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:cc0f5ef4d2b52f2e0c91eaa5a2cee6e0f9a238048bc8ab9dbd1abc1494d7ea4f
+oid sha256:16ae53ea8bef04d350b327e2ee9da1305b4ef18108ecd768301c6f50a70baa42
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40a33386f93e86016fd1185c614311651304cb7f3f40afa90bda33b8a598d2b
+oid sha256:ae3825f8cfae8e0566bfdccab9c986662835fe4811f11cc76709ec4e7c0bbf46
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f32210760d9bd87e910a71eaa4962928b2302f7db910a55673bfa9668edf32
+oid sha256:58d5f103336098fd2c8f7780ffcefd69ebb30e58f14fa8ad185cdcbffe8b564a
 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": 0.006564838723795352,
+  "epoch": 0.008753118298393803,
   "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": 0.9686,
       "step": 75
+    },
+    {
+      "epoch": 0.0066523699067792905,
+      "grad_norm": 9.327075958251953,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5583,
+      "step": 76
+    },
+    {
+      "epoch": 0.0067399010897632285,
+      "grad_norm": 4.473588943481445,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.0545,
+      "step": 77
+    },
+    {
+      "epoch": 0.0068274322727471665,
+      "grad_norm": 3.9445409774780273,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6244,
+      "step": 78
+    },
+    {
+      "epoch": 0.006914963455731104,
+      "grad_norm": 5.083326816558838,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0767,
+      "step": 79
+    },
+    {
+      "epoch": 0.007002494638715042,
+      "grad_norm": 6.513574600219727,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.9368,
+      "step": 80
+    },
+    {
+      "epoch": 0.00709002582169898,
+      "grad_norm": 7.046454429626465,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.1531,
+      "step": 81
+    },
+    {
+      "epoch": 0.00709002582169898,
+      "eval_loss": 1.0759859085083008,
+      "eval_runtime": 593.8303,
+      "eval_samples_per_second": 16.202,
+      "eval_steps_per_second": 2.026,
+      "step": 81
+    },
+    {
+      "epoch": 0.007177557004682918,
+      "grad_norm": 4.693303108215332,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7735,
+      "step": 82
+    },
+    {
+      "epoch": 0.007265088187666856,
+      "grad_norm": 8.385747909545898,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.7089,
+      "step": 83
+    },
+    {
+      "epoch": 0.007352619370650794,
+      "grad_norm": 6.136774063110352,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3297,
+      "step": 84
+    },
+    {
+      "epoch": 0.007440150553634732,
+      "grad_norm": 3.841578245162964,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9133,
+      "step": 85
+    },
+    {
+      "epoch": 0.00752768173661867,
+      "grad_norm": 7.677609920501709,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5916,
+      "step": 86
+    },
+    {
+      "epoch": 0.007615212919602608,
+      "grad_norm": 5.711431980133057,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.1635,
+      "step": 87
+    },
+    {
+      "epoch": 0.007702744102586546,
+      "grad_norm": 7.733930587768555,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7545,
+      "step": 88
+    },
+    {
+      "epoch": 0.007790275285570484,
+      "grad_norm": 5.98483419418335,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.341,
+      "step": 89
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "grad_norm": 6.578056335449219,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6057,
+      "step": 90
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "eval_loss": 1.0588805675506592,
+      "eval_runtime": 593.2579,
+      "eval_samples_per_second": 16.217,
+      "eval_steps_per_second": 2.028,
+      "step": 90
+    },
+    {
+      "epoch": 0.007965337651538361,
+      "grad_norm": 7.1567254066467285,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.1115,
+      "step": 91
+    },
+    {
+      "epoch": 0.008052868834522298,
+      "grad_norm": 5.749832630157471,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9597,
+      "step": 92
+    },
+    {
+      "epoch": 0.008140400017506237,
+      "grad_norm": 5.210885524749756,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.1092,
+      "step": 93
+    },
+    {
+      "epoch": 0.008227931200490174,
+      "grad_norm": 5.195158958435059,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8463,
+      "step": 94
+    },
+    {
+      "epoch": 0.008315462383474113,
+      "grad_norm": 4.231655597686768,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1316,
+      "step": 95
+    },
+    {
+      "epoch": 0.00840299356645805,
+      "grad_norm": 4.998682975769043,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7935,
+      "step": 96
+    },
+    {
+      "epoch": 0.008490524749441989,
+      "grad_norm": 4.3534393310546875,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.1026,
+      "step": 97
+    },
+    {
+      "epoch": 0.008578055932425927,
+      "grad_norm": 7.271274566650391,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.9494,
+      "step": 98
+    },
+    {
+      "epoch": 0.008665587115409865,
+      "grad_norm": 5.391103744506836,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.99,
+      "step": 99
+    },
+    {
+      "epoch": 0.008665587115409865,
+      "eval_loss": 1.0554673671722412,
+      "eval_runtime": 593.3095,
+      "eval_samples_per_second": 16.216,
+      "eval_steps_per_second": 2.028,
+      "step": 99
+    },
+    {
+      "epoch": 0.008753118298393803,
+      "grad_norm": 5.200128078460693,
+      "learning_rate": 0.0,
+      "loss": 0.8922,
+      "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": 1.5389063141916672e+16,
+  "total_flos": 2.0484438563487744e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null