update RohanGivenCode.py with max_len i.e., new_tokens

RohanGivenCode.py

@@ -1,300 +1,300 @@
-
-import os
-import math
-import time
-import inspect
-from dataclasses import dataclass
-import torch
-import torch.nn as nn
-from torch.nn import functional as F
-import tiktoken
-
-#1 --- Seema start here
-class CausalSelfAttention(nn.Module):
-
-    def __init__(self, config):
-        super().__init__()
-        assert config.n_embd % config.n_head == 0
-        # key, query, value projections for all heads, but in a batch
-        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
-        # output projection
-        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
-        self.c_proj.NANGPT_SCALE_INIT = 1
-        # regularization
-        self.n_head = config.n_head
-        self.n_embd = config.n_embd
-        self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size)).view(1, 1, config.block_size, config.block_size))
-
-    def forward(self, x):
-        B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
-        # calculate query, key, values for all heads in batch and move head forward to be the batch dim
-        # nh is "number of heads", hs is "head size", and C (number of channels) = nh * hs
-        # e.g. in GPT-2 (124M), n_head=12, hs=64, so nh*hs=C=768 channels in the Transformer
-        qkv = self.c_attn(x)
-        q, k, v = qkv.split(self.n_embd, dim=2)
-        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
-        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
-        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
-
-        # att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
-        # att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float('-inf'))
-        # att = F.softmax(att, dim=-1)
-        # y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
-
-        y = F.scaled_dot_product_attention(q, k, v, is_causal = True) # Flash attention
-
-        y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
-        # output projection
-        y = self.c_proj(y)
-        return y
-
-
-class MLP(nn.Module):
-
-    def __init__(self, config):
-        super().__init__()
-        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd)
-        self.gelu    = nn.GELU(approximate='tanh')
-        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd)
-        self.c_proj.NANOGPT_SCALE_INIT = 1
-
-    def forward(self, x):
-        x = self.c_fc(x)
-        x = self.gelu(x)
-        x = self.c_proj(x)
-        return x
-
-class Block(nn.Module):
-
-    def __init__(self, config):
-        super().__init__()
-        self.ln_1 = nn.LayerNorm(config.n_embd)
-        self.attn = CausalSelfAttention(config)
-        self.ln_2 = nn.LayerNorm(config.n_embd)
-        self.mlp = MLP(config)
-
-    def forward(self, x):
-        x = x + self.attn(self.ln_1(x))
-        x = x + self.mlp(self.ln_2(x))
-        return x
-
-
-@dataclass
-class GPTConfig:
-    block_size: int = 1024 # max sequence length
-    vocab_size: int = 50304 # number of tokens: 50,000 BPE merges + 256 bytes tokens + 1 <|endoftext|> token
-    n_layer: int = 12 # number of layers
-    n_head: int = 12 # number of heads
-    n_embd: int = 768 # embedding dimension
-
-
-
-class GPT(nn.Module):
-
-    def __init__(self, config):
-        super().__init__()
-        self.config = config
-
-        self.transformer = nn.ModuleDict(dict(
-            wte = nn.Embedding(config.vocab_size, config.n_embd),
-            wpe = nn.Embedding(config.block_size, config.n_embd),
-            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
-            ln_f = nn.LayerNorm(config.n_embd),
-        ))
-        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
-
-        # weight sharing
-        self.transformer.wte.weight = self.lm_head.weight
-
-        # weight initialization
-        self.apply(self._init_weights)
-
-    def _init_weights(self, module):
-        if isinstance(module, nn.Linear):
-            std = 0.02
-            if hasattr(module, 'NANGPT_SCALE_INIT'):
-                std *= (2 * self.config.n_layer) ** -0.5
-            torch.nn.init.normal_(module.weight, mean = 0.0, std = std)
-            if module.bias is not None:
-                torch.nn.init.zeros_(module.bias)
-        elif isinstance(module, nn.Embedding):
-            torch.nn.init.normal_(module.weight, mean=0.0, std = 0.02)
