Model save

README.md

@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # recreate_llama_68M_vanilla
 
-This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the anon8231489123/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json dataset.
+This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3086
-- Accuracy: 0.4590
+- Loss: 2.3603
+- Accuracy: 0.5811
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 12
-- eval_batch_size: 24
+- train_batch_size: 24
+- eval_batch_size: 48
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -48,6 +48,19 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| 3.406         | 0.2644 | 1000  | 3.2345          | 0.5035   |
+| 2.8119        | 0.5288 | 2000  | 2.8216          | 0.5365   |
+| 2.6076        | 0.7932 | 3000  | 2.6553          | 0.5501   |
+| 2.4729        | 1.0576 | 4000  | 2.5761          | 0.5581   |
+| 2.4323        | 1.3221 | 5000  | 2.5363          | 0.5617   |
+| 2.3824        | 1.5865 | 6000  | 2.4913          | 0.5660   |
+| 2.3719        | 1.8509 | 7000  | 2.4664          | 0.5686   |
+| 2.3021        | 2.1153 | 8000  | 2.4404          | 0.5716   |
+| 2.2848        | 2.3797 | 9000  | 2.4080          | 0.5755   |
+| 2.2653        | 2.6441 | 10000 | 2.3834          | 0.5785   |
+| 2.2447        | 2.9085 | 11000 | 2.3603          | 0.5811   |
 
 
 ### Framework versions

events.out.tfevents.1717488111.isl-gpu33.2434801.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ced7335b794f6217b140b697a465134ef27bfb433181ef21d12c2c0b1dd6ed
-size 13146
+oid sha256:be85f504bca71a575e7d21a6c09da598a15be6f6a806bb426595d8f930fff8ae
+size 13500

log.txt

@@ -885,3 +885,136 @@ Loading cached processed dataset at /home/dshteyma/.cache/huggingface/datasets/j
 [INFO|tokenization_utils_base.py:2512] 2024-06-04 06:34:46,021 >> Special tokens file saved in ./training_outputs_job_116987_1_04-06_01-01/special_tokens_map.json
 /home/dshteyma/miniconda3/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
   warnings.warn('Was asked to gather along dimension 0, but all '
+
 97%|█████████▋| 11001/11346 [5:32:56<3:58:05, 41.41s/it]
 97%|█████████▋| 11002/11346 [5:32:58<2:49:05, 29.49s/it]
 97%|█████████▋| 11003/11346 [5:33:00<2:00:54, 21.15s/it]
 97%|█████████▋| 11004/11346 [5:33:01<1:27:16, 15.31s/it]
 97%|█████████▋| 11005/11346 [5:33:03<1:03:47, 11.22s/it]
 97%|█████████▋| 11006/11346 [5:33:05<47:22,  8.36s/it]  
 97%|█████████▋| 11007/11346 [5:33:06<35:56,  6.36s/it]
 97%|█████████▋| 11008/11346 [5:33:08<27:55,  4.96s/it]
 97%|█████████▋| 11009/11346 [5:33:10<22:20,  3.98s/it]
 97%|█████████▋| 11010/11346 [5:33:11<18:24,  3.29s/it]
