Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff81e41190c817ebf8f37207606e63febf39277578e6f3ca74630e04d8ff8e9
+oid sha256:11dd72790d6a465d025f95c802d569c339bc1bc9b5c0a580bf10da1d23d5bd17
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a527f55f80d06f8e9f075945dff0f3b3afe5b5f2b0907e099fb789989bf1b79
+oid sha256:2d7eb811d5551250e0d439333a90b424681ba3aa2c1bf462035fae9665a87142
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386379ab5b06664652ca18a38c999de2e1d4c6b16a573009f2f310376626549e
+oid sha256:d724c0f66ae2f6d7b2ea9f9518bb75bcb3a68d61389e3e9cfd859d68b7c44b44
 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": 0.005656748500961648,
+  "epoch": 0.00754233133461553,
   "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": 2.4686,
       "step": 75
+    },
+    {
+      "epoch": 0.005732171814307803,
+      "grad_norm": 0.8557270169258118,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.37,
+      "step": 76
+    },
+    {
+      "epoch": 0.005807595127653958,
+      "grad_norm": 3.060455322265625,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.7771,
+      "step": 77
+    },
+    {
+      "epoch": 0.0058830184410001134,
+      "grad_norm": 0.7005658149719238,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.377,
+      "step": 78
+    },
+    {
+      "epoch": 0.005958441754346269,
+      "grad_norm": 1.1821985244750977,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.4553,
+      "step": 79
+    },
+    {
+      "epoch": 0.006033865067692424,
+      "grad_norm": 0.8524439930915833,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.4688,
+      "step": 80
+    },
+    {
+      "epoch": 0.006109288381038579,
+      "grad_norm": 1.0849894285202026,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.5193,
+      "step": 81
+    },
+    {
+      "epoch": 0.006109288381038579,
+      "eval_loss": 2.4592955112457275,
+      "eval_runtime": 1323.4238,
+      "eval_samples_per_second": 8.436,
+      "eval_steps_per_second": 1.055,
+      "step": 81
+    },
+    {
+      "epoch": 0.0061847116943847345,
+      "grad_norm": 0.606669545173645,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3663,
+      "step": 82
+    },
+    {
+      "epoch": 0.00626013500773089,
+      "grad_norm": 0.716972291469574,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.4092,
+      "step": 83
+    },
+    {
+      "epoch": 0.006335558321077045,
+      "grad_norm": 0.848617434501648,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.3845,
+      "step": 84
+    },
+    {
+      "epoch": 0.0064109816344232,
+      "grad_norm": 0.7678719758987427,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4621,
+      "step": 85
+    },
+    {
+      "epoch": 0.0064864049477693555,
+      "grad_norm": 0.7551043033599854,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.5631,
+      "step": 86
+    },
+    {
+      "epoch": 0.006561828261115511,
+      "grad_norm": 0.7578583359718323,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.3585,
+      "step": 87
+    },
+    {
+      "epoch": 0.006637251574461666,
+      "grad_norm": 0.6959741711616516,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.4228,
+      "step": 88
+    },
+    {
+      "epoch": 0.006712674887807821,
+      "grad_norm": 0.9423866271972656,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.523,
+      "step": 89
+    },
+    {
+      "epoch": 0.0067880982011539765,
+      "grad_norm": 0.7611425518989563,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.4523,
+      "step": 90
+    },
+    {
+      "epoch": 0.0067880982011539765,
+      "eval_loss": 2.459738254547119,
+      "eval_runtime": 1323.4409,
+      "eval_samples_per_second": 8.436,
+      "eval_steps_per_second": 1.055,
+      "step": 90
+    },
+    {
+      "epoch": 0.006863521514500132,
+      "grad_norm": 0.8202887177467346,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.299,
+      "step": 91
+    },
+    {
+      "epoch": 0.006938944827846287,
+      "grad_norm": 0.9283888339996338,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3971,
+      "step": 92
+    },
+    {
+      "epoch": 0.007014368141192442,
+      "grad_norm": 1.0150047540664673,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.4436,
+      "step": 93
+    },
+    {
+      "epoch": 0.0070897914545385975,
+      "grad_norm": 0.8555284142494202,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.4183,
+      "step": 94
+    },
+    {
+      "epoch": 0.007165214767884753,
+      "grad_norm": 0.7611926198005676,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.3982,
+      "step": 95
+    },
+    {
+      "epoch": 0.007240638081230908,
+      "grad_norm": 0.9337876439094543,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.4278,
+      "step": 96
+    },
+    {
+      "epoch": 0.007316061394577064,
+      "grad_norm": 0.8473365306854248,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.5949,
+      "step": 97
+    },
+    {
+      "epoch": 0.007391484707923219,
+      "grad_norm": 0.8833069205284119,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.4205,
+      "step": 98
+    },
+    {
+      "epoch": 0.007466908021269375,
+      "grad_norm": 0.707373321056366,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.3859,
+      "step": 99
+    },
+    {
+      "epoch": 0.007466908021269375,
+      "eval_loss": 2.459726572036743,
+      "eval_runtime": 1323.3201,
+      "eval_samples_per_second": 8.437,
+      "eval_steps_per_second": 1.055,
+      "step": 99
+    },
+    {
+      "epoch": 0.00754233133461553,
+      "grad_norm": 0.8906799554824829,
+      "learning_rate": 0.0,
+      "loss": 2.4652,
+      "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": 2.617690146471936e+16,
+  "total_flos": 3.506716988669952e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null