Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b59b05d4d7850072eeb9aa0f65bf4580bbd3570da2e6a6175aeece9378a919a
+oid sha256:2cd5eca4e52dae30819f6b48f07bc2ad1ebb201aa59e7a31606a1b1af6354ca9
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fd25555b718eaa9b3876588d8e63bb881be10b399ad79b0eacee6b37c58c4c
+oid sha256:802b0698a0752e8bd9cdc87a9ea6d2550de45edc3064c36d376f3aa417a887b5
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.10608203677510608,
+  "epoch": 0.14144271570014144,
   "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": 10.3216,
       "step": 75
+    },
+    {
+      "epoch": 0.1074964639321075,
+      "grad_norm": 0.4224359095096588,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3781,
+      "step": 76
+    },
+    {
+      "epoch": 0.10891089108910891,
+      "grad_norm": 0.4484782814979553,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.4068,
+      "step": 77
+    },
+    {
+      "epoch": 0.11032531824611033,
+      "grad_norm": 0.5123302936553955,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3564,
+      "step": 78
+    },
+    {
+      "epoch": 0.11173974540311174,
+      "grad_norm": 0.4218631684780121,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3618,
+      "step": 79
+    },
+    {
+      "epoch": 0.11315417256011315,
+      "grad_norm": 0.42611196637153625,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3381,
+      "step": 80
+    },
+    {
+      "epoch": 0.11456859971711457,
+      "grad_norm": 0.529184103012085,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3574,
+      "step": 81
+    },
+    {
+      "epoch": 0.11456859971711457,
+      "eval_loss": 10.370150566101074,
+      "eval_runtime": 2.6606,
+      "eval_samples_per_second": 223.63,
+      "eval_steps_per_second": 28.189,
+      "step": 81
+    },
+    {
+      "epoch": 0.11598302687411598,
+      "grad_norm": 0.4486333429813385,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3334,
+      "step": 82
+    },
+    {
+      "epoch": 0.1173974540311174,
+      "grad_norm": 0.4583194851875305,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3476,
+      "step": 83
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 0.4722030758857727,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3803,
+      "step": 84
+    },
+    {
+      "epoch": 0.12022630834512023,
+      "grad_norm": 0.4358254671096802,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3708,
+      "step": 85
+    },
+    {
+      "epoch": 0.12164073550212164,
+      "grad_norm": 0.48637402057647705,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3381,
+      "step": 86
+    },
+    {
+      "epoch": 0.12305516265912306,
+      "grad_norm": 0.44234755635261536,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3848,
+      "step": 87
+    },
+    {
+      "epoch": 0.12446958981612447,
+      "grad_norm": 0.4407705068588257,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3555,
+      "step": 88
+    },
+    {
+      "epoch": 0.12588401697312587,
+      "grad_norm": 0.4632669985294342,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.372,
+      "step": 89
+    },
+    {
+      "epoch": 0.1272984441301273,
+      "grad_norm": 0.4367517828941345,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3723,
+      "step": 90
+    },
+    {
+      "epoch": 0.1272984441301273,
+      "eval_loss": 10.368699073791504,
+      "eval_runtime": 3.1316,
+      "eval_samples_per_second": 189.997,
+      "eval_steps_per_second": 23.949,
+      "step": 90
+    },
+    {
+      "epoch": 0.12871287128712872,
+      "grad_norm": 0.4396042823791504,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3532,
+      "step": 91
+    },
+    {
+      "epoch": 0.13012729844413012,
+      "grad_norm": 0.4347197115421295,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3587,
+      "step": 92
+    },
+    {
+      "epoch": 0.13154172560113153,
+      "grad_norm": 0.4603777229785919,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3664,
+      "step": 93
+    },
+    {
+      "epoch": 0.13295615275813297,
+      "grad_norm": 0.4331743121147156,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3389,
+      "step": 94
+    },
+    {
+      "epoch": 0.13437057991513437,
+      "grad_norm": 0.4679202437400818,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3191,
+      "step": 95
+    },
+    {
+      "epoch": 0.13578500707213578,
+      "grad_norm": 0.4195132255554199,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3916,
+      "step": 96
+    },
+    {
+      "epoch": 0.1371994342291372,
+      "grad_norm": 0.43738165497779846,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3699,
+      "step": 97
+    },
+    {
+      "epoch": 0.13861386138613863,
+      "grad_norm": 0.4121885299682617,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3656,
+      "step": 98
+    },
+    {
+      "epoch": 0.14002828854314003,
+      "grad_norm": 0.43712252378463745,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3805,
+      "step": 99
+    },
+    {
+      "epoch": 0.14002828854314003,
+      "eval_loss": 10.368454933166504,
+      "eval_runtime": 3.0224,
+      "eval_samples_per_second": 196.862,
+      "eval_steps_per_second": 24.815,
+      "step": 99
+    },
+    {
+      "epoch": 0.14144271570014144,
+      "grad_norm": 0.3934689462184906,
+      "learning_rate": 0.0,
+      "loss": 10.346,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null