 97%|█████████▋| 11011/11346 [5:33:13<15:40,  2.81s/it]
 97%|█████████▋| 11012/11346 [5:33:15<13:44,  2.47s/it]
 97%|█████████▋| 11013/11346 [5:33:16<12:23,  2.23s/it]
 97%|█████████▋| 11014/11346 [5:33:18<11:26,  2.07s/it]
 97%|█████████▋| 11015/11346 [5:33:20<10:46,  1.95s/it]
 97%|█████████▋| 11016/11346 [5:33:22<10:17,  1.87s/it]
 97%|█████████▋| 11017/11346 [5:33:23<09:56,  1.81s/it]
 97%|█████████▋| 11018/11346 [5:33:25<09:42,  1.77s/it]
 97%|█████████▋| 11019/11346 [5:33:27<09:31,  1.75s/it]
 97%|█████████▋| 11020/11346 [5:33:28<09:23,  1.73s/it]
 97%|█████████▋| 11021/11346 [5:33:30<09:18,  1.72s/it]
 97%|█████████▋| 11022/11346 [5:33:32<09:13,  1.71s/it]
 97%|█████████▋| 11023/11346 [5:33:33<09:09,  1.70s/it]
 97%|█████████▋| 11024/11346 [5:33:35<09:05,  1.70s/it]
 97%|█████████▋| 11025/11346 [5:33:37<09:03,  1.69s/it]
 97%|█████████▋| 11026/11346 [5:33:38<09:00,  1.69s/it]
 97%|█████████▋| 11027/11346 [5:33:40<08:58,  1.69s/it]
 97%|█████████▋| 11028/11346 [5:33:42<08:55,  1.68s/it]
 97%|█████████▋| 11029/11346 [5:33:43<08:54,  1.69s/it]
 97%|█████████▋| 11030/11346 [5:33:45<08:52,  1.69s/it]
 97%|█████████▋| 11031/11346 [5:33:47<08:50,  1.68s/it]
 97%|█████████▋| 11032/11346 [5:33:48<08:48,  1.68s/it]
 97%|█████████▋| 11033/11346 [5:33:50<08:46,  1.68s/it]
 97%|█████████▋| 11034/11346 [5:33:52<08:44,  1.68s/it]
 97%|█████████▋| 11035/11346 [5:33:54<08:43,  1.68s/it]
 97%|█████████▋| 11036/11346 [5:33:55<08:41,  1.68s/it]
 97%|█████████▋| 11037/11346 [5:33:57<08:40,  1.68s/it]
 97%|█████████▋| 11038/11346 [5:33:59<08:38,  1.68s/it]
 97%|█████████▋| 11039/11346 [5:34:00<08:37,  1.69s/it]
 97%|█████████▋| 11040/11346 [5:34:02<08:35,  1.68s/it]
 97%|█████████▋| 11041/11346 [5:34:04<08:33,  1.68s/it]
 97%|█████████▋| 11042/11346 [5:34:05<08:31,  1.68s/it]
 97%|█████████▋| 11043/11346 [5:34:07<08:30,  1.69s/it]
 97%|█████████▋| 11044/11346 [5:34:09<08:28,  1.68s/it]
 97%|█████████▋| 11045/11346 [5:34:10<08:27,  1.68s/it]
 97%|█████████▋| 11046/11346 [5:34:12<08:25,  1.69s/it]
 97%|█████████▋| 11047/11346 [5:34:14<08:23,  1.69s/it]
 97%|█████████▋| 11048/11346 [5:34:15<08:22,  1.68s/it]
 97%|█████████▋| 11049/11346 [5:34:17<08:20,  1.68s/it]
 97%|█████████▋| 11050/11346 [5:34:19<08:18,  1.68s/it]
 97%|█████████▋| 11051/11346 [5:34:20<08:16,  1.68s/it]
 97%|█████████▋| 11052/11346 [5:34:22<08:15,  1.69s/it]
 97%|█████████▋| 11053/11346 [5:34:24<08:13,  1.69s/it]
 97%|█████████▋| 11054/11346 [5:34:26<08:12,  1.69s/it]
 97%|█████████▋| 11055/11346 [5:34:27<08:10,  1.68s/it]
 97%|█████████▋| 11056/11346 [5:34:29<08:08,  1.68s/it]