-
-#1 --- Seema end here
-
-#============================================================================================================
-
-#2 --- Raja start here
-    def forward(self, idx, targets=None):
-        # idx is of shape (B, T)
-        B, T = idx.size()
-        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
-        # forward the token and posisition embeddings
-        pos = torch.arange(0, T, dtype=torch.long, device=idx.device) # shape (T)
-        pos_emb = self.transformer.wpe(pos) # position embeddings of shape (T, n_embd)
-        tok_emb = self.transformer.wte(idx) # token embeddings of shape (B, T, n_embd)
-        x = tok_emb + pos_emb
-        # forward the blocks of the transformer
-        for block in self.transformer.h:
-            x = block(x)
-        # forward the final layernorm and the classifier
-        x = self.transformer.ln_f(x)
-        logits = self.lm_head(x) # (B, T, vocab_size)
-        loss = None
-        if targets is not None:
-            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
-        return logits, loss
-
-    def configure_optimizers(self, weight_decay, learning_rate, device_type):
-        # start with all of the candidate parameters (that require grad)
-        param_dict = {pn: p for pn, p in self.named_parameters()}
-        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
-        # create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
-        # i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
-        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
-        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
-        optim_groups = [
-            {'params': decay_params, 'weight_decay': weight_decay},
-            {'params': nodecay_params, 'weight_decay': 0.0}
-        ]
-        num_decay_params = sum(p.numel() for p in decay_params)
-        num_nodecay_params = sum(p.numel() for p in nodecay_params)
-
-        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
-        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
-        # Create AdamW optimizer and use the fused version if it is available
-        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
-        use_fused = fused_available and device_type == "cuda"
-
-        print(f"using fused AdamW: {use_fused}")
-        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9, 0.95), eps=1e-8, fused=use_fused)
-        return optimizer
-
-# model = GPT.from_pretrained('gpt2')
-
-
-#2 --- Raja end here
-
-
-#============================================================================================================
-
-#3 --- Yasaswini start here
-class DataLoaderLite:
-    def __init__(self, B, T, text_input):
-        self.B = B
-        self.T = T
-
-        self.enc = tiktoken.get_encoding('gpt2')
-        tokens = self.enc.encode(text_input)
-        self.tokens = torch.tensor(tokens)
-        print(f'loaded {len(self.tokens)} tokens')
-        print(f'1 epoch = {len(self.tokens) // (B * T)} batches')
-
-        # state
-        self.current_position = 0
-
-    def next_batch(self):
-        B, T = self.B, self.T
-        buf = self.tokens[self.current_position: self.current_position + B * T + 1]
-        x = (buf[:-1]).view(B, T) # inputs
-        y = (buf[1:]).view(B, T) # targets
-        # advance the position in the tensor
-        self.current_position += B*T
-        # if loading the next batch would be out of bounds, reset
-        if self.current_position + (B * T + 1) > len(self.tokens):
-            self.current_position = 0
-        return x, y
-
-def get_model(device):
-    # CHANGES IN CURRENT CODE
-    torch.set_float32_matmul_precision('high')
-    model = GPT(GPTConfig())
-    model.to(device)
-    # model = torch.compile(model)
-    return model
-
-
-
-
-def get_lr(it):
-    # CODE UPDATE HERE
-    # warmup_steps = 10
-    # max_steps = 50
-    warmup_steps = 100
-
-    max_lr = 6e-4
-    min_lr = max_lr * 0.1
-    if it < warmup_steps:
-        return max_lr * (it + 1) / warmup_steps
-    if it > max_steps:
-        return min_lr
-    decay_ratio = (it - warmup_steps) / (max_steps - warmup_steps)
-    assert 0 <= decay_ratio <=1
-    coeff = 0.5 * (1.0 + math.cos(math.pi * decay_ratio))
-    return min_lr + coeff * (max_lr - min_lr)
-
-
-
-# optimizer = torch.optim.AdamW(model.parameters(), lr = 3e-4, betas=(0.9, 0.95), eps=1e-8)
