Model save

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: JackFram/llama-68m
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ShareGPT_llama2_68M
+  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. -->
+
+# ShareGPT_llama2_68M
+
+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: 2.3636
+- Accuracy: 0.5808
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- 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
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| 3.406         | 0.2644 | 1000  | 3.2345          | 0.5035   |
+| 2.8119        | 0.5288 | 2000  | 2.8214          | 0.5365   |
+| 2.607         | 0.7932 | 3000  | 2.6572          | 0.5498   |
+| 2.4734        | 1.0576 | 4000  | 2.5736          | 0.5582   |
+| 2.4335        | 1.3221 | 5000  | 2.5336          | 0.5617   |
+| 2.3858        | 1.5865 | 6000  | 2.4896          | 0.5663   |
+| 2.374         | 1.8509 | 7000  | 2.4711          | 0.5681   |
+| 2.3044        | 2.1153 | 8000  | 2.4485          | 0.5702   |
+| 2.2873        | 2.3797 | 9000  | 2.4132          | 0.5747   |
+| 2.2669        | 2.6441 | 10000 | 2.3879          | 0.5778   |
+| 2.2463        | 2.9085 | 11000 | 2.3636          | 0.5808   |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

events.out.tfevents.1717581940.isl-gpu3.8841.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8de856a1f961632671784314fe7bc2dec61ad2339a407fa3cb8f457b4d34c9
-size 13144
+oid sha256:55b54284af5abf9d627497986ff9de84b6dd7eaae5ecdd5a7498dd98e0da5e39
+size 13498

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0.dev0"
+}

log.txt

@@ -884,3 +884,140 @@ Loading cached processed dataset at /home/dshteyma/.cache/huggingface/datasets/j
 [INFO|tokenization_utils_base.py:2512] 2024-06-05 06:17:44,763 >> Special tokens file saved in ./training_outputs_job_117568_1_05-06_03-05/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 [3:12:05<2:18:29, 24.09s/it]
 97%|█████████▋| 11002/11346 [3:12:06<1:38:20, 17.15s/it]
 97%|█████████▋| 11003/11346 [3:12:07<1:10:18, 12.30s/it]
 97%|█████████▋| 11004/11346 [3:12:08<50:43,  8.90s/it]  
 97%|█████████▋| 11005/11346 [3:12:09<37:03,  6.52s/it]
 97%|█████████▋| 11006/11346 [3:12:10<27:30,  4.86s/it]
 97%|█████████▋| 11007/11346 [3:12:11<20:50,  3.69s/it]
 97%|█████████▋| 11008/11346 [3:12:12<16:11,  2.87s/it]
 97%|█████████▋| 11009/11346 [3:12:13<12:56,  2.30s/it]
 97%|█████████▋| 11010/11346 [3:12:14<10:40,  1.91s/it]
 97%|█████████▋| 11011/11346 [3:12:15<09:04,  1.62s/it]
 97%|█████████▋| 11012/11346 [3:12:16<07:57,  1.43s/it]
 97%|█████████▋| 11013/11346 [3:12:17<07:09,  1.29s/it]
