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:f6fdf6dd9d1f4d4b9cd88d1b93b4d823d7b339663307f6b0b46b5ada3ee3a91e
+oid sha256:dbd21ef4fbda996ca370ba69e9a5d5505c76c698344e563657f9222b9e3c9705
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b2dc95425d7b4589fcda2c3fb2c2dfe7735f6107df9fdfa3cd94066b198146
+oid sha256:7c0aab241c22440e3da3aebe943d4039e56301243027dff5685e6b14e4dcfa74
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ffb3bbcae13d3c8fcd45cf15a774d6b9dbb4edf8a95da70978b37d6d5b2b51
+oid sha256:58c1c954300678eeaa15622bac3409a2def9ca25fdd8baef820315b41a21d62a
 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": 0.08605851979345955,
+  "epoch": 0.11474469305794607,
   "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": 0.0282,
       "step": 75
+    },
+    {
+      "epoch": 0.08720596672403902,
+      "grad_norm": 0.15878649055957794,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0163,
+      "step": 76
+    },
+    {
+      "epoch": 0.08835341365461848,
+      "grad_norm": 0.1350821554660797,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0142,
+      "step": 77
+    },
+    {
+      "epoch": 0.08950086058519793,
+      "grad_norm": 0.23871316015720367,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0273,
+      "step": 78
+    },
+    {
+      "epoch": 0.09064830751577739,
+      "grad_norm": 0.1733366698026657,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0254,
+      "step": 79
+    },
+    {
+      "epoch": 0.09179575444635686,
+      "grad_norm": 0.2403794825077057,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0262,
+      "step": 80
+    },
+    {
+      "epoch": 0.09294320137693632,
+      "grad_norm": 0.2295757383108139,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0312,
+      "step": 81
+    },
+    {
+      "epoch": 0.09294320137693632,
+      "eval_loss": 0.022903697565197945,
+      "eval_runtime": 41.322,
+      "eval_samples_per_second": 17.763,
+      "eval_steps_per_second": 2.226,
+      "step": 81
+    },
+    {
+      "epoch": 0.09409064830751578,
+      "grad_norm": 0.17668524384498596,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.019,
+      "step": 82
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.21054485440254211,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0203,
+      "step": 83
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 0.11086580157279968,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0166,
+      "step": 84
+    },
+    {
+      "epoch": 0.09753298909925416,
+      "grad_norm": 0.16344071924686432,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0274,
+      "step": 85
+    },
+    {
+      "epoch": 0.09868043602983362,
+      "grad_norm": 0.2489679902791977,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0383,
+      "step": 86
+    },
+    {
+      "epoch": 0.09982788296041308,
+      "grad_norm": 0.18206056952476501,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0257,
+      "step": 87
+    },
+    {
+      "epoch": 0.10097532989099255,
+      "grad_norm": 0.407734215259552,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0322,
+      "step": 88
+    },
+    {
+      "epoch": 0.102122776821572,
+      "grad_norm": 0.30174148082733154,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.022,
+      "step": 89
+    },
+    {
+      "epoch": 0.10327022375215146,
+      "grad_norm": 0.17461110651493073,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0224,
+      "step": 90
+    },
+    {
+      "epoch": 0.10327022375215146,
+      "eval_loss": 0.022746024653315544,
+      "eval_runtime": 42.4871,
+      "eval_samples_per_second": 17.276,
+      "eval_steps_per_second": 2.165,
+      "step": 90
+    },
+    {
+      "epoch": 0.10441767068273092,
+      "grad_norm": 0.18326325714588165,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0138,
+      "step": 91
+    },
+    {
+      "epoch": 0.10556511761331039,
+      "grad_norm": 0.12514610588550568,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.014,
+      "step": 92
+    },
+    {
+      "epoch": 0.10671256454388985,
+      "grad_norm": 0.25040769577026367,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0246,
+      "step": 93
+    },
+    {
+      "epoch": 0.1078600114744693,
+      "grad_norm": 0.19364497065544128,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0211,
+      "step": 94
+    },
+    {
+      "epoch": 0.10900745840504876,
+      "grad_norm": 0.15431857109069824,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0268,
+      "step": 95
+    },
+    {
+      "epoch": 0.11015490533562823,
+      "grad_norm": 0.28512442111968994,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0514,
+      "step": 96
+    },
+    {
+      "epoch": 0.11130235226620769,
+      "grad_norm": 0.15576301515102386,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0255,
+      "step": 97
+    },
+    {
+      "epoch": 0.11244979919678715,
+      "grad_norm": 0.24590234458446503,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0286,
+      "step": 98
+    },
+    {
+      "epoch": 0.11359724612736662,
+      "grad_norm": 0.18634286522865295,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0212,
+      "step": 99
+    },
+    {
+      "epoch": 0.11359724612736662,
+      "eval_loss": 0.022740166634321213,
+      "eval_runtime": 41.5125,
+      "eval_samples_per_second": 17.681,
+      "eval_steps_per_second": 2.216,
+      "step": 99
+    },
+    {
+      "epoch": 0.11474469305794607,
+      "grad_norm": 0.19473059475421906,
+      "learning_rate": 0.0,
+      "loss": 0.025,
+      "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": 1.2628779532812288e+16,
+  "total_flos": 1.6402897554112512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null