Training in progress, epoch 1

6a3d37d565774c52a8a95e75642966bf/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "ibm/TTM",
+  "adaptive_patching_levels": 3,
+  "architectures": [
+    "TinyTimeMixerForPrediction"
+  ],
+  "context_length": 1024,
+  "d_model": 192,
+  "d_model_scale": 3,
+  "decoder_adaptive_patching_levels": 0,
+  "decoder_d_model": 128,
+  "decoder_d_model_scale": 2,
+  "decoder_mode": "common_channel",
+  "decoder_num_layers": 2,
+  "decoder_raw_residual": false,
+  "dropout": 0.2,
+  "expansion_factor": 2,
+  "frequency_token_vocab_size": 5,
+  "gated_attn": true,
+  "head_dropout": 0.2,
+  "init_processing": true,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mode": "common_channel",
+  "model_type": "tinytimemixer",
+  "norm_eps": 1e-05,
+  "norm_mlp": "LayerNorm",
+  "num_input_channels": 1,
+  "num_layers": 2,
+  "num_patches": 16,
+  "patch_last": true,
+  "patch_length": 64,
+  "patch_stride": 64,
+  "positional_encoding_type": "sincos",
+  "post_init": false,
+  "prediction_channel_indices": null,
+  "prediction_filter_length": null,
+  "prediction_length": 96,
+  "resolution_prefix_tuning": false,
+  "scaling": "std",
+  "self_attn": false,
+  "self_attn_heads": 1,
+  "stride_ratio": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_decoder": true,
+  "use_positional_encoding": false
+}

6a3d37d565774c52a8a95e75642966bf/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a58455dd4af9762c0bec4676cf933d3af9101055dfbbe3cd3f00075b16796db
+size 3804872

cc81c2c05e6d49e7b2919c447ff5f6fe/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "ibm/TTM",
+  "adaptive_patching_levels": 3,
+  "architectures": [
+    "TinyTimeMixerForPrediction"
+  ],
+  "context_length": 1024,
+  "d_model": 192,
+  "d_model_scale": 3,
+  "decoder_adaptive_patching_levels": 0,
+  "decoder_d_model": 128,
+  "decoder_d_model_scale": 2,
+  "decoder_mode": "common_channel",
+  "decoder_num_layers": 2,
+  "decoder_raw_residual": false,
+  "dropout": 0.2,
+  "expansion_factor": 2,
+  "frequency_token_vocab_size": 5,
+  "gated_attn": true,
+  "head_dropout": 0.2,
+  "init_processing": true,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mode": "common_channel",
+  "model_type": "tinytimemixer",
+  "norm_eps": 1e-05,
+  "norm_mlp": "LayerNorm",
+  "num_input_channels": 1,
+  "num_layers": 2,
+  "num_patches": 16,
+  "patch_last": true,
+  "patch_length": 64,
+  "patch_stride": 64,
+  "positional_encoding_type": "sincos",
+  "post_init": false,
+  "prediction_channel_indices": null,
+  "prediction_filter_length": null,
+  "prediction_length": 96,
+  "resolution_prefix_tuning": false,
+  "scaling": "std",
+  "self_attn": false,
+  "self_attn_heads": 1,
+  "stride_ratio": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_decoder": true,
+  "use_positional_encoding": false
+}

cc81c2c05e6d49e7b2919c447ff5f6fe/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d146ccc6e7cd4c5b12bedc6b059435d021526a7846972227070336b83d825160
+size 3804872

gpu_insight/internal/gpu_data_202405301944

@@ -0,0 +1,8 @@
+{"type":"gpu","timestamp":1717065841821,"core_clk":"1410","gpu_idx":0,"power_draw":61,"temp":"32","vmem_clk":"1593"}
+{"power_draw":61,"temp":"33","vmem_clk":"1593","type":"gpu","timestamp":1717065841821,"core_clk":"1410","gpu_idx":1}
+{"vmem_clk":"1593","power_draw":58,"temp":"30","core_clk":"1410","gpu_idx":2,"type":"gpu","timestamp":1717065841821}
+{"type":"gpu","timestamp":1717065841821,"core_clk":"1410","gpu_idx":3,"power_draw":62,"temp":"33","vmem_clk":"1593"}
+{"timestamp":1717065841821,"type":"gpu","gpu_idx":4,"core_clk":"1410","temp":"30","power_draw":64,"vmem_clk":"1593"}
+{"type":"gpu","timestamp":1717065841821,"core_clk":"1410","gpu_idx":5,"power_draw":61,"temp":"32","vmem_clk":"1593"}
+{"power_draw":61,"temp":"31","vmem_clk":"1593","type":"gpu","timestamp":1717065841821,"core_clk":"1410","gpu_idx":6}
+{"timestamp":1717065841821,"type":"gpu","gpu_idx":7,"core_clk":"1410","temp":"32","power_draw":62,"vmem_clk":"1593"}

