Upload 11 files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7787c716d1038a1fb967d1b297c8d1438ce12350aa613bd2259ef27323cc67
+size 880378597

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6204c15c7cef356c5a2b4b4c254c71adf9564022176bf383168968f0b09e8115
+size 440202673

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5576f27bac8ba4b04ab0c91fd47df8e65ae8b4a4174a1c7bbb5b1452bfdf042e
+size 16543

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc90c5dbe2e57551d6e2915d3d15597313188c44f130a61cf6880a2932ee296
+size 623

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 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "camembert-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9486271036315324,
+  "global_step": 11000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.374631268436578e-05,
+      "loss": 3.876,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.696569920844328e-05,
+      "loss": 1.5925,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.2254052016585e-05,
+      "loss": 1.2572,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.754240482472673e-05,
+      "loss": 1.1371,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.283075763286845e-05,
+      "loss": 1.0932,
+      "step": 2500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 7.811911044101018e-05,
+      "loss": 1.0323,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.340746324915191e-05,
+      "loss": 1.0333,
+      "step": 3500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.869581605729364e-05,
+      "loss": 0.9684,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.398416886543535e-05,
+      "loss": 0.9606,
+      "step": 4500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.927252167357709e-05,
+      "loss": 0.9397,
+      "step": 5000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4560874481718815e-05,
+      "loss": 0.8899,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0070745944976807,
+      "eval_runtime": 18.4896,
+      "eval_samples_per_second": 176.37,
+      "eval_steps_per_second": 7.355,
+      "step": 5645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.984922728986054e-05,
+      "loss": 0.733,
+      "step": 6000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.5137580098002266e-05,
+      "loss": 0.6544,
+      "step": 6500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.0425932906143985e-05,
+      "loss": 0.6608,
+      "step": 7000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.6493,
+      "step": 7500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.100263852242744e-05,
+      "loss": 0.6352,
+      "step": 8000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.629099133056917e-05,
+      "loss": 0.6268,
+      "step": 8500
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.1579344138710894e-05,
+      "loss": 0.6172,
+      "step": 9000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.686769694685262e-05,
+      "loss": 0.6159,
+      "step": 9500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.2156049754994346e-05,
+      "loss": 0.5908,
+      "step": 10000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.444402563136073e-06,
+      "loss": 0.59,
+      "step": 10500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.7327553712777988e-06,
+      "loss": 0.582,
+      "step": 11000
+    }
+  ],
+  "max_steps": 11290,
+  "num_train_epochs": 2,
+  "total_flos": 6.897685654641254e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580efb47b2e7da692d570accc6059a82e6be119ff2c4da4064ea4a41e3332569
+size 3375