 97%|█████████▋| 11014/11346 [3:12:18<06:36,  1.19s/it]
 97%|█████████▋| 11015/11346 [3:12:19<06:13,  1.13s/it]
 97%|█████████▋| 11016/11346 [3:12:20<05:56,  1.08s/it]
 97%|█████████▋| 11017/11346 [3:12:21<05:45,  1.05s/it]
 97%|█████████▋| 11018/11346 [3:12:22<05:37,  1.03s/it]
 97%|█████████▋| 11019/11346 [3:12:23<05:30,  1.01s/it]
 97%|█████████▋| 11020/11346 [3:12:24<05:26,  1.00s/it]
 97%|█████████▋| 11021/11346 [3:12:25<05:22,  1.01it/s]
 97%|█████████▋| 11022/11346 [3:12:25<05:20,  1.01it/s]
 97%|█████████▋| 11023/11346 [3:12:26<05:17,  1.02it/s]
 97%|█████████▋| 11024/11346 [3:12:27<05:15,  1.02it/s]
 97%|█████████▋| 11025/11346 [3:12:28<05:13,  1.02it/s]
 97%|█████████▋| 11026/11346 [3:12:29<05:11,  1.03it/s]
 97%|█████████▋| 11027/11346 [3:12:30<05:10,  1.03it/s]
 97%|█████████▋| 11028/11346 [3:12:31<05:09,  1.03it/s]
 97%|█████████▋| 11029/11346 [3:12:32<05:08,  1.03it/s]
 97%|█████████▋| 11030/11346 [3:12:33<05:07,  1.03it/s]
 97%|█████████▋| 11031/11346 [3:12:34<05:06,  1.03it/s]
 97%|█████████▋| 11032/11346 [3:12:35<05:05,  1.03it/s]
 97%|█████████▋| 11033/11346 [3:12:36<05:04,  1.03it/s]
 97%|█████████▋| 11034/11346 [3:12:37<05:03,  1.03it/s]
 97%|█████████▋| 11035/11346 [3:12:38<05:02,  1.03it/s]
 97%|█████████▋| 11036/11346 [3:12:39<05:01,  1.03it/s]
 97%|█████████▋| 11037/11346 [3:12:40<05:00,  1.03it/s]
 97%|█████████▋| 11038/11346 [3:12:41<04:59,  1.03it/s]
 97%|█████████▋| 11039/11346 [3:12:42<04:58,  1.03it/s]
 97%|█████████▋| 11040/11346 [3:12:43<04:57,  1.03it/s]
 97%|█████████▋| 11041/11346 [3:12:44<04:56,  1.03it/s]
 97%|█████████▋| 11042/11346 [3:12:45<04:55,  1.03it/s]
 97%|█████████▋| 11043/11346 [3:12:46<04:54,  1.03it/s]
 97%|█████████▋| 11044/11346 [3:12:47<04:53,  1.03it/s]
 97%|█████████▋| 11045/11346 [3:12:48<04:52,  1.03it/s]
 97%|█████████▋| 11046/11346 [3:12:49<04:51,  1.03it/s]
 97%|█████████▋| 11047/11346 [3:12:50<04:50,  1.03it/s]
 97%|█████████▋| 11048/11346 [3:12:51<04:49,  1.03it/s]
 97%|█████████▋| 11049/11346 [3:12:52<04:48,  1.03it/s]
 97%|█████████▋| 11050/11346 [3:12:53<04:47,  1.03it/s]
 97%|█████████▋| 11051/11346 [3:12:54<04:46,  1.03it/s]
 97%|█████████▋| 11052/11346 [3:12:55<04:45,  1.03it/s]
 97%|█████████▋| 11053/11346 [3:12:56<04:44,  1.03it/s]
 97%|█████████▋| 11054/11346 [3:12:57<04:43,  1.03it/s]
 97%|█████████▋| 11055/11346 [3:12:58<04:42,  1.03it/s]
 97%|█████████▋| 11056/11346 [3:12:59<04:41,  1.03it/s]
 97%|█████████▋| 11057/11346 [3:12:59<04:40,  1.03it/s]
 97%|█████████▋| 11058/11346 [3:13:00<04:39,  1.03it/s]
