shaurya-06/adapter

README.md

@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10
+- num_epochs: 15
 
 ### Training results
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b89ebdcdd1526c540859ee6d1c964e45224b8e532ab7c36722c70ab6c9dcd18c
+oid sha256:40e249aa5cad4bb1b7d9575ed7d47d455a84d71b94d53384e03bc1c6e5effa39
 size 15734784

runs/Apr28_21-24-34_757a20c23d9b/events.out.tfevents.1714339477.757a20c23d9b.200681.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f663efec6bd8ba8c52344b4f9163479e5c7b28256c75f9a4ee9e39094c1b696b
+size 7566

runs/Apr28_21-25-46_757a20c23d9b/events.out.tfevents.1714339550.757a20c23d9b.200681.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7609afb8c70a30e2dc5211ecc898d0051b5aa52ecf354601ec6c1a02e28c4a6e
+size 8416

trainer_state.json

@@ -1,197 +1,113 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.6,
+  "epoch": 14.4,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.4,
-      "grad_norm": 0.46419957280158997,
-      "learning_rate": 0.0001999633286223284,
-      "loss": 0.5697,
-      "step": 5
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 0.47279733419418335,
-      "learning_rate": 0.00019868265225415265,
-      "loss": 0.581,
-      "step": 10
-    },
     {
       "epoch": 1.2,
-      "grad_norm": 0.34838807582855225,
-      "learning_rate": 0.00019559521426716118,
-      "loss": 0.5531,
+      "grad_norm": 0.8679821491241455,
+      "learning_rate": 0.00019868265225415265,
+      "loss": 4.9095,
       "step": 15
     },
-    {
-      "epoch": 1.6,
-      "grad_norm": 0.4025287628173828,
-      "learning_rate": 0.00019075754196709572,
-      "loss": 0.528,
-      "step": 20
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.5065444707870483,
-      "learning_rate": 0.0001842582073616649,
-      "loss": 0.5522,
-      "step": 25
-    },
     {
       "epoch": 2.4,
-      "grad_norm": 0.47670507431030273,
-      "learning_rate": 0.00017621620551276366,
-      "loss": 0.5206,
+      "grad_norm": 1.064207911491394,
+      "learning_rate": 0.00019075754196709572,
+      "loss": 3.2019,
       "step": 30
     },
-    {
-      "epoch": 2.8,
-      "grad_norm": 0.39348119497299194,
-      "learning_rate": 0.00016677877587886956,
-      "loss": 0.5305,
-      "step": 35
-    },
-    {
-      "epoch": 3.2,
-      "grad_norm": 0.5051579475402832,
-      "learning_rate": 0.00015611870653623825,
-      "loss": 0.5061,
-      "step": 40
-    },
     {
       "epoch": 3.6,
-      "grad_norm": 0.43032407760620117,
-      "learning_rate": 0.00014443117063539038,
-      "loss": 0.4894,
+      "grad_norm": 0.6014457941055298,
+      "learning_rate": 0.00017621620551276366,
+      "loss": 1.7706,
       "step": 45
     },
-    {
-      "epoch": 4.0,
-      "grad_norm": 0.42734888195991516,
-      "learning_rate": 0.000131930153013598,
-      "loss": 0.4779,
-      "step": 50
-    },
-    {
-      "epoch": 4.4,
-      "grad_norm": 0.3881720006465912,
-      "learning_rate": 0.00011884453238783185,
-      "loss": 0.4904,
-      "step": 55
-    },
     {
       "epoch": 4.8,
-      "grad_norm": 0.4254741072654724,
-      "learning_rate": 0.00010541389085854176,
-      "loss": 0.4678,
+      "grad_norm": 0.4954649806022644,
+      "learning_rate": 0.00015611870653623825,
+      "loss": 1.2936,
       "step": 60
     },
-    {
-      "epoch": 5.2,
-      "grad_norm": 0.3979746997356415,
-      "learning_rate": 9.18841274472569e-05,
-      "loss": 0.4605,
-      "step": 65
-    },
-    {
-      "epoch": 5.6,
-      "grad_norm": 0.5344672799110413,
-      "learning_rate": 7.85029559788976e-05,
-      "loss": 0.4667,
