Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261f8727997945eb87e0bb82facc9b388349955b33cdb62b6807af15ec1fdceb
+oid sha256:afedcef01aff06d1a1629af9649652465294544d1766b2b66e5256f4566d41c0
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c1e6436794826f46c90dbc8a3888e0168b34c222f452abc2c1e417b5fed11c
+oid sha256:842bcbe5659887f2e97d02481adc2aece3d74b7321b3d04cb710caf350a1400c
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682fa06fe8ef6e09ffdeef985646187c38172ce94e6a1d0b34ec5f6df8451d9d
+oid sha256:9e1e3cb587636d18b6ef8df94bb236a247027fd147ec9de2e9e9f59d9d4f903a
 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": 0.2577873254564984,
+  "epoch": 0.34371643394199786,
   "eval_steps": 50,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -548,6 +548,189 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 2.2528,
       "step": 75
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.31380581855773926,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2103,
+      "step": 76
+    },
+    {
+      "epoch": 0.2646616541353383,
+      "grad_norm": 0.35320228338241577,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.2328,
+      "step": 77
+    },
+    {
+      "epoch": 0.2680988184747583,
+      "grad_norm": 0.3124861419200897,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.2054,
+      "step": 78
+    },
+    {
+      "epoch": 0.2715359828141783,
+      "grad_norm": 0.4113110899925232,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.0905,
+      "step": 79
+    },
+    {
+      "epoch": 0.2749731471535983,
+      "grad_norm": 0.47795024514198303,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.3201,
+      "step": 80
+    },
+    {
+      "epoch": 0.27841031149301826,
+      "grad_norm": 0.29258468747138977,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.2022,
+      "step": 81
+    },
+    {
+      "epoch": 0.28184747583243824,
+      "grad_norm": 0.28537437319755554,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2611,
+      "step": 82
+    },
+    {
+      "epoch": 0.28528464017185823,
+      "grad_norm": 0.3414091467857361,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.2069,
+      "step": 83
+    },
+    {
+      "epoch": 0.2887218045112782,
+      "grad_norm": 0.39266514778137207,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.2485,
+      "step": 84
+    },
+    {
+      "epoch": 0.2921589688506982,
+      "grad_norm": 0.5153230428695679,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1257,
+      "step": 85
+    },
+    {
+      "epoch": 0.2955961331901181,
+      "grad_norm": 0.31598207354545593,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.1899,
+      "step": 86
+    },
+    {
+      "epoch": 0.2990332975295381,
+      "grad_norm": 0.3173138201236725,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.209,
+      "step": 87
+    },
+    {
+      "epoch": 0.3024704618689581,
+      "grad_norm": 0.28669506311416626,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1869,
+      "step": 88
+    },
+    {
+      "epoch": 0.3059076262083781,
+      "grad_norm": 0.31095296144485474,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.164,
+      "step": 89
+    },
+    {
+      "epoch": 0.30934479054779807,
+      "grad_norm": 0.27381399273872375,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.202,
+      "step": 90
+    },
+    {
+      "epoch": 0.31278195488721805,
+      "grad_norm": 0.4227629601955414,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3388,
+      "step": 91
+    },
+    {
+      "epoch": 0.31621911922663803,
+      "grad_norm": 0.4945060908794403,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1518,
+      "step": 92
+    },
+    {
+      "epoch": 0.319656283566058,
+      "grad_norm": 0.3266584873199463,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.3398,
+      "step": 93
+    },
+    {
+      "epoch": 0.323093447905478,
+      "grad_norm": 0.2841348648071289,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1788,
+      "step": 94
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.2800915539264679,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.121,
+      "step": 95
+    },
+    {
+      "epoch": 0.3299677765843179,
+      "grad_norm": 0.3364481031894684,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2739,
+      "step": 96
+    },
+    {
+      "epoch": 0.3334049409237379,
+      "grad_norm": 0.5338711738586426,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.2574,
+      "step": 97
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.29511675238609314,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1717,
+      "step": 98
+    },
+    {
+      "epoch": 0.34027926960257787,
+      "grad_norm": 0.31296125054359436,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.1663,
+      "step": 99
+    },
+    {
+      "epoch": 0.34371643394199786,
+      "grad_norm": 0.2975694537162781,
+      "learning_rate": 0.0,
+      "loss": 2.1862,
+      "step": 100
+    },
+    {
+      "epoch": 0.34371643394199786,
+      "eval_loss": 2.2586705684661865,
+      "eval_runtime": 16.6976,
+      "eval_samples_per_second": 29.345,
+      "eval_steps_per_second": 29.345,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -562,12 +745,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1619041760575488.0,
+  "total_flos": 2162580270612480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null