Update

README.md

@@ -0,0 +1,57 @@
+---
+license: cc-by-nc-nd-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: ./dapt_kogpt2
+model-index:
+- name: dapt_kogpt2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dapt_kogpt2
+
+This model is a fine-tuned version of [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.28.0
+- Pytorch 1.13.1
+- Datasets 2.15.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 2.042313535626118,
+    "train_runtime": 4896.3607,
+    "train_samples": 2498,
+    "train_samples_per_second": 1.02,
+    "train_steps_per_second": 0.127
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "kakaobrain/kogpt",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "TensorParallelPreTrainedModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 128,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 64512
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "transformers_version": "4.28.0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68de0ae3fc8c195beba9d98f86de4a7b6b1a0c0de6cd4e89de78f8ec8e8c77b1
+size 10101805879

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cdb39d7ef06822b7c77ce9ea5fb40b2e956a55e5f8fa6fb21c1b9e65df15f2
+size 9866019601

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f976b146876dd869b78e7342278b6b5a3e556b0dd8cdfd3457c3d8e65e86da
+size 4815741195

pytorch_model.bin.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 24680689776.0
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00003-of-00003.bin",
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.3.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 2.042313535626118,
+    "train_runtime": 4896.3607,
+    "train_samples": 2498,
+    "train_samples_per_second": 1.02,
+    "train_steps_per_second": 0.127
+}

trainer_state.json

@@ -0,0 +1,403 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9983987189751802,
+  "global_step": 624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.996794871794872e-05,
+      "loss": 2.5842,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.967948717948718e-05,
+      "loss": 2.511,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.935897435897436e-05,
+      "loss": 2.4961,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.903846153846154e-05,
+      "loss": 2.4203,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.8717948717948718e-05,
+      "loss": 2.3722,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8397435897435897e-05,
+      "loss": 2.4072,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.807692307692308e-05,
+      "loss": 2.4484,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.775641025641026e-05,
+      "loss": 2.3817,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 2.4138,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7115384615384617e-05,
+      "loss": 2.3693,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6794871794871796e-05,
+      "loss": 2.3947,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6474358974358975e-05,
+      "loss": 2.3659,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 2.3695,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 2.343,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5512820512820516e-05,
+      "loss": 2.3434,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.5192307692307693e-05,
+      "loss": 2.3407,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.4871794871794874e-05,
+      "loss": 2.3595,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.4551282051282051e-05,
+      "loss": 2.3485,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.4230769230769232e-05,
+      "loss": 2.3488,
+      "step": 180
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.3910256410256411e-05,
+      "loss": 2.4007,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.3589743589743592e-05,
+      "loss": 2.3197,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3269230769230769e-05,
+      "loss": 2.324,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.294871794871795e-05,
+      "loss": 2.3546,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.2628205128205129e-05,
+      "loss": 2.3547,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 2.3702,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.1987179487179487e-05,
+      "loss": 2.3071,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 2.3233,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1346153846153847e-05,
+      "loss": 2.3361,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1025641025641028e-05,
+      "loss": 2.3152,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0705128205128205e-05,
+      "loss": 2.3653,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0384615384615386e-05,
+      "loss": 2.3031,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0064102564102565e-05,
+      "loss": 2.3035,
+      "step": 310
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 1.8449,
+      "step": 320
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.423076923076923e-06,
+      "loss": 1.7192,
+      "step": 330
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.102564102564104e-06,
+      "loss": 1.7361,
+      "step": 340
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.782051282051283e-06,
+      "loss": 1.7584,
+      "step": 350
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 1.7269,
+      "step": 360
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.141025641025641e-06,
+      "loss": 1.7208,
+      "step": 370
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.820512820512822e-06,
+      "loss": 1.7485,
+      "step": 380
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.7506,
+      "step": 390
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 1.7193,
+      "step": 400
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.858974358974359e-06,
+      "loss": 1.6919,
+      "step": 410
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 6.538461538461539e-06,
+      "loss": 1.7516,
+      "step": 420
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 6.217948717948718e-06,
+      "loss": 1.7129,
+      "step": 430
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.897435897435898e-06,
+      "loss": 1.7253,
+      "step": 440
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.576923076923077e-06,
+      "loss": 1.7259,
+      "step": 450
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.256410256410257e-06,
+      "loss": 1.7065,
+      "step": 460
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 4.935897435897436e-06,
+      "loss": 1.709,
+      "step": 470
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.6774,
+      "step": 480
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.294871794871795e-06,
+      "loss": 1.7154,
+      "step": 490
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.974358974358974e-06,
+      "loss": 1.6767,
+      "step": 500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.653846153846154e-06,
+      "loss": 1.7006,
+      "step": 510
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6998,
+      "step": 520
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.012820512820513e-06,
+      "loss": 1.7088,
+      "step": 530
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.6923076923076923e-06,
+      "loss": 1.6739,
+      "step": 540
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.371794871794872e-06,
+      "loss": 1.6906,
+      "step": 550
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 1.7699,
+      "step": 560
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.7307692307692308e-06,
+      "loss": 1.6989,
+      "step": 570
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.4102564102564104e-06,
+      "loss": 1.6954,
+      "step": 580
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.0897435897435899e-06,
+      "loss": 1.7052,
+      "step": 590
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.7458,
+      "step": 600
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.4871794871794876e-07,
+      "loss": 1.7088,
+      "step": 610
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.282051282051282e-07,
+      "loss": 1.7122,
+      "step": 620
+    },
+    {
+      "epoch": 2.0,
+      "step": 624,
+      "total_flos": 1.810492168297513e+17,
+      "train_loss": 2.042313535626118,
+      "train_runtime": 4896.3607,
+      "train_samples_per_second": 1.02,
+      "train_steps_per_second": 0.127
+    }
+  ],
+  "max_steps": 624,
+  "num_train_epochs": 2,
+  "total_flos": 1.810492168297513e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ede7954441393fcedaeae18f6372bf237f2f5aace7c182e12cd8735bec6f01c
+size 3579