 97%|█████████▋| 11059/11346 [3:13:01<04:38,  1.03it/s]
 97%|█████████▋| 11060/11346 [3:13:02<04:37,  1.03it/s]
 97%|█████████▋| 11061/11346 [3:13:03<04:36,  1.03it/s]
 97%|█████████▋| 11062/11346 [3:13:04<04:35,  1.03it/s]
 98%|█████████▊| 11063/11346 [3:13:05<04:34,  1.03it/s]
 98%|█████████▊| 11064/11346 [3:13:06<04:33,  1.03it/s]
 98%|█████████▊| 11065/11346 [3:13:07<04:32,  1.03it/s]
 98%|█████████▊| 11066/11346 [3:13:08<04:31,  1.03it/s]
 98%|█████████▊| 11067/11346 [3:13:09<04:31,  1.03it/s]
 98%|█████████▊| 11068/11346 [3:13:10<04:30,  1.03it/s]
 98%|█████████▊| 11069/11346 [3:13:11<04:29,  1.03it/s]
 98%|█████████▊| 11070/11346 [3:13:12<04:28,  1.03it/s]
 98%|█████████▊| 11071/11346 [3:13:13<04:27,  1.03it/s]
 98%|█████████▊| 11072/11346 [3:13:14<04:26,  1.03it/s]
 98%|█████████▊| 11073/11346 [3:13:15<04:25,  1.03it/s]
 98%|█████████▊| 11074/11346 [3:13:16<04:24,  1.03it/s]
 98%|█████████▊| 11075/11346 [3:13:17<04:23,  1.03it/s]
 98%|█████████▊| 11076/11346 [3:13:18<04:22,  1.03it/s]
 98%|█████████▊| 11077/11346 [3:13:19<04:21,  1.03it/s]
 98%|█████████▊| 11078/11346 [3:13:20<04:20,  1.03it/s]
 98%|█████████▊| 11079/11346 [3:13:21<04:19,  1.03it/s]
 98%|█████████▊| 11080/11346 [3:13:22<04:18,  1.03it/s]
 98%|█████████▊| 11081/11346 [3:13:23<04:17,  1.03it/s]
 98%|█████████▊| 11082/11346 [3:13:24<04:16,  1.03it/s]
 98%|█████████▊| 11083/11346 [3:13:25<04:15,  1.03it/s]
 98%|█████████▊| 11084/11346 [3:13:26<04:14,  1.03it/s]
 98%|█████████▊| 11085/11346 [3:13:27<04:13,  1.03it/s]
 98%|█████████▊| 11086/11346 [3:13:28<04:12,  1.03it/s]
 98%|█████████▊| 11087/11346 [3:13:29<04:11,  1.03it/s]
 98%|█████████▊| 11088/11346 [3:13:30<04:10,  1.03it/s]
 98%|█████████▊| 11089/11346 [3:13:31<04:09,  1.03it/s]
 98%|█████████▊| 11090/11346 [3:13:32<04:08,  1.03it/s]
 98%|█████████▊| 11091/11346 [3:13:33<04:07,  1.03it/s]
 98%|█████████▊| 11092/11346 [3:13:34<04:06,  1.03it/s]
 98%|█████████▊| 11093/11346 [3:13:34<04:05,  1.03it/s]
 98%|█████████▊| 11094/11346 [3:13:35<04:04,  1.03it/s]
 98%|█████████▊| 11095/11346 [3:13:36<04:03,  1.03it/s]
 98%|█████████▊| 11096/11346 [3:13:37<04:02,  1.03it/s]
 98%|█████████▊| 11097/11346 [3:13:38<04:01,  1.03it/s]
 98%|█████████▊| 11098/11346 [3:13:39<04:00,  1.03it/s]
 98%|█████████▊| 11099/11346 [3:13:40<03:59,  1.03it/s]
 98%|█████████▊| 11100/11346 [3:13:41<03:58,  1.03it/s]
 98%|█████████▊| 11101/11346 [3:13:42<03:57,  1.03it/s]
 98%|█████████▊| 11102/11346 [3:13:43<03:57,  1.03it/s]
 98%|█████████▊| 11103/11346 [3:13:44<03:56,  1.03it/s]
 98%|█████████▊| 11104/11346 [3:13:45<03:55,  1.03it/s]
