Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198d342ef19c8d689e7d5807eef3d0db68d68033424117e91cd08740f64cb48e
+oid sha256:e94000994e49a5b7ea7e66dd28d1a7859c2a40464068833c5c3660070b2f5cd0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56acf5affbb1287f1122bd505d97a6ef8790e1fbf13e5129a98d6ed4d987c9e0
+oid sha256:d0c235426aff5e7816c3778a2a10f2600144918273ca7af95ecdf7e1f3637895
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
+oid sha256:9246553064bea11894d1cdc342a12358c62b3d7caceee2321170ee68aed86db4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0633445945945946,
+  "epoch": 0.08445945945945946,
   "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": 3.931,
       "eval_steps_per_second": 1.969,
       "step": 75
+    },
+    {
+      "epoch": 0.06418918918918919,
+      "grad_norm": 0.20781630277633667,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0065,
+      "step": 76
+    },
+    {
+      "epoch": 0.06503378378378379,
+      "grad_norm": 0.7386759519577026,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 0.0431,
+      "step": 77
+    },
+    {
+      "epoch": 0.06587837837837837,
+      "grad_norm": 3.0190958976745605,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 0.2471,
+      "step": 78
+    },
+    {
+      "epoch": 0.06672297297297297,
+      "grad_norm": 4.477311134338379,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.8406,
+      "step": 79
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 0.9087244272232056,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0187,
+      "step": 80
+    },
+    {
+      "epoch": 0.06841216216216216,
+      "grad_norm": 2.032402276992798,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 0.3885,
+      "step": 81
+    },
+    {
+      "epoch": 0.06925675675675676,
+      "grad_norm": 5.099620819091797,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1469,
+      "step": 82
+    },
+    {
+      "epoch": 0.07010135135135136,
+      "grad_norm": 1.4657068252563477,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 0.0909,
+      "step": 83
+    },
+    {
+      "epoch": 0.07094594594594594,
+      "grad_norm": 0.7036009430885315,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 0.0208,
+      "step": 84
+    },
+    {
+      "epoch": 0.07179054054054054,
+      "grad_norm": 7.542021751403809,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.0755,
+      "step": 85
+    },
+    {
+      "epoch": 0.07263513513513513,
+      "grad_norm": 0.7535510063171387,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 0.0495,
+      "step": 86
+    },
+    {
+      "epoch": 0.07347972972972973,
+      "grad_norm": 2.493562936782837,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 0.2186,
+      "step": 87
+    },
+    {
+      "epoch": 0.07432432432432433,
+      "grad_norm": 3.849121332168579,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.2773,
+      "step": 88
+    },
+    {
+      "epoch": 0.07516891891891891,
+      "grad_norm": 4.295147895812988,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 0.448,
+      "step": 89
+    },
+    {
+      "epoch": 0.07601351351351351,
+      "grad_norm": 3.61863112449646,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.329,
+      "step": 90
+    },
+    {
+      "epoch": 0.07685810810810811,
+      "grad_norm": 5.776922702789307,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4583,
+      "step": 91
+    },
+    {
+      "epoch": 0.0777027027027027,
+      "grad_norm": 2.3311469554901123,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 0.2086,
+      "step": 92
+    },
+    {
+      "epoch": 0.0785472972972973,
+      "grad_norm": 0.32096993923187256,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 0.0184,
+      "step": 93
+    },
+    {
+      "epoch": 0.07939189189189189,
+      "grad_norm": 0.9880800843238831,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0559,
+      "step": 94
+    },
+    {
+      "epoch": 0.08023648648648649,
+      "grad_norm": 5.171363830566406,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.4847,
+      "step": 95
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 3.456587314605713,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 0.2026,
+      "step": 96
+    },
+    {
+      "epoch": 0.08192567567567567,
+      "grad_norm": 3.7345874309539795,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.5642,
+      "step": 97
+    },
+    {
+      "epoch": 0.08277027027027027,
+      "grad_norm": 4.7123541831970215,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 0.4377,
+      "step": 98
+    },
+    {
+      "epoch": 0.08361486486486487,
+      "grad_norm": 2.566887617111206,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 0.2207,
+      "step": 99
+    },
+    {
+      "epoch": 0.08445945945945946,
+      "grad_norm": 1.7636704444885254,
+      "learning_rate": 0.0,
+      "loss": 0.0955,
+      "step": 100
+    },
+    {
+      "epoch": 0.08445945945945946,
+      "eval_loss": 0.14757972955703735,
+      "eval_runtime": 126.9347,
+      "eval_samples_per_second": 3.931,
+      "eval_steps_per_second": 1.97,
+      "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": 9.9164117532672e+16,
+  "total_flos": 1.32218823376896e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null