Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - generated_from_trainer
 - dataset_size:10635
 - loss:MultipleNegativesSymmetricRankingLoss
-base_model: microsoft/mpnet-base
+base_model: sentence-transformers/all-mpnet-base-v2
 widget:
 - source_sentence: '12 Rules For Life: An Antidote to Chaos by Jordan B. Peterson'
   sentences:
@@ -40,16 +40,16 @@ pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
 
-# SentenceTransformer based on microsoft/mpnet-base
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the train dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the train dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
-- **Maximum Sequence Length:** 512 tokens
+- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 -->
+- **Maximum Sequence Length:** 384 tokens
 - **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
@@ -67,8 +67,9 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [m
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
   (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
 )
 ```
 
@@ -201,7 +202,7 @@ You can finetune this model on your own dataset.
 - `per_device_train_batch_size`: 16
 - `per_device_eval_batch_size`: 16
 - `learning_rate`: 2e-05
-- `num_train_epochs`: 10
+- `num_train_epochs`: 7
 - `warmup_ratio`: 0.1
 
 #### All Hyperparameters
@@ -224,7 +225,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 10
+- `num_train_epochs`: 7
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -326,49 +327,27 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss | train loss |
 |:------:|:----:|:-------------:|:----------:|
-| 0.3008 | 200  | 2.8113        | 2.0799     |
-| 0.6015 | 400  | 2.0877        | 1.9239     |
-| 0.9023 | 600  | 1.9258        | 1.8882     |
-| 1.2030 | 800  | 1.7382        | 1.8684     |
-| 1.5038 | 1000 | 1.7232        | 1.8226     |
-| 1.8045 | 1200 | 1.6814        | 1.8167     |
-| 2.1053 | 1400 | 1.5764        | 1.8133     |
-| 2.4060 | 1600 | 1.5333        | 1.7898     |
-| 2.7068 | 1800 | 1.5216        | 1.7782     |
-| 3.0075 | 2000 | 1.4966        | 1.7663     |
-| 3.3083 | 2200 | 1.4325        | 1.7642     |
-| 3.6090 | 2400 | 1.4043        | 1.7956     |
-| 3.9098 | 2600 | 1.4212        | 1.7609     |
-| 4.2105 | 2800 | 1.3808        | 1.7611     |
-| 4.5113 | 3000 | 1.35          | 1.7671     |
-| 4.8120 | 3200 | 1.3644        | 1.7517     |
-| 5.1128 | 3400 | 1.304         | 1.7712     |
-| 5.4135 | 3600 | 1.288         | 1.7820     |
-| 5.7143 | 3800 | 1.3051        | 1.7699     |
-| 6.0150 | 4000 | 1.2803        | 1.7678     |
-| 6.3158 | 4200 | 1.2026        | 1.7812     |
-| 6.6165 | 4400 | 1.2602        | 1.7846     |
-| 6.9173 | 4600 | 1.2392        | 1.7733     |
-| 7.2180 | 4800 | 1.2088        | 1.7745     |
-| 7.5188 | 5000 | 1.1791        | 1.7867     |
-| 7.8195 | 5200 | 1.1946        | 1.7779     |
-| 8.1203 | 5400 | 1.1617        | 1.7931     |
-| 8.4211 | 5600 | 1.1495        | 1.7911     |
-| 8.7218 | 5800 | 1.1635        | 1.7949     |
-| 9.0226 | 6000 | 1.1324        | 1.7962     |
-| 9.3233 | 6200 | 1.1304        | 1.8035     |
-| 9.6241 | 6400 | 1.1126        | 1.8056     |
-| 9.9248 | 6600 | 1.0986        | 1.8062     |
+| 0.6006 | 200  | 2.5755        | 2.4113     |
+| 1.2012 | 400  | 2.2395        | 2.3553     |
+| 1.8018 | 600  | 2.0813        | 2.3290     |
+| 2.4024 | 800  | 1.9813        | 2.3169     |
+| 3.0030 | 1000 | 1.9233        | 2.3081     |
