Training in progress, step 1000

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "indictrans-en-ne-checkpoint-1B",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "IndicTransForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": null,
+  "auto_map": {
+    "AutoConfig": "configuration_indictrans.IndicTransConfig",
+    "AutoModelForSeq2SeqLM": "modeling_indictrans.IndicTransForConditionalGeneration"
+  },
+  "bos_token_id": 0,
+  "decoder_attention_heads": 16,
+  "decoder_embed_dim": 1024,
+  "decoder_ffn_dim": 8192,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 18,
+  "decoder_normalize_before": true,
+  "decoder_start_token_id": 2,
+  "decoder_vocab_size": 126655,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_embed_dim": 1024,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 18,
+  "encoder_normalize_before": true,
+  "encoder_vocab_size": 32322,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layernorm_embedding": false,
+  "max_source_positions": 256,
+  "max_target_positions": 256,
+  "model_type": "IndicTrans",
+  "num_hidden_layers": 18,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "share_decoder_input_output_embed": false,
+  "tokenizer_class": "IndicTransTokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a7c256ba8b530e926c130018efd5022d90c2436d49de0135a35fac5807059e
+size 2247492800

runs/Sep23_12-40-43_ip-10-192-10-70/events.out.tfevents.1727095547.ip-10-192-10-70.11246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6250c6954d3a7a88c16ee4cc08170723607ddea4ed2bbbb1a610366624ba40
+size 9018

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271ead5b5b1cb18f742bfb72f1e8cd2b227ea97eee672f9542b2283446209c63
+size 5368