Upload with huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+tags:
+- text2text-generation
+- definition-modeling
+metrics:
+- rouge
+model-index:
+- name: mt0-definition-ru-xl
+  results: []
+language:
+- ru
+widget:
+- text: "Мы сели в тачку и поехали по ресторанам. Что такое тачка?"
+  example_title: "Definition generation"
+---
+
+# mt0-definition-ru-xl
+
+This model is a version of [mt0-xl](https://huggingface.co/bigscience/mt0-xl) finetuned on the Russian part of CoDWoE dataset.
+
+It achieves the following results on the evaluation set:
+- Loss: 1.6241
+- Rouge1: 0.2536
+- Rouge2: 0.003
+- Rougel: 0.2531
+- Rougelsum: 0.2527
+- Gen Len: 24.0693
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.0449        | 1.0   | 512  | 1.6755          | 0.0817 | 0.0    | 0.0778 | 0.0817    | 16.7581 |
+| 1.707         | 2.0   | 1025 | 1.6182          | 0.096  | 0.0    | 0.097  | 0.1       | 15.8621 |
+| 1.5398        | 3.0   | 1537 | 1.6085          | 0.1394 | 0.0034 | 0.1401 | 0.1416    | 16.4765 |
+| 1.4142        | 4.0   | 2050 | 1.6016          | 0.1132 | 0.0    | 0.1132 | 0.1098    | 16.2732 |
+| 1.3102        | 5.0   | 2562 | 1.6241          | 0.2082 | 0.0034 | 0.2054 | 0.2061    | 16.2877 |
+| 1.2162        | 6.0   | 3075 | 1.6281          | 0.1549 | 0.0    | 0.1549 | 0.1549    | 16.1581 |
+| 1.1364        | 7.0   | 3587 | 1.6622          | 0.1583 | 0.0    | 0.1575 | 0.1589    | 15.9925 |
+| 1.0649        | 8.0   | 4100 | 1.6812          | 0.2033 | 0.0137 | 0.2012 | 0.2027    | 16.5099 |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 1.13.1+rocm5.2
+- Datasets 2.12.0
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 8.0,
+    "eval_gen_len": 24.06929198682766,
+    "eval_loss": 1.6240657567977905,
+    "eval_rouge1": 0.2536,
+    "eval_rouge2": 0.003,
+    "eval_rougeL": 0.2531,
+    "eval_rougeLsum": 0.2527,
+    "eval_runtime": 635.3216,
+    "eval_samples": 7288,
+    "eval_samples_per_second": 11.471,
+    "eval_steps_per_second": 0.359,
+    "train_loss": 1.429130665848895,
+    "train_runtime": 9768.8261,
+    "train_samples": 65584,
+    "train_samples_per_second": 134.272,
+    "train_steps_per_second": 1.048
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "mt0-xl",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 8.0,
+    "eval_gen_len": 24.06929198682766,
+    "eval_loss": 1.6240657567977905,
+    "eval_rouge1": 0.2536,
+    "eval_rouge2": 0.003,
+    "eval_rougeL": 0.2531,
+    "eval_rougeLsum": 0.2527,
+    "eval_runtime": 635.3216,
+    "eval_samples": 7288,
+    "eval_samples_per_second": 11.471,
+    "eval_steps_per_second": 0.359
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0519cc6dc79c0fcbc0f8f27d4e48c28178c7c577df247a331dc728c70182766
+size 9977020596

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c74cc690ee7006a16c32655d698367209d2739396c548ca02b6fc8aef2eaef
+size 4993663292

pytorch_model.bin.index.json

@@ -0,0 +1,566 @@
+{
+  "metadata": {
+    "total_size": 14970478592
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