 97%|█████████▋| 11057/11346 [5:34:31<08:06,  1.68s/it]
 97%|█████████▋| 11058/11346 [5:34:32<08:04,  1.68s/it]
 97%|█████████▋| 11059/11346 [5:34:34<08:03,  1.68s/it]
 97%|█████████▋| 11060/11346 [5:34:36<08:01,  1.69s/it]
 97%|█████████▋| 11061/11346 [5:34:37<08:00,  1.68s/it]
 97%|█████████▋| 11062/11346 [5:34:39<07:58,  1.69s/it]
 98%|█████████▊| 11063/11346 [5:34:41<07:56,  1.69s/it]
 98%|█████████▊| 11064/11346 [5:34:42<07:55,  1.69s/it]
 98%|█████████▊| 11065/11346 [5:34:44<07:53,  1.69s/it]
 98%|█████████▊| 11066/11346 [5:34:46<07:51,  1.69s/it]
 98%|█████████▊| 11067/11346 [5:34:47<07:49,  1.68s/it]
 98%|█████████▊| 11068/11346 [5:34:49<07:48,  1.68s/it]
 98%|█████████▊| 11069/11346 [5:34:51<07:46,  1.68s/it]
 98%|█████████▊| 11070/11346 [5:34:52<07:44,  1.68s/it]
 98%|█████████▊| 11071/11346 [5:34:54<07:42,  1.68s/it]
 98%|█████████▊| 11072/11346 [5:34:56<07:40,  1.68s/it]
 98%|█████████▊| 11073/11346 [5:34:58<07:39,  1.68s/it]
 98%|█████████▊| 11074/11346 [5:34:59<07:37,  1.68s/it]
 98%|█████████▊| 11075/11346 [5:35:01<07:36,  1.68s/it]
 98%|█████████▊| 11076/11346 [5:35:03<07:35,  1.69s/it]
 98%|█████████▊| 11077/11346 [5:35:04<07:33,  1.68s/it]
 98%|█████████▊| 11078/11346 [5:35:06<07:31,  1.69s/it]
 98%|█████████▊| 11079/11346 [5:35:08<07:29,  1.68s/it]
 98%|█████████▊| 11080/11346 [5:35:09<07:28,  1.68s/it]
 98%|█████████▊| 11081/11346 [5:35:11<07:26,  1.69s/it]
 98%|█████████▊| 11082/11346 [5:35:13<07:24,  1.69s/it]
 98%|█████████▊| 11083/11346 [5:35:14<07:23,  1.69s/it]
 98%|█████████▊| 11084/11346 [5:35:16<07:21,  1.69s/it]
 98%|█████████▊| 11085/11346 [5:35:18<07:19,  1.69s/it]
 98%|█████████▊| 11086/11346 [5:35:19<07:18,  1.68s/it]
 98%|█████████▊| 11087/11346 [5:35:21<07:16,  1.68s/it]
 98%|█████████▊| 11088/11346 [5:35:23<07:14,  1.68s/it]
 98%|█████████▊| 11089/11346 [5:35:24<07:12,  1.68s/it]
 98%|█████████▊| 11090/11346 [5:35:26<07:11,  1.68s/it]
 98%|█████████▊| 11091/11346 [5:35:28<07:09,  1.68s/it]
 98%|█████████▊| 11092/11346 [5:35:30<07:07,  1.68s/it]
 98%|█████████▊| 11093/11346 [5:35:31<07:05,  1.68s/it]
 98%|█████████▊| 11094/11346 [5:35:33<07:03,  1.68s/it]
 98%|█████████▊| 11095/11346 [5:35:35<07:02,  1.68s/it]
 98%|█████████▊| 11096/11346 [5:35:36<07:01,  1.68s/it]
 98%|█████████▊| 11097/11346 [5:35:38<06:59,  1.68s/it]
 98%|█████████▊| 11098/11346 [5:35:40<06:57,  1.69s/it]
 98%|█████████▊| 11099/11346 [5:35:41<06:56,  1.68s/it]
 98%|█████████▊| 11100/11346 [5:35:43<06:54,  1.68s/it]
 98%|█████████▊| 11101/11346 [5:35:45<06:52,  1.68s/it]
 98%|█████████▊| 11102/11346 [5:35:46<06:50,  1.68s/it]
 98%|█████████▊| 11103/11346 [5:35:48<06:49,  1.68s/it]
