Training in progress, epoch 1

config.json

@@ -1,89 +1,33 @@
 {
-  "_name_or_path": "DataMonke/distilbert-base-uncased-sentiment-analysis-movie-reviews",
-  "amp": 1,
+  "_name_or_path": "liliaciolite/rotten_tomatoes_sentiment_analysis",
+  "activation": "gelu",
   "architectures": [
-    "FlaubertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "asm": false,
   "attention_dropout": 0.1,
-  "bos_index": 0,
-  "bos_token_id": 0,
-  "bptt": 512,
-  "causal": false,
-  "clip_grad_norm": 5,
+  "dim": 768,
   "dropout": 0.1,
-  "emb_dim": 512,
-  "embed_init_std": 0.02209708691207961,
-  "encoder_only": true,
-  "end_n_top": 5,
-  "eos_index": 1,
-  "fp16": true,
-  "gelu_activation": true,
-  "group_by_size": true,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
-  "id2lang": {
-    "0": "fr"
-  },
-  "init_std": 0.02,
-  "is_encoder": true,
+  "initializer_range": 0.02,
   "label2id": {
     "negative": 0,
     "positive": 1
   },
-  "lang2id": {
-    "fr": 0
-  },
-  "lang_id": 0,
-  "langs": [
-    "fr"
-  ],
-  "layer_norm_eps": 1e-06,
-  "layerdrop": 0.2,
-  "lg_sampling_factor": -1,
-  "lgs": "fr",
-  "mask_index": 5,
-  "mask_token_id": 0,
-  "max_batch_size": 0,
   "max_position_embeddings": 512,
-  "max_vocab": -1,
-  "mlm_steps": [
-    [
-      "fr",
-      null
-    ]
-  ],
-  "model_type": "flaubert",
-  "n_heads": 8,
-  "n_langs": 1,
+  "model_type": "distilbert",
+  "n_heads": 12,
   "n_layers": 6,
-  "pad_index": 2,
-  "pad_token_id": 2,
-  "pre_norm": true,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "sample_alpha": 0,
-  "share_inout_emb": true,
-  "sinusoidal_embeddings": false,
-  "start_n_top": 5,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "first",
-  "summary_use_proj": true,
-  "tokens_per_batch": -1,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
-  "unk_index": 3,
-  "use_lang_emb": true,
-  "vocab_size": 68729,
-  "word_blank": 0,
-  "word_dropout": 0,
-  "word_keep": 0.1,
-  "word_mask": 0.8,
-  "word_mask_keep_rand": "0.8,0.1,0.1",
-  "word_pred": 0.15,
-  "word_rand": 0.1,
-  "word_shuffle": 0
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c191f563db356077f5c021010ea37921834be97001a7c2cab18e5f42c882c925
-size 217481552
+oid sha256:9f748de07dbdf7ca0f1470bfa431ce494318f6ba37c35c91441d8391a2702ce9
+size 267832560

runs/Oct26_21-36-34_LAPTOP-0SLVIA1T/events.out.tfevents.1729996595.LAPTOP-0SLVIA1T.40368.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d99c8a0564bd5fe74ff3af5f61b1e4c16736668dda2aaa719395eef6e69cf55
-size 6428
+oid sha256:aa2d46c698ed25aea360144f49a618116b13679f8fe92760bd3af1ff2bf99e0a
+size 7105

runs/Oct26_21-39-46_LAPTOP-0SLVIA1T/events.out.tfevents.1729996788.LAPTOP-0SLVIA1T.40368.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccedc0b0289cd9875f4a8f3c6093aefb15316e6df313e6d142e3487eb702059
+size 5362

special_tokens_map.json

@@ -1,53 +1,34 @@
 {
-  "additional_special_tokens": [
-    "<special0>",
-    "<special1>",
-    "<special2>",
-    "<special3>",
-    "<special4>",
-    "<special5>",
-    "<special6>",
-    "<special7>",
-    "<special8>",
-    "<special9>"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
-    "content": "</s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<special1>",
+    "content": "[MASK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,111 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "</s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "<pad>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<special0>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<special1>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<special2>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<special3>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<special4>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<special5>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<special6>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<special7>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<special8>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<special9>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -113,29 +41,22 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<special0>",
-    "<special1>",
-    "<special2>",
-    "<special3>",
-    "<special4>",
-    "<special5>",
-    "<special6>",
-    "<special7>",
-    "<special8>",
-    "<special9>"
-  ],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "</s>",
-  "do_lower_case": false,
-  "do_lowercase": false,
-  "id2lang": null,
-  "lang2id": null,
-  "mask_token": "<special1>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "FlaubertTokenizer",
-  "unk_token": "<unk>"
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4d7c76612d91907944d5f617352e7ce4a16741f64a696f005f3bb4873a4afc
+oid sha256:4fa360f50e53d8f30ae2de5360af3cf5f04b8a754099ad4050cea65ec2c7bc2b
 size 5240