gpu_insight/user/gpu_data_202405301944

@@ -0,0 +1,9 @@
+{"gpu_idx":0,"timestamp":1717065841821,"vmem_usage_mib":"0","type":"gpu","vmem_usage":"0","usage":"0"}
+{"usage":"0","vmem_usage":"0","type":"gpu","vmem_usage_mib":"0","timestamp":1717065841821,"gpu_idx":1}
+{"usage":"0","vmem_usage":"0","vmem_usage_mib":"0","timestamp":1717065841821,"type":"gpu","gpu_idx":2}
+{"vmem_usage":"0","usage":"0","gpu_idx":3,"vmem_usage_mib":"0","timestamp":1717065841821,"type":"gpu"}
+{"vmem_usage_mib":"0","timestamp":1717065841821,"type":"gpu","gpu_idx":4,"usage":"0","vmem_usage":"0"}
+{"vmem_usage":"0","usage":"0","gpu_idx":5,"vmem_usage_mib":"0","timestamp":1717065841821,"type":"gpu"}
+{"timestamp":1717065841821,"vmem_usage_mib":"0","type":"gpu","gpu_idx":6,"usage":"0","vmem_usage":"0"}
+{"gpu_idx":7,"type":"gpu","vmem_usage_mib":"0","timestamp":1717065841821,"vmem_usage":"0","usage":"0"}
+{"gpu_count":"8","type":"svr","timestamp":1717065841821}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39c02fc129bee831ea168f923c430975aa74e747fa3081de3dbd98b5c08ba52
+oid sha256:a10d15dc96c794e0fb0efe39c58b9f7118ce3eb873a6c29a432b2cab271cef0f
 size 3804872

runs/May30_19-32-13_one/events.out.tfevents.1717065649.one.682896.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c12d2db9c7a29881dbdaae16df8e20b911b58bea51e1b87c7a560191f0c160
+size 359

runs/May30_19-40-50_one/events.out.tfevents.1717065651.one.682896.30

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cfb16e73a6dd2a106edaa2512e7f94efe535f4b51232f6e38e375e07dc3420
+size 8056

runs/May30_19-44-08_one/events.out.tfevents.1717065850.one.2160426.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e27ef1ef5b614269e1d0228ed3b0a7737f9428dc09306257334a807f19de9d
+size 5816

tmplk3ewan2/_remote_module_non_scriptable.py

@@ -0,0 +1,81 @@
+from typing import *
+
+import torch
+import torch.distributed.rpc as rpc
+from torch import Tensor
+from torch._jit_internal import Future
+from torch.distributed.rpc import RRef
+from typing import Tuple  # pyre-ignore: unused import
+
+
+module_interface_cls = None
+
+
+def forward_async(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    return rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+
+
+def forward(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    ret_fut = rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+    return ret_fut.wait()
+
+
+_generated_methods = [
+    forward_async,
+    forward,
+]
+
+
+
+
+def _remote_forward(
+    module_rref: RRef[module_interface_cls], device: str, is_device_map_set: bool, *args, **kwargs):
+    module = module_rref.local_value()
+    device = torch.device(device)
+
+    if device.type != "cuda":
+        return module.forward(*args, **kwargs)
+
+    # If the module is on a cuda device,
+    # move any CPU tensor in args or kwargs to the same cuda device.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.to(device) if isinstance(i, Tensor) else i for i in *args)``.
+    args = (*args,)
+    out_args: Tuple[()] = ()
+    for arg in args:
+        arg = (arg.to(device),) if isinstance(arg, Tensor) else (arg,)
+        out_args = out_args + arg
+
+    kwargs = {**kwargs}
+    for k, v in kwargs.items():
+        if isinstance(v, Tensor):
+            kwargs[k] = kwargs[k].to(device)
+
+    if is_device_map_set:
+        return module.forward(*out_args, **kwargs)
+
+    # If the device map is empty, then only CPU tensors are allowed to send over wire,
+    # so have to move any GPU tensor to CPU in the output.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.cpu() if isinstance(i, Tensor) else i for i in module.forward(*out_args, **kwargs))``.
+    ret: Tuple[()] = ()
+    for i in module.forward(*out_args, **kwargs):
+        i = (i.cpu(),) if isinstance(i, Tensor) else (i,)
+        ret = ret + i
+    return ret

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:745e06af3d2625351d0cec480cd8eb020ae9c1429265188fe4c8522dc0a575da
+oid sha256:5b27962ac8e469ac1c66fbf58f433c3ca5739ac324e0db3e16cafd87de64f050
 size 5048