 98%|█████████▊| 11104/11346 [5:35:50<07:04,  1.76s/it]
 98%|█████████▊| 11105/11346 [5:35:52<06:57,  1.73s/it]
 98%|█████████▊| 11106/11346 [5:35:53<06:52,  1.72s/it]
 98%|█████████▊| 11107/11346 [5:35:55<06:48,  1.71s/it]
 98%|█████████▊| 11108/11346 [5:35:57<06:45,  1.70s/it]
 98%|█████████▊| 11109/11346 [5:35:58<06:41,  1.70s/it]
 98%|█████████▊| 11110/11346 [5:36:00<06:39,  1.69s/it]
 98%|█████████▊| 11111/11346 [5:36:02<06:36,  1.69s/it]
 98%|█████████▊| 11112/11346 [5:36:03<06:35,  1.69s/it]
 98%|█████████▊| 11113/11346 [5:36:05<06:33,  1.69s/it]
 98%|█████████▊| 11114/11346 [5:36:07<06:31,  1.69s/it]
 98%|█████████▊| 11115/11346 [5:36:09<06:29,  1.69s/it]
 98%|█████████▊| 11116/11346 [5:36:10<06:27,  1.69s/it]
 98%|█████████▊| 11117/11346 [5:36:12<06:25,  1.68s/it]
 98%|█████████▊| 11118/11346 [5:36:14<06:24,  1.68s/it]
 98%|█████████▊| 11119/11346 [5:36:15<06:22,  1.68s/it]
 98%|█████████▊| 11120/11346 [5:36:17<06:20,  1.68s/it]
 98%|█████████▊| 11121/11346 [5:36:19<06:19,  1.69s/it]
 98%|█████████▊| 11122/11346 [5:36:20<06:17,  1.69s/it]
 98%|█████████▊| 11123/11346 [5:36:22<06:16,  1.69s/it]
 98%|█████████▊| 11124/11346 [5:36:24<06:14,  1.69s/it]
 98%|█████████▊| 11125/11346 [5:36:25<06:12,  1.69s/it]
 98%|█████████▊| 11126/11346 [5:36:27<06:10,  1.68s/it]
 98%|█████████▊| 11127/11346 [5:36:29<06:09,  1.68s/it]
 98%|█████████▊| 11128/11346 [5:36:30<06:07,  1.68s/it]
 98%|█████████▊| 11129/11346 [5:36:32<06:05,  1.68s/it]
 98%|█████████▊| 11130/11346 [5:36:34<06:03,  1.68s/it]
 98%|█████████▊| 11131/11346 [5:36:35<06:01,  1.68s/it]
 98%|█████████▊| 11132/11346 [5:36:37<06:00,  1.68s/it]
 98%|█████████▊| 11133/11346 [5:36:39<05:58,  1.68s/it]
 98%|█████████▊| 11134/11346 [5:36:41<05:56,  1.68s/it]
 98%|█████████▊| 11135/11346 [5:36:42<05:55,  1.68s/it]
 98%|█████████▊| 11136/11346 [5:36:44<05:53,  1.68s/it]
 98%|█████████▊| 11137/11346 [5:36:46<05:51,  1.68s/it]
 98%|█████████▊| 11138/11346 [5:36:47<05:50,  1.68s/it]
 98%|█████████▊| 11139/11346 [5:36:49<05:48,  1.68s/it]
 98%|█████████▊| 11140/11346 [5:36:51<05:47,  1.68s/it]
 98%|█████████▊| 11141/11346 [5:36:52<05:45,  1.68s/it]
 98%|█████████▊| 11142/11346 [5:36:54<05:43,  1.68s/it]
 98%|█████████▊| 11143/11346 [5:36:56<05:41,  1.68s/it]
 98%|█████████▊| 11144/11346 [5:36:57<05:40,  1.69s/it]
 98%|█████████▊| 11145/11346 [5:36:59<05:38,  1.68s/it]
 98%|█████████▊| 11146/11346 [5:37:01<05:37,  1.69s/it]
 98%|█████████▊| 11147/11346 [5:37:02<05:35,  1.68s/it]
 98%|█████████▊| 11148/11346 [5:37:04<05:33,  1.68s/it]
 98%|█████████▊| 11149/11346 [5:37:06<05:31,  1.68s/it]
