Upload folder using huggingface_hub

README.md

@@ -7,14 +7,14 @@ tags:
 - generated_from_trainer
 base_model: microsoft/phi-2
 model-index:
-- name: trivia
+- name: glaiveNew
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# trivia
+# glaiveNew
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the trivia dataset.
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-10
+- learning_rate: 5e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 30.0
+- num_epochs: 3.0
 
 ### Training results
 

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a4860ecef30d83bb4e8ca7d2b06962573b59019755b3618ef7a1d2dd861a98
+oid sha256:9abcb87ca0fc0f59556142c682feb9092e98296cd75e9449e28864e34339661a
 size 10502640

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 28.8,
-    "total_flos": 1335967054725120.0,
-    "train_loss": 7.109028116861979,
-    "train_runtime": 593.1625,
-    "train_samples_per_second": 5.058,
-    "train_steps_per_second": 0.303
+    "epoch": 2.88,
+    "total_flos": 133622157312000.0,
+    "train_loss": 6.60821893480089,
+    "train_runtime": 59.777,
+    "train_samples_per_second": 5.019,
+    "train_steps_per_second": 0.301
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 28.8,
-    "total_flos": 1335967054725120.0,
-    "train_loss": 7.109028116861979,
-    "train_runtime": 593.1625,
-    "train_samples_per_second": 5.058,
-    "train_steps_per_second": 0.303
+    "epoch": 2.88,
+    "total_flos": 133622157312000.0,
+    "train_loss": 6.60821893480089,
+    "train_runtime": 59.777,
+    "train_samples_per_second": 5.019,
+    "train_steps_per_second": 0.301
 }

