Training in progress, epoch 1

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "bigscience/bloom-560m",
-  "apply_residual_connection_post_layernorm": false,
+  "_name_or_path": "roberta-large-mnli",
+  "_num_labels": 3,
   "architectures": [
-    "BloomForTokenClassification"
+    "RobertaForTokenClassification"
   ],
-  "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
-  "bias_dropout_fusion": true,
-  "bos_token_id": 1,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
   "finetuning_task": "ner",
-  "hidden_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
     "0": "O",
@@ -20,6 +20,7 @@
     "4": "PER"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "LOC": 1,
     "MISC": 2,
@@ -27,21 +28,16 @@
     "ORG": 3,
     "PER": 4
   },
-  "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,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
-  "unk_token_id": 0,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250880
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7484c5b7b96e424d6c318e81d4322a9cc5468fbc88e1ee086e8d0b2cb1f342
-size 2236978473
+oid sha256:96a2868051db6047f47ddffc97275ea93f3045d7dac7f9f9bb0a8e576312997f
+size 1417400429

runs/May02_06-20-35_51314e236b96/1683008995.0958967/events.out.tfevents.1683008995.51314e236b96.429.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108127d8f51e40af828d5736804b0715e6479f6084f97ad75b9713f603318be0
+size 5855

runs/May02_06-20-35_51314e236b96/events.out.tfevents.1683008995.51314e236b96.429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6df417eadeaeeca44bee99f06c551748403c281a7e01dc0abecc36f9cf8c877
+size 4853

special_tokens_map.json

@@ -1,6 +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>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:f825587324fca021d7303de2c97caf864712963b1883810f503d426f2dcdf187
+size 2108617

tokenizer_config.json

@@ -1,11 +1,15 @@
 {
   "add_prefix_space": true,
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "padding_side": "left",
-  "tokenizer_class": "BloomTokenizer",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55be6fc73e9ffca6429c166ba721f9a44e68ac854bdf22b20698ef42ec8fed5
+oid sha256:6d8403f7ba564e2ca16eb95d92c01ae81a710dc9f27340da82d5b6816cff1401
 size 3515