-def train_the_model(train_loader):
-  model = get_model(device)
-  optimizer = model.configure_optimizers(weight_decay=0.1, learning_rate=6e-4, device_type=device)
-  for step in range(max_steps):
-      t0 = time.time()
-      x, y = train_loader.next_batch()
-      x, y = x.to(device), y.to(device)
-      optimizer.zero_grad()
-      # NEW CODE ADDED HERE
-      with torch.autocast(device_type=device, dtype=torch.bfloat16):
-          logits, loss = model(x, y)
-      loss.backward()
-      norm = torch.nn.utils.clip_grad_norm(model.parameters(), 1.0)
-      # NEW CODE
-      lr = get_lr(step)
-      for param_group in optimizer.param_groups:
-          param_group['lr'] = lr
-
-      optimizer.step()
-      torch.cuda.synchronize()
-      t1 = time.time()
-      dt = (t1 - t0) * 1000
-      tokens_per_sec = (train_loader.B * train_loader.T) / (t1 - t0)
-      print(f'step{step} | loss: {loss.item()} | dt: {dt:.2f}ms | tok/sec: {tokens_per_sec: .2f} | norm: {norm:.2f}')
-  return model, loss
-
-
-#From here inference
-def infer_the_model(device, test_loader, save1_or_load0):
-    x, y = test_loader.next_batch()
-    model = get_model(device)
-    if save1_or_load0 == 0:
-        model.load_state_dict(torch.load('model_weights.pth', map_location=torch.device(device)))
-    torch.manual_seed(42)
-    torch.cuda.manual_seed(42)
-    while x.size(1) < max_length:
-        # forward the model to get the logits
-        with torch.no_grad():
-            logits = model(x)[0] # (B, T, vocab_size)
-            # take the logits at the last position
-            logits = logits[:, -1, :] # (B, vocab_size)
-            # get the probabilities
-            probs = F.softmax(logits, dim=-1)
-            # do top-k sampling of 50 (huggingface pipeline default)
-            # topk_probs here becomes (5, 50), topk_indices is (5, 50)
-            topk_probs, topk_indices = torch.topk(probs, 50, dim=-1)
-            # select a token from the top-k probabilities
-            # note: multinomial does not demand the input to sum to 1
-            ix = torch.multinomial(topk_probs, 1) # (B, 1)
-            # gather the corresponding indices
-            xcol = torch.gather(topk_indices, -1, ix) # (B, 1)
-            # append to the sequence
-            x = torch.cat((x, xcol), dim=1)
-
-    # print the generated text
-    retval = ""
-    for i in range(num_return_sequences):
-        tokens = x[i, :max_length].tolist()
-        decoded = test_loader.enc.decode(tokens)
-        print(">", decoded)
-        retval += decoded
-    return retval
+
+import os
+import math
+import time
+import inspect
+from dataclasses import dataclass
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+import tiktoken
+
+#1 --- Seema start here
+class CausalSelfAttention(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        # key, query, value projections for all heads, but in a batch
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
+        # output projection
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
+        self.c_proj.NANGPT_SCALE_INIT = 1
+        # regularization
+        self.n_head = config.n_head
+        self.n_embd = config.n_embd
+        self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size)).view(1, 1, config.block_size, config.block_size))
+
+    def forward(self, x):
+        B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
+        # calculate query, key, values for all heads in batch and move head forward to be the batch dim
+        # nh is "number of heads", hs is "head size", and C (number of channels) = nh * hs
+        # e.g. in GPT-2 (124M), n_head=12, hs=64, so nh*hs=C=768 channels in the Transformer
+        qkv = self.c_attn(x)
+        q, k, v = qkv.split(self.n_embd, dim=2)
+        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+
+        # att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
+        # att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float('-inf'))
+        # att = F.softmax(att, dim=-1)
+        # y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
+
+        y = F.scaled_dot_product_attention(q, k, v, is_causal = True) # Flash attention
+
+        y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
+        # output projection
+        y = self.c_proj(y)
+        return y
+
+
+class MLP(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd)
