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:dfae236f9aef4ffae0d2dc3add1c3ae43f0499627c9e3d90ac69f23423bcd2d9
+oid sha256:1e19ac289a877da13c243aee01328cbd9e479b968acc8d783a9b585767b695d4
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140996d2e64c1880b893653ce7428c0b2205d01ca132b4c09e8302a1767eaff6
+oid sha256:7d85b9082f3729e45fceb081898f73486322a2778df581411a767d063d99215b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59be80405ac792f4b72fa6e647c924d184f288dc7865f0d6cf63e34885fd1f4
+oid sha256:88203699ff63b8d9ffa268b6ba4d842af9d79765b3c7aca8e0b7ff0645587887
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004839334107626791,
+  "epoch": 0.0064524454768357204,
   "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": 3.5721239031346067e-06,
       "loss": 10.3765,
       "step": 75
+    },
+    {
+      "epoch": 0.0049038585623951475,
+      "grad_norm": 0.027317577973008156,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 10.3783,
+      "step": 76
+    },
+    {
+      "epoch": 0.004968383017163505,
+      "grad_norm": 0.025673918426036835,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 10.3762,
+      "step": 77
+    },
+    {
+      "epoch": 0.005032907471931862,
+      "grad_norm": 0.02838023565709591,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 10.3741,
+      "step": 78
+    },
+    {
+      "epoch": 0.0050974319267002195,
+      "grad_norm": 0.033573299646377563,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 10.3773,
+      "step": 79
+    },
+    {
+      "epoch": 0.005161956381468577,
+      "grad_norm": 0.025929216295480728,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 10.3751,
+      "step": 80
+    },
+    {
+      "epoch": 0.005226480836236934,
+      "grad_norm": 0.033958472311496735,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 10.3768,
+      "step": 81
+    },
+    {
+      "epoch": 0.005226480836236934,
+      "eval_loss": 10.377635955810547,
+      "eval_runtime": 93.9485,
+      "eval_samples_per_second": 138.917,
+      "eval_steps_per_second": 17.371,
+      "step": 81
+    },
+    {
+      "epoch": 0.005291005291005291,
+      "grad_norm": 0.02693011797964573,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 10.375,
+      "step": 82
+    },
+    {
+      "epoch": 0.005355529745773648,
+      "grad_norm": 0.03208151459693909,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 10.3803,
+      "step": 83
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 0.028754878789186478,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 10.3747,
+      "step": 84
+    },
+    {
+      "epoch": 0.005484578655310363,
+      "grad_norm": 0.025995273143053055,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 10.3748,
+      "step": 85
+    },
+    {
+      "epoch": 0.00554910311007872,
+      "grad_norm": 0.026898324489593506,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 10.378,
+      "step": 86
+    },
+    {
+      "epoch": 0.0056136275648470775,
+      "grad_norm": 0.02781934104859829,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 10.3788,
+      "step": 87
+    },
+    {
+      "epoch": 0.005678152019615434,
+      "grad_norm": 0.03010799176990986,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 10.3764,
+      "step": 88
+    },
+    {
+      "epoch": 0.005742676474383791,
+      "grad_norm": 0.02704032137989998,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 10.3737,
+      "step": 89
+    },
+    {
+      "epoch": 0.005807200929152149,
+      "grad_norm": 0.02597571723163128,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 10.3775,
+      "step": 90
+    },
+    {
+      "epoch": 0.005807200929152149,
+      "eval_loss": 10.377629280090332,
+      "eval_runtime": 94.4816,
+      "eval_samples_per_second": 138.133,
+      "eval_steps_per_second": 17.273,
+      "step": 90
+    },
+    {
+      "epoch": 0.005871725383920506,
+      "grad_norm": 0.03344319388270378,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 10.3786,
+      "step": 91
+    },
+    {
+      "epoch": 0.005936249838688863,
+      "grad_norm": 0.025218836963176727,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 10.3796,
+      "step": 92
+    },
+    {
+      "epoch": 0.006000774293457221,
+      "grad_norm": 0.03514518216252327,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 10.3775,
+      "step": 93
+    },
+    {
+      "epoch": 0.006065298748225577,
+      "grad_norm": 0.03037307597696781,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 10.3771,
+      "step": 94
+    },
+    {
+      "epoch": 0.0061298232029939346,
+      "grad_norm": 0.025971580296754837,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 10.3797,
+      "step": 95
+    },
+    {
+      "epoch": 0.006194347657762292,
+      "grad_norm": 0.027631748467683792,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 10.3774,
+      "step": 96
+    },
+    {
+      "epoch": 0.006258872112530649,
+      "grad_norm": 0.02829601615667343,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 10.3786,
+      "step": 97
+    },
+    {
+      "epoch": 0.006323396567299007,
+      "grad_norm": 0.032121721655130386,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 10.3746,
+      "step": 98
+    },
+    {
+      "epoch": 0.006387921022067364,
+      "grad_norm": 0.033310312777757645,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 10.3775,
+      "step": 99
+    },
+    {
+      "epoch": 0.006387921022067364,
+      "eval_loss": 10.377626419067383,
+      "eval_runtime": 94.5259,
+      "eval_samples_per_second": 138.068,
+      "eval_steps_per_second": 17.265,
+      "step": 99
+    },
+    {
+      "epoch": 0.0064524454768357204,
+      "grad_norm": 0.03267132118344307,
+      "learning_rate": 0.0,
+      "loss": 10.3777,
+      "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": 4053439610880.0,
+  "total_flos": 5387151998976.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null