Upload 8 files

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "sonoisa/t5-base-japanese",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "eos_token_ids": [
+    1
+  ],
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 512,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_beams": 4,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e435cb13753551be0a69839f63f522c7f3282d173110e8e1f18a2840dd41cd3b
+size 1783380741

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33e5e7933d5a811d67076ee781d17258f9b64cfe1a368a2d5e8ffa7d7b709cd
+size 891702929

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de1186541a41952220406ecd97fea50194d3120298c2a9b5c2e32852f87959ef
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893e53cc3b5e3a251539c9844ad4d52c1a33d9af95866ca80ccd1d2f3679ba3e
+size 627

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 7750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.35483870967742e-06,
+      "loss": 51.2618,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.70967741935484e-06,
+      "loss": 36.8478,
+      "step": 1000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 14.232,
+      "step": 1500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 7.4193548387096784e-06,
+      "loss": 0.4812,
+      "step": 2000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 6.774193548387097e-06,
+      "loss": 0.3559,
+      "step": 2500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 6.129032258064517e-06,
+      "loss": 0.2781,
+      "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 5.483870967741935e-06,
+      "loss": 0.2514,
+      "step": 3500
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.2306,
+      "step": 4000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 4.193548387096774e-06,
+      "loss": 0.2238,
+      "step": 4500
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.548387096774194e-06,
+      "loss": 0.2172,
+      "step": 5000
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.903225806451613e-06,
+      "loss": 0.2119,
+      "step": 5500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 2.2580645161290324e-06,
+      "loss": 0.2101,
+      "step": 6000
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.2073,
+      "step": 6500
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 9.67741935483871e-07,
+      "loss": 0.2082,
+      "step": 7000
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 3.2258064516129035e-07,
+      "loss": 0.2024,
+      "step": 7500
+    }
+  ],
+  "max_steps": 7750,
+  "num_train_epochs": 5,
+  "total_flos": 9435041316864000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c9b8f89f9124ddf262004bde272b6ae8cd33cb567a541a522381a64a876691
+size 3579