+        self.gelu    = nn.GELU(approximate='tanh')
+        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd)
+        self.c_proj.NANOGPT_SCALE_INIT = 1
+
+    def forward(self, x):
+        x = self.c_fc(x)
+        x = self.gelu(x)
+        x = self.c_proj(x)
+        return x
+
+class Block(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.ln_1 = nn.LayerNorm(config.n_embd)
+        self.attn = CausalSelfAttention(config)
+        self.ln_2 = nn.LayerNorm(config.n_embd)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+
+@dataclass
+class GPTConfig:
+    block_size: int = 1024 # max sequence length
+    vocab_size: int = 50304 # number of tokens: 50,000 BPE merges + 256 bytes tokens + 1 <|endoftext|> token
+    n_layer: int = 12 # number of layers
+    n_head: int = 12 # number of heads
+    n_embd: int = 768 # embedding dimension
+
+
+
+class GPT(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+
+        self.transformer = nn.ModuleDict(dict(
+            wte = nn.Embedding(config.vocab_size, config.n_embd),
+            wpe = nn.Embedding(config.block_size, config.n_embd),
+            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
+            ln_f = nn.LayerNorm(config.n_embd),
+        ))
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+
+        # weight sharing
+        self.transformer.wte.weight = self.lm_head.weight
+
+        # weight initialization
+        self.apply(self._init_weights)
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            std = 0.02
+            if hasattr(module, 'NANGPT_SCALE_INIT'):
+                std *= (2 * self.config.n_layer) ** -0.5
+            torch.nn.init.normal_(module.weight, mean = 0.0, std = std)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std = 0.02)
+
+#1 --- Seema end here
+
+#============================================================================================================
+
+#2 --- Raja start here
+    def forward(self, idx, targets=None):
+        # idx is of shape (B, T)
+        B, T = idx.size()
+        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
+        # forward the token and posisition embeddings
+        pos = torch.arange(0, T, dtype=torch.long, device=idx.device) # shape (T)
+        pos_emb = self.transformer.wpe(pos) # position embeddings of shape (T, n_embd)
+        tok_emb = self.transformer.wte(idx) # token embeddings of shape (B, T, n_embd)
+        x = tok_emb + pos_emb
+        # forward the blocks of the transformer
+        for block in self.transformer.h:
+            x = block(x)
+        # forward the final layernorm and the classifier
+        x = self.transformer.ln_f(x)
+        logits = self.lm_head(x) # (B, T, vocab_size)
+        loss = None
+        if targets is not None:
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
+        return logits, loss
+
+    def configure_optimizers(self, weight_decay, learning_rate, device_type):
+        # start with all of the candidate parameters (that require grad)
+        param_dict = {pn: p for pn, p in self.named_parameters()}
+        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
+        # create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
+        # i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
+        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
+        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
+        optim_groups = [
+            {'params': decay_params, 'weight_decay': weight_decay},
+            {'params': nodecay_params, 'weight_decay': 0.0}
+        ]
+        num_decay_params = sum(p.numel() for p in decay_params)
+        num_nodecay_params = sum(p.numel() for p in nodecay_params)
+
+        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
+        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
+        # Create AdamW optimizer and use the fused version if it is available
+        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
+        use_fused = fused_available and device_type == "cuda"
+
+        print(f"using fused AdamW: {use_fused}")
+        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9, 0.95), eps=1e-8, fused=use_fused)
+        return optimizer
+
+# model = GPT.from_pretrained('gpt2')
+
+
+#2 --- Raja end here
+
+
+#============================================================================================================
