Add camrun24 1G mOSCAR

README.md

@@ -0,0 +1,2 @@
+# CamemBert-Gpt POIDS UNIQUEMENT
+Projet Final pour Sorbonne Université, machine learning avancé

cam_run24/checkpoints/checkpoint-1000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run24/checkpoints/checkpoint-1000/metrics_report.txt

@@ -0,0 +1,32 @@
+=== Training Metrics Report ===
+
+Current State:
+Step: 1000
+Tokens Processed: 163,840,000
+Training Progress: 61.04%
+
+Recent Metrics:
+Step 250:
+  loss: 9.0778
+  grad_norm: 7.743047714233398
+  learning_rate: 1.7500000000000002e-05
+  epoch: 0.0125
+
+Step 500:
+  loss: 6.3809
+  grad_norm: 3.5750033855438232
+  learning_rate: 3.5000000000000004e-05
+  epoch: 0.025
+
+Step 750:
+  loss: 5.9896
+  grad_norm: 4.1413140296936035
+  learning_rate: 5.2499999999999995e-05
+  epoch: 0.0375
+
+Step 1000:
+  loss: 5.9116
+  grad_norm: 6.747597694396973
+  learning_rate: 7.000000000000001e-05
+  epoch: 0.05
+

cam_run24/checkpoints/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2e4741f9fa11564176572868bebc6443c6173af3f63c0c66c804dd607ac6ee
+size 498813948

cam_run24/checkpoints/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

cam_run24/checkpoints/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

cam_run24/checkpoints/checkpoint-1000/trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cc7ab8ccdc62dab416f5565a07c0fb0917508c2a5efb53230b956db67ef044
+size 1272

cam_run24/checkpoints/checkpoint-10000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run24/checkpoints/checkpoint-10000/metrics_report.txt

@@ -0,0 +1,38 @@
+=== Training Metrics Report ===
+
+Current State:
+Step: 10000
+Tokens Processed: 1,638,400,000
+Training Progress: 610.35%
+
+Recent Metrics:
+Step 9000:
+  loss: 1.0834
+  grad_norm: 3.596336841583252
+  learning_rate: 0.0006297900000000001
+  epoch: 0.45
+
+Step 9250:
+  loss: 1.2132
+  grad_norm: 3.082534074783325
+  learning_rate: 0.00064694
+  epoch: 0.4625
+
+Step 9500:
+  loss: 1.1674
+  grad_norm: 46.47481918334961
+  learning_rate: 0.0006642299999999999
+  epoch: 0.475
+
+Step 9750:
+  loss: 1.1172
+  grad_norm: 3.1326756477355957
+  learning_rate: 0.00068173
+  epoch: 0.4875
+
+Step 10000:
+  loss: 1.0835
+  grad_norm: 3.4375391006469727
+  learning_rate: 0.00069923
+  epoch: 0.5
+

cam_run24/checkpoints/checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5396c0cfbb5dc161c5a3c48cda1d57daba5b4c5df8c07d069fcaf9efbc693b
+size 498813948

cam_run24/checkpoints/checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

cam_run24/checkpoints/checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

cam_run24/checkpoints/checkpoint-10000/trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247313d53800315171e4a59a9338d776ffea9bc85ab7d21c1e98938363d32daa
+size 3256

cam_run24/checkpoints/checkpoint-15000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run24/checkpoints/checkpoint-15000/metrics_report.txt