trainer_log.jsonl

@@ -1,37 +1,4 @@
-{"current_steps": 5, "total_steps": 180, "loss": 7.386, "learning_rate": 4.990486745229364e-10, "epoch": 0.8, "percentage": 2.78, "elapsed_time": "0:00:16", "remaining_time": "0:09:43"}
-{"current_steps": 10, "total_steps": 180, "loss": 6.7817, "learning_rate": 4.962019382530521e-10, "epoch": 1.6, "percentage": 5.56, "elapsed_time": "0:00:33", "remaining_time": "0:09:23"}
-{"current_steps": 15, "total_steps": 180, "loss": 7.1632, "learning_rate": 4.914814565722671e-10, "epoch": 2.4, "percentage": 8.33, "elapsed_time": "0:00:49", "remaining_time": "0:09:04"}
-{"current_steps": 20, "total_steps": 180, "loss": 7.0109, "learning_rate": 4.849231551964771e-10, "epoch": 3.2, "percentage": 11.11, "elapsed_time": "0:01:05", "remaining_time": "0:08:47"}
-{"current_steps": 25, "total_steps": 180, "loss": 7.1004, "learning_rate": 4.765769467591626e-10, "epoch": 4.0, "percentage": 13.89, "elapsed_time": "0:01:21", "remaining_time": "0:08:27"}
-{"current_steps": 30, "total_steps": 180, "loss": 6.9577, "learning_rate": 4.665063509461097e-10, "epoch": 4.8, "percentage": 16.67, "elapsed_time": "0:01:38", "remaining_time": "0:08:11"}
-{"current_steps": 35, "total_steps": 180, "loss": 7.1725, "learning_rate": 4.54788011072248e-10, "epoch": 5.6, "percentage": 19.44, "elapsed_time": "0:01:54", "remaining_time": "0:07:55"}
-{"current_steps": 40, "total_steps": 180, "loss": 7.1535, "learning_rate": 4.415111107797445e-10, "epoch": 6.4, "percentage": 22.22, "elapsed_time": "0:02:11", "remaining_time": "0:07:39"}
-{"current_steps": 45, "total_steps": 180, "loss": 6.9961, "learning_rate": 4.267766952966369e-10, "epoch": 7.2, "percentage": 25.0, "elapsed_time": "0:02:28", "remaining_time": "0:07:24"}
-{"current_steps": 50, "total_steps": 180, "loss": 7.1581, "learning_rate": 4.106969024216348e-10, "epoch": 8.0, "percentage": 27.78, "elapsed_time": "0:02:44", "remaining_time": "0:07:08"}
-{"current_steps": 55, "total_steps": 180, "loss": 7.3208, "learning_rate": 3.933941090877615e-10, "epoch": 8.8, "percentage": 30.56, "elapsed_time": "0:03:02", "remaining_time": "0:06:54"}
-{"current_steps": 60, "total_steps": 180, "loss": 6.7152, "learning_rate": 3.7500000000000005e-10, "epoch": 9.6, "percentage": 33.33, "elapsed_time": "0:03:19", "remaining_time": "0:06:39"}
-{"current_steps": 65, "total_steps": 180, "loss": 7.1168, "learning_rate": 3.556545654351749e-10, "epoch": 10.4, "percentage": 36.11, "elapsed_time": "0:03:36", "remaining_time": "0:06:23"}
-{"current_steps": 70, "total_steps": 180, "loss": 7.143, "learning_rate": 3.3550503583141725e-10, "epoch": 11.2, "percentage": 38.89, "elapsed_time": "0:03:52", "remaining_time": "0:06:06"}
-{"current_steps": 75, "total_steps": 180, "loss": 7.2724, "learning_rate": 3.147047612756302e-10, "epoch": 12.0, "percentage": 41.67, "elapsed_time": "0:04:09", "remaining_time": "0:05:49"}
-{"current_steps": 80, "total_steps": 180, "loss": 6.995, "learning_rate": 2.9341204441673265e-10, "epoch": 12.8, "percentage": 44.44, "elapsed_time": "0:04:26", "remaining_time": "0:05:32"}
-{"current_steps": 85, "total_steps": 180, "loss": 7.1134, "learning_rate": 2.717889356869146e-10, "epoch": 13.6, "percentage": 47.22, "elapsed_time": "0:04:42", "remaining_time": "0:05:15"}
-{"current_steps": 90, "total_steps": 180, "loss": 7.2029, "learning_rate": 2.5e-10, "epoch": 14.4, "percentage": 50.0, "elapsed_time": "0:04:59", "remaining_time": "0:04:59"}
-{"current_steps": 95, "total_steps": 180, "loss": 7.4673, "learning_rate": 2.2821106431308546e-10, "epoch": 15.2, "percentage": 52.78, "elapsed_time": "0:05:15", "remaining_time": "0:04:42"}
-{"current_steps": 100, "total_steps": 180, "loss": 6.8563, "learning_rate": 2.0658795558326743e-10, "epoch": 16.0, "percentage": 55.56, "elapsed_time": "0:05:31", "remaining_time": "0:04:25"}
