Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a59417f02f343cdf584efa5362ea57afc96725c82b6658dac136d3d062ab76
+oid sha256:475eeb4c8dfab6aa3faae21d917394ba9336a156a25387c331b49a2a704dfe5e
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b608ea363de94a45670583355d7aca66ecb6b7accf523a0e24f02a7748448f9c
+oid sha256:1d01edb98aba82d43c58dc463a30256b8f4dbb671634e17effcc8871cfc5b97c
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13045082dd395ff23ec01ea62abb7ab1984d0af8f8c2441c419760ff666be782
+oid sha256:d6516708bef1a97795da04892fd3df3bf2305ac978924d9e7083e4eed6ef52b1
 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": 0.04120596112904334,
+  "epoch": 0.05494128150539111,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 220.335,
       "eval_steps_per_second": 110.168,
       "step": 75
+    },
+    {
+      "epoch": 0.04175537394409724,
+      "grad_norm": 0.18881097435951233,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.805,
+      "step": 76
+    },
+    {
+      "epoch": 0.042304786759151156,
+      "grad_norm": 0.208832249045372,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.8029,
+      "step": 77
+    },
+    {
+      "epoch": 0.04285419957420507,
+      "grad_norm": 0.19329778850078583,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.802,
+      "step": 78
+    },
+    {
+      "epoch": 0.04340361238925898,
+      "grad_norm": 0.20163513720035553,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.8032,
+      "step": 79
+    },
+    {
+      "epoch": 0.04395302520431289,
+      "grad_norm": 0.19688774645328522,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.8037,
+      "step": 80
+    },
+    {
+      "epoch": 0.044502438019366805,
+      "grad_norm": 0.19582399725914001,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.8032,
+      "step": 81
+    },
+    {
+      "epoch": 0.04505185083442071,
+      "grad_norm": 0.16219070553779602,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.8132,
+      "step": 82
+    },
+    {
+      "epoch": 0.04560126364947462,
+      "grad_norm": 0.21864815056324005,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.8021,
+      "step": 83
+    },
+    {
+      "epoch": 0.046150676464528535,
+      "grad_norm": 0.1872103065252304,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.8065,
+      "step": 84
+    },
+    {
+      "epoch": 0.04670008927958245,
+      "grad_norm": 0.21468770503997803,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.8071,
+      "step": 85
+    },
+    {
+      "epoch": 0.04724950209463636,
+      "grad_norm": 0.2009747177362442,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.8053,
+      "step": 86
+    },
+    {
+      "epoch": 0.047798914909690265,
+      "grad_norm": 0.20177090167999268,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.8031,
+      "step": 87
+    },
+    {
+      "epoch": 0.04834832772474418,
+      "grad_norm": 0.18578961491584778,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.8091,
+      "step": 88
+    },
+    {
+      "epoch": 0.04889774053979809,
+      "grad_norm": 0.20493243634700775,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.7979,
+      "step": 89
+    },
+    {
+      "epoch": 0.049447153354852,
+      "grad_norm": 0.19400815665721893,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.8031,
+      "step": 90
+    },
+    {
+      "epoch": 0.049996566169905915,
+      "grad_norm": 0.20439405739307404,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.8008,
+      "step": 91
+    },
+    {
+      "epoch": 0.05054597898495983,
+      "grad_norm": 0.21862730383872986,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.8059,
+      "step": 92
+    },
+    {
+      "epoch": 0.05109539180001373,
+      "grad_norm": 0.1954014152288437,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.8072,
+      "step": 93
+    },
+    {
+      "epoch": 0.051644804615067645,
+      "grad_norm": 0.19296152889728546,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.8057,
+      "step": 94
+    },
+    {
+      "epoch": 0.05219421743012156,
+      "grad_norm": 0.20052501559257507,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.7977,
+      "step": 95
+    },
+    {
+      "epoch": 0.05274363024517547,
+      "grad_norm": 0.20131036639213562,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.8016,
+      "step": 96
+    },
+    {
+      "epoch": 0.05329304306022938,
+      "grad_norm": 0.20154723525047302,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.802,
+      "step": 97
+    },
+    {
+      "epoch": 0.05384245587528329,
+      "grad_norm": 0.171908438205719,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.8097,
+      "step": 98
+    },
+    {
+      "epoch": 0.0543918686903372,
+      "grad_norm": 0.18649089336395264,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.8051,
+      "step": 99
+    },
+    {
+      "epoch": 0.05494128150539111,
+      "grad_norm": 0.21302233636379242,
+      "learning_rate": 0.0,
+      "loss": 10.8014,
+      "step": 100
+    },
+    {
+      "epoch": 0.05494128150539111,
+      "eval_loss": 10.80360221862793,
+      "eval_runtime": 13.7784,
+      "eval_samples_per_second": 222.522,
+      "eval_steps_per_second": 111.261,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 42839946166272.0,
+  "total_flos": 57297658970112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null