+
+#3 --- Yasaswini start here
+class DataLoaderLite:
+    def __init__(self, B, T, text_input):
+        self.B = B
+        self.T = T
+
+        self.enc = tiktoken.get_encoding('gpt2')
+        tokens = self.enc.encode(text_input)
+        self.tokens = torch.tensor(tokens)
+        print(f'loaded {len(self.tokens)} tokens')
+        print(f'1 epoch = {len(self.tokens) // (B * T)} batches')
+
+        # state
+        self.current_position = 0
+
+    def next_batch(self):
+        B, T = self.B, self.T
+        buf = self.tokens[self.current_position: self.current_position + B * T + 1]
+        x = (buf[:-1]).view(B, T) # inputs
+        y = (buf[1:]).view(B, T) # targets
+        # advance the position in the tensor
+        self.current_position += B*T
+        # if loading the next batch would be out of bounds, reset
+        if self.current_position + (B * T + 1) > len(self.tokens):
+            self.current_position = 0
+        return x, y
+
+def get_model(device):
+    # CHANGES IN CURRENT CODE
+    torch.set_float32_matmul_precision('high')
+    model = GPT(GPTConfig())
+    model.to(device)
+    # model = torch.compile(model)
+    return model
+
+
+
+
+def get_lr(it):
+    # CODE UPDATE HERE
+    # warmup_steps = 10
+    # max_steps = 50
+    warmup_steps = 100
+
+    max_lr = 6e-4
+    min_lr = max_lr * 0.1
+    if it < warmup_steps:
+        return max_lr * (it + 1) / warmup_steps
+    if it > max_steps:
+        return min_lr
+    decay_ratio = (it - warmup_steps) / (max_steps - warmup_steps)
+    assert 0 <= decay_ratio <=1
+    coeff = 0.5 * (1.0 + math.cos(math.pi * decay_ratio))
+    return min_lr + coeff * (max_lr - min_lr)
+
+
+
+# optimizer = torch.optim.AdamW(model.parameters(), lr = 3e-4, betas=(0.9, 0.95), eps=1e-8)
+def train_the_model(train_loader):
+  model = get_model(device)
+  optimizer = model.configure_optimizers(weight_decay=0.1, learning_rate=6e-4, device_type=device)
+  for step in range(max_steps):
+      t0 = time.time()
+      x, y = train_loader.next_batch()
+      x, y = x.to(device), y.to(device)
+      optimizer.zero_grad()
+      # NEW CODE ADDED HERE
+      with torch.autocast(device_type=device, dtype=torch.bfloat16):
+          logits, loss = model(x, y)
+      loss.backward()
+      norm = torch.nn.utils.clip_grad_norm(model.parameters(), 1.0)
+      # NEW CODE
+      lr = get_lr(step)
+      for param_group in optimizer.param_groups:
+          param_group['lr'] = lr
+
+      optimizer.step()
+      torch.cuda.synchronize()
+      t1 = time.time()
+      dt = (t1 - t0) * 1000
+      tokens_per_sec = (train_loader.B * train_loader.T) / (t1 - t0)
+      print(f'step{step} | loss: {loss.item()} | dt: {dt:.2f}ms | tok/sec: {tokens_per_sec: .2f} | norm: {norm:.2f}')
+  return model, loss
+
+
+#From here inference
+def infer_the_model(device, test_loader, save1_or_load0, max_length):
+    x, y = test_loader.next_batch()
+    model = get_model(device)
+    if save1_or_load0 == 0:
+        model.load_state_dict(torch.load('model_weights.pth', map_location=torch.device(device)))
+    torch.manual_seed(42)
+    torch.cuda.manual_seed(42)
+    while x.size(1) < max_length:
+        # forward the model to get the logits
+        with torch.no_grad():
+            logits = model(x)[0] # (B, T, vocab_size)
+            # take the logits at the last position
+            logits = logits[:, -1, :] # (B, vocab_size)
+            # get the probabilities
+            probs = F.softmax(logits, dim=-1)
+            # do top-k sampling of 50 (huggingface pipeline default)
+            # topk_probs here becomes (5, 50), topk_indices is (5, 50)
+            topk_probs, topk_indices = torch.topk(probs, 50, dim=-1)
+            # select a token from the top-k probabilities
+            # note: multinomial does not demand the input to sum to 1
+            ix = torch.multinomial(topk_probs, 1) # (B, 1)
+            # gather the corresponding indices
+            xcol = torch.gather(topk_indices, -1, ix) # (B, 1)
+            # append to the sequence
+            x = torch.cat((x, xcol), dim=1)
+
+    # print the generated text
+    retval = ""
+    for i in range(num_return_sequences):
+        tokens = x[i, :max_length].tolist()
+        decoded = test_loader.enc.decode(tokens)
+        print(">", decoded)
+        retval += decoded
+    return retval