-{"current_steps": 105, "total_steps": 180, "loss": 7.0683, "learning_rate": 1.852952387243698e-10, "epoch": 16.8, "percentage": 58.33, "elapsed_time": "0:05:48", "remaining_time": "0:04:08"}
-{"current_steps": 110, "total_steps": 180, "loss": 7.1976, "learning_rate": 1.6449496416858284e-10, "epoch": 17.6, "percentage": 61.11, "elapsed_time": "0:06:04", "remaining_time": "0:03:52"}
-{"current_steps": 115, "total_steps": 180, "loss": 7.1575, "learning_rate": 1.443454345648252e-10, "epoch": 18.4, "percentage": 63.89, "elapsed_time": "0:06:20", "remaining_time": "0:03:35"}
-{"current_steps": 120, "total_steps": 180, "loss": 7.073, "learning_rate": 1.2500000000000006e-10, "epoch": 19.2, "percentage": 66.67, "elapsed_time": "0:06:37", "remaining_time": "0:03:18"}
-{"current_steps": 125, "total_steps": 180, "loss": 7.0932, "learning_rate": 1.0660589091223855e-10, "epoch": 20.0, "percentage": 69.44, "elapsed_time": "0:06:53", "remaining_time": "0:03:01"}
-{"current_steps": 130, "total_steps": 180, "loss": 7.1324, "learning_rate": 8.930309757836516e-11, "epoch": 20.8, "percentage": 72.22, "elapsed_time": "0:07:09", "remaining_time": "0:02:45"}
-{"current_steps": 135, "total_steps": 180, "loss": 7.1434, "learning_rate": 7.322330470336314e-11, "epoch": 21.6, "percentage": 75.0, "elapsed_time": "0:07:27", "remaining_time": "0:02:29"}
-{"current_steps": 140, "total_steps": 180, "loss": 7.0423, "learning_rate": 5.848888922025552e-11, "epoch": 22.4, "percentage": 77.78, "elapsed_time": "0:07:42", "remaining_time": "0:02:12"}
-{"current_steps": 145, "total_steps": 180, "loss": 7.3638, "learning_rate": 4.5211988927752025e-11, "epoch": 23.2, "percentage": 80.56, "elapsed_time": "0:07:59", "remaining_time": "0:01:55"}
-{"current_steps": 150, "total_steps": 180, "loss": 6.8454, "learning_rate": 3.3493649053890324e-11, "epoch": 24.0, "percentage": 83.33, "elapsed_time": "0:08:15", "remaining_time": "0:01:39"}
-{"current_steps": 155, "total_steps": 180, "loss": 7.1881, "learning_rate": 2.3423053240837516e-11, "epoch": 24.8, "percentage": 86.11, "elapsed_time": "0:08:31", "remaining_time": "0:01:22"}
-{"current_steps": 160, "total_steps": 180, "loss": 7.1249, "learning_rate": 1.5076844803522922e-11, "epoch": 25.6, "percentage": 88.89, "elapsed_time": "0:08:48", "remaining_time": "0:01:06"}
-{"current_steps": 165, "total_steps": 180, "loss": 7.1924, "learning_rate": 8.51854342773295e-12, "epoch": 26.4, "percentage": 91.67, "elapsed_time": "0:09:04", "remaining_time": "0:00:49"}
-{"current_steps": 170, "total_steps": 180, "loss": 6.9059, "learning_rate": 3.798061746947995e-12, "epoch": 27.2, "percentage": 94.44, "elapsed_time": "0:09:20", "remaining_time": "0:00:32"}
-{"current_steps": 175, "total_steps": 180, "loss": 7.2371, "learning_rate": 9.513254770636138e-13, "epoch": 28.0, "percentage": 97.22, "elapsed_time": "0:09:37", "remaining_time": "0:00:16"}
-{"current_steps": 180, "total_steps": 180, "loss": 7.0767, "learning_rate": 0.0, "epoch": 28.8, "percentage": 100.0, "elapsed_time": "0:09:53", "remaining_time": "0:00:00"}
-{"current_steps": 180, "total_steps": 180, "epoch": 28.8, "percentage": 100.0, "elapsed_time": "0:09:53", "remaining_time": "0:00:00"}
+{"current_steps": 5, "total_steps": 18, "loss": 7.2633, "learning_rate": 4.1069690242163484e-05, "epoch": 0.8, "percentage": 27.78, "elapsed_time": "0:00:17", "remaining_time": "0:00:45"}
+{"current_steps": 10, "total_steps": 18, "loss": 6.3067, "learning_rate": 2.0658795558326743e-05, "epoch": 1.6, "percentage": 55.56, "elapsed_time": "0:00:33", "remaining_time": "0:00:27"}
+{"current_steps": 15, "total_steps": 18, "loss": 6.4305, "learning_rate": 3.3493649053890326e-06, "epoch": 2.4, "percentage": 83.33, "elapsed_time": "0:00:50", "remaining_time": "0:00:10"}
+{"current_steps": 18, "total_steps": 18, "epoch": 2.88, "percentage": 100.0, "elapsed_time": "0:00:59", "remaining_time": "0:00:00"}

