Training in progress, step 300

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "amazon/chronos-t5-tiny",
+  "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,
+      "low_limit": -15
+    },
+    "top_k": 50,
+    "top_p": 1.0,
+    "use_eos_token": true
+  },
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 256,
+  "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": 4,
+  "num_layers": 4,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 4096
+}

logs/events.out.tfevents.1725390452.e4dfe24b710e.304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2504e16f6a513ba896c9b8f51e88d22feb3d7c32ef9069b035ba77c1eff95561
+size 17917

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d1bed5d192e18aa0488714793f9b39f5df2a8ec3c5833198b56e0950ddf26b
+size 33588312

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2210fc05defd6c83c1db2b3be0a7094ede644773d73516f0cd7469ab0b1eb3b9
+size 5112