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:a1e57ae67ac3afc1c4e06d45788e5749aa51d1f9bb659b9bc143433051edf251
+oid sha256:088ca40bc0cfbc95952c19a435cd567e3bb1470347257bc20ee40ba070670c40
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a7d9e3c650d93087f5b6a982f872d9dd92e8cc279d80be35ea92fbe8565232
+oid sha256:f9174b7acb50fd54d489ecb4041c5575e00edcb51783f55b51d25af09611d20a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a79706890c30c5942b9d8a70c3e5d50cc13d686f1c01a812174732b723e41a
+oid sha256:a17368636147bbba1c209d8261960a23a9b988ad407a5408841a23156efe8900
 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": 0.005591590248266607,
+  "epoch": 0.007455453664355476,
   "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": 0.6162,
       "step": 75
+    },
+    {
+      "epoch": 0.005666144784910162,
+      "grad_norm": 3.3704497814178467,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9727,
+      "step": 76
+    },
+    {
+      "epoch": 0.005740699321553717,
+      "grad_norm": 2.8851423263549805,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8882,
+      "step": 77
+    },
+    {
+      "epoch": 0.005815253858197271,
+      "grad_norm": 3.439664602279663,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2121,
+      "step": 78
+    },
+    {
+      "epoch": 0.005889808394840826,
+      "grad_norm": 3.186978816986084,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.789,
+      "step": 79
+    },
+    {
+      "epoch": 0.005964362931484381,
+      "grad_norm": 3.047581911087036,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6949,
+      "step": 80
+    },
+    {
+      "epoch": 0.006038917468127935,
+      "grad_norm": 4.091953277587891,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.3274,
+      "step": 81
+    },
+    {
+      "epoch": 0.006038917468127935,
+      "eval_loss": 0.9921898245811462,
+      "eval_runtime": 1834.9348,
+      "eval_samples_per_second": 6.156,
+      "eval_steps_per_second": 0.77,
+      "step": 81
+    },
+    {
+      "epoch": 0.0061134720047714905,
+      "grad_norm": 2.8362438678741455,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6543,
+      "step": 82
+    },
+    {
+      "epoch": 0.006188026541415045,
+      "grad_norm": 3.722740650177002,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0046,
+      "step": 83
+    },
+    {
+      "epoch": 0.0062625810780586,
+      "grad_norm": 2.977998971939087,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.7849,
+      "step": 84
+    },
+    {
+      "epoch": 0.0063371356147021544,
+      "grad_norm": 3.894702196121216,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0554,
+      "step": 85
+    },
+    {
+      "epoch": 0.00641169015134571,
+      "grad_norm": 3.460470199584961,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.7595,
+      "step": 86
+    },
+    {
+      "epoch": 0.006486244687989264,
+      "grad_norm": 4.5167155265808105,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3252,
+      "step": 87
+    },
+    {
+      "epoch": 0.006560799224632819,
+      "grad_norm": 2.837597131729126,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9637,
+      "step": 88
+    },
+    {
+      "epoch": 0.006635353761276374,
+      "grad_norm": 3.9109745025634766,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.3869,
+      "step": 89
+    },
+    {
+      "epoch": 0.006709908297919929,
+      "grad_norm": 3.083695888519287,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.1615,
+      "step": 90
+    },
+    {
+      "epoch": 0.006709908297919929,
+      "eval_loss": 0.9879239797592163,
+      "eval_runtime": 1835.3859,
+      "eval_samples_per_second": 6.154,
+      "eval_steps_per_second": 0.769,
+      "step": 90
+    },
+    {
+      "epoch": 0.006784462834563483,
+      "grad_norm": 3.445347547531128,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2251,
+      "step": 91
+    },
+    {
+      "epoch": 0.006859017371207038,
+      "grad_norm": 4.91117525100708,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.2883,
+      "step": 92
+    },
+    {
+      "epoch": 0.006933571907850593,
+      "grad_norm": 4.425319671630859,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.7649,
+      "step": 93
+    },
+    {
+      "epoch": 0.007008126444494147,
+      "grad_norm": 3.255776882171631,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8542,
+      "step": 94
+    },
+    {
+      "epoch": 0.007082680981137702,
+      "grad_norm": 6.230947017669678,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.0066,
+      "step": 95
+    },
+    {
+      "epoch": 0.007157235517781257,
+      "grad_norm": 2.7322230339050293,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.669,
+      "step": 96
+    },
+    {
+      "epoch": 0.007231790054424812,
+      "grad_norm": 2.8557915687561035,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.054,
+      "step": 97
+    },
+    {
+      "epoch": 0.007306344591068366,
+      "grad_norm": 3.587625741958618,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.292,
+      "step": 98
+    },
+    {
+      "epoch": 0.0073808991277119216,
+      "grad_norm": 3.0693485736846924,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.1408,
+      "step": 99
+    },
+    {
+      "epoch": 0.0073808991277119216,
+      "eval_loss": 0.9858196377754211,
+      "eval_runtime": 1834.8841,
+      "eval_samples_per_second": 6.156,
+      "eval_steps_per_second": 0.77,
+      "step": 99
+    },
+    {
+      "epoch": 0.007455453664355476,
+      "grad_norm": 2.8233108520507812,
+      "learning_rate": 0.0,
+      "loss": 0.8195,
+      "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": 8.012382662452838e+16,
+  "total_flos": 1.0757365611626496e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null