Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6895dd0f008a3b1793ff0dee3fce0864a7cd6b74bd854434e519e1d08c1951a3
+oid sha256:c454dc7692cfb10de91d7a6716edf374209a7dc5e892fe1860a7a9ab8c22d396
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdce86633bebb4fc20f99e2f6e38a6f0a11192acccd31b3719395efe31c3ca3f
+oid sha256:2b42392f50ffadda46d17726619fc0e58b3e84adcf3e9217eca1a32457cc91a5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.0022162465648178247,
+  "epoch": 0.0029549954197570995,
   "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": 1.3518,
       "step": 75
+    },
+    {
+      "epoch": 0.0022457965190153953,
+      "grad_norm": 1.7539479732513428,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4559,
+      "step": 76
+    },
+    {
+      "epoch": 0.0022753464732129663,
+      "grad_norm": 3.0132052898406982,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3995,
+      "step": 77
+    },
+    {
+      "epoch": 0.0023048964274105374,
+      "grad_norm": 1.756522536277771,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3779,
+      "step": 78
+    },
+    {
+      "epoch": 0.0023344463816081084,
+      "grad_norm": 1.5066357851028442,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0589,
+      "step": 79
+    },
+    {
+      "epoch": 0.0023639963358056794,
+      "grad_norm": 2.2123162746429443,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8266,
+      "step": 80
+    },
+    {
+      "epoch": 0.0023935462900032504,
+      "grad_norm": 1.886515736579895,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.243,
+      "step": 81
+    },
+    {
+      "epoch": 0.0023935462900032504,
+      "eval_loss": 0.8142053484916687,
+      "eval_runtime": 5878.778,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 0.606,
+      "step": 81
+    },
+    {
+      "epoch": 0.0024230962442008215,
+      "grad_norm": 2.1723697185516357,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4304,
+      "step": 82
+    },
+    {
+      "epoch": 0.0024526461983983925,
+      "grad_norm": 2.0525877475738525,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.8475,
+      "step": 83
+    },
+    {
+      "epoch": 0.0024821961525959635,
+      "grad_norm": 2.5386929512023926,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6719,
+      "step": 84
+    },
+    {
+      "epoch": 0.0025117461067935345,
+      "grad_norm": 2.252152681350708,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4212,
+      "step": 85
+    },
+    {
+      "epoch": 0.0025412960609911056,
+      "grad_norm": 1.8140268325805664,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5093,
+      "step": 86
+    },
+    {
+      "epoch": 0.0025708460151886766,
+      "grad_norm": 1.8527106046676636,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.2675,
+      "step": 87
+    },
+    {
+      "epoch": 0.0026003959693862476,
+      "grad_norm": 2.5611603260040283,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6779,
+      "step": 88
+    },
+    {
+      "epoch": 0.0026299459235838187,
+      "grad_norm": 1.9794793128967285,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4951,
+      "step": 89
+    },
+    {
+      "epoch": 0.0026594958777813892,
+      "grad_norm": 2.645522356033325,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.1865,
+      "step": 90
+    },
+    {
+      "epoch": 0.0026594958777813892,
+      "eval_loss": 0.8100898861885071,
+      "eval_runtime": 5873.9152,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 0.607,
+      "step": 90
+    },
+    {
+      "epoch": 0.0026890458319789603,
+      "grad_norm": 2.2799620628356934,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.8531,
+      "step": 91
+    },
+    {
+      "epoch": 0.0027185957861765313,
+      "grad_norm": 2.1321165561676025,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8171,
+      "step": 92
+    },
+    {
+      "epoch": 0.0027481457403741023,
+      "grad_norm": 2.29913067817688,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.4964,
+      "step": 93
+    },
+    {
+      "epoch": 0.0027776956945716733,
+      "grad_norm": 1.9983808994293213,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6192,
+      "step": 94
+    },
+    {
+      "epoch": 0.0028072456487692444,
+      "grad_norm": 2.9566855430603027,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.0019,
+      "step": 95
+    },
+    {
+      "epoch": 0.0028367956029668154,
+      "grad_norm": 1.9108870029449463,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1594,
+      "step": 96
+    },
+    {
+      "epoch": 0.0028663455571643864,
+      "grad_norm": 2.6722331047058105,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5236,
+      "step": 97
+    },
+    {
+      "epoch": 0.0028958955113619574,
+      "grad_norm": 2.226942300796509,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.7669,
+      "step": 98
+    },
+    {
+      "epoch": 0.0029254454655595285,
+      "grad_norm": 2.0672061443328857,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.5335,
+      "step": 99
+    },
+    {
+      "epoch": 0.0029254454655595285,
+      "eval_loss": 0.8091546893119812,
+      "eval_runtime": 5873.6433,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 0.607,
+      "step": 99
+    },
+    {
+      "epoch": 0.0029549954197570995,
+      "grad_norm": 2.509993314743042,
+      "learning_rate": 0.0,
+      "loss": 1.5607,
+      "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": 9.5217449435136e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null