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:b35f5ca39c2115cb22c66259ccbc08928e240e62184bba51e29fe18d9758ed78
+oid sha256:ad9b760e7fe1226c68370084bdb0a7f5ad20d4fe2a7c1dbafefdffa337f59eda
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff44d13a2b733f952bf5d7186d292e53cf42b64d7b35475c41c85eecdf45042
+oid sha256:8aefd69e1a266946e32d1813dde2dcbe1addaa55e913e15a87335267a0e6a542
 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": 0.009752291788570315,
+  "epoch": 0.013003055718093752,
   "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": 2.0381,
       "step": 75
+    },
+    {
+      "epoch": 0.009882322345751251,
+      "grad_norm": 1.298410415649414,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1707,
+      "step": 76
+    },
+    {
+      "epoch": 0.01001235290293219,
+      "grad_norm": 1.3010650873184204,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.0897,
+      "step": 77
+    },
+    {
+      "epoch": 0.010142383460113126,
+      "grad_norm": 1.2823667526245117,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.0057,
+      "step": 78
+    },
+    {
+      "epoch": 0.010272414017294064,
+      "grad_norm": 1.2673335075378418,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.0045,
+      "step": 79
+    },
+    {
+      "epoch": 0.010402444574475,
+      "grad_norm": 1.324704647064209,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.84,
+      "step": 80
+    },
+    {
+      "epoch": 0.010532475131655939,
+      "grad_norm": 1.1766488552093506,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.7806,
+      "step": 81
+    },
+    {
+      "epoch": 0.010532475131655939,
+      "eval_loss": 1.9837571382522583,
+      "eval_runtime": 799.2258,
+      "eval_samples_per_second": 8.104,
+      "eval_steps_per_second": 1.013,
+      "step": 81
+    },
+    {
+      "epoch": 0.010662505688836877,
+      "grad_norm": 1.2173551321029663,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2352,
+      "step": 82
+    },
+    {
+      "epoch": 0.010792536246017814,
+      "grad_norm": 1.2597392797470093,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.1417,
+      "step": 83
+    },
+    {
+      "epoch": 0.010922566803198752,
+      "grad_norm": 1.2642908096313477,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0654,
+      "step": 84
+    },
+    {
+      "epoch": 0.011052597360379689,
+      "grad_norm": 1.2878029346466064,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8471,
+      "step": 85
+    },
+    {
+      "epoch": 0.011182627917560627,
+      "grad_norm": 1.230512261390686,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.9458,
+      "step": 86
+    },
+    {
+      "epoch": 0.011312658474741564,
+      "grad_norm": 1.211297869682312,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.7435,
+      "step": 87
+    },
+    {
+      "epoch": 0.011442689031922502,
+      "grad_norm": 1.316711187362671,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.0913,
+      "step": 88
+    },
+    {
+      "epoch": 0.01157271958910344,
+      "grad_norm": 1.300204873085022,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.8695,
+      "step": 89
+    },
+    {
+      "epoch": 0.011702750146284377,
+      "grad_norm": 1.2553035020828247,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.9202,
+      "step": 90
+    },
+    {
+      "epoch": 0.011702750146284377,
+      "eval_loss": 1.9816246032714844,
+      "eval_runtime": 798.9606,
+      "eval_samples_per_second": 8.107,
+      "eval_steps_per_second": 1.014,
+      "step": 90
+    },
+    {
+      "epoch": 0.011832780703465315,
+      "grad_norm": 1.2506071329116821,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9214,
+      "step": 91
+    },
+    {
+      "epoch": 0.011962811260646251,
+      "grad_norm": 1.312584400177002,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0434,
+      "step": 92
+    },
+    {
+      "epoch": 0.01209284181782719,
+      "grad_norm": 1.123725414276123,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.7767,
+      "step": 93
+    },
+    {
+      "epoch": 0.012222872375008126,
+      "grad_norm": 1.2313117980957031,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0018,
+      "step": 94
+    },
+    {
+      "epoch": 0.012352902932189064,
+      "grad_norm": 1.2406659126281738,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.864,
+      "step": 95
+    },
+    {
+      "epoch": 0.012482933489370003,
+      "grad_norm": 1.2575771808624268,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.9768,
+      "step": 96
+    },
+    {
+      "epoch": 0.01261296404655094,
+      "grad_norm": 1.2818968296051025,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1945,
+      "step": 97
+    },
+    {
+      "epoch": 0.012742994603731878,
+      "grad_norm": 1.3092225790023804,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.8902,
+      "step": 98
+    },
+    {
+      "epoch": 0.012873025160912814,
+      "grad_norm": 1.2523261308670044,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.0882,
+      "step": 99
+    },
+    {
+      "epoch": 0.012873025160912814,
+      "eval_loss": 1.9812949895858765,
+      "eval_runtime": 799.1597,
+      "eval_samples_per_second": 8.105,
+      "eval_steps_per_second": 1.014,
+      "step": 99
+    },
+    {
+      "epoch": 0.013003055718093752,
+      "grad_norm": 1.25538170337677,
+      "learning_rate": 0.0,
+      "loss": 2.1543,
+      "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