Training in progress, epoch 0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "BigTMiami/amazon_pretraining_5M_model_corrected",
+  "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": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fafd28b3a7a78f75c25276839aab270d65f3acedc5ac18dcc3d6ea8568de5e
+size 498813948

runs/Apr16_20-21-06_ec2cbfe8c2a4/events.out.tfevents.1713298869.ec2cbfe8c2a4.385.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf3c78d353cef77e6c3bbf1b40436f917c2a766b805c466d975dfd18b21e54b
+size 5218

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef72ec9377f7ac0d50025b5da6c6a07b3fcc3020b79ccd022ceba020514e190
+size 4984