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:ad48eaa977a009bfeaa4a4d759a03a4a6fbd002e4a3d8a91c4ca3ea5db7e61b9
+oid sha256:7f3dcb63fd4ee02739e508a350a9d9ecabb7136c4cc8d34d4190e6eb9f8a133c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0145a333d4f2f729910d1819cba6bd9f73308b39a32214bc30f3cb78e3091965
+oid sha256:cfcbbdf95fd69c8ee8ca6df14d5a003a656e7261cd42f5aff0cb01c2905b6962
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2938b827d7faa6c9d8f750cf3ec2800eb55262cf6e2b002f8dc231a945f215
+oid sha256:59f07e81c41b6cf55c58bb4bd45b2323cfee60f84ecf35b2e00b49ffedb00af3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e065eb1df69232f27b2d6dee4b867fd634a18790e0a17aa825c7410bd9375464
+oid sha256:905303b87ecc46aa6aaf81b00c155fd103e4b31b96d4375ee8edfcc7d47b2bd3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b640f4f5c64f317409bfc71b559a9a115df0faf4a8c53e2bd4a99f3d4e7cab
+oid sha256:86800ed2d2a85fa26550212a2c302c8af5639ae33b223ae3299553a733c14086
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c49bbf34da6895a83a15832e3ad8bf7a6bde93994ac74a6ed64bcd326286c8
+oid sha256:a122133d433c2e22afc9d1482775365de2d3de6ef31c9e7721d9fde2375c8122
 size 15024

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": 1.048951048951049,
+  "epoch": 1.3986013986013985,
   "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": 10.0928,
       "step": 75
+    },
+    {
+      "epoch": 1.062937062937063,
+      "grad_norm": 0.04595685005187988,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.9266,
+      "step": 76
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.049153126776218414,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3148,
+      "step": 77
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.05073670297861099,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.641,
+      "step": 78
+    },
+    {
+      "epoch": 1.104895104895105,
+      "grad_norm": 0.044325049966573715,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.0433,
+      "step": 79
+    },
+    {
+      "epoch": 1.118881118881119,
+      "grad_norm": 0.04824868589639664,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.0382,
+      "step": 80
+    },
+    {
+      "epoch": 1.132867132867133,
+      "grad_norm": 0.050049543380737305,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.8138,
+      "step": 81
+    },
+    {
+      "epoch": 1.132867132867133,
+      "eval_loss": 10.373720169067383,
+      "eval_runtime": 0.2474,
+      "eval_samples_per_second": 970.223,
+      "eval_steps_per_second": 32.341,
+      "step": 81
+    },
+    {
+      "epoch": 1.1468531468531469,
+      "grad_norm": 0.05412643030285835,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.0682,
+      "step": 82
+    },
+    {
+      "epoch": 1.1608391608391608,
+      "grad_norm": 0.04766753688454628,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 9.9111,
+      "step": 83
+    },
+    {
+      "epoch": 1.1748251748251748,
+      "grad_norm": 0.049063920974731445,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.8495,
+      "step": 84
+    },
+    {
+      "epoch": 1.1888111888111887,
+      "grad_norm": 0.05320300906896591,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.4015,
+      "step": 85
+    },
+    {
+      "epoch": 1.2027972027972027,
+      "grad_norm": 0.052162427455186844,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.1188,
+      "step": 86
+    },
+    {
+      "epoch": 1.2167832167832167,
+      "grad_norm": 0.05713256821036339,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 11.3542,
+      "step": 87
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.03999221324920654,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3934,
+      "step": 88
+    },
+    {
+      "epoch": 1.2447552447552448,
+      "grad_norm": 0.04331766068935394,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 8.8227,
+      "step": 89
+    },
+    {
+      "epoch": 1.2587412587412588,
+      "grad_norm": 0.061157867312431335,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.7923,
+      "step": 90
+    },
+    {
+      "epoch": 1.2587412587412588,
+      "eval_loss": 10.373579025268555,
+      "eval_runtime": 0.227,
+      "eval_samples_per_second": 1057.372,
+      "eval_steps_per_second": 35.246,
+      "step": 90
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.04732262343168259,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 9.998,
+      "step": 91
+    },
+    {
+      "epoch": 1.2867132867132867,
+      "grad_norm": 0.04708394780755043,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 9.6389,
+      "step": 92
+    },
+    {
+      "epoch": 1.3006993006993006,
+      "grad_norm": 0.05312468856573105,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 11.1191,
+      "step": 93
+    },
+    {
+      "epoch": 1.3146853146853146,
+      "grad_norm": 0.05056404694914818,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.2935,
+      "step": 94
+    },
+    {
+      "epoch": 1.3286713286713288,
+      "grad_norm": 0.0460284948348999,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.076,
+      "step": 95
+    },
+    {
+      "epoch": 1.3426573426573427,
+      "grad_norm": 0.04575815796852112,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 9.8108,
+      "step": 96
+    },
+    {
+      "epoch": 1.3566433566433567,
+      "grad_norm": 0.05185329541563988,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 11.363,
+      "step": 97
+    },
+    {
+      "epoch": 1.3706293706293706,
+      "grad_norm": 0.04732576757669449,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.0063,
+      "step": 98
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.046071410179138184,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.6642,
+      "step": 99
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "eval_loss": 10.373554229736328,
+      "eval_runtime": 0.2254,
+      "eval_samples_per_second": 1065.008,
+      "eval_steps_per_second": 35.5,
+      "step": 99
+    },
+    {
+      "epoch": 1.3986013986013985,
+      "grad_norm": 0.055754274129867554,
+      "learning_rate": 0.0,
+      "loss": 10.3559,
+      "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": 23457647296512.0,
+  "total_flos": 31381467955200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null