updated model

README.md

@@ -0,0 +1,67 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: berties-pretrained
+  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. -->
+
+# berties-pretrained
+
+This model is a fine-tuned version of [Jean-Baptiste/camembert-ner](https://huggingface.co/Jean-Baptiste/camembert-ner) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3922
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.7047        | 0.21  | 500  | 5.0371          |
+| 4.4116        | 0.43  | 1000 | 4.5143          |
+| 4.0711        | 0.64  | 1500 | 4.3272          |
+| 3.8657        | 0.86  | 2000 | 4.1704          |
+| 3.6971        | 1.07  | 2500 | 3.9951          |
+| 3.5093        | 1.29  | 3000 | 3.7682          |
+| 3.3598        | 1.5   | 3500 | 3.6554          |
+| 3.2389        | 1.72  | 4000 | 3.6167          |
+| 3.1984        | 1.93  | 4500 | 3.4445          |
+| 3.1063        | 2.15  | 5000 | 3.4206          |
+| 3.0063        | 2.36  | 5500 | 3.4164          |
+| 3.0069        | 2.57  | 6000 | 3.4115          |
+| 2.9954        | 2.79  | 6500 | 3.3463          |
+
+
+### Framework versions
+
+- Transformers 4.15.0
+- Pytorch 1.10.0+cu111
+- Datasets 1.17.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.392239809036255,
+    "eval_runtime": 8.4705,
+    "eval_samples": 981,
+    "eval_samples_per_second": 115.814,
+    "eval_steps_per_second": 14.521,
+    "perplexity": 29.732472807173135,
+    "train_loss": 3.5777804869601746,
+    "train_runtime": 2142.1553,
+    "train_samples": 18647,
+    "train_samples_per_second": 26.114,
+    "train_steps_per_second": 3.264
+}

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/tmp/berties-pretrained",
+  "_name_or_path": "Jean-Baptiste/camembert-ner",
   "architectures": [
-    "CamembertModel"
+    "CamembertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 5,

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.392239809036255,
+    "eval_runtime": 8.4705,
+    "eval_samples": 981,
+    "eval_samples_per_second": 115.814,
+    "eval_steps_per_second": 14.521,
+    "perplexity": 29.732472807173135
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d3123210d9e3dde8faf7bd5195a007e196faea43ab5ee12ea7f95ac38cb621
-size 442566449
+oid sha256:3006eea8290de245cf656d4dfa4d2d8246ee705987ad6e513087e30a8167da22
+size 442707627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "name_or_path": "Jean-Baptiste/camembert-ner", "special_tokens_map_file": "/root/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.5777804869601746,
+    "train_runtime": 2142.1553,
+    "train_samples": 18647,
+    "train_samples_per_second": 26.114,
+    "train_steps_per_second": 3.264
+}

trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 3.346250057220459,
+  "best_model_checkpoint": "/tmp/berties-pretrained/checkpoint-6500",
+  "epoch": 3.0,
+  "global_step": 6993,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.642499642499642e-05,
+      "loss": 5.7047,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 5.037093639373779,
+      "eval_runtime": 8.5329,
+      "eval_samples_per_second": 114.967,
+      "eval_steps_per_second": 14.415,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.2849992849992856e-05,
+      "loss": 4.4116,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 4.514286041259766,
+      "eval_runtime": 8.497,
+      "eval_samples_per_second": 115.452,
+      "eval_steps_per_second": 14.476,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.9274989274989276e-05,
+      "loss": 4.0711,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 4.327243804931641,
+      "eval_runtime": 8.5359,
+      "eval_samples_per_second": 114.926,
+      "eval_steps_per_second": 14.41,
+      "step": 1500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.56999856999857e-05,
+      "loss": 3.8657,
+      "step": 2000
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 4.17035436630249,
+      "eval_runtime": 8.541,
+      "eval_samples_per_second": 114.858,
+      "eval_steps_per_second": 14.401,
+      "step": 2000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.212498212498213e-05,
+      "loss": 3.6971,
+      "step": 2500
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 3.9950718879699707,
+      "eval_runtime": 8.4686,
+      "eval_samples_per_second": 115.84,
+      "eval_steps_per_second": 14.524,
+      "step": 2500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.854997854997855e-05,
+      "loss": 3.5093,
+      "step": 3000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 3.768172264099121,
+      "eval_runtime": 8.4968,
+      "eval_samples_per_second": 115.455,
+      "eval_steps_per_second": 14.476,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4974974974974976e-05,
+      "loss": 3.3598,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 3.655388832092285,
+      "eval_runtime": 8.4823,
+      "eval_samples_per_second": 115.652,
+      "eval_steps_per_second": 14.501,
+      "step": 3500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.13999713999714e-05,
+      "loss": 3.2389,
+      "step": 4000
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 3.6167075634002686,
+      "eval_runtime": 8.4937,
+      "eval_samples_per_second": 115.497,
+      "eval_steps_per_second": 14.481,
+      "step": 4000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.7824967824967826e-05,
+      "loss": 3.1984,
+      "step": 4500
+    },
+    {
+      "epoch": 1.93,
+      "eval_loss": 3.4444828033447266,
+      "eval_runtime": 8.5242,
+      "eval_samples_per_second": 115.084,
+      "eval_steps_per_second": 14.429,
+      "step": 4500
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.4249964249964251e-05,
+      "loss": 3.1063,
+      "step": 5000
+    },
+    {
+      "epoch": 2.15,
+      "eval_loss": 3.4205729961395264,
+      "eval_runtime": 8.5145,
+      "eval_samples_per_second": 115.215,
+      "eval_steps_per_second": 14.446,
+      "step": 5000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.0674960674960675e-05,
+      "loss": 3.0063,
+      "step": 5500
+    },
+    {
+      "epoch": 2.36,
+      "eval_loss": 3.416414976119995,
+      "eval_runtime": 8.5224,
+      "eval_samples_per_second": 115.108,
+      "eval_steps_per_second": 14.432,
+      "step": 5500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.0999570999571e-06,
+      "loss": 3.0069,
+      "step": 6000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 3.4115302562713623,
+      "eval_runtime": 8.4853,
+      "eval_samples_per_second": 115.611,
+      "eval_steps_per_second": 14.496,
+      "step": 6000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.5249535249535254e-06,
+      "loss": 2.9954,
+      "step": 6500
+    },
+    {
+      "epoch": 2.79,
+      "eval_loss": 3.346250057220459,
+      "eval_runtime": 8.4716,
+      "eval_samples_per_second": 115.799,
+      "eval_steps_per_second": 14.519,
+      "step": 6500
+    },
+    {
+      "epoch": 3.0,
+      "step": 6993,
+      "total_flos": 1415406837275046.0,
+      "train_loss": 3.5777804869601746,
+      "train_runtime": 2142.1553,
+      "train_samples_per_second": 26.114,
+      "train_steps_per_second": 3.264
+    }
+  ],
+  "max_steps": 6993,
+  "num_train_epochs": 3,
+  "total_flos": 1415406837275046.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afce8d3d3462ca4f935b775e19a9239db8230d9e97923bdf6e43d2df813e9fb
+size 2927