@@ -0,0 +1,38 @@
+=== Training Metrics Report ===
+
+Current State:
+Step: 15000
+Tokens Processed: 2,457,600,000
+Training Progress: 915.53%
+
+Recent Metrics:
+Step 14000:
+  loss: 0.9014
+  grad_norm: 2.5185256004333496
+  learning_rate: 0.00042080989
+  epoch: 0.7
+
+Step 14250:
+  loss: 0.8956
+  grad_norm: 2.4787769317626953
+  learning_rate: 0.0004033123900000001
+  epoch: 0.7125
+
+Step 14500:
+  loss: 0.8823
+  grad_norm: 2.4841043949127197
+  learning_rate: 0.0003858148899999999
+  epoch: 0.725
+
+Step 14750:
+  loss: 0.8753
+  grad_norm: 2.531907081604004
+  learning_rate: 0.00036831739
+  epoch: 0.7375
+
+Step 15000:
+  loss: 0.8753
+  grad_norm: 2.6155550479888916
+  learning_rate: 0.00035081989
+  epoch: 0.75
+

cam_run24/checkpoints/checkpoint-15000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b3b31bbff6f96cb0711a5c041040d2c6570a4c9751a3b9ad9aa6b40623280c
+size 498813948

cam_run24/checkpoints/checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

cam_run24/checkpoints/checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

cam_run24/checkpoints/checkpoint-15000/trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16d59d9332f6115f06577d99f194c43ee1a81cba96cd933d2bfc414d9938b55
+size 4344

cam_run24/checkpoints/checkpoint-20000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run24/checkpoints/checkpoint-20000/metrics_report.txt

@@ -0,0 +1,38 @@
+=== Training Metrics Report ===
+
+Current State:
+Step: 20000
+Tokens Processed: 3,276,800,000
+Training Progress: 1220.70%
+
+Recent Metrics:
+Step 19000:
+  loss: 0.7501
+  grad_norm: 2.222653388977051
+  learning_rate: 7.092987999999998e-05
+  epoch: 0.95
+
+Step 19250:
+  loss: 0.7459
+  grad_norm: 2.1408591270446777
+  learning_rate: 5.343238000000004e-05
+  epoch: 0.9625
+
+Step 19500:
+  loss: 0.7407
+  grad_norm: 2.2472920417785645
+  learning_rate: 3.593488000000002e-05
+  epoch: 0.975
+
+Step 19750:
+  loss: 0.7389
+  grad_norm: 2.1884987354278564
+  learning_rate: 1.843738e-05
+  epoch: 0.9875
+
+Step 20000:
+  loss: 0.7345
+  grad_norm: 2.1019210815429688
+  learning_rate: 9.398799999999853e-07
+  epoch: 1.0
+

cam_run24/checkpoints/checkpoint-20000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a707e260d3dab5cf94b0b4170f7c05d7b9aa9447e9ee52d4286733196d68780c
+size 498813948

cam_run24/checkpoints/checkpoint-20000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

cam_run24/checkpoints/checkpoint-20000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

cam_run24/checkpoints/checkpoint-20000/trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94805ea9524dd42e4bf4135009aae4c4c8d63f9ffe4d2fe19613c35be62374f4
+size 5432

cam_run24/checkpoints/checkpoint-500/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cam_run24/checkpoints/checkpoint-500/metrics_report.txt

@@ -0,0 +1,20 @@
+=== Training Metrics Report ===
+
+Current State:
+Step: 500
+Tokens Processed: 81,920,000
+Training Progress: 30.52%
+
+Recent Metrics:
+Step 250:
+  loss: 9.0778
+  grad_norm: 7.743047714233398
+  learning_rate: 1.7500000000000002e-05
+  epoch: 0.0125
+
+Step 500:
+  loss: 6.3809
+  grad_norm: 3.5750033855438232
+  learning_rate: 3.5000000000000004e-05
+  epoch: 0.025
+

cam_run24/checkpoints/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fe6694ca2ed9de3e9f1fa172d621a44ad9d07e3af6ee58cbc71c13151b6b15
+size 498813948

cam_run24/checkpoints/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

cam_run24/checkpoints/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

cam_run24/checkpoints/checkpoint-500/trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09936da2393321341d0f870e8eac64babb2760bbd7d1690d9c2e520d65f0961a
+size 1208

cam_run24/checkpoints/checkpoint-5000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}