+| 3.6036 | 1200 | 1.8338        | 2.3076     |
+| 4.2042 | 1400 | 1.8029        | 2.3380     |
+| 4.8048 | 1600 | 1.7766        | 2.3005     |
+| 5.4054 | 1800 | 1.722         | 2.3254     |
+| 6.0060 | 2000 | 1.7217        | 2.3215     |
+| 6.6066 | 2200 | 1.6759        | 2.3322     |
 
 
 ### Framework Versions
 - Python: 3.10.12
 - Sentence Transformers: 4.1.0
 - Transformers: 4.52.4
-- PyTorch: 2.6.0+cu124
+- PyTorch: 2.5.1+cu124
 - Accelerate: 1.8.1
 - Datasets: 3.6.0
-- Tokenizers: 0.21.1
+- Tokenizers: 0.21.2
 
 ## Citation
 

config_sentence_transformers.json

@@ -2,7 +2,7 @@
   "__version__": {
     "sentence_transformers": "4.1.0",
     "transformers": "4.52.4",
-    "pytorch": "2.6.0+cu124"
+    "pytorch": "2.5.1+cu124"
   },
   "prompts": {},
   "default_prompt_name": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070b8e311a59229e3d1911753c8912809c4b6c99f9cf43c46f1c8ac5dfe915e0
+oid sha256:2ddbdb6468cca74299465849d3460bd26cc567441655d3084af35bb3acd7144e
 size 437967672

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636d83f75ef3b6379d2de1380140e9e6db0862aa30c2f61df168fa48a5f11f94
-size 871331770
+oid sha256:43f6626a50f5d4a1fe140af797071be81b4523615afa4e4b6d5795ee9ef59320
+size 876058170

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784b875c2b86372c41eaa4d7d8efaa50c3c0a99edec1ace8f8b943345f97b54f
+oid sha256:e9887d9179089333ff9b4030c7aa932e0435c5243b5cc42026e85559ac64ae3e
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b9b94e19b7c7a2fcd96ee21ab65fa9d6c05333276c875f55a40f3bff2d6f6f
+oid sha256:190fc72819eea0b8f2844c8816cd0625c6bce70b27c2d3b3ce154d7ea3cae54a
 size 1064

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 384,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -9,7 +9,7 @@
   "cls_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -37,7 +37,7 @@
   "sep_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 384,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -56,11 +56,18 @@
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

trainer_state.json

@@ -2,513 +2,183 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 7.0,
   "eval_steps": 200,
-  "global_step": 6650,
+  "global_step": 2331,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.3007518796992481,
-      "grad_norm": 23.491586685180664,
-      "learning_rate": 5.984962406015038e-06,
-      "loss": 2.8113,
+      "epoch": 0.6006006006006006,
+      "grad_norm": 9.713151931762695,
+      "learning_rate": 1.700854700854701e-05,
+      "loss": 2.5755,
       "step": 200
     },
     {
-      "epoch": 0.3007518796992481,
-      "eval_train_loss": 2.0799365043640137,
-      "eval_train_runtime": 5.0075,
-      "eval_train_samples_per_second": 1070.204,
-      "eval_train_steps_per_second": 66.9,
+      "epoch": 0.6006006006006006,
+      "eval_train_loss": 2.4112653732299805,
+      "eval_train_runtime": 16.1652,
+      "eval_train_samples_per_second": 331.515,
+      "eval_train_steps_per_second": 10.393,
       "step": 200
     },
     {
-      "epoch": 0.6015037593984962,
-      "grad_norm": 34.29732131958008,
-      "learning_rate": 1.2e-05,
-      "loss": 2.0877,
+      "epoch": 1.2012012012012012,
+      "grad_norm": 8.402304649353027,
+      "learning_rate": 1.8426323319027183e-05,
+      "loss": 2.2395,
       "step": 400
     },
     {
-      "epoch": 0.6015037593984962,
-      "eval_train_loss": 1.923947811126709,
-      "eval_train_runtime": 5.0362,
-      "eval_train_samples_per_second": 1064.098,