 98%|█████████▊| 11105/11346 [3:13:46<03:54,  1.03it/s]
 98%|█████████▊| 11106/11346 [3:13:47<03:53,  1.03it/s]
 98%|█████████▊| 11107/11346 [3:13:48<03:52,  1.03it/s]
 98%|█████████▊| 11108/11346 [3:13:49<03:51,  1.03it/s]
 98%|█████████▊| 11109/11346 [3:13:50<03:50,  1.03it/s]
 98%|█████████▊| 11110/11346 [3:13:51<03:49,  1.03it/s]
 98%|█████████▊| 11111/11346 [3:13:52<03:48,  1.03it/s]
 98%|█████████▊| 11112/11346 [3:13:53<03:47,  1.03it/s]
 98%|█████████▊| 11113/11346 [3:13:54<03:46,  1.03it/s]
 98%|█████████▊| 11114/11346 [3:13:55<03:45,  1.03it/s]
 98%|█████████▊| 11115/11346 [3:13:56<03:44,  1.03it/s]
 98%|█████████▊| 11116/11346 [3:13:57<03:43,  1.03it/s]
 98%|█████████▊| 11117/11346 [3:13:58<03:42,  1.03it/s]
 98%|█████████▊| 11118/11346 [3:13:59<03:41,  1.03it/s]
 98%|█████████▊| 11119/11346 [3:14:00<03:40,  1.03it/s]
 98%|█████████▊| 11120/11346 [3:14:01<03:39,  1.03it/s]
 98%|█████████▊| 11121/11346 [3:14:02<03:38,  1.03it/s]
 98%|█████████▊| 11122/11346 [3:14:03<03:37,  1.03it/s]
 98%|█████████▊| 11123/11346 [3:14:04<03:36,  1.03it/s]
 98%|█████████▊| 11124/11346 [3:14:05<03:35,  1.03it/s]
 98%|█████████▊| 11125/11346 [3:14:06<03:34,  1.03it/s]
 98%|█████████▊| 11126/11346 [3:14:07<03:33,  1.03it/s]
 98%|█████████▊| 11127/11346 [3:14:08<03:32,  1.03it/s]
 98%|█████���███▊| 11128/11346 [3:14:08<03:31,  1.03it/s]
 98%|█████████▊| 11129/11346 [3:14:09<03:30,  1.03it/s]
 98%|█████████▊| 11130/11346 [3:14:10<03:29,  1.03it/s]
 98%|█████████▊| 11131/11346 [3:14:11<03:28,  1.03it/s]
 98%|█████████▊| 11132/11346 [3:14:12<03:27,  1.03it/s]
 98%|█████████▊| 11133/11346 [3:14:13<03:26,  1.03it/s]
 98%|█████████▊| 11134/11346 [3:14:14<03:25,  1.03it/s]
 98%|█████████▊| 11135/11346 [3:14:15<03:24,  1.03it/s]
 98%|█████████▊| 11136/11346 [3:14:16<03:23,  1.03it/s]
 98%|█████████▊| 11137/11346 [3:14:17<03:23,  1.03it/s]
 98%|█████████▊| 11138/11346 [3:14:18<03:21,  1.03it/s]
 98%|█████████▊| 11139/11346 [3:14:19<03:21,  1.03it/s]
 98%|█████████▊| 11140/11346 [3:14:20<03:20,  1.03it/s]
 98%|█████████▊| 11141/11346 [3:14:21<03:19,  1.03it/s]
 98%|█████████▊| 11142/11346 [3:14:22<03:18,  1.03it/s]
 98%|█████████▊| 11143/11346 [3:14:23<03:17,  1.03it/s]
 98%|█████████▊| 11144/11346 [3:14:24<03:16,  1.03it/s]
 98%|█████████▊| 11145/11346 [3:14:25<03:15,  1.03it/s]
 98%|█████████▊| 11146/11346 [3:14:26<03:14,  1.03it/s]
 98%|█████████▊| 11147/11346 [3:14:27<03:13,  1.03it/s]
 98%|█████████▊| 11148/11346 [3:14:28<03:12,  1.03it/s]
 98%|█████████▊| 11149/11346 [3:14:29<03:11,  1.03it/s]
 98%|█████████▊| 11150/11346 [3:14:30<03:10,  1.03it/s]