trainer_state.json

@@ -1,281 +1,50 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.8,
+  "epoch": 2.88,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.8,
-      "grad_norm": 2.3331761360168457,
-      "learning_rate": 4.990486745229364e-10,
-      "loss": 7.386,
+      "grad_norm": 2.860818386077881,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 7.2633,
       "step": 5
     },
     {
       "epoch": 1.6,
-      "grad_norm": 2.494887351989746,
-      "learning_rate": 4.962019382530521e-10,
-      "loss": 6.7817,
+      "grad_norm": 4.06754207611084,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 6.3067,
       "step": 10
     },
     {
       "epoch": 2.4,
-      "grad_norm": 2.389345407485962,
-      "learning_rate": 4.914814565722671e-10,
-      "loss": 7.1632,
+      "grad_norm": 4.378876686096191,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 6.4305,
       "step": 15
     },
     {
-      "epoch": 3.2,
-      "grad_norm": 2.437628984451294,
-      "learning_rate": 4.849231551964771e-10,
-      "loss": 7.0109,
-      "step": 20
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 3.2548422813415527,
-      "learning_rate": 4.765769467591626e-10,
-      "loss": 7.1004,
-      "step": 25
-    },
-    {
-      "epoch": 4.8,
-      "grad_norm": 2.268507480621338,
-      "learning_rate": 4.665063509461097e-10,
-      "loss": 6.9577,
-      "step": 30
-    },
-    {
-      "epoch": 5.6,
-      "grad_norm": 2.739196300506592,
-      "learning_rate": 4.54788011072248e-10,
-      "loss": 7.1725,
-      "step": 35
-    },
-    {
-      "epoch": 6.4,
-      "grad_norm": 2.399449348449707,
-      "learning_rate": 4.415111107797445e-10,
-      "loss": 7.1535,
-      "step": 40
-    },
-    {
-      "epoch": 7.2,
-      "grad_norm": 2.798766613006592,
-      "learning_rate": 4.267766952966369e-10,
-      "loss": 6.9961,
-      "step": 45
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 2.742884635925293,
-      "learning_rate": 4.106969024216348e-10,
-      "loss": 7.1581,
-      "step": 50
-    },
-    {
-      "epoch": 8.8,
-      "grad_norm": 3.0411534309387207,
-      "learning_rate": 3.933941090877615e-10,
-      "loss": 7.3208,
-      "step": 55
-    },
-    {
-      "epoch": 9.6,
-      "grad_norm": 2.590532064437866,
-      "learning_rate": 3.7500000000000005e-10,
-      "loss": 6.7152,
-      "step": 60
-    },
-    {
-      "epoch": 10.4,
-      "grad_norm": 2.6501505374908447,
-      "learning_rate": 3.556545654351749e-10,
-      "loss": 7.1168,
-      "step": 65
-    },
-    {
-      "epoch": 11.2,
-      "grad_norm": 2.6842129230499268,
-      "learning_rate": 3.3550503583141725e-10,
-      "loss": 7.143,
-      "step": 70
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 2.7974400520324707,
-      "learning_rate": 3.147047612756302e-10,
-      "loss": 7.2724,
-      "step": 75
-    },
-    {
-      "epoch": 12.8,
-      "grad_norm": 2.68391489982605,
-      "learning_rate": 2.9341204441673265e-10,
-      "loss": 6.995,
-      "step": 80
-    },
-    {
-      "epoch": 13.6,
-      "grad_norm": 3.0854671001434326,
-      "learning_rate": 2.717889356869146e-10,
-      "loss": 7.1134,
-      "step": 85
-    },
-    {
-      "epoch": 14.4,
-      "grad_norm": 2.772061347961426,
-      "learning_rate": 2.5e-10,
-      "loss": 7.2029,
-      "step": 90
-    },
-    {
-      "epoch": 15.2,
-      "grad_norm": 2.6627767086029053,
-      "learning_rate": 2.2821106431308546e-10,
-      "loss": 7.4673,
-      "step": 95
-    },
-    {
-      "epoch": 16.0,
-      "grad_norm": 2.7043120861053467,
-      "learning_rate": 2.0658795558326743e-10,