 98%|█████████▊| 11150/11346 [5:37:07<05:30,  1.68s/it]
 98%|█████████▊| 11151/11346 [5:37:09<05:28,  1.68s/it]
 98%|█████████▊| 11152/11346 [5:37:11<05:26,  1.68s/it]
 98%|█████████▊| 11153/11346 [5:37:13<05:24,  1.68s/it]
 98%|█████████▊| 11154/11346 [5:37:14<05:22,  1.68s/it]
 98%|█████████▊| 11155/11346 [5:37:16<05:21,  1.68s/it]
 98%|█████████▊| 11156/11346 [5:37:18<05:19,  1.68s/it]
 98%|█████████▊| 11157/11346 [5:37:19<05:17,  1.68s/it]
 98%|█████████▊| 11158/11346 [5:37:21<05:16,  1.68s/it]
 98%|█████████▊| 11159/11346 [5:37:23<05:14,  1.68s/it]
 98%|█████████▊| 11160/11346 [5:37:24<05:12,  1.68s/it]
 98%|█████████▊| 11161/11346 [5:37:26<05:11,  1.68s/it]
 98%|█████████▊| 11162/11346 [5:37:28<05:09,  1.68s/it]
 98%|█████████▊| 11163/11346 [5:37:29<05:07,  1.68s/it]
 98%|█████████▊| 11164/11346 [5:37:31<05:06,  1.68s/it]
 98%|█████████▊| 11165/11346 [5:37:33<05:04,  1.68s/it]
 98%|█████████▊| 11166/11346 [5:37:34<05:03,  1.68s/it]
 98%|█████████▊| 11167/11346 [5:37:36<05:01,  1.68s/it]
 98%|█████████▊| 11168/11346 [5:37:38<04:59,  1.68s/it]
 98%|█████████▊| 11169/11346 [5:37:39<04:58,  1.69s/it]
 98%|█████████▊| 11170/11346 [5:37:41<04:56,  1.69s/it]
 98%|█████████▊| 11171/11346 [5:37:43<04:54,  1.68s/it]
 98%|█████████▊| 11172/11346 [5:37:44<04:53,  1.68s/it]
 98%|█████████▊| 11173/11346 [5:37:46<04:51,  1.68s/it]
 98%|█████████▊| 11174/11346 [5:37:48<04:49,  1.68s/it]
 98%|█████████▊| 11175/11346 [5:37:50<04:47,  1.68s/it]
 99%|█████████▊| 11176/11346 [5:37:51<04:46,  1.68s/it]
 99%|█████████▊| 11177/11346 [5:37:53<04:44,  1.68s/it]
 99%|█████████▊| 11178/11346 [5:37:55<04:42,  1.68s/it]
 99%|█████████▊| 11179/11346 [5:37:56<04:41,  1.68s/it]
 99%|█████████▊| 11180/11346 [5:37:58<04:39,  1.68s/it]
 99%|█████████▊| 11181/11346 [5:38:00<04:37,  1.68s/it]
 99%|█████████▊| 11182/11346 [5:38:01<04:36,  1.68s/it]
 99%|█████████▊| 11183/11346 [5:38:03<04:34,  1.68s/it]
 99%|█████████▊| 11184/11346 [5:38:05<04:32,  1.68s/it]
 99%|█████████▊| 11185/11346 [5:38:06<04:31,  1.68s/it]
 99%|█████████▊| 11186/11346 [5:38:08<04:29,  1.68s/it]
 99%|█████████▊| 11187/11346 [5:38:10<04:27,  1.68s/it]
 99%|█████████▊| 11188/11346 [5:38:11<04:26,  1.68s/it]
 99%|█████████▊| 11189/11346 [5:38:13<04:24,  1.68s/it]
 99%|█████████▊| 11190/11346 [5:38:15<04:22,  1.68s/it]
 99%|█████████▊| 11191/11346 [5:38:16<04:21,  1.68s/it]
 99%|█████████▊| 11192/11346 [5:38:18<04:19,  1.68s/it]
 99%|█████████▊| 11193/11346 [5:38:20<04:17,  1.68s/it]
 99%|█████████▊| 11194/11346 [5:38:22<04:16,  1.68s/it]
 99%|█████████▊| 11195/11346 [5:38:23<04:14,  1.68s/it]
 99%|█████████▊| 11196/11346 [5:38:25<04:12,  1.68s/it]