 98%|█████████▊| 11151/11346 [3:14:31<03:09,  1.03it/s]
 98%|█████████▊| 11152/11346 [3:14:32<03:08,  1.03it/s]
 98%|█████████▊| 11153/11346 [3:14:33<03:07,  1.03it/s]
 98%|█████████▊| 11154/11346 [3:14:34<03:06,  1.03it/s]
 98%|█████████▊| 11155/11346 [3:14:35<03:05,  1.03it/s]
 98%|█████████▊| 11156/11346 [3:14:36<03:04,  1.03it/s]
 98%|█████████▊| 11157/11346 [3:14:37<03:03,  1.03it/s]
 98%|█████████▊| 11158/11346 [3:14:38<03:02,  1.03it/s]
 98%|█████████▊| 11159/11346 [3:14:39<03:01,  1.03it/s]
 98%|█████████▊| 11160/11346 [3:14:40<03:00,  1.03it/s]
 98%|█████████▊| 11161/11346 [3:14:41<02:59,  1.03it/s]
 98%|█████████▊| 11162/11346 [3:14:42<02:58,  1.03it/s]
 98%|█████████▊| 11163/11346 [3:14:42<02:57,  1.03it/s]
 98%|█████████▊| 11164/11346 [3:14:43<02:56,  1.03it/s]
 98%|█████████▊| 11165/11346 [3:14:44<02:55,  1.03it/s]
 98%|█████████▊| 11166/11346 [3:14:45<02:54,  1.03it/s]
 98%|█████████▊| 11167/11346 [3:14:46<02:53,  1.03it/s]
 98%|█████████▊| 11168/11346 [3:14:47<02:52,  1.03it/s]
 98%|█████████▊| 11169/11346 [3:14:48<02:51,  1.03it/s]
 98%|█████████▊| 11170/11346 [3:14:49<02:50,  1.03it/s]
 98%|█████████▊| 11171/11346 [3:14:50<02:49,  1.03it/s]
 98%|█████████▊| 11172/11346 [3:14:51<02:49,  1.03it/s]
 98%|█████████▊| 11173/11346 [3:14:52<02:48,  1.03it/s]
 98%|█████████▊| 11174/11346 [3:14:53<02:47,  1.03it/s]
 98%|█████████▊| 11175/11346 [3:14:54<02:46,  1.03it/s]
 99%|█████████▊| 11176/11346 [3:14:55<02:45,  1.03it/s]
 99%|█████████▊| 11177/11346 [3:14:56<02:44,  1.03it/s]
 99%|█████████▊| 11178/11346 [3:14:57<02:43,  1.03it/s]
 99%|█████████▊| 11179/11346 [3:14:58<02:42,  1.03it/s]
 99%|█████████▊| 11180/11346 [3:14:59<02:41,  1.03it/s]
 99%|█████████▊| 11181/11346 [3:15:00<02:40,  1.03it/s]
 99%|█████████▊| 11182/11346 [3:15:01<02:39,  1.03it/s]
 99%|█████████▊| 11183/11346 [3:15:02<02:38,  1.03it/s]
 99%|█████████▊| 11184/11346 [3:15:03<02:37,  1.03it/s]
 99%|█████████▊| 11185/11346 [3:15:04<02:36,  1.03it/s]
 99%|█████████▊| 11186/11346 [3:15:05<02:35,  1.03it/s]
 99%|█████████▊| 11187/11346 [3:15:06<02:34,  1.03it/s]
 99%|█████████▊| 11188/11346 [3:15:07<02:33,  1.03it/s]
 99%|█████████▊| 11189/11346 [3:15:08<02:32,  1.03it/s]
 99%|█████████▊| 11190/11346 [3:15:09<02:31,  1.03it/s]
 99%|█████████▊| 11191/11346 [3:15:10<02:30,  1.03it/s]
 99%|█████████▊| 11192/11346 [3:15:11<02:30,  1.03it/s]
 99%|█████████▊| 11193/11346 [3:15:12<02:29,  1.03it/s]
 99%|█████████▊| 11194/11346 [3:15:13<02:28,  1.03it/s]
 99%|█████████▊| 11195/11346 [3:15:14<02:26,  1.03it/s]
 99%|█████████▊| 11196/11346 [3:15:15<02:25,  1.03it/s]