-      "eval_train_steps_per_second": 66.519,
+      "epoch": 1.2012012012012012,
+      "eval_train_loss": 2.3553037643432617,
+      "eval_train_runtime": 16.1973,
+      "eval_train_samples_per_second": 330.857,
+      "eval_train_steps_per_second": 10.372,
       "step": 400
     },
     {
-      "epoch": 0.9022556390977443,
-      "grad_norm": 38.32964324951172,
-      "learning_rate": 1.8015037593984962e-05,
-      "loss": 1.9258,
+      "epoch": 1.8018018018018018,
+      "grad_norm": 8.638038635253906,
+      "learning_rate": 1.6518836432999526e-05,
+      "loss": 2.0813,
       "step": 600
     },
     {
-      "epoch": 0.9022556390977443,
-      "eval_train_loss": 1.888200283050537,
-      "eval_train_runtime": 4.9999,
-      "eval_train_samples_per_second": 1071.817,
-      "eval_train_steps_per_second": 67.001,
+      "epoch": 1.8018018018018018,
+      "eval_train_loss": 2.3290350437164307,
+      "eval_train_runtime": 15.8942,
+      "eval_train_samples_per_second": 337.167,
+      "eval_train_steps_per_second": 10.57,
       "step": 600
     },
     {
-      "epoch": 1.2030075187969924,
-      "grad_norm": 15.528878211975098,
-      "learning_rate": 1.9552213868003343e-05,
-      "loss": 1.7382,
+      "epoch": 2.4024024024024024,
+      "grad_norm": 8.17331314086914,
+      "learning_rate": 1.4611349546971865e-05,
+      "loss": 1.9813,
       "step": 800
     },
     {
-      "epoch": 1.2030075187969924,
-      "eval_train_loss": 1.8683608770370483,
-      "eval_train_runtime": 5.0138,
-      "eval_train_samples_per_second": 1068.861,
-      "eval_train_steps_per_second": 66.816,
+      "epoch": 2.4024024024024024,
+      "eval_train_loss": 2.316850423812866,
+      "eval_train_runtime": 16.4597,
+      "eval_train_samples_per_second": 325.584,
+      "eval_train_steps_per_second": 10.207,
       "step": 800
     },
     {
-      "epoch": 1.5037593984962405,
-      "grad_norm": 13.27901554107666,
-      "learning_rate": 1.8883876357560568e-05,
-      "loss": 1.7232,
+      "epoch": 3.003003003003003,
+      "grad_norm": 8.972688674926758,
+      "learning_rate": 1.2703862660944206e-05,
+      "loss": 1.9233,
       "step": 1000
     },
     {
-      "epoch": 1.5037593984962405,
-      "eval_train_loss": 1.8225561380386353,
-      "eval_train_runtime": 5.0119,
-      "eval_train_samples_per_second": 1069.261,
-      "eval_train_steps_per_second": 66.841,
+      "epoch": 3.003003003003003,
+      "eval_train_loss": 2.3080697059631348,
+      "eval_train_runtime": 16.059,
+      "eval_train_samples_per_second": 333.707,
+      "eval_train_steps_per_second": 10.461,
       "step": 1000
     },
     {
-      "epoch": 1.8045112781954886,
-      "grad_norm": 11.53130054473877,
-      "learning_rate": 1.8215538847117796e-05,
-      "loss": 1.6814,
+      "epoch": 3.6036036036036037,
+      "grad_norm": 8.94318962097168,
+      "learning_rate": 1.0796375774916547e-05,
+      "loss": 1.8338,
       "step": 1200
     },
     {
-      "epoch": 1.8045112781954886,
-      "eval_train_loss": 1.8166730403900146,
-      "eval_train_runtime": 5.0134,
-      "eval_train_samples_per_second": 1068.945,
-      "eval_train_steps_per_second": 66.822,
+      "epoch": 3.6036036036036037,
+      "eval_train_loss": 2.3076283931732178,
+      "eval_train_runtime": 16.1704,
+      "eval_train_samples_per_second": 331.408,
+      "eval_train_steps_per_second": 10.389,
       "step": 1200
