Upload 13 files

config.json

@@ -0,0 +1,36 @@
+{
+ "architectures": [
+ "MambaForCausalLM"
+ ],
+ "bos_token_id": 0,
+ "conv_kernel": 4,
+ "eos_token_id": 0,
+ "expand": 2,
+ "fused_add_norm": true,
+ "hidden_act": "silu",
+ "hidden_size": 2560,
+ "initializer_range": 0.1,
+ "intermediate_size": 5120,
+ "layer_norm_epsilon": 1e-05,
+ "model_type": "mamba",
+ "n_layer": 48,
+ "num_hidden_layers": 48,
+ "pad_token_id": 0,
+ "pad_vocab_size_multiple": 8,
+ "rescale_prenorm_residual": false,
+ "residual_in_fp32": true,
+ "rms_norm": true,
+ "state_size": 16,
+ "time_step_floor": 0.0001,
+ "time_step_init_scheme": "random",
+ "time_step_max": 0.1,
+ "time_step_min": 0.001,
+ "time_step_rank": 160,
+ "time_step_scale": 1.0,
+ "torch_dtype": "float32",
+ "transformers_version": "4.40.2",
+ "use_bias": false,
+ "use_cache": true,
+ "use_conv_bias": true,
+ "vocab_size": 50280
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 0,
+ "eos_token_id": 0,
+ "pad_token_id": 0,
+ "transformers_version": "4.40.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838dd34d8cb25920d35a5c51cdd9073ca088aaa3b271629d1a816bf1a8a6635b
+size 16867928192

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a678b6cab9205fd1d151e5d26791993f0a96e73f8ba167a9cab93741b13fcac
+size 4969794150

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba90f4f7fa53b1e9100320dc4c8d67c54abcae4b8605172aef6c699ac0eca024
+size 3464130832

pytorch_model.bin.index.json

@@ -0,0 +1,490 @@
+{
+ "metadata": {
+ "total_size": 8433756160
+ },
+ "weight_map": {
+ "backbone.embeddings.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.0.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.1.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.10.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.11.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.12.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.13.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.14.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.15.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.16.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.17.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.18.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.19.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.2.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.20.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.21.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.22.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.23.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.24.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.25.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.26.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.27.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.27.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.27.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.27.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.27.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.27.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.27.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.27.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.27.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.27.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.28.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.28.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.29.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.3.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.3.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.30.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.30.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.31.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.32.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.33.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.34.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.35.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.36.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.37.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.38.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.39.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.4.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.4.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.40.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.40.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.41.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.42.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.43.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.44.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.45.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.46.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.A_log": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.D": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.47.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "backbone.layers.5.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.5.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.6.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.7.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.8.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.A_log": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.D": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.layers.9.norm.weight": "pytorch_model-00001-of-00002.bin",
+ "backbone.norm_f.weight": "pytorch_model-00002-of-00002.bin",
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin"
+ }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc64bf6a873f34fcb769fab5500f16454496f43d925a41af135f38c72a487bd7
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,214 @@
+{
+ "add_bos_token": false,
+ "add_eos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<|padding|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "50254": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50255": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50256": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50257": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50258": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50259": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50260": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50261": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50262": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50263": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50264": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50265": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50266": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50267": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50268": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50269": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50270": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50271": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50272": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50273": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50274": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50275": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50276": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "GPTNeoXTokenizer",
+ "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,1848 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.06357098388017114,
+ "eval_steps": 100000000,
+ "global_step": 7800,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 8.15012613848348e-06,
+ "grad_norm": 43.29102325439453,
+ "learning_rate": 1.0000000000000001e-07,
+ "loss": 81.0533,
+ "step": 1
+ },
+ {
+ "epoch": 0.0002445037841545044,
+ "grad_norm": 42.03493881225586,
+ "learning_rate": 3e-06,
+ "loss": 70.3325,
+ "step": 30
+ },
+