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:d14bbfe51bc75cac5e3bceec9905bf9c40ab623c2a5b19c7df510d5b56ee22a8
+oid sha256:6b2c202d6de5c02f4b89fad36575d1afc8e67250747b6381dcff5f253c68c04f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45214e59812db1d270679919152e8157031d9d1bdce713e9cacb349f0897db03
+oid sha256:b79e36cdc90d52a47fd89fc0231e19bb87dbce0c1e7ddd99cbb378a9dd7fb506
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7390d69c035960909a3614dd1bb0738527d72c78eaafed1ea04f6c83d7885b4d
+oid sha256:9842831702632f624f0d8eca81553d1ceb1a47fa6fd1c3fa71fed9b149a9b02d
 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": 0.044896737503741395,
+  "epoch": 0.059862316671655195,
   "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": 10.3491,
       "step": 75
+    },
+    {
+      "epoch": 0.045495360670457945,
+      "grad_norm": 0.10774772614240646,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3513,
+      "step": 76
+    },
+    {
+      "epoch": 0.0460939838371745,
+      "grad_norm": 0.10038568079471588,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.353,
+      "step": 77
+    },
+    {
+      "epoch": 0.04669260700389105,
+      "grad_norm": 0.10181721299886703,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3517,
+      "step": 78
+    },
+    {
+      "epoch": 0.0472912301706076,
+      "grad_norm": 0.10325980931520462,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3504,
+      "step": 79
+    },
+    {
+      "epoch": 0.04788985333732416,
+      "grad_norm": 0.1077234223484993,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3515,
+      "step": 80
+    },
+    {
+      "epoch": 0.04848847650404071,
+      "grad_norm": 0.11477098613977432,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3494,
+      "step": 81
+    },
+    {
+      "epoch": 0.04848847650404071,
+      "eval_loss": 10.349677085876465,
+      "eval_runtime": 19.2103,
+      "eval_samples_per_second": 73.242,
+      "eval_steps_per_second": 9.162,
+      "step": 81
+    },
+    {
+      "epoch": 0.04908709967075726,
+      "grad_norm": 0.10639707744121552,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3508,
+      "step": 82
+    },
+    {
+      "epoch": 0.04968572283747381,
+      "grad_norm": 0.10731644928455353,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3518,
+      "step": 83
+    },
+    {
+      "epoch": 0.050284346004190364,
+      "grad_norm": 0.11128324270248413,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3501,
+      "step": 84
+    },
+    {
+      "epoch": 0.050882969170906914,
+      "grad_norm": 0.1119207963347435,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.349,
+      "step": 85
+    },
+    {
+      "epoch": 0.051481592337623464,
+      "grad_norm": 0.12384051084518433,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3503,
+      "step": 86
+    },
+    {
+      "epoch": 0.05208021550434002,
+      "grad_norm": 0.11188597977161407,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3501,
+      "step": 87
+    },
+    {
+      "epoch": 0.05267883867105657,
+      "grad_norm": 0.10519222915172577,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3496,
+      "step": 88
+    },
+    {
+      "epoch": 0.05327746183777312,
+      "grad_norm": 0.10873488336801529,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3502,
+      "step": 89
+    },
+    {
+      "epoch": 0.05387608500448968,
+      "grad_norm": 0.11624474823474884,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.349,
+      "step": 90
+    },
+    {
+      "epoch": 0.05387608500448968,
+      "eval_loss": 10.34931755065918,
+      "eval_runtime": 19.207,
+      "eval_samples_per_second": 73.255,
+      "eval_steps_per_second": 9.163,
+      "step": 90
+    },
+    {
+      "epoch": 0.054474708171206226,
+      "grad_norm": 0.10113722831010818,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3514,
+      "step": 91
+    },
+    {
+      "epoch": 0.055073331337922776,
+      "grad_norm": 0.10293326526880264,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3512,
+      "step": 92
+    },
+    {
+      "epoch": 0.05567195450463933,
+      "grad_norm": 0.1147138923406601,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3492,
+      "step": 93
+    },
+    {
+      "epoch": 0.05627057767135588,
+      "grad_norm": 0.11943775415420532,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3465,
+      "step": 94
+    },
+    {
+      "epoch": 0.05686920083807243,
+      "grad_norm": 0.09904798120260239,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3508,
+      "step": 95
+    },
+    {
+      "epoch": 0.05746782400478898,
+      "grad_norm": 0.10152188688516617,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3515,
+      "step": 96
+    },
+    {
+      "epoch": 0.05806644717150554,
+      "grad_norm": 0.10223829746246338,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3493,
+      "step": 97
+    },
+    {
+      "epoch": 0.05866507033822209,
+      "grad_norm": 0.112350694835186,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3513,
+      "step": 98
+    },
+    {
+      "epoch": 0.05926369350493864,
+      "grad_norm": 0.10627704858779907,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.348,
+      "step": 99
+    },
+    {
+      "epoch": 0.05926369350493864,
+      "eval_loss": 10.34925365447998,
+      "eval_runtime": 19.147,
+      "eval_samples_per_second": 73.484,
+      "eval_steps_per_second": 9.192,
+      "step": 99
+    },
+    {
+      "epoch": 0.059862316671655195,
+      "grad_norm": 0.10532322525978088,
+      "learning_rate": 0.0,
+      "loss": 10.3493,
+      "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": 7845366988800.0,
+  "total_flos": 10460489318400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null