End of training

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- edbeeching/decision_transformer_gym_replay
+model-index:
+- name: decision-transformer-halfcheetah-v4
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# decision-transformer-halfcheetah-v4
+
+This model was trained from scratch on the halfcheetah-expert-v2 dataset.
+
+## 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: 0.0001
+- train_batch_size: 128
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 240
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/kaggle/working/output/checkpoint-1500",
+  "act_dim": 6,
+  "action_tanh": true,
+  "activation_function": "relu",
+  "architectures": [
+    "DecisionTransformerModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_ep_len": 4096,
+  "model_type": "decision_transformer",
+  "n_head": 1,
+  "n_inner": null,
+  "n_layer": 3,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "state_dim": 17,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 1
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45cf309a786ab65e029160c8538a809d8c92252c09ecc24ca5fecbe94e4e7b7
+size 5034448

runs/Jul07_21-01-13_fbcba7e8594d/events.out.tfevents.1720386074.fbcba7e8594d.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9750ea4599e7401aa7e0528d223772e894ef1d60ac8cffe94b4112a9493597c
+size 4750

runs/Jul07_21-12-15_fbcba7e8594d/events.out.tfevents.1720386735.fbcba7e8594d.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffb36f8fef69439e9ebf4818b87b4d248f8d16ad0fe9b8acf1d475ba2eeb2f4
+size 5383

runs/Jul08_05-33-28_fb7ef35e3a82/events.out.tfevents.1720416809.fb7ef35e3a82.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55466a8b1adf0328674dc428fb6e431f507edecd87ac6846c4ee0caf8e08626e
+size 5104

runs/Jul08_06-40-47_fb7ef35e3a82/events.out.tfevents.1720420848.fb7ef35e3a82.1653.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7350c7975cf4d035fa0f3f99cfd33840956fa266fa24ef5818ad61acc19fa25
+size 4750

runs/Jul08_06-41-39_fb7ef35e3a82/events.out.tfevents.1720420899.fb7ef35e3a82.1653.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e263080cd579b7fb52cf66b6beb750f9f7cd0380d4df57b5372c3b984dd51c
+size 5104

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e095af7e701fe49810bb473ad2040dc2b836d3cb3af80d617bd8ba33eb5965
+size 5112