Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96de5cfc8ad4e1367b5003483e843ecf17f5076c23d5edf5cb93c083c22eb584
+oid sha256:ff5bbb031b011135d3352177aaf4cf9aafba35ea792111d5abb211124ca0cc7c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b9d795a998e316d766b93c148f0bbf0b69464d1fee75f9043951f137031227
+oid sha256:13d985b3092432ff8cdc4a72be5e0437afca898f6c1bb6d0e4d0b9f7abbb9203
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.273224043715847,
+  "epoch": 0.36429872495446264,
   "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": 2.3239,
       "step": 75
+    },
+    {
+      "epoch": 0.2768670309653916,
+      "grad_norm": 0.4745643734931946,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.8367,
+      "step": 76
+    },
+    {
+      "epoch": 0.28051001821493626,
+      "grad_norm": 0.4549967348575592,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.7923,
+      "step": 77
+    },
+    {
+      "epoch": 0.28415300546448086,
+      "grad_norm": 0.47961729764938354,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.6126,
+      "step": 78
+    },
+    {
+      "epoch": 0.2877959927140255,
+      "grad_norm": 0.5160456299781799,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.1749,
+      "step": 79
+    },
+    {
+      "epoch": 0.29143897996357016,
+      "grad_norm": 0.5414844155311584,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.1319,
+      "step": 80
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 0.493795245885849,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.4321,
+      "step": 81
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "eval_loss": 1.2079052925109863,
+      "eval_runtime": 36.1692,
+      "eval_samples_per_second": 6.387,
+      "eval_steps_per_second": 0.802,
+      "step": 81
+    },
+    {
+      "epoch": 0.2987249544626594,
+      "grad_norm": 0.4035077691078186,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2268,
+      "step": 82
+    },
+    {
+      "epoch": 0.302367941712204,
+      "grad_norm": 0.5749051570892334,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.4172,
+      "step": 83
+    },
+    {
+      "epoch": 0.30601092896174864,
+      "grad_norm": 0.4956679046154022,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.4672,
+      "step": 84
+    },
+    {
+      "epoch": 0.30965391621129323,
+      "grad_norm": 0.4985373616218567,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3654,
+      "step": 85
+    },
+    {
+      "epoch": 0.3132969034608379,
+      "grad_norm": 0.5308910608291626,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.7148,
+      "step": 86
+    },
+    {
+      "epoch": 0.31693989071038253,
+      "grad_norm": 0.4863481819629669,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.6911,
+      "step": 87
+    },
+    {
+      "epoch": 0.3205828779599271,
+      "grad_norm": 0.5271903276443481,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.4235,
+      "step": 88
+    },
+    {
+      "epoch": 0.3242258652094718,
+      "grad_norm": 0.8417030572891235,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.751,
+      "step": 89
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.5473344922065735,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.7978,
+      "step": 90
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "eval_loss": 1.2071353197097778,
+      "eval_runtime": 36.1551,
+      "eval_samples_per_second": 6.389,
+      "eval_steps_per_second": 0.802,
+      "step": 90
+    },
+    {
+      "epoch": 0.331511839708561,
+      "grad_norm": 0.5116857886314392,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.5153,
+      "step": 91
+    },
+    {
+      "epoch": 0.33515482695810567,
+      "grad_norm": 0.5217396020889282,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.7007,
+      "step": 92
+    },
+    {
+      "epoch": 0.33879781420765026,
+      "grad_norm": 0.5024887323379517,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.5093,
+      "step": 93
+    },
+    {
+      "epoch": 0.3424408014571949,
+      "grad_norm": 0.4722921550273895,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.9873,
+      "step": 94
+    },
+    {
+      "epoch": 0.3460837887067395,
+      "grad_norm": 0.4431920051574707,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.131,
+      "step": 95
+    },
+    {
+      "epoch": 0.34972677595628415,
+      "grad_norm": 0.42745113372802734,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.5188,
+      "step": 96
+    },
+    {
+      "epoch": 0.3533697632058288,
+      "grad_norm": 0.45441219210624695,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.4616,
+      "step": 97
+    },
+    {
+      "epoch": 0.3570127504553734,
+      "grad_norm": 0.5230512022972107,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.4404,
+      "step": 98
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 0.5193710327148438,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.6006,
+      "step": 99
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "eval_loss": 1.2068439722061157,
+      "eval_runtime": 36.1635,
+      "eval_samples_per_second": 6.388,
+      "eval_steps_per_second": 0.802,
+      "step": 99
+    },
+    {
+      "epoch": 0.36429872495446264,
+      "grad_norm": 0.6576356887817383,
+      "learning_rate": 0.0,
+      "loss": 2.6989,
+      "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": 9.5217449435136e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null