-      "step": 70
-    },
     {
       "epoch": 6.0,
-      "grad_norm": 0.44632646441459656,
-      "learning_rate": 6.551536973720298e-05,
-      "loss": 0.4588,
+      "grad_norm": 0.418344110250473,
+      "learning_rate": 0.000131930153013598,
+      "loss": 1.0465,
       "step": 75
     },
-    {
-      "epoch": 6.4,
-      "grad_norm": 0.45458871126174927,
-      "learning_rate": 5.3159155930021e-05,
-      "loss": 0.4698,
-      "step": 80
-    },
-    {
-      "epoch": 6.8,
-      "grad_norm": 0.46564164757728577,
-      "learning_rate": 4.16605420892506e-05,
-      "loss": 0.4429,
-      "step": 85
-    },
     {
       "epoch": 7.2,
-      "grad_norm": 0.4069627523422241,
-      "learning_rate": 3.123005411465766e-05,
-      "loss": 0.451,
+      "grad_norm": 0.40778854489326477,
+      "learning_rate": 0.00010541389085854176,
+      "loss": 0.9186,
       "step": 90
     },
     {
-      "epoch": 7.6,
-      "grad_norm": 0.3835998475551605,
-      "learning_rate": 2.205866179584084e-05,
-      "loss": 0.4238,
-      "step": 95
+      "epoch": 8.4,
+      "grad_norm": 0.3741260766983032,
+      "learning_rate": 7.85029559788976e-05,
+      "loss": 0.8364,
+      "step": 105
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.4063926935195923,
-      "learning_rate": 1.4314282383241096e-05,
-      "loss": 0.4493,
-      "step": 100
+      "epoch": 9.6,
+      "grad_norm": 0.4041515290737152,
+      "learning_rate": 5.3159155930021e-05,
+      "loss": 0.7861,
+      "step": 120
     },
     {
-      "epoch": 8.4,
-      "grad_norm": 0.3951762318611145,
-      "learning_rate": 8.138706223637827e-06,
-      "loss": 0.4394,
-      "step": 105
+      "epoch": 10.8,
+      "grad_norm": 0.3697131872177124,
+      "learning_rate": 3.123005411465766e-05,
+      "loss": 0.7488,
+      "step": 135
     },
     {
-      "epoch": 8.8,
-      "grad_norm": 0.408200204372406,
-      "learning_rate": 3.6450007480777093e-06,
-      "loss": 0.4367,
-      "step": 110
+      "epoch": 12.0,
+      "grad_norm": 0.4183999001979828,
+      "learning_rate": 1.4314282383241096e-05,
+      "loss": 0.7274,
+      "step": 150
     },
     {
-      "epoch": 9.2,
-      "grad_norm": 0.5846555233001709,
-      "learning_rate": 9.154403421193225e-07,
-      "loss": 0.429,
-      "step": 115
+      "epoch": 13.2,
+      "grad_norm": 0.4263518154621124,
+      "learning_rate": 3.6450007480777093e-06,
+      "loss": 0.7245,
+      "step": 165
     },
     {
-      "epoch": 9.6,
-      "grad_norm": 0.3439011573791504,
+      "epoch": 14.4,
+      "grad_norm": 0.3251570165157318,
       "learning_rate": 0.0,
-      "loss": 0.4372,
-      "step": 120
+      "loss": 0.7288,
+      "step": 180
     },
     {
-      "epoch": 9.6,
-      "step": 120,
-      "total_flos": 77528353996800.0,
-      "train_loss": 0.4846629718939463,
-      "train_runtime": 54.9394,
-      "train_samples_per_second": 18.202,
-      "train_steps_per_second": 2.184
+      "epoch": 14.4,
+      "step": 180,
+      "total_flos": 116292530995200.0,
+      "train_loss": 1.4744000752766928,
+      "train_runtime": 81.674,
+      "train_samples_per_second": 18.366,
+      "train_steps_per_second": 2.204
     }
   ],
-  "logging_steps": 5,
-  "max_steps": 120,
+  "logging_steps": 15,
+  "max_steps": 180,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 77528353996800.0,
+  "total_flos": 116292530995200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99d9de74d1a3b9b5e5e92d75fa38b4585c6562b7ce7aaa44691e6d0f1d9a8f5b
+oid sha256:c67cb9db299dcc048f1694cd0a11b03c9a64221d6c98c783770f63b50ac522de
 size 5176