Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72cd7418a2a2092a935344b43e02fd994f508a4eb87c88d89d166e4652138b13
+oid sha256:cfc1b3a0e15c831f74222fc7562034bbd523d7d20847d4489d1f1b55daceaeea
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960721d5bf95a3bc787e2150ee178ec3995d03682dcf497004b09a8077f42832
+oid sha256:9ad200aeb208c6146f7742cf8cba03bcb0f9109d3fc8912ef40729e5996d7869
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.012614582457320663,
+  "epoch": 0.01681944327642755,
   "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": 1.4885,
       "step": 75
+    },
+    {
+      "epoch": 0.012782776890084939,
+      "grad_norm": 1.483782172203064,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3165,
+      "step": 76
+    },
+    {
+      "epoch": 0.012950971322849213,
+      "grad_norm": 1.4379521608352661,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3113,
+      "step": 77
+    },
+    {
+      "epoch": 0.013119165755613489,
+      "grad_norm": 1.0006632804870605,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5895,
+      "step": 78
+    },
+    {
+      "epoch": 0.013287360188377765,
+      "grad_norm": 1.4230875968933105,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.2327,
+      "step": 79
+    },
+    {
+      "epoch": 0.01345555462114204,
+      "grad_norm": 1.181827187538147,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2924,
+      "step": 80
+    },
+    {
+      "epoch": 0.013623749053906316,
+      "grad_norm": 1.012495517730713,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4839,
+      "step": 81
+    },
+    {
+      "epoch": 0.013623749053906316,
+      "eval_loss": 1.4747848510742188,
+      "eval_runtime": 545.785,
+      "eval_samples_per_second": 9.174,
+      "eval_steps_per_second": 1.147,
+      "step": 81
+    },
+    {
+      "epoch": 0.013791943486670592,
+      "grad_norm": 1.032563328742981,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8136,
+      "step": 82
+    },
+    {
+      "epoch": 0.013960137919434866,
+      "grad_norm": 1.0499074459075928,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.688,
+      "step": 83
+    },
+    {
+      "epoch": 0.014128332352199142,
+      "grad_norm": 1.2386319637298584,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4919,
+      "step": 84
+    },
+    {
+      "epoch": 0.014296526784963418,
+      "grad_norm": 1.0924066305160522,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2622,
+      "step": 85
+    },
+    {
+      "epoch": 0.014464721217727693,
+      "grad_norm": 1.3552666902542114,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3832,
+      "step": 86
+    },
+    {
+      "epoch": 0.014632915650491969,
+      "grad_norm": 1.0566046237945557,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5985,
+      "step": 87
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "grad_norm": 0.946866512298584,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.2197,
+      "step": 88
+    },
+    {
+      "epoch": 0.014969304516020519,
+      "grad_norm": 1.3783427476882935,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.3164,
+      "step": 89
+    },
+    {
+      "epoch": 0.015137498948784795,
+      "grad_norm": 1.2547637224197388,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5152,
+      "step": 90
+    },
+    {
+      "epoch": 0.015137498948784795,
+      "eval_loss": 1.4738831520080566,
+      "eval_runtime": 545.9993,
+      "eval_samples_per_second": 9.17,
+      "eval_steps_per_second": 1.147,
+      "step": 90
+    },
+    {
+      "epoch": 0.01530569338154907,
+      "grad_norm": 0.9993924498558044,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4568,
+      "step": 91
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "grad_norm": 1.0368496179580688,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.867,
+      "step": 92
+    },
+    {
+      "epoch": 0.01564208224707762,
+      "grad_norm": 1.1751809120178223,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.4571,
+      "step": 93
+    },
+    {
+      "epoch": 0.015810276679841896,
+      "grad_norm": 1.076346516609192,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4661,
+      "step": 94
+    },
+    {
+      "epoch": 0.015978471112606172,
+      "grad_norm": 1.3952112197875977,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.633,
+      "step": 95
+    },
+    {
+      "epoch": 0.016146665545370448,
+      "grad_norm": 1.2313469648361206,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3663,
+      "step": 96
+    },
+    {
+      "epoch": 0.016314859978134724,
+      "grad_norm": 1.0370843410491943,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5571,
+      "step": 97
+    },
+    {
+      "epoch": 0.016483054410899,
+      "grad_norm": 1.068371295928955,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.7084,
+      "step": 98
+    },
+    {
+      "epoch": 0.016651248843663275,
+      "grad_norm": 0.8754643201828003,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.604,
+      "step": 99
+    },
+    {
+      "epoch": 0.016651248843663275,
+      "eval_loss": 1.4737608432769775,
+      "eval_runtime": 545.0763,
+      "eval_samples_per_second": 9.186,
+      "eval_steps_per_second": 1.148,
+      "step": 99
+    },
+    {
+      "epoch": 0.01681944327642755,
+      "grad_norm": 1.1264235973358154,
+      "learning_rate": 0.0,
+      "loss": 1.6279,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null