Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d0cff8548dc5af4b8cb758aab0529c37901481cf2e17faf1cc41fb1a3fe719
+oid sha256:73c287d1cd15c20c08bd3e715cc99d240da6ddbf663b952f1b105d32a6da7fe4
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1ee2215d0456fa6debc3e9eda3e896e5e7527e920a574eb85cd4655f4ec72f
+oid sha256:862bff549a9bee8077d171c8ec84dc86fc6009d31084960526bd3377714ebd63
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a488ec6d3f5e5a798465f5dc551e4b485f1f571042f5124861158cd9d793a28
+oid sha256:37bc9f091951863adc5f18668a30a9e6aac3f21f8c892b02b33c031686cfb847
 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": 0.0028740587457607636,
+  "epoch": 0.003832078327681018,
   "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": 8.4948,
       "step": 75
+    },
+    {
+      "epoch": 0.0029123795290375734,
+      "grad_norm": 1.3906676769256592,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 8.5319,
+      "step": 76
+    },
+    {
+      "epoch": 0.0029507003123143837,
+      "grad_norm": 1.549890160560608,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 8.3946,
+      "step": 77
+    },
+    {
+      "epoch": 0.002989021095591194,
+      "grad_norm": 1.4431867599487305,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 8.3487,
+      "step": 78
+    },
+    {
+      "epoch": 0.003027341878868004,
+      "grad_norm": 1.5942152738571167,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 8.3657,
+      "step": 79
+    },
+    {
+      "epoch": 0.003065662662144814,
+      "grad_norm": 1.3526906967163086,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 8.5344,
+      "step": 80
+    },
+    {
+      "epoch": 0.0031039834454216243,
+      "grad_norm": 1.568245530128479,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 8.4987,
+      "step": 81
+    },
+    {
+      "epoch": 0.0031039834454216243,
+      "eval_loss": 8.4481782913208,
+      "eval_runtime": 197.166,
+      "eval_samples_per_second": 111.459,
+      "eval_steps_per_second": 13.932,
+      "step": 81
+    },
+    {
+      "epoch": 0.0031423042286984346,
+      "grad_norm": 1.4625965356826782,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.3553,
+      "step": 82
+    },
+    {
+      "epoch": 0.003180625011975245,
+      "grad_norm": 1.6190887689590454,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 8.4586,
+      "step": 83
+    },
+    {
+      "epoch": 0.003218945795252055,
+      "grad_norm": 1.4923970699310303,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 8.3606,
+      "step": 84
+    },
+    {
+      "epoch": 0.003257266578528865,
+      "grad_norm": 1.470651626586914,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 8.3707,
+      "step": 85
+    },
+    {
+      "epoch": 0.0032955873618056753,
+      "grad_norm": 1.3880239725112915,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 8.5658,
+      "step": 86
+    },
+    {
+      "epoch": 0.0033339081450824855,
+      "grad_norm": 1.5443851947784424,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 8.381,
+      "step": 87
+    },
+    {
+      "epoch": 0.003372228928359296,
+      "grad_norm": 1.3600224256515503,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 8.4857,
+      "step": 88
+    },
+    {
+      "epoch": 0.0034105497116361056,
+      "grad_norm": 1.3307414054870605,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 8.3026,
+      "step": 89
+    },
+    {
+      "epoch": 0.003448870494912916,
+      "grad_norm": 1.3035300970077515,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 8.3625,
+      "step": 90
+    },
+    {
+      "epoch": 0.003448870494912916,
+      "eval_loss": 8.436622619628906,
+      "eval_runtime": 197.0498,
+      "eval_samples_per_second": 111.525,
+      "eval_steps_per_second": 13.941,
+      "step": 90
+    },
+    {
+      "epoch": 0.003487191278189726,
+      "grad_norm": 1.4547570943832397,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 8.4409,
+      "step": 91
+    },
+    {
+      "epoch": 0.0035255120614665365,
+      "grad_norm": 1.3213475942611694,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 8.4133,
+      "step": 92
+    },
+    {
+      "epoch": 0.0035638328447433467,
+      "grad_norm": 1.3285075426101685,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 8.4509,
+      "step": 93
+    },
+    {
+      "epoch": 0.0036021536280201566,
+      "grad_norm": 1.4316322803497314,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 8.4731,
+      "step": 94
+    },
+    {
+      "epoch": 0.003640474411296967,
+      "grad_norm": 1.4853651523590088,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 8.4,
+      "step": 95
+    },
+    {
+      "epoch": 0.003678795194573777,
+      "grad_norm": 1.407329797744751,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 8.4689,
+      "step": 96
+    },
+    {
+      "epoch": 0.0037171159778505874,
+      "grad_norm": 1.4351682662963867,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 8.3587,
+      "step": 97
+    },
+    {
+      "epoch": 0.0037554367611273972,
+      "grad_norm": 1.4511561393737793,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 8.4413,
+      "step": 98
+    },
+    {
+      "epoch": 0.0037937575444042075,
+      "grad_norm": 1.4957984685897827,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 8.3962,
+      "step": 99
+    },
+    {
+      "epoch": 0.0037937575444042075,
+      "eval_loss": 8.434378623962402,
+      "eval_runtime": 197.6671,
+      "eval_samples_per_second": 111.177,
+      "eval_steps_per_second": 13.897,
+      "step": 99
+    },
+    {
+      "epoch": 0.003832078327681018,
+      "grad_norm": 1.5082837343215942,
+      "learning_rate": 0.0,
+      "loss": 8.2469,
+      "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": 20362140057600.0,
+  "total_flos": 27149520076800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null