     },
     {
-      "epoch": 2.1052631578947367,
-      "grad_norm": 14.417011260986328,
-      "learning_rate": 1.754720133667502e-05,
-      "loss": 1.5764,
+      "epoch": 4.2042042042042045,
+      "grad_norm": 10.612234115600586,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.8029,
       "step": 1400
     },
     {
-      "epoch": 2.1052631578947367,
-      "eval_train_loss": 1.8132838010787964,
-      "eval_train_runtime": 5.0144,
-      "eval_train_samples_per_second": 1068.73,
-      "eval_train_steps_per_second": 66.808,
+      "epoch": 4.2042042042042045,
+      "eval_train_loss": 2.337951183319092,
+      "eval_train_runtime": 16.2105,
+      "eval_train_samples_per_second": 330.588,
+      "eval_train_steps_per_second": 10.364,
       "step": 1400
     },
     {
-      "epoch": 2.406015037593985,
-      "grad_norm": 11.700883865356445,
-      "learning_rate": 1.6878863826232248e-05,
-      "loss": 1.5333,
+      "epoch": 4.804804804804805,
+      "grad_norm": 8.080140113830566,
+      "learning_rate": 6.981402002861231e-06,
+      "loss": 1.7766,
       "step": 1600
     },
     {
-      "epoch": 2.406015037593985,
-      "eval_train_loss": 1.7898207902908325,
-      "eval_train_runtime": 5.0228,
-      "eval_train_samples_per_second": 1066.927,
-      "eval_train_steps_per_second": 66.695,
+      "epoch": 4.804804804804805,
+      "eval_train_loss": 2.300466775894165,
+      "eval_train_runtime": 16.2606,
+      "eval_train_samples_per_second": 329.569,
+      "eval_train_steps_per_second": 10.332,
       "step": 1600
     },
     {
-      "epoch": 2.706766917293233,
-      "grad_norm": 13.112250328063965,
-      "learning_rate": 1.6210526315789473e-05,
-      "loss": 1.5216,
+      "epoch": 5.405405405405405,
+      "grad_norm": 8.161681175231934,
+      "learning_rate": 5.073915116833572e-06,
+      "loss": 1.722,
       "step": 1800
     },
     {
-      "epoch": 2.706766917293233,
-      "eval_train_loss": 1.7781648635864258,
-      "eval_train_runtime": 5.0052,
-      "eval_train_samples_per_second": 1070.687,
-      "eval_train_steps_per_second": 66.93,
+      "epoch": 5.405405405405405,
+      "eval_train_loss": 2.325410842895508,
+      "eval_train_runtime": 16.2864,
+      "eval_train_samples_per_second": 329.047,
+      "eval_train_steps_per_second": 10.315,
       "step": 1800
     },
     {
-      "epoch": 3.007518796992481,
-      "grad_norm": 11.557127952575684,
-      "learning_rate": 1.55421888053467e-05,
-      "loss": 1.4966,
+      "epoch": 6.006006006006006,
+      "grad_norm": 9.505444526672363,
+      "learning_rate": 3.1664282308059137e-06,
+      "loss": 1.7217,
       "step": 2000
     },
     {
-      "epoch": 3.007518796992481,
-      "eval_train_loss": 1.7662715911865234,
-      "eval_train_runtime": 5.0354,
-      "eval_train_samples_per_second": 1064.268,
-      "eval_train_steps_per_second": 66.529,
+      "epoch": 6.006006006006006,
+      "eval_train_loss": 2.3215274810791016,
+      "eval_train_runtime": 15.9019,
+      "eval_train_samples_per_second": 337.003,
+      "eval_train_steps_per_second": 10.565,
       "step": 2000
     },
     {
-      "epoch": 3.308270676691729,
-      "grad_norm": 10.65110969543457,
-      "learning_rate": 1.4873851294903927e-05,
-      "loss": 1.4325,
+      "epoch": 6.606606606606607,
+      "grad_norm": 11.631622314453125,
+      "learning_rate": 1.2589413447782547e-06,
+      "loss": 1.6759,
       "step": 2200
