Upload folder using 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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.23.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6423dd3761b7dfb12b20bc03d149c7da659aeb7381de6eb5a3f5b37a75c2491e
+size 4659378441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd686456f30d60e0ee54ecd25c920e34f87cb76500a3e99ab77847de6aa4415
+size 2329700173

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7881420f92c0a0f637367df8cd1545c1097ca75392bf7d7235519ffcb52a8b
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcff0f602943f45b0b950f1a216f30a415f839ec8831d22b64e41bb8dabc21d
+size 623

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 sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.951282251149739,
+  "global_step": 51000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu 1": 47.2965,
+      "eval_bleu 2": 23.1902,
+      "eval_bleu 3": 14.6246,
+      "eval_bleu 4": 9.6335,
+      "eval_loss": 1.3517687320709229,
+      "eval_rouge1": 43.2204,
+      "eval_rouge2": 24.6102,
+      "eval_rougeL": 40.4882,
+      "eval_rougeLsum": 40.4761,
+      "eval_runtime": 1600.4083,
+      "eval_samples_per_second": 7.769,
+      "eval_score": 15.5358,
+      "eval_sim_cos": 0.6463,
+      "eval_steps_per_second": 3.885,
+      "step": 6414
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu 1": 47.949,
+      "eval_bleu 2": 24.0739,
+      "eval_bleu 3": 15.4108,
+      "eval_bleu 4": 10.3292,
+      "eval_loss": 1.319871425628662,
+      "eval_rouge1": 44.2409,
+      "eval_rouge2": 25.6661,
+      "eval_rougeL": 41.4928,
+      "eval_rougeLsum": 41.476,
+      "eval_runtime": 1606.4407,
+      "eval_samples_per_second": 7.74,
+      "eval_score": 16.4734,
+      "eval_sim_cos": 0.6557,
+      "eval_steps_per_second": 3.87,
+      "step": 12828
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu 1": 48.1714,
+      "eval_bleu 2": 24.217,
+      "eval_bleu 3": 15.5556,
+      "eval_bleu 4": 10.4478,
+      "eval_loss": 1.2945514917373657,
+      "eval_rouge1": 44.4763,
+      "eval_rouge2": 25.8995,
+      "eval_rougeL": 41.6564,
+      "eval_rougeLsum": 41.6407,
+      "eval_runtime": 1602.2223,
+      "eval_samples_per_second": 7.76,
+      "eval_score": 16.5559,
+      "eval_sim_cos": 0.6574,
+      "eval_steps_per_second": 3.88,
+      "step": 19242
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu 1": 48.4961,
+      "eval_bleu 2": 24.3718,
+      "eval_bleu 3": 15.6336,
+      "eval_bleu 4": 10.4299,
+      "eval_loss": 1.2831354141235352,
+      "eval_rouge1": 44.5981,
+      "eval_rouge2": 25.9806,
+      "eval_rougeL": 41.7916,
+      "eval_rougeLsum": 41.7751,
+      "eval_runtime": 1595.7575,
+      "eval_samples_per_second": 7.792,
+      "eval_score": 16.4937,
+      "eval_sim_cos": 0.6593,
+      "eval_steps_per_second": 3.896,
+      "step": 25656
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu 1": 48.4402,
+      "eval_bleu 2": 24.4505,
+      "eval_bleu 3": 15.6646,
+      "eval_bleu 4": 10.481,
+      "eval_loss": 1.2756314277648926,
+      "eval_rouge1": 44.9511,
+      "eval_rouge2": 26.2566,
+      "eval_rougeL": 42.0807,
+      "eval_rougeLsum": 42.0625,
+      "eval_runtime": 1605.6345,
+      "eval_samples_per_second": 7.744,
+      "eval_score": 16.7616,
+      "eval_sim_cos": 0.6608,
+      "eval_steps_per_second": 3.872,
+      "step": 32070
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu 1": 48.3818,
+      "eval_bleu 2": 24.4415,
+      "eval_bleu 3": 15.6406,
+      "eval_bleu 4": 10.5001,
+      "eval_loss": 1.271834373474121,
+      "eval_rouge1": 44.9649,
+      "eval_rouge2": 26.3034,
+      "eval_rougeL": 42.1112,
+      "eval_rougeLsum": 42.1042,
+      "eval_runtime": 1605.5674,
+      "eval_samples_per_second": 7.744,
+      "eval_score": 16.781,
+      "eval_sim_cos": 0.6605,
+      "eval_steps_per_second": 3.872,
+      "step": 38484
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu 1": 48.4976,
+      "eval_bleu 2": 24.6629,
+      "eval_bleu 3": 15.8386,
+      "eval_bleu 4": 10.6292,
+      "eval_loss": 1.2709890604019165,
+      "eval_rouge1": 45.2463,
+      "eval_rouge2": 26.5671,
+      "eval_rougeL": 42.3523,
+      "eval_rougeLsum": 42.3345,
+      "eval_runtime": 1602.7698,
+      "eval_samples_per_second": 7.758,
+      "eval_score": 17.0337,
+      "eval_sim_cos": 0.6626,
+      "eval_steps_per_second": 3.879,
+      "step": 44898
+    }
+  ],
+  "max_steps": 51312,
+  "num_train_epochs": 8,
+  "total_flos": 5.709133356989737e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793602bb0db79612fe1da8f61ab91dea79ba72b4fa856afd1af6e80e25a440f8
+size 3567