 99%|█████████▊| 11197/11346 [5:38:27<04:10,  1.68s/it]
 99%|█████████▊| 11198/11346 [5:38:28<04:09,  1.68s/it]
 99%|█████████▊| 11199/11346 [5:38:30<04:07,  1.68s/it]
 99%|█████████▊| 11200/11346 [5:38:32<04:05,  1.68s/it]
 99%|█████████▊| 11201/11346 [5:38:33<04:03,  1.68s/it]
 99%|█████████▊| 11202/11346 [5:38:35<04:02,  1.68s/it]
 99%|█████████▊| 11203/11346 [5:38:37<04:00,  1.68s/it]
 99%|█████████▊| 11204/11346 [5:38:38<03:59,  1.68s/it]
 99%|█████████▉| 11205/11346 [5:38:40<03:57,  1.68s/it]
 99%|█████████▉| 11206/11346 [5:38:42<03:55,  1.68s/it]
 99%|█████████▉| 11207/11346 [5:38:43<03:54,  1.68s/it]
 99%|█████████▉| 11208/11346 [5:38:45<03:52,  1.68s/it]
 99%|█████████▉| 11209/11346 [5:38:47<03:50,  1.68s/it]
 99%|█████████▉| 11210/11346 [5:38:48<03:49,  1.68s/it]
 99%|█████████▉| 11211/11346 [5:38:50<03:47,  1.68s/it]
 99%|█████████▉| 11212/11346 [5:38:52<03:45,  1.68s/it]
 99%|█████████▉| 11213/11346 [5:38:54<03:43,  1.68s/it]
 99%|█████████▉| 11214/11346 [5:38:55<03:42,  1.69s/it]
 99%|█████████▉| 11215/11346 [5:38:57<03:40,  1.68s/it]
 99%|█████████▉| 11216/11346 [5:38:59<03:39,  1.69s/it]
 99%|█████████▉| 11217/11346 [5:39:00<03:37,  1.69s/it]
 99%|█████████▉| 11218/11346 [5:39:02<03:35,  1.68s/it]
 99%|█████████▉| 11219/11346 [5:39:04<03:33,  1.68s/it]
 99%|█████████▉| 11220/11346 [5:39:05<03:32,  1.69s/it]
 99%|█████████▉| 11221/11346 [5:39:07<03:30,  1.69s/it]
 99%|█████████▉| 11222/11346 [5:39:09<03:28,  1.69s/it]
 99%|█████████▉| 11223/11346 [5:39:10<03:27,  1.69s/it]
 99%|█████████▉| 11224/11346 [5:39:12<03:25,  1.68s/it]
 99%|█████████▉| 11225/11346 [5:39:14<03:23,  1.69s/it]
 99%|█████████▉| 11226/11346 [5:39:15<03:22,  1.69s/it]
 99%|█████████▉| 11227/11346 [5:39:17<03:20,  1.68s/it]
 99%|█████████▉| 11228/11346 [5:39:19<03:18,  1.68s/it]
 99%|█████████▉| 11229/11346 [5:39:20<03:17,  1.69s/it]
 99%|█████████▉| 11230/11346 [5:39:22<03:15,  1.69s/it]
 99%|█████████▉| 11231/11346 [5:39:24<03:13,  1.69s/it]
 99%|█████████▉| 11232/11346 [5:39:26<03:12,  1.68s/it]
 99%|█████████▉| 11233/11346 [5:39:27<03:10,  1.68s/it]
 99%|█████████▉| 11234/11346 [5:39:29<03:08,  1.68s/it]
 99%|█████████▉| 11235/11346 [5:39:31<03:06,  1.68s/it]
 99%|█████████▉| 11236/11346 [5:39:32<03:05,  1.68s/it]
 99%|█████████▉| 11237/11346 [5:39:34<03:03,  1.68s/it]
 99%|█████████▉| 11238/11346 [5:39:36<03:01,  1.68s/it]
 99%|█████████▉| 11239/11346 [5:39:37<03:00,  1.68s/it]
 99%|█████████▉| 11240/11346 [5:39:39<02:58,  1.68s/it]
 99%|█████████▉| 11241/11346 [5:39:41<02:56,  1.68s/it]
 99%|█████████▉| 11242/11346 [5:39:42<02:55,  1.68s/it]
