Training in progress, epoch 0, checkpoint

checkpoint-915829/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-915829/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-915829/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3c83045696778259cfd58c8f28d35b6bee1a123b438fc07c5125616b20baae
+size 537476677

checkpoint-915829/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcae008b13c7b3ab08dfbb1f8a7258c7407dce4e0a8cbb147650696154357e4
+size 268727709

checkpoint-915829/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54c6a4a3f79dfca326aa3e32d057b62d6a953f26ebae07c9802938595865df1
+size 14575

checkpoint-915829/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6e1b4132044023316aec7b4236a59e9f56c8393fdc6fbe989fed52f96932ba
+size 627

checkpoint-915829/special_tokens_map.json

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

checkpoint-915829/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-915829/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98bc3e225e2b7f260ad4750c53c5ae83f8f1c68d99a74934cdef851d31acf86
+size 4219