Upload 4 files

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "google/t5-efficient-mini",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "chronos_config": {
+    "context_length": 512,
+    "eos_token_id": 1,
+    "model_type": "seq2seq",
+    "n_special_tokens": 2,
+    "n_tokens": 4096,
+    "num_samples": 20,
+    "pad_token_id": 0,
+    "prediction_length": 64,
+    "temperature": 1.0,
+    "tokenizer_class": "MeanScaleUniformBins",
+    "tokenizer_kwargs": {
+      "high_limit": 15.0,
+      "low_limit": -15.0
+    },
+    "top_k": 50,
+    "top_p": 1.0,
+    "use_eos_token": true
+  },
+  "classifier_dropout": 0.0,
+  "d_ff": 1536,
+  "d_kv": 64,
+  "d_model": 384,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 0.05,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 4,
+  "num_heads": 8,
+  "num_layers": 4,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92cad8c8b2daa1fe13a919af62a51d45f2f3d93bfc873e22d9a311926ee6286
+size 81835152

training_info.json

@@ -0,0 +1,61 @@
+{
+    "training_config": {
+        "training_data_paths": "['/nobackup/projects/bdman17/Choronos/data_round2/time_series_2018.arrow']",
+        "probability": "[1.0]",
+        "context_length": 512,
+        "max_steps": 200000,
+        "save_steps": 25000,
+        "log_steps": 500,
+        "per_device_train_batch_size": 256,
+        "learning_rate": 0.001,
+        "optim": "adamw_torch_fused",
+        "shuffle_buffer_length": 100000,
+        "gradient_accumulation_steps": 1,
+        "model_id": "google/t5-efficient-mini",
+        "model_type": "seq2seq",
+        "random_init": true,
+        "tie_embeddings": true,
+        "output_dir": "/nobackup/projects/bdman17/Choronos/models/Mini_new_R2/2018",
+        "tf32": true,
+        "torch_compile": true,
+        "tokenizer_class": "MeanScaleUniformBins",
+        "tokenizer_kwargs": "{'low_limit': -15.0, 'high_limit': 15.0}",
+        "n_tokens": 4096,
+        "n_special_tokens": 2,
+        "pad_token_id": 0,
+        "eos_token_id": 1,
+        "use_eos_token": true,
+        "lr_scheduler_type": "linear",
+        "warmup_ratio": 0.0,
+        "dataloader_num_workers": 20,
+        "num_samples": 20,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "seed": 1234,
+        "model_name": "Mini_R2_2018",
+        "max_missing_prop": 0.9,
+        "min_past": 60,
+        "prediction_length": 64
+    },
+    "job_info": {
+        "cuda_available": true,
+        "device_count": 1,
+        "device_names": {
+            "0": "NVIDIA GH200 480GB"
+        },
+        "mem_info": {
+            "0": [
+                52732624896,
+                102005473280
+            ]
+        },
+        "torchelastic_launched": false,
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "torch_version": "2.3.0a0+ebedce2",
+        "numpy_version": "1.24.4",
+        "gluonts_version": "0.16.0",
+        "transformers_version": "4.41.0.dev0",
+        "accelerate_version": "0.34.2"
+    }
+}