Training in progress, epoch 0, checkpoint

checkpoint-1450069/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-1450069/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-1450069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd8b8fdc3ffa8d2014b4480bfc0c6b2d57efa1461d5be70b84626c2e182ffd7
+size 537476677

checkpoint-1450069/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f7dcdd6dc28e93b7fc7754ea303075c72fb80f987802be0fe3d2d598053d89
+size 268727709

checkpoint-1450069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29595a7402cc8094d7f1981fb49bcc9be3c1cb66ed683c149ac01e358a6dc878
+size 14575

checkpoint-1450069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbdbb3f93cb7bafa1e3e23b4e3b22d7c72bc4cdd0935f9079d8b35600aa9e0b
+size 627

checkpoint-1450069/special_tokens_map.json

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

checkpoint-1450069/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-1450069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19210a8a165e2313b631e8c1f3049ede89d424df610ea7634941549352933940
+size 4219