-      "loss": 6.8563,
-      "step": 100
-    },
-    {
-      "epoch": 16.8,
-      "grad_norm": 2.4765264987945557,
-      "learning_rate": 1.852952387243698e-10,
-      "loss": 7.0683,
-      "step": 105
-    },
-    {
-      "epoch": 17.6,
-      "grad_norm": 2.775627613067627,
-      "learning_rate": 1.6449496416858284e-10,
-      "loss": 7.1976,
-      "step": 110
-    },
-    {
-      "epoch": 18.4,
-      "grad_norm": 2.3891263008117676,
-      "learning_rate": 1.443454345648252e-10,
-      "loss": 7.1575,
-      "step": 115
-    },
-    {
-      "epoch": 19.2,
-      "grad_norm": 2.5396955013275146,
-      "learning_rate": 1.2500000000000006e-10,
-      "loss": 7.073,
-      "step": 120
-    },
-    {
-      "epoch": 20.0,
-      "grad_norm": 2.4532394409179688,
-      "learning_rate": 1.0660589091223855e-10,
-      "loss": 7.0932,
-      "step": 125
-    },
-    {
-      "epoch": 20.8,
-      "grad_norm": 2.822531223297119,
-      "learning_rate": 8.930309757836516e-11,
-      "loss": 7.1324,
-      "step": 130
-    },
-    {
-      "epoch": 21.6,
-      "grad_norm": 2.5621225833892822,
-      "learning_rate": 7.322330470336314e-11,
-      "loss": 7.1434,
-      "step": 135
-    },
-    {
-      "epoch": 22.4,
-      "grad_norm": 2.63484263420105,
-      "learning_rate": 5.848888922025552e-11,
-      "loss": 7.0423,
-      "step": 140
-    },
-    {
-      "epoch": 23.2,
-      "grad_norm": 2.882169246673584,
-      "learning_rate": 4.5211988927752025e-11,
-      "loss": 7.3638,
-      "step": 145
-    },
-    {
-      "epoch": 24.0,
-      "grad_norm": 2.356477975845337,
-      "learning_rate": 3.3493649053890324e-11,
-      "loss": 6.8454,
-      "step": 150
-    },
-    {
-      "epoch": 24.8,
-      "grad_norm": 3.1740143299102783,
-      "learning_rate": 2.3423053240837516e-11,
-      "loss": 7.1881,
-      "step": 155
-    },
-    {
-      "epoch": 25.6,
-      "grad_norm": 2.634425640106201,
-      "learning_rate": 1.5076844803522922e-11,
-      "loss": 7.1249,
-      "step": 160
-    },
-    {
-      "epoch": 26.4,
-      "grad_norm": 2.412172317504883,
-      "learning_rate": 8.51854342773295e-12,
-      "loss": 7.1924,
-      "step": 165
-    },
-    {
-      "epoch": 27.2,
-      "grad_norm": 2.655557870864868,
-      "learning_rate": 3.798061746947995e-12,
-      "loss": 6.9059,
-      "step": 170
-    },
-    {
-      "epoch": 28.0,
-      "grad_norm": 2.859827756881714,
-      "learning_rate": 9.513254770636138e-13,
-      "loss": 7.2371,
-      "step": 175
-    },
-    {
-      "epoch": 28.8,
-      "grad_norm": 2.7501277923583984,
-      "learning_rate": 0.0,
-      "loss": 7.0767,
-      "step": 180
-    },
-    {
-      "epoch": 28.8,
-      "step": 180,
-      "total_flos": 1335967054725120.0,
-      "train_loss": 7.109028116861979,
-      "train_runtime": 593.1625,
-      "train_samples_per_second": 5.058,
-      "train_steps_per_second": 0.303
+      "epoch": 2.88,
+      "step": 18,
+      "total_flos": 133622157312000.0,
+      "train_loss": 6.60821893480089,
+      "train_runtime": 59.777,
+      "train_samples_per_second": 5.019,
+      "train_steps_per_second": 0.301
     }
   ],
   "logging_steps": 5,
-  "max_steps": 180,
+  "max_steps": 18,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 30,
+  "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1335967054725120.0,
+  "total_flos": 133622157312000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ca302ed42091be2724cc3ec6e2a8ab6f813368320dc36808ada89634d0b367
-size 5112
+oid sha256:877561c09d9ec252be597601fb20cc3870d9bf16887509642b7e8821a1e2e78c
+size 5176