Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a287676bbd6f56d37f538890e248a985709aec41e5ac8693e31707472bf73c8
+oid sha256:b2c8cff9af06dd712ff13c88c735c83ca54820163845588570d7f89f81183a3d
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34529dce16c4845c072ff791f693d7dd4e45b301779591a7e33a893eb9958053
+oid sha256:7f38061e3b1967adeafca703a072ea01762a4fd7571325005277b3ebb7d7a870
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2a6c1fad65370da9eade91936da117eb2ff339138d90a034c81a393a67e9ee
+oid sha256:eb0d20a833c3eaa429ec7d9b9437586bc1fea9f0bb8193a1a4900b9a0205c8fb
 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": 0.002433563710697946,
+  "epoch": 0.003244751614263928,
   "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": 0.9388,
       "step": 75
+    },
+    {
+      "epoch": 0.0024660112268405855,
+      "grad_norm": 0.6627998948097229,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1794,
+      "step": 76
+    },
+    {
+      "epoch": 0.0024984587429832247,
+      "grad_norm": 0.5571295022964478,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.2429,
+      "step": 77
+    },
+    {
+      "epoch": 0.002530906259125864,
+      "grad_norm": 0.7011799216270447,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0675,
+      "step": 78
+    },
+    {
+      "epoch": 0.002563353775268503,
+      "grad_norm": 0.7084078192710876,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0732,
+      "step": 79
+    },
+    {
+      "epoch": 0.0025958012914111426,
+      "grad_norm": 0.728354275226593,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1039,
+      "step": 80
+    },
+    {
+      "epoch": 0.002628248807553782,
+      "grad_norm": 0.7055922746658325,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0463,
+      "step": 81
+    },
+    {
+      "epoch": 0.002628248807553782,
+      "eval_loss": 1.0919792652130127,
+      "eval_runtime": 410.0116,
+      "eval_samples_per_second": 63.298,
+      "eval_steps_per_second": 7.914,
+      "step": 81
+    },
+    {
+      "epoch": 0.002660696323696421,
+      "grad_norm": 0.6339782476425171,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1567,
+      "step": 82
+    },
+    {
+      "epoch": 0.00269314383983906,
+      "grad_norm": 0.8945773839950562,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.1069,
+      "step": 83
+    },
+    {
+      "epoch": 0.0027255913559816997,
+      "grad_norm": 0.7640128135681152,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0045,
+      "step": 84
+    },
+    {
+      "epoch": 0.002758038872124339,
+      "grad_norm": 0.7280663847923279,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.056,
+      "step": 85
+    },
+    {
+      "epoch": 0.002790486388266978,
+      "grad_norm": 0.5676079988479614,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0548,
+      "step": 86
+    },
+    {
+      "epoch": 0.0028229339044096176,
+      "grad_norm": 0.5649421215057373,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.026,
+      "step": 87
+    },
+    {
+      "epoch": 0.002855381420552257,
+      "grad_norm": 0.534390389919281,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0154,
+      "step": 88
+    },
+    {
+      "epoch": 0.002887828936694896,
+      "grad_norm": 0.6375171542167664,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0314,
+      "step": 89
+    },
+    {
+      "epoch": 0.002920276452837535,
+      "grad_norm": 0.8114333748817444,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2451,
+      "step": 90
+    },
+    {
+      "epoch": 0.002920276452837535,
+      "eval_loss": 1.0911792516708374,
+      "eval_runtime": 410.057,
+      "eval_samples_per_second": 63.291,
+      "eval_steps_per_second": 7.914,
+      "step": 90
+    },
+    {
+      "epoch": 0.0029527239689801747,
+      "grad_norm": 0.7806537747383118,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2908,
+      "step": 91
+    },
+    {
+      "epoch": 0.002985171485122814,
+      "grad_norm": 0.7690258622169495,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0371,
+      "step": 92
+    },
+    {
+      "epoch": 0.003017619001265453,
+      "grad_norm": 0.6484013199806213,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0125,
+      "step": 93
+    },
+    {
+      "epoch": 0.003050066517408092,
+      "grad_norm": 0.7861148715019226,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.1867,
+      "step": 94
+    },
+    {
+      "epoch": 0.003082514033550732,
+      "grad_norm": 0.5767760872840881,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9655,
+      "step": 95
+    },
+    {
+      "epoch": 0.003114961549693371,
+      "grad_norm": 0.6316145658493042,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1651,
+      "step": 96
+    },
+    {
+      "epoch": 0.00314740906583601,
+      "grad_norm": 0.621796190738678,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.0775,
+      "step": 97
+    },
+    {
+      "epoch": 0.0031798565819786497,
+      "grad_norm": 0.6306882500648499,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1397,
+      "step": 98
+    },
+    {
+      "epoch": 0.003212304098121289,
+      "grad_norm": 0.5787349343299866,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0839,
+      "step": 99
+    },
+    {
+      "epoch": 0.003212304098121289,
+      "eval_loss": 1.0910366773605347,
+      "eval_runtime": 409.9187,
+      "eval_samples_per_second": 63.313,
+      "eval_steps_per_second": 7.916,
+      "step": 99
+    },
+    {
+      "epoch": 0.003244751614263928,
+      "grad_norm": 0.7515978813171387,
+      "learning_rate": 0.0,
+      "loss": 1.1321,
+      "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": 7977607983267840.0,
+  "total_flos": 1.0705435229159424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null