 99%|█████████▊| 11197/11346 [3:15:16<02:24,  1.03it/s]
 99%|█████████▊| 11198/11346 [3:15:17<02:23,  1.03it/s]
 99%|█████████▊| 11199/11346 [3:15:17<02:22,  1.03it/s]
 99%|█████████▊| 11200/11346 [3:15:18<02:21,  1.03it/s]
 99%|█████████▊| 11201/11346 [3:15:19<02:20,  1.03it/s]
 99%|█████████▊| 11202/11346 [3:15:20<02:20,  1.03it/s]
 99%|█████████▊| 11203/11346 [3:15:21<02:19,  1.03it/s]
 99%|█████████▊| 11204/11346 [3:15:22<02:18,  1.03it/s]
 99%|█████████▉| 11205/11346 [3:15:23<02:17,  1.03it/s]
 99%|█████████▉| 11206/11346 [3:15:24<02:16,  1.03it/s]
 99%|█████████▉| 11207/11346 [3:15:25<02:15,  1.03it/s]
 99%|█████████▉| 11208/11346 [3:15:26<02:14,  1.03it/s]
 99%|█████████▉| 11209/11346 [3:15:27<02:13,  1.03it/s]
 99%|█████████▉| 11210/11346 [3:15:28<02:12,  1.03it/s]
 99%|█████████▉| 11211/11346 [3:15:29<02:11,  1.03it/s]
 99%|█████████▉| 11212/11346 [3:15:30<02:10,  1.03it/s]
 99%|█████████▉| 11213/11346 [3:15:31<02:09,  1.03it/s]
 99%|█████████▉| 11214/11346 [3:15:32<02:08,  1.03it/s]
 99%|█████████▉| 11215/11346 [3:15:33<02:07,  1.03it/s]
 99%|█████████▉| 11216/11346 [3:15:34<02:06,  1.03it/s]
 99%|█████████▉| 11217/11346 [3:15:35<02:05,  1.03it/s]
 99%|█████████▉| 11218/11346 [3:15:36<02:04,  1.03it/s]
 99%|█████████▉| 11219/11346 [3:15:37<02:03,  1.03it/s]
 99%|█████████▉| 11220/11346 [3:15:38<02:02,  1.03it/s]
 99%|█████████▉| 11221/11346 [3:15:39<02:01,  1.03it/s]
 99%|█████████▉| 11222/11346 [3:15:40<02:00,  1.03it/s]
 99%|█████████▉| 11223/11346 [3:15:41<01:59,  1.03it/s]
 99%|█████████▉| 11224/11346 [3:15:42<01:58,  1.03it/s]
 99%|█████████▉| 11225/11346 [3:15:43<01:57,  1.03it/s]
 99%|█████████▉| 11226/11346 [3:15:44<01:56,  1.03it/s]
 99%|█████████▉| 11227/11346 [3:15:45<01:55,  1.03it/s]
 99%|█████████▉| 11228/11346 [3:15:46<01:54,  1.03it/s]
 99%|█████████▉| 11229/11346 [3:15:47<01:53,  1.03it/s]
 99%|█████████▉| 11230/11346 [3:15:48<01:52,  1.03it/s]
 99%|█████████▉| 11231/11346 [3:15:49<01:51,  1.03it/s]
 99%|█████████▉| 11232/11346 [3:15:50<01:50,  1.03it/s]
 99%|█████████▉| 11233/11346 [3:15:51<01:49,  1.03it/s]
 99%|█████████▉| 11234/11346 [3:15:52<01:48,  1.03it/s]
 99%|█████████▉| 11235/11346 [3:15:52<01:47,  1.03it/s]
 99%|█████████▉| 11236/11346 [3:15:53<01:46,  1.03it/s]
 99%|█████████▉| 11237/11346 [3:15:54<01:45,  1.03it/s]
 99%|█████████▉| 11238/11346 [3:15:55<01:44,  1.03it/s]
 99%|█████████▉| 11239/11346 [3:15:56<01:43,  1.03it/s]
 99%|█████████▉| 11240/11346 [3:15:57<01:43,  1.03it/s]
 99%|█████████▉| 11241/11346 [3:15:58<01:42,  1.03it/s]
 99%|█████████▉| 11242/11346 [3:15:59<01:41,  1.03it/s]