     },
     {
-      "epoch": 3.308270676691729,
-      "eval_train_loss": 1.764186143875122,
-      "eval_train_runtime": 5.0269,
-      "eval_train_samples_per_second": 1066.066,
-      "eval_train_steps_per_second": 66.642,
+      "epoch": 6.606606606606607,
+      "eval_train_loss": 2.3322482109069824,
+      "eval_train_runtime": 15.9374,
+      "eval_train_samples_per_second": 336.253,
+      "eval_train_steps_per_second": 10.541,
       "step": 2200
-    },
-    {
-      "epoch": 3.6090225563909772,
-      "grad_norm": 11.466296195983887,
-      "learning_rate": 1.4205513784461153e-05,
-      "loss": 1.4043,
-      "step": 2400
-    },
-    {
-      "epoch": 3.6090225563909772,
-      "eval_train_loss": 1.7955785989761353,
-      "eval_train_runtime": 5.06,
-      "eval_train_samples_per_second": 1059.097,
-      "eval_train_steps_per_second": 66.206,
-      "step": 2400
-    },
-    {
-      "epoch": 3.909774436090226,
-      "grad_norm": 9.564383506774902,
-      "learning_rate": 1.353717627401838e-05,
-      "loss": 1.4212,
-      "step": 2600
-    },
-    {
-      "epoch": 3.909774436090226,
-      "eval_train_loss": 1.7609018087387085,
-      "eval_train_runtime": 5.0402,
-      "eval_train_samples_per_second": 1063.247,
-      "eval_train_steps_per_second": 66.465,
-      "step": 2600
-    },
-    {
-      "epoch": 4.2105263157894735,
-      "grad_norm": 12.078660011291504,
-      "learning_rate": 1.2868838763575606e-05,
-      "loss": 1.3808,
-      "step": 2800
-    },
-    {
-      "epoch": 4.2105263157894735,
-      "eval_train_loss": 1.7610782384872437,
-      "eval_train_runtime": 5.0859,
-      "eval_train_samples_per_second": 1053.692,
-      "eval_train_steps_per_second": 65.868,
-      "step": 2800
-    },
-    {
-      "epoch": 4.511278195488722,
-      "grad_norm": 10.561222076416016,
-      "learning_rate": 1.2200501253132832e-05,
-      "loss": 1.35,
-      "step": 3000
-    },
-    {
-      "epoch": 4.511278195488722,
-      "eval_train_loss": 1.7670680284500122,
-      "eval_train_runtime": 5.0558,
-      "eval_train_samples_per_second": 1059.976,
-      "eval_train_steps_per_second": 66.261,
-      "step": 3000
-    },
-    {
-      "epoch": 4.81203007518797,
-      "grad_norm": 14.785975456237793,
-      "learning_rate": 1.1532163742690059e-05,
-      "loss": 1.3644,
-      "step": 3200
-    },
-    {
-      "epoch": 4.81203007518797,
-      "eval_train_loss": 1.751652479171753,
-      "eval_train_runtime": 5.0835,
-      "eval_train_samples_per_second": 1054.196,
-      "eval_train_steps_per_second": 65.9,
-      "step": 3200
-    },
-    {
-      "epoch": 5.112781954887218,
-      "grad_norm": 10.927189826965332,
-      "learning_rate": 1.0863826232247285e-05,
-      "loss": 1.304,
-      "step": 3400
-    },
-    {
-      "epoch": 5.112781954887218,
-      "eval_train_loss": 1.7712498903274536,
-      "eval_train_runtime": 5.0673,
-      "eval_train_samples_per_second": 1057.559,
-      "eval_train_steps_per_second": 66.11,
-      "step": 3400
-    },
-    {
-      "epoch": 5.413533834586466,
-      "grad_norm": 14.33267879486084,
-      "learning_rate": 1.0195488721804511e-05,
-      "loss": 1.288,
-      "step": 3600
-    },
-    {
-      "epoch": 5.413533834586466,
-      "eval_train_loss": 1.7820113897323608,
-      "eval_train_runtime": 5.086,
-      "eval_train_samples_per_second": 1053.672,
-      "eval_train_steps_per_second": 65.867,