 99%|█████████▉| 11243/11346 [5:39:44<02:53,  1.68s/it]
 99%|█████████▉| 11244/11346 [5:39:46<02:51,  1.68s/it]
 99%|█████████▉| 11245/11346 [5:39:47<02:50,  1.68s/it]
 99%|█████████▉| 11246/11346 [5:39:49<02:48,  1.68s/it]
 99%|█████████▉| 11247/11346 [5:39:51<02:46,  1.69s/it]
 99%|█████████▉| 11248/11346 [5:39:52<02:45,  1.69s/it]
 99%|█████████▉| 11249/11346 [5:39:54<02:43,  1.69s/it]
 99%|█████████▉| 11250/11346 [5:39:56<02:41,  1.69s/it]
 99%|█████████▉| 11251/11346 [5:39:58<02:40,  1.69s/it]
 99%|█████████▉| 11252/11346 [5:39:59<02:38,  1.69s/it]
 99%|█████████▉| 11253/11346 [5:40:01<02:36,  1.69s/it]
 99%|█████████▉| 11254/11346 [5:40:03<02:34,  1.68s/it]
 99%|█████████▉| 11255/11346 [5:40:04<02:33,  1.68s/it]
 99%|█████████▉| 11256/11346 [5:40:06<02:31,  1.69s/it]
 99%|█████████▉| 11257/11346 [5:40:08<02:29,  1.68s/it]
 99%|█████████▉| 11258/11346 [5:40:09<02:28,  1.68s/it]
 99%|█████████▉| 11259/11346 [5:40:11<02:26,  1.68s/it]
 99%|█████████▉| 11260/11346 [5:40:13<02:24,  1.68s/it]
 99%|█████████▉| 11261/11346 [5:40:14<02:23,  1.68s/it]
 99%|█████████▉| 11262/11346 [5:40:16<02:21,  1.68s/it]
 99%|█████████▉| 11263/11346 [5:40:18<02:19,  1.68s/it]
 99%|█████████▉| 11264/11346 [5:40:19<02:17,  1.68s/it]
 99%|█████████▉| 11265/11346 [5:40:21<02:16,  1.68s/it]
 99%|█████████▉| 11266/11346 [5:40:23<02:14,  1.68s/it]
 99%|█████████▉| 11267/11346 [5:40:24<02:12,  1.68s/it]
 99%|█████████▉| 11268/11346 [5:40:26<02:11,  1.68s/it]
 99%|█████████▉| 11269/11346 [5:40:28<02:09,  1.68s/it]
 99%|█████████▉| 11270/11346 [5:40:30<02:07,  1.68s/it]
 99%|█████████▉| 11271/11346 [5:40:31<02:06,  1.68s/it]
 99%|█████████▉| 11272/11346 [5:40:33<02:04,  1.68s/it]
 99%|█████████▉| 11273/11346 [5:40:35<02:02,  1.68s/it]
 99%|█████████▉| 11274/11346 [5:40:36<02:01,  1.68s/it]
 99%|█████████▉| 11275/11346 [5:40:38<01:59,  1.68s/it]
 99%|█████████▉| 11276/11346 [5:40:40<01:57,  1.68s/it]
 99%|█████████▉| 11277/11346 [5:40:41<01:56,  1.68s/it]
 99%|█████████▉| 11278/11346 [5:40:43<01:54,  1.68s/it]
 99%|█████████▉| 11279/11346 [5:40:45<01:52,  1.68s/it]
 99%|█████████▉| 11280/11346 [5:40:46<01:51,  1.69s/it]
 99%|█████████▉| 11281/11346 [5:40:48<01:49,  1.69s/it]
 99%|█████████▉| 11282/11346 [5:40:50<01:47,  1.68s/it]
 99%|█████████▉| 11283/11346 [5:40:51<01:46,  1.68s/it]
 99%|█████████▉| 11284/11346 [5:40:53<01:44,  1.69s/it]
 99%|█████████▉| 11285/11346 [5:40:55<01:42,  1.68s/it]
 99%|█████████▉| 11286/11346 [5:40:56<01:41,  1.68s/it]
 99%|█████████▉| 11287/11346 [5:40:58<01:39,  1.68s/it]
 99%|█████████▉| 11288/11346 [5:41:00<01:37,  1.68s/it]
 99%|█████████▉| 11289/11346 [5:41:02<01:36,  1.69s/it]