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

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
+size 16315219

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 1.429130665848895,
+    "train_runtime": 9768.8261,
+    "train_samples": 65584,
+    "train_samples_per_second": 134.272,
+    "train_steps_per_second": 1.048
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.2082,
+  "best_model_checkpoint": "mt0-xl_russian_natprompt_adafactor/checkpoint-2562",
+  "epoch": 8.0,
+  "global_step": 4100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.75e-05,
+      "loss": 2.0449,
+      "step": 512
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 16.75809549945115,
+      "eval_loss": 1.6754746437072754,
+      "eval_rouge1": 0.0817,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0778,
+      "eval_rougeLsum": 0.0817,
+      "eval_runtime": 196.0938,
+      "eval_samples_per_second": 37.166,
+      "eval_steps_per_second": 1.163,
+      "step": 512
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.4995117187500005e-05,
+      "loss": 1.707,
+      "step": 1025
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 15.862102085620197,
+      "eval_loss": 1.6181610822677612,
+      "eval_rouge1": 0.096,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.097,
+      "eval_rougeLsum": 0.1,
+      "eval_runtime": 171.5849,
+      "eval_samples_per_second": 42.475,
+      "eval_steps_per_second": 1.329,
+      "step": 1025
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.24951171875e-05,
+      "loss": 1.5398,
+      "step": 1537
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 16.47653677277717,
+      "eval_loss": 1.6085278987884521,
+      "eval_rouge1": 0.1394,
+      "eval_rouge2": 0.0034,
+      "eval_rougeL": 0.1401,
+      "eval_rougeLsum": 0.1416,
+      "eval_runtime": 171.9932,
+      "eval_samples_per_second": 42.374,
+      "eval_steps_per_second": 1.326,
+      "step": 1537
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.9990234375e-05,
+      "loss": 1.4142,
+      "step": 2050
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 16.273188803512625,
+      "eval_loss": 1.6016370058059692,
+      "eval_rouge1": 0.1132,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.1132,
+      "eval_rougeLsum": 0.1098,
+      "eval_runtime": 171.2054,
+      "eval_samples_per_second": 42.569,
+      "eval_steps_per_second": 1.332,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.7490234375e-05,
+      "loss": 1.3102,
+      "step": 2562
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 16.287733260153676,
+      "eval_loss": 1.6240657567977905,
+      "eval_rouge1": 0.2082,
+      "eval_rouge2": 0.0034,
+      "eval_rougeL": 0.2054,
+      "eval_rougeLsum": 0.2061,
+      "eval_runtime": 170.3025,
+      "eval_samples_per_second": 42.794,
+      "eval_steps_per_second": 1.339,
+      "step": 2562
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.49853515625e-05,
+      "loss": 1.2162,
+      "step": 3075
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 16.158068057080133,
+      "eval_loss": 1.6281158924102783,
+      "eval_rouge1": 0.1549,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.1549,
+      "eval_rougeLsum": 0.1549,
+      "eval_runtime": 171.3659,
+      "eval_samples_per_second": 42.529,
+      "eval_steps_per_second": 1.33,
+      "step": 3075
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.2485351562499996e-05,
+      "loss": 1.1364,
+      "step": 3587
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 15.992453347969265,
+      "eval_loss": 1.6622037887573242,
+      "eval_rouge1": 0.1583,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.1575,
+      "eval_rougeLsum": 0.1589,
+      "eval_runtime": 254.3332,
+      "eval_samples_per_second": 28.655,
+      "eval_steps_per_second": 0.896,
+      "step": 3587
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.998046875e-05,
+      "loss": 1.0649,
+      "step": 4100
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 16.509879253567508,
+      "eval_loss": 1.6811630725860596,
+      "eval_rouge1": 0.2033,
+      "eval_rouge2": 0.0137,
+      "eval_rougeL": 0.2012,
+      "eval_rougeLsum": 0.2027,
+      "eval_runtime": 173.1353,
+      "eval_samples_per_second": 42.094,
+      "eval_steps_per_second": 1.317,
+      "step": 4100
+    },
+    {
+      "epoch": 8.0,
+      "step": 4100,
+      "total_flos": 9.102827646479237e+17,
+      "train_loss": 1.429130665848895,
+      "train_runtime": 9768.8261,
+      "train_samples_per_second": 134.272,
+      "train_steps_per_second": 1.048
+    }
+  ],
+  "max_steps": 10240,
+  "num_train_epochs": 20,
+  "total_flos": 9.102827646479237e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd882549d0b55e5e64fc1bccbe7a30e73de399085741636b5d21642c59b40dda
+size 4091

upload.py

@@ -0,0 +1,11 @@
+#!/bin/env python3
+
+import sys
+from huggingface_hub import HfApi
+from huggingface_hub import create_repo
+
+create_repo(sys.argv[1])
+api = HfApi()
+
+api.upload_folder(folder_path=".", repo_id=sys.argv[1], repo_type="model")
+