-      "step": 3600
-    },
-    {
-      "epoch": 5.714285714285714,
-      "grad_norm": 11.89034366607666,
-      "learning_rate": 9.527151211361737e-06,
-      "loss": 1.3051,
-      "step": 3800
-    },
-    {
-      "epoch": 5.714285714285714,
-      "eval_train_loss": 1.7699248790740967,
-      "eval_train_runtime": 5.1253,
-      "eval_train_samples_per_second": 1045.605,
-      "eval_train_steps_per_second": 65.363,
-      "step": 3800
-    },
-    {
-      "epoch": 6.015037593984962,
-      "grad_norm": 10.595609664916992,
-      "learning_rate": 8.858813700918964e-06,
-      "loss": 1.2803,
-      "step": 4000
-    },
-    {
-      "epoch": 6.015037593984962,
-      "eval_train_loss": 1.7678076028823853,
-      "eval_train_runtime": 5.1035,
-      "eval_train_samples_per_second": 1050.07,
-      "eval_train_steps_per_second": 65.642,
-      "step": 4000
-    },
-    {
-      "epoch": 6.315789473684211,
-      "grad_norm": 14.781892776489258,
-      "learning_rate": 8.190476190476192e-06,
-      "loss": 1.2026,
-      "step": 4200
-    },
-    {
-      "epoch": 6.315789473684211,
-      "eval_train_loss": 1.7812011241912842,
-      "eval_train_runtime": 5.1217,
-      "eval_train_samples_per_second": 1046.331,
-      "eval_train_steps_per_second": 65.408,
-      "step": 4200
-    },
-    {
-      "epoch": 6.616541353383458,
-      "grad_norm": 11.254812240600586,
-      "learning_rate": 7.522138680033417e-06,
-      "loss": 1.2602,
-      "step": 4400
-    },
-    {
-      "epoch": 6.616541353383458,
-      "eval_train_loss": 1.7846208810806274,
-      "eval_train_runtime": 5.1259,
-      "eval_train_samples_per_second": 1045.481,
-      "eval_train_steps_per_second": 65.355,
-      "step": 4400
-    },
-    {
-      "epoch": 6.917293233082707,
-      "grad_norm": 9.643959999084473,
-      "learning_rate": 6.8538011695906435e-06,
-      "loss": 1.2392,
-      "step": 4600
-    },
-    {
-      "epoch": 6.917293233082707,
-      "eval_train_loss": 1.7733409404754639,
-      "eval_train_runtime": 5.1326,
-      "eval_train_samples_per_second": 1044.114,
-      "eval_train_steps_per_second": 65.269,
-      "step": 4600
-    },
-    {
-      "epoch": 7.2180451127819545,
-      "grad_norm": 12.258922576904297,
-      "learning_rate": 6.18546365914787e-06,
-      "loss": 1.2088,
-      "step": 4800
-    },
-    {
-      "epoch": 7.2180451127819545,
-      "eval_train_loss": 1.7745392322540283,
-      "eval_train_runtime": 5.1493,
-      "eval_train_samples_per_second": 1040.714,
-      "eval_train_steps_per_second": 65.057,
-      "step": 4800
-    },
-    {
-      "epoch": 7.518796992481203,
-      "grad_norm": 12.351716041564941,
-      "learning_rate": 5.517126148705096e-06,
-      "loss": 1.1791,
-      "step": 5000
-    },
-    {
-      "epoch": 7.518796992481203,
-      "eval_train_loss": 1.7866636514663696,
-      "eval_train_runtime": 5.144,
-      "eval_train_samples_per_second": 1041.787,
-      "eval_train_steps_per_second": 65.124,
-      "step": 5000
-    },
-    {
-      "epoch": 7.819548872180452,
-      "grad_norm": 15.052789688110352,
-      "learning_rate": 4.8487886382623224e-06,
-      "loss": 1.1946,
-      "step": 5200
-    },
-    {
-      "epoch": 7.819548872180452,
-      "eval_train_loss": 1.7778518199920654,
-      "eval_train_runtime": 5.1357,
-      "eval_train_samples_per_second": 1043.481,
-      "eval_train_steps_per_second": 65.23,
-      "step": 5200
-    },
