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:b04b254fea6384da247eb0a47cfe514a357f56950c4fad7f6f3c69161a4c6bcf
+oid sha256:47201f4ea2b19636d0882f0fd6ef713488b1742d9919c87d43199e061a7bf49d
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33670bbcb384f1ed413009a3e73309d2d87cd5e3e270dbc97be5eb1721b7fa7f
+oid sha256:9f4ebe7dc4710a743cb875545e67b85bc401253d9e54df64354a4d005509c9dc
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89fe62ba11fd524dc8ac92cbe7ad137582974ce3a195a4798437b8afb671e8bc
+oid sha256:9894624012ff6f9536624b999ba403e82a9d62f05c945e58fdc652978ab6ac9f
 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": 0.010239606799098914,
+  "epoch": 0.01365280906546522,
   "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": 1.1567,
       "step": 75
+    },
+    {
+      "epoch": 0.010376134889753566,
+      "grad_norm": 0.13075454533100128,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0036,
+      "step": 76
+    },
+    {
+      "epoch": 0.010512662980408219,
+      "grad_norm": 0.1945352852344513,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.2375,
+      "step": 77
+    },
+    {
+      "epoch": 0.010649191071062871,
+      "grad_norm": 0.1744111329317093,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0812,
+      "step": 78
+    },
+    {
+      "epoch": 0.010785719161717524,
+      "grad_norm": 0.15505953133106232,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1332,
+      "step": 79
+    },
+    {
+      "epoch": 0.010922247252372175,
+      "grad_norm": 0.1417454183101654,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0222,
+      "step": 80
+    },
+    {
+      "epoch": 0.011058775343026827,
+      "grad_norm": 0.1598300337791443,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0383,
+      "step": 81
+    },
+    {
+      "epoch": 0.011058775343026827,
+      "eval_loss": 1.0898100137710571,
+      "eval_runtime": 243.897,
+      "eval_samples_per_second": 25.289,
+      "eval_steps_per_second": 3.161,
+      "step": 81
+    },
+    {
+      "epoch": 0.01119530343368148,
+      "grad_norm": 0.17551879584789276,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0462,
+      "step": 82
+    },
+    {
+      "epoch": 0.011331831524336132,
+      "grad_norm": 0.13904789090156555,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0482,
+      "step": 83
+    },
+    {
+      "epoch": 0.011468359614990785,
+      "grad_norm": 0.17219290137290955,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.25,
+      "step": 84
+    },
+    {
+      "epoch": 0.011604887705645437,
+      "grad_norm": 0.20321820676326752,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.097,
+      "step": 85
+    },
+    {
+      "epoch": 0.011741415796300088,
+      "grad_norm": 0.1325589269399643,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9449,
+      "step": 86
+    },
+    {
+      "epoch": 0.01187794388695474,
+      "grad_norm": 0.16319213807582855,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.2643,
+      "step": 87
+    },
+    {
+      "epoch": 0.012014471977609393,
+      "grad_norm": 0.15970468521118164,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9925,
+      "step": 88
+    },
+    {
+      "epoch": 0.012151000068264046,
+      "grad_norm": 0.17611786723136902,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.1965,
+      "step": 89
+    },
+    {
+      "epoch": 0.012287528158918698,
+      "grad_norm": 0.15889012813568115,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9813,
+      "step": 90
+    },
+    {
+      "epoch": 0.012287528158918698,
+      "eval_loss": 1.0891379117965698,
+      "eval_runtime": 244.0249,
+      "eval_samples_per_second": 25.276,
+      "eval_steps_per_second": 3.16,
+      "step": 90
+    },
+    {
+      "epoch": 0.012424056249573349,
+      "grad_norm": 0.17122295498847961,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0401,
+      "step": 91
+    },
+    {
+      "epoch": 0.012560584340228002,
+      "grad_norm": 0.14136753976345062,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.858,
+      "step": 92
+    },
+    {
+      "epoch": 0.012697112430882654,
+      "grad_norm": 0.16805991530418396,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0906,
+      "step": 93
+    },
+    {
+      "epoch": 0.012833640521537307,
+      "grad_norm": 0.17546240985393524,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0872,
+      "step": 94
+    },
+    {
+      "epoch": 0.01297016861219196,
+      "grad_norm": 0.16446717083454132,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1252,
+      "step": 95
+    },
+    {
+      "epoch": 0.01310669670284661,
+      "grad_norm": 0.16491715610027313,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2288,
+      "step": 96
+    },
+    {
+      "epoch": 0.013243224793501263,
+      "grad_norm": 0.1417722851037979,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.002,
+      "step": 97
+    },
+    {
+      "epoch": 0.013379752884155915,
+      "grad_norm": 0.14609864354133606,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1695,
+      "step": 98
+    },
+    {
+      "epoch": 0.013516280974810568,
+      "grad_norm": 0.18153584003448486,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0607,
+      "step": 99
+    },
+    {
+      "epoch": 0.013516280974810568,
+      "eval_loss": 1.0889930725097656,
+      "eval_runtime": 243.8388,
+      "eval_samples_per_second": 25.295,
+      "eval_steps_per_second": 3.162,
+      "step": 99
+    },
+    {
+      "epoch": 0.01365280906546522,
+      "grad_norm": 0.15827305614948273,
+      "learning_rate": 0.0,
+      "loss": 1.1212,
+      "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": 9984877088735232.0,
+  "total_flos": 1.338179403644928e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null