 99%|█████████▉| 11243/11346 [3:16:00<01:40,  1.03it/s]
 99%|█████████▉| 11244/11346 [3:16:01<01:39,  1.03it/s]
 99%|█████████▉| 11245/11346 [3:16:02<01:38,  1.03it/s]
 99%|█████████▉| 11246/11346 [3:16:03<01:37,  1.03it/s]
 99%|█████████▉| 11247/11346 [3:16:04<01:36,  1.03it/s]
 99%|█████████▉| 11248/11346 [3:16:05<01:35,  1.03it/s]
 99%|█████████▉| 11249/11346 [3:16:06<01:34,  1.03it/s]
 99%|█████████▉| 11250/11346 [3:16:07<01:33,  1.03it/s]
 99%|█████████▉| 11251/11346 [3:16:08<01:32,  1.03it/s]
 99%|█████████▉| 11252/11346 [3:16:09<01:31,  1.03it/s]
 99%|█████████▉| 11253/11346 [3:16:10<01:30,  1.03it/s]
 99%|█████████▉| 11254/11346 [3:16:11<01:29,  1.03it/s]
 99%|█████████▉| 11255/11346 [3:16:12<01:28,  1.03it/s]
 99%|█████████▉| 11256/11346 [3:16:13<01:27,  1.03it/s]
 99%|█████████▉| 11257/11346 [3:16:14<01:26,  1.03it/s]
 99%|█████████▉| 11258/11346 [3:16:15<01:25,  1.03it/s]
 99%|█████████▉| 11259/11346 [3:16:16<01:24,  1.03it/s]
 99%|█████████▉| 11260/11346 [3:16:17<01:23,  1.03it/s]
 99%|█████████▉| 11261/11346 [3:16:18<01:22,  1.03it/s]
 99%|█████████▉| 11262/11346 [3:16:19<01:21,  1.03it/s]
 99%|█████████▉| 11263/11346 [3:16:20<01:20,  1.03it/s]
 99%|█████████▉| 11264/11346 [3:16:21<01:19,  1.03it/s]
 99%|█████████▉| 11265/11346 [3:16:22<01:18,  1.03it/s]
 99%|█████████▉| 11266/11346 [3:16:23<01:17,  1.03it/s]
 99%|█████████▉| 11267/11346 [3:16:24<01:16,  1.03it/s]
 99%|█████████▉| 11268/11346 [3:16:25<01:15,  1.03it/s]
 99%|█████████▉| 11269/11346 [3:16:26<01:14,  1.03it/s]
 99%|█████████▉| 11270/11346 [3:16:27<01:13,  1.03it/s]
 99%|█████████▉| 11271/11346 [3:16:27<01:12,  1.03it/s]
 99%|█████████▉| 11272/11346 [3:16:28<01:11,  1.03it/s]
 99%|█████████▉| 11273/11346 [3:16:29<01:10,  1.03it/s]
 99%|█████████▉| 11274/11346 [3:16:30<01:09,  1.03it/s]
 99%|█████████▉| 11275/11346 [3:16:31<01:08,  1.03it/s]
 99%|█████████▉| 11276/11346 [3:16:32<01:07,  1.03it/s]
 99%|█████████▉| 11277/11346 [3:16:33<01:07,  1.03it/s]
 99%|█████████▉| 11278/11346 [3:16:34<01:06,  1.03it/s]
 99%|█████████▉| 11279/11346 [3:16:35<01:05,  1.03it/s]
 99%|█████████▉| 11280/11346 [3:16:36<01:04,  1.03it/s]
 99%|█████████▉| 11281/11346 [3:16:37<01:03,  1.03it/s]
 99%|█████████▉| 11282/11346 [3:16:38<01:02,  1.03it/s]
 99%|█████████▉| 11283/11346 [3:16:39<01:01,  1.03it/s]
 99%|█████████▉| 11284/11346 [3:16:40<01:00,  1.03it/s]
 99%|█████████▉| 11285/11346 [3:16:41<00:59,  1.03it/s]
 99%|█████████▉| 11286/11346 [3:16:42<00:58,  1.03it/s]
 99%|█████████▉| 11287/11346 [3:16:43<00:57,  1.03it/s]
 99%|█████████▉| 11288/11346 [3:16:44<00:56,  1.03it/s]