-    {
-      "epoch": 8.1203007518797,
-      "grad_norm": 8.957300186157227,
-      "learning_rate": 4.18045112781955e-06,
-      "loss": 1.1617,
-      "step": 5400
-    },
-    {
-      "epoch": 8.1203007518797,
-      "eval_train_loss": 1.7931042909622192,
-      "eval_train_runtime": 5.1877,
-      "eval_train_samples_per_second": 1033.016,
-      "eval_train_steps_per_second": 64.576,
-      "step": 5400
-    },
-    {
-      "epoch": 8.421052631578947,
-      "grad_norm": 13.89137077331543,
-      "learning_rate": 3.5121136173767755e-06,
-      "loss": 1.1495,
-      "step": 5600
-    },
-    {
-      "epoch": 8.421052631578947,
-      "eval_train_loss": 1.791070818901062,
-      "eval_train_runtime": 5.1363,
-      "eval_train_samples_per_second": 1043.352,
-      "eval_train_steps_per_second": 65.222,
-      "step": 5600
-    },
-    {
-      "epoch": 8.721804511278195,
-      "grad_norm": 11.32971477508545,
-      "learning_rate": 2.8437761069340018e-06,
-      "loss": 1.1635,
-      "step": 5800
-    },
-    {
-      "epoch": 8.721804511278195,
-      "eval_train_loss": 1.794918417930603,
-      "eval_train_runtime": 5.1728,
-      "eval_train_samples_per_second": 1035.991,
-      "eval_train_steps_per_second": 64.762,
-      "step": 5800
-    },
-    {
-      "epoch": 9.022556390977444,
-      "grad_norm": 13.075417518615723,
-      "learning_rate": 2.1754385964912285e-06,
-      "loss": 1.1324,
-      "step": 6000
-    },
-    {
-      "epoch": 9.022556390977444,
-      "eval_train_loss": 1.7962439060211182,
-      "eval_train_runtime": 5.1942,
-      "eval_train_samples_per_second": 1031.737,
-      "eval_train_steps_per_second": 64.496,
-      "step": 6000
-    },
-    {
-      "epoch": 9.323308270676693,
-      "grad_norm": 12.90481948852539,
-      "learning_rate": 1.5071010860484548e-06,
-      "loss": 1.1304,
-      "step": 6200
-    },
-    {
-      "epoch": 9.323308270676693,
-      "eval_train_loss": 1.8035305738449097,
-      "eval_train_runtime": 5.1397,
-      "eval_train_samples_per_second": 1042.671,
-      "eval_train_steps_per_second": 65.179,
-      "step": 6200
-    },
-    {
-      "epoch": 9.62406015037594,
-      "grad_norm": 12.501527786254883,
-      "learning_rate": 8.38763575605681e-07,
-      "loss": 1.1126,
-      "step": 6400
-    },
-    {
-      "epoch": 9.62406015037594,
-      "eval_train_loss": 1.8056447505950928,
-      "eval_train_runtime": 5.1771,
-      "eval_train_samples_per_second": 1035.144,
-      "eval_train_steps_per_second": 64.709,
-      "step": 6400
-    },
-    {
-      "epoch": 9.924812030075188,
-      "grad_norm": 10.318084716796875,
-      "learning_rate": 1.704260651629073e-07,
-      "loss": 1.0986,
-      "step": 6600
-    },
-    {
-      "epoch": 9.924812030075188,
-      "eval_train_loss": 1.806175947189331,
-      "eval_train_runtime": 5.1696,
-      "eval_train_samples_per_second": 1036.634,
-      "eval_train_steps_per_second": 64.802,
-      "step": 6600
     }
   ],
   "logging_steps": 200,
-  "max_steps": 6650,
+  "max_steps": 2331,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 7,
   "save_steps": 3000,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -523,7 +193,7 @@
     }
   },
   "total_flos": 0.0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5426350813d7892767af2be085b90ee8f4228e448896c2b7304612735ddb7b6
+oid sha256:20f9cc1bfbf387326ed07dacc8a11b82a6ff607c0cb073f258fc1350a90ff02a
 size 5496