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:ec61d51887fa1635105dd93bf3d67fd95aef710d1c947df51240e07aad05e56c
+oid sha256:145dce7cab399510176d8c2d62bb806ae85e206dfada453397ed63c814d0d9e7
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd8472d97fb49f4b4c4d762f66393259d03ef10cebedc47d416d8ceef776322
+oid sha256:0864d0b37b0cadceceadfbe74b83e9243cea3bded28525f3d94cf1a0ef765482
 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": 0.007632034191513178,
+  "epoch": 0.010176045588684237,
   "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": 1.4009,
       "step": 75
+    },
+    {
+      "epoch": 0.00773379464740002,
+      "grad_norm": 1.2919002771377563,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4346,
+      "step": 76
+    },
+    {
+      "epoch": 0.007835555103286863,
+      "grad_norm": 1.4373382329940796,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4364,
+      "step": 77
+    },
+    {
+      "epoch": 0.007937315559173706,
+      "grad_norm": 1.385779619216919,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.6165,
+      "step": 78
+    },
+    {
+      "epoch": 0.008039076015060547,
+      "grad_norm": 1.3356062173843384,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.6996,
+      "step": 79
+    },
+    {
+      "epoch": 0.008140836470947389,
+      "grad_norm": 1.318934440612793,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.6859,
+      "step": 80
+    },
+    {
+      "epoch": 0.008242596926834232,
+      "grad_norm": 1.155403733253479,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.7573,
+      "step": 81
+    },
+    {
+      "epoch": 0.008242596926834232,
+      "eval_loss": 0.7968220710754395,
+      "eval_runtime": 1284.6177,
+      "eval_samples_per_second": 6.442,
+      "eval_steps_per_second": 0.806,
+      "step": 81
+    },
+    {
+      "epoch": 0.008344357382721074,
+      "grad_norm": 1.1096798181533813,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.661,
+      "step": 82
+    },
+    {
+      "epoch": 0.008446117838607917,
+      "grad_norm": 1.2522647380828857,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.5441,
+      "step": 83
+    },
+    {
+      "epoch": 0.008547878294494759,
+      "grad_norm": 1.340035080909729,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7935,
+      "step": 84
+    },
+    {
+      "epoch": 0.008649638750381602,
+      "grad_norm": 1.2466191053390503,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4701,
+      "step": 85
+    },
+    {
+      "epoch": 0.008751399206268443,
+      "grad_norm": 1.26437246799469,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5294,
+      "step": 86
+    },
+    {
+      "epoch": 0.008853159662155287,
+      "grad_norm": 1.3288912773132324,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.6922,
+      "step": 87
+    },
+    {
+      "epoch": 0.008954920118042128,
+      "grad_norm": 1.0862417221069336,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6976,
+      "step": 88
+    },
+    {
+      "epoch": 0.009056680573928971,
+      "grad_norm": 1.2148205041885376,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.5862,
+      "step": 89
+    },
+    {
+      "epoch": 0.009158441029815813,
+      "grad_norm": 1.1240460872650146,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5123,
+      "step": 90
+    },
+    {
+      "epoch": 0.009158441029815813,
+      "eval_loss": 0.7945318818092346,
+      "eval_runtime": 1284.9418,
+      "eval_samples_per_second": 6.441,
+      "eval_steps_per_second": 0.805,
+      "step": 90
+    },
+    {
+      "epoch": 0.009260201485702656,
+      "grad_norm": 1.0402065515518188,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.635,
+      "step": 91
+    },
+    {
+      "epoch": 0.009361961941589498,
+      "grad_norm": 1.3618654012680054,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.6066,
+      "step": 92
+    },
+    {
+      "epoch": 0.00946372239747634,
+      "grad_norm": 1.2600781917572021,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6762,
+      "step": 93
+    },
+    {
+      "epoch": 0.009565482853363182,
+      "grad_norm": 1.1988401412963867,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5618,
+      "step": 94
+    },
+    {
+      "epoch": 0.009667243309250026,
+      "grad_norm": 1.271689534187317,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5301,
+      "step": 95
+    },
+    {
+      "epoch": 0.009769003765136867,
+      "grad_norm": 1.163633942604065,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.6356,
+      "step": 96
+    },
+    {
+      "epoch": 0.00987076422102371,
+      "grad_norm": 1.243078351020813,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5035,
+      "step": 97
+    },
+    {
+      "epoch": 0.009972524676910552,
+      "grad_norm": 1.2242130041122437,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6991,
+      "step": 98
+    },
+    {
+      "epoch": 0.010074285132797395,
+      "grad_norm": 1.125364899635315,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.5159,
+      "step": 99
+    },
+    {
+      "epoch": 0.010074285132797395,
+      "eval_loss": 0.794076681137085,
+      "eval_runtime": 1285.0085,
+      "eval_samples_per_second": 6.44,
+      "eval_steps_per_second": 0.805,
+      "step": 99
+    },
+    {
+      "epoch": 0.010176045588684237,
+      "grad_norm": 1.3278838396072388,
+      "learning_rate": 0.0,
+      "loss": 1.7742,
+      "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": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null