Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494d0efe1465cd1d1e5538529c4709840b8a2b42fff87c20760125d12c72b15c
+oid sha256:8a4dd9349d30e27035a221d3913793bfe4ea4b917fca35f457ddee7229ad726f
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e436bcbfec6f6f2d8a8d5b3e3015e6d07c235acc0b9af1a1397f4c8aa3abb8a
+oid sha256:497b81da389311abdbc60dae33b5ec02c746cabc2763c22463f7945bccc1a678
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8cac434a01c98b0ba70df09b0cafab9e52c9ecf2a28261286c530124931632
+oid sha256:82dbbc4601610461bc0da9a0c0ff13d2db3a20cb0db2ccfb27d98c86f47415a7
 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": 1.0143,
       "step": 75
+    },
+    {
+      "epoch": 0.0066523699067792905,
+      "grad_norm": 8.679134368896484,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6159,
+      "step": 76
+    },
+    {
+      "epoch": 0.0067399010897632285,
+      "grad_norm": 4.6100850105285645,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.0441,
+      "step": 77
+    },
+    {
+      "epoch": 0.0068274322727471665,
+      "grad_norm": 3.9601824283599854,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6739,
+      "step": 78
+    },
+    {
+      "epoch": 0.006914963455731104,
+      "grad_norm": 5.406814098358154,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1113,
+      "step": 79
+    },
+    {
+      "epoch": 0.007002494638715042,
+      "grad_norm": 6.396301746368408,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.9932,
+      "step": 80
+    },
+    {
+      "epoch": 0.00709002582169898,
+      "grad_norm": 8.984944343566895,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.2545,
+      "step": 81
+    },
+    {
+      "epoch": 0.00709002582169898,
+      "eval_loss": 1.1259727478027344,
+      "eval_runtime": 295.1355,
+      "eval_samples_per_second": 32.599,
+      "eval_steps_per_second": 4.076,
+      "step": 81
+    },
+    {
+      "epoch": 0.007177557004682918,
+      "grad_norm": 4.506406784057617,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7675,
+      "step": 82
+    },
+    {
+      "epoch": 0.007265088187666856,
+      "grad_norm": 7.563035011291504,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.7437,
+      "step": 83
+    },
+    {
+      "epoch": 0.007352619370650794,
+      "grad_norm": 7.010645389556885,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3697,
+      "step": 84
+    },
+    {
+      "epoch": 0.007440150553634732,
+      "grad_norm": 4.244420051574707,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9396,
+      "step": 85
+    },
+    {
+      "epoch": 0.00752768173661867,
+      "grad_norm": 6.9684576988220215,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.6496,
+      "step": 86
+    },
+    {
+      "epoch": 0.007615212919602608,
+      "grad_norm": 6.6828718185424805,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.2345,
+      "step": 87
+    },
+    {
+      "epoch": 0.007702744102586546,
+      "grad_norm": 13.264280319213867,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6867,
+      "step": 88
+    },
+    {
+      "epoch": 0.007790275285570484,
+      "grad_norm": 5.590743064880371,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.3572,
+      "step": 89
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "grad_norm": 5.790264129638672,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7421,
+      "step": 90
+    },
+    {
+      "epoch": 0.007877806468554422,
+      "eval_loss": 1.1100659370422363,
+      "eval_runtime": 295.112,
+      "eval_samples_per_second": 32.601,
+      "eval_steps_per_second": 4.076,
+      "step": 90
+    },
+    {
+      "epoch": 0.007965337651538361,
+      "grad_norm": 6.471609115600586,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.1764,
+      "step": 91
+    },
+    {
+      "epoch": 0.008052868834522298,
+      "grad_norm": 5.196161270141602,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0228,
+      "step": 92
+    },
+    {
+      "epoch": 0.008140400017506237,
+      "grad_norm": 5.157146453857422,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.1801,
+      "step": 93
+    },
+    {
+      "epoch": 0.008227931200490174,
+      "grad_norm": 5.235270023345947,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8866,
+      "step": 94
+    },
+    {
+      "epoch": 0.008315462383474113,
+      "grad_norm": 4.621222972869873,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1422,
+      "step": 95
+    },
+    {
+      "epoch": 0.00840299356645805,
+      "grad_norm": 5.371739387512207,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8709,
+      "step": 96
+    },
+    {
+      "epoch": 0.008490524749441989,
+      "grad_norm": 4.3551130294799805,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.1157,
+      "step": 97
+    },
+    {
+      "epoch": 0.008578055932425927,
+      "grad_norm": 7.401463031768799,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0076,
+      "step": 98
+    },
+    {
+      "epoch": 0.008665587115409865,
+      "grad_norm": 5.7351531982421875,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0131,
+      "step": 99
+    },
+    {
+      "epoch": 0.008665587115409865,
+      "eval_loss": 1.1067209243774414,
+      "eval_runtime": 295.2298,
+      "eval_samples_per_second": 32.588,
+      "eval_steps_per_second": 4.075,
+      "step": 99
+    },
+    {
+      "epoch": 0.008753118298393803,
+      "grad_norm": 4.822691917419434,
+      "learning_rate": 0.0,
+      "loss": 0.9012,
+      "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