Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ebb1c811c278da61d8417db8a68ff2842ef87beb2f81bcceb2f3142567de8dc
+oid sha256:24fba60a1c81afdfc1c14e8f52d9af85f040ad0c938dea86b64f8c4f36ea0e4f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba02a14c6f771bb617f25e19a99a07de9a6b3bc77bba3b2b5d39f299abd6e05
+oid sha256:3dd466dc393f22f595de9b1e086338f5eedf1a026a9a76786d240897a1a2f812
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e22754a50989957f67d01fa4c0776a1096e12a9d53d6690d9918c79bd28901
+oid sha256:645bab620ff2fe510fcb1367eeea60ef578d406a19db5e232c44f7a6b9ab769e
 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": 0.10615711252653928,
+  "epoch": 0.14154281670205238,
   "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": 0.1629,
       "step": 75
+    },
+    {
+      "epoch": 0.1075725406935598,
+      "grad_norm": 0.7451173663139343,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1308,
+      "step": 76
+    },
+    {
+      "epoch": 0.10898796886058032,
+      "grad_norm": 0.8794470429420471,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1099,
+      "step": 77
+    },
+    {
+      "epoch": 0.11040339702760085,
+      "grad_norm": 1.5756449699401855,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.121,
+      "step": 78
+    },
+    {
+      "epoch": 0.11181882519462137,
+      "grad_norm": 1.5091930627822876,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1289,
+      "step": 79
+    },
+    {
+      "epoch": 0.11323425336164189,
+      "grad_norm": 0.8172638416290283,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0927,
+      "step": 80
+    },
+    {
+      "epoch": 0.11464968152866242,
+      "grad_norm": 0.6090733408927917,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1133,
+      "step": 81
+    },
+    {
+      "epoch": 0.11464968152866242,
+      "eval_loss": 0.10955800116062164,
+      "eval_runtime": 127.1359,
+      "eval_samples_per_second": 4.68,
+      "eval_steps_per_second": 0.59,
+      "step": 81
+    },
+    {
+      "epoch": 0.11606510969568294,
+      "grad_norm": 0.45214489102363586,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.098,
+      "step": 82
+    },
+    {
+      "epoch": 0.11748053786270347,
+      "grad_norm": 0.7153350114822388,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0853,
+      "step": 83
+    },
+    {
+      "epoch": 0.11889596602972399,
+      "grad_norm": 0.5856150984764099,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0897,
+      "step": 84
+    },
+    {
+      "epoch": 0.12031139419674451,
+      "grad_norm": 0.5094517469406128,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1127,
+      "step": 85
+    },
+    {
+      "epoch": 0.12172682236376504,
+      "grad_norm": 2.3627333641052246,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1412,
+      "step": 86
+    },
+    {
+      "epoch": 0.12314225053078556,
+      "grad_norm": 0.7735049724578857,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1132,
+      "step": 87
+    },
+    {
+      "epoch": 0.12455767869780608,
+      "grad_norm": 0.5762856602668762,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1129,
+      "step": 88
+    },
+    {
+      "epoch": 0.1259731068648266,
+      "grad_norm": 1.0163521766662598,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1242,
+      "step": 89
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 0.4653487205505371,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1007,
+      "step": 90
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "eval_loss": 0.10906722396612167,
+      "eval_runtime": 127.0759,
+      "eval_samples_per_second": 4.682,
+      "eval_steps_per_second": 0.59,
+      "step": 90
+    },
+    {
+      "epoch": 0.12880396319886767,
+      "grad_norm": 1.58189857006073,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1539,
+      "step": 91
+    },
+    {
+      "epoch": 0.13021939136588817,
+      "grad_norm": 1.1043466329574585,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1043,
+      "step": 92
+    },
+    {
+      "epoch": 0.1316348195329087,
+      "grad_norm": 1.41648530960083,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1185,
+      "step": 93
+    },
+    {
+      "epoch": 0.13305024769992924,
+      "grad_norm": 0.4491123557090759,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1167,
+      "step": 94
+    },
+    {
+      "epoch": 0.13446567586694974,
+      "grad_norm": 2.0084850788116455,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1225,
+      "step": 95
+    },
+    {
+      "epoch": 0.13588110403397027,
+      "grad_norm": 0.3125413656234741,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1013,
+      "step": 96
+    },
+    {
+      "epoch": 0.1372965322009908,
+      "grad_norm": 0.47210630774497986,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0968,
+      "step": 97
+    },
+    {
+      "epoch": 0.1387119603680113,
+      "grad_norm": 0.8656429052352905,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1112,
+      "step": 98
+    },
+    {
+      "epoch": 0.14012738853503184,
+      "grad_norm": 0.3149074912071228,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0945,
+      "step": 99
+    },
+    {
+      "epoch": 0.14012738853503184,
+      "eval_loss": 0.10777448117733002,
+      "eval_runtime": 127.1053,
+      "eval_samples_per_second": 4.681,
+      "eval_steps_per_second": 0.59,
+      "step": 99
+    },
+    {
+      "epoch": 0.14154281670205238,
+      "grad_norm": 0.4153774678707123,
+      "learning_rate": 0.0,
+      "loss": 0.0999,
+      "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": 1.0534799426558362e+17,
+  "total_flos": 1.4132952751826534e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null