 99%|█████████▉| 11289/11346 [3:16:45<00:55,  1.03it/s]
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
                                                       
+[INFO|trainer.py:3353] 2024-06-05 06:23:20,294 >> Saving model checkpoint to ./training_outputs_job_117568_1_05-06_03-05
+[INFO|configuration_utils.py:471] 2024-06-05 06:23:20,311 >> Configuration saved in ./training_outputs_job_117568_1_05-06_03-05/config.json
+[INFO|configuration_utils.py:705] 2024-06-05 06:23:20,317 >> Configuration saved in ./training_outputs_job_117568_1_05-06_03-05/generation_config.json
+[INFO|modeling_utils.py:2592] 2024-06-05 06:23:21,244 >> Model weights saved in ./training_outputs_job_117568_1_05-06_03-05/model.safetensors
+[INFO|tokenization_utils_base.py:2503] 2024-06-05 06:23:21,257 >> tokenizer config file saved in ./training_outputs_job_117568_1_05-06_03-05/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2512] 2024-06-05 06:23:21,262 >> Special tokens file saved in ./training_outputs_job_117568_1_05-06_03-05/special_tokens_map.json
+[INFO|trainer.py:3353] 2024-06-05 06:23:21,329 >> Saving model checkpoint to ./training_outputs_job_117568_1_05-06_03-05
+[INFO|configuration_utils.py:471] 2024-06-05 06:23:21,336 >> Configuration saved in ./training_outputs_job_117568_1_05-06_03-05/config.json
+[INFO|configuration_utils.py:705] 2024-06-05 06:23:21,341 >> Configuration saved in ./training_outputs_job_117568_1_05-06_03-05/generation_config.json
+[INFO|modeling_utils.py:2592] 2024-06-05 06:23:22,285 >> Model weights saved in ./training_outputs_job_117568_1_05-06_03-05/model.safetensors
+[INFO|tokenization_utils_base.py:2503] 2024-06-05 06:23:22,298 >> tokenizer config file saved in ./training_outputs_job_117568_1_05-06_03-05/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2512] 2024-06-05 06:23:22,300 >> Special tokens file saved in ./training_outputs_job_117568_1_05-06_03-05/special_tokens_map.json
+[INFO|modelcard.py:450] 2024-06-05 06:23:22,687 >> 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': 0.5807555064675771}]}
+{'eval_loss': 2.363588571548462, 'eval_accuracy': 0.5807555064675771, 'eval_runtime': 73.5703, 'eval_samples_per_second': 25.01, 'eval_steps_per_second': 0.53, 'epoch': 2.91}
+{'train_runtime': 11859.9653, 'train_samples_per_second': 22.954, 'train_steps_per_second': 0.957, 'train_loss': 2.595605703293699, 'epoch': 3.0}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e903c8192088cc20bfbad6524ded36e628b87bdc9a0177b9a612910063e0a56
+oid sha256:a17359d967a2437a262b86ae9b99694739acb6f6f3f1ccd934e818c0a27e6539
 size 272123144