Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForTokenClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-MajorClaim",
+    "2": "I-MajorClaim",
+    "3": "B-Claim",
+    "4": "I-Claim",
+    "5": "B-Premise",
+    "6": "I-Premise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-Claim": 3,
+    "B-MajorClaim": 1,
+    "B-Premise": 5,
+    "I-Claim": 4,
+    "I-MajorClaim": 2,
+    "I-Premise": 6,
+    "O": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

meta_data/meta_s42_e5_cvi0.json

@@ -0,0 +1 @@
+{"B-Claim": {"precision": 0.4620938628158845, "recall": 0.4507042253521127, "f1-score": 0.45632798573975053, "support": 284.0}, "B-MajorClaim": {"precision": 0.7, "recall": 0.5957446808510638, "f1-score": 0.6436781609195402, "support": 141.0}, "B-Premise": {"precision": 0.6952247191011236, "recall": 0.6991525423728814, "f1-score": 0.6971830985915493, "support": 708.0}, "I-Claim": {"precision": 0.5342320909331219, "recall": 0.48441994247363374, "f1-score": 0.5081081081081082, "support": 4172.0}, "I-MajorClaim": {"precision": 0.7541263517359135, "recall": 0.6379393355801637, "f1-score": 0.6911841418883673, "support": 2077.0}, "I-Premise": {"precision": 0.8258639910813824, "recall": 0.8874690519926524, "f1-score": 0.8555589775177087, "support": 12521.0}, "O": {"precision": 0.886796294411076, "recall": 0.8690143655227454, "f1-score": 0.8778152869451302, "support": 10024.0}, "accuracy": 0.7978079994653657, "macro avg": {"precision": 0.6940481871540717, "recall": 0.660634877735036, "f1-score": 0.6756936799585934, "support": 29927.0}, "weighted avg": {"precision": 0.7935035105957297, "recall": 0.7978079994653657, "f1-score": 0.7946353555655076, "support": 29927.0}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0465492519f07d335890fa011362bb5d28152afd1e73e74c87bd553830cb9e4a
+size 2236921156

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115741e229e6690e083cfff9e352463f54ec7541c2fc3c2a0d42fa6e5631668e
+size 14500470

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2da0857bc7479d04191b9c566cdf67414cfe146549c31286587d475f6b25e3
+size 4664