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
                                                       
+[INFO|trainer.py:3353] 2024-06-04 06:44:27,410 >> Saving model checkpoint to ./training_outputs_job_116987_1_04-06_01-01
+[INFO|configuration_utils.py:471] 2024-06-04 06:44:27,424 >> Configuration saved in ./training_outputs_job_116987_1_04-06_01-01/config.json
+[INFO|configuration_utils.py:705] 2024-06-04 06:44:27,429 >> Configuration saved in ./training_outputs_job_116987_1_04-06_01-01/generation_config.json
+[INFO|modeling_utils.py:2592] 2024-06-04 06:44:28,362 >> Model weights saved in ./training_outputs_job_116987_1_04-06_01-01/model.safetensors
+[INFO|tokenization_utils_base.py:2503] 2024-06-04 06:44:28,373 >> tokenizer config file saved in ./training_outputs_job_116987_1_04-06_01-01/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2512] 2024-06-04 06:44:28,377 >> Special tokens file saved in ./training_outputs_job_116987_1_04-06_01-01/special_tokens_map.json
+[INFO|trainer.py:3353] 2024-06-04 06:44:28,428 >> Saving model checkpoint to ./training_outputs_job_116987_1_04-06_01-01
+[INFO|configuration_utils.py:471] 2024-06-04 06:44:28,432 >> Configuration saved in ./training_outputs_job_116987_1_04-06_01-01/config.json
+[INFO|configuration_utils.py:705] 2024-06-04 06:44:28,436 >> Configuration saved in ./training_outputs_job_116987_1_04-06_01-01/generation_config.json
+[INFO|modeling_utils.py:2592] 2024-06-04 06:44:29,368 >> Model weights saved in ./training_outputs_job_116987_1_04-06_01-01/model.safetensors
+[INFO|tokenization_utils_base.py:2503] 2024-06-04 06:44:29,380 >> tokenizer config file saved in ./training_outputs_job_116987_1_04-06_01-01/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2512] 2024-06-04 06:44:29,384 >> Special tokens file saved in ./training_outputs_job_116987_1_04-06_01-01/special_tokens_map.json
+[INFO|modelcard.py:450] 2024-06-04 06:44:29,735 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'metrics': [{'name': 'Accuracy', 'type': 'accuracy', 'value': 0.5811017183152439}]}
+{'eval_loss': 2.3603451251983643, 'eval_accuracy': 0.5811017183152439, 'eval_runtime': 129.0604, 'eval_samples_per_second': 14.257, 'eval_steps_per_second': 0.302, 'epoch': 2.91}
+{'train_runtime': 20556.3593, 'train_samples_per_second': 13.243, 'train_steps_per_second': 0.552, 'train_loss': 2.5941595100713495, 'epoch': 3.0}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc14bc1aa3fc1823ccb031040b9ec256d82370fb17f467cc3dc6ab295cb077f0
+oid sha256:4da20f027b42fc4101ece18c5fdcbc8330d01d2227400bc85f4697eff0c2ee26
 size 272123144