epoch": 0.0052053384983203705,
+      "grad_norm": 0.22677578032016754,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.7329,
+      "step": 86
+    },
+    {
+      "epoch": 0.005265865690161305,
+      "grad_norm": 0.2145584374666214,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 11.7153,
+      "step": 87
+    },
+    {
+      "epoch": 0.00532639288200224,
+      "grad_norm": 0.17731419205665588,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.7272,
+      "step": 88
+    },
+    {
+      "epoch": 0.005386920073843174,
+      "grad_norm": 0.23729726672172546,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 11.7359,
+      "step": 89
+    },
+    {
+      "epoch": 0.005447447265684109,
+      "grad_norm": 0.22121621668338776,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.7261,
+      "step": 90
+    },
+    {
+      "epoch": 0.005447447265684109,
+      "eval_loss": 11.726103782653809,
+      "eval_runtime": 336.8287,
+      "eval_samples_per_second": 41.306,
+      "eval_steps_per_second": 5.166,
+      "step": 90
+    },
+    {
+      "epoch": 0.005507974457525043,
+      "grad_norm": 0.21789056062698364,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.7314,
+      "step": 91
+    },
+    {
+      "epoch": 0.005568501649365978,
+      "grad_norm": 0.19966021180152893,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.7244,
+      "step": 92
+    },
+    {
+      "epoch": 0.005629028841206913,
+      "grad_norm": 0.20656844973564148,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 11.7306,
+      "step": 93
+    },
+    {
+      "epoch": 0.005689556033047847,
+      "grad_norm": 0.2266276627779007,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.7377,
+      "step": 94
+    },
+    {
+      "epoch": 0.005750083224888782,
+      "grad_norm": 0.17420396208763123,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 11.7294,
+      "step": 95
+    },
+    {
+      "epoch": 0.005810610416729716,
+      "grad_norm": 0.20751972496509552,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.7151,
+      "step": 96
+    },
+    {
+      "epoch": 0.005871137608570651,
+      "grad_norm": 0.21522480249404907,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 11.727,
+      "step": 97
+    },
+    {
+      "epoch": 0.005931664800411585,
+      "grad_norm": 0.23325194418430328,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.7354,
+      "step": 98
+    },
+    {
+      "epoch": 0.00599219199225252,
+      "grad_norm": 0.18077197670936584,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 11.734,
+      "step": 99
+    },
+    {
+      "epoch": 0.00599219199225252,
+      "eval_loss": 11.725984573364258,
+      "eval_runtime": 336.6356,
+      "eval_samples_per_second": 41.33,
+      "eval_steps_per_second": 5.169,
+      "step": 99
+    },
+    {
+      "epoch": 0.006052719184093454,
+      "grad_norm": 0.2148895114660263,
+      "learning_rate": 0.0,
+      "loss": 11.7166,
+      "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": 15277503283200.0,
+  "total_flos": 20370004377600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null