Training in progress, epoch 0, checkpoint

checkpoint-1755351/config.json

@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}

checkpoint-1755351/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}

checkpoint-1755351/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194330bf1f39ce9b900319ed8514c9bb6e405d86d66c4a287d9d0fdc330efc97
+size 537476677

checkpoint-1755351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546c2b6a4677e96eecdf816258d2d68d0f5c5cde35c3a8d0f8f4a033ff5dddd2
+size 268727709

checkpoint-1755351/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8db98c3bc6b09d34c48a630c6761cbb732a76e15bdae8a4e13cb19619601f7d
+size 14511

checkpoint-1755351/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d0c8a02efe0230959ae3003f5a93e3b2151a11739b99ec9a62090559b7b21d
+size 627

checkpoint-1755351/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-1755351/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-1755351/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b953098e7b6506db46fcf286cd4905f7d47edd3154b6d3e062e0225c65de8ac9
+size 4219