Training in progress, epoch 1

config.json

@@ -1,17 +1,16 @@
 {
-  "_name_or_path": "bigscience/bloom-560m",
-  "apply_residual_connection_post_layernorm": false,
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BloomForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
-  "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_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "LOC",
@@ -20,6 +19,7 @@
     "4": "PER"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LOC": 1,
     "MISC": 2,
@@ -27,21 +27,17 @@
     "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.27.4",
-  "unk_token_id": 0,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250880
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5697383b86907232af0ff4d55d6a4a6d1a2787b16dae7b7db4d3a44f574da61b
-size 2236978473
+oid sha256:531adf2c6ce95418caf1ce44eb4c6525dd9a596c57bde581047dc5b61ee5812f
+size 1109900333

runs/Apr12_10-11-03_73143cfa88a1/1681294272.2417843/events.out.tfevents.1681294272.73143cfa88a1.7174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e54d86f16d58480199b275a92280e9e4397883321b29e090d1492a4390a903
+size 5838

runs/Apr12_10-11-03_73143cfa88a1/events.out.tfevents.1681294272.73143cfa88a1.7174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7961360aa25249e23c563ebdd0ea8a26eeb69756e2455ad8d8fdcc54f0db0602
+size 4184

runs/Apr12_10-13-36_73143cfa88a1/1681294421.731169/events.out.tfevents.1681294421.73143cfa88a1.8154.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251b0b2dc209f9464e3ea2525608c5f7753818f91380af273598278b20703968
+size 5838

runs/Apr12_10-13-36_73143cfa88a1/events.out.tfevents.1681294421.73143cfa88a1.8154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff9beb2c6bdab7de8c872f3cdc11a678509e2b57e839f6fdff41a68498d4cfc
+size 4867

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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -1,11 +1,20 @@
 {
   "add_prefix_space": true,
   "bos_token": "<s>",
+  "cls_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "padding_side": "left",
+  "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "tokenizer_class": "BloomTokenizer",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:009127740ee8e945c63b91b5a82f982bd0f7cf76edb73cd0df6b1cfd9c938038
+oid sha256:9d7b90ee939184a714e612e73c7a17e6ed983132412c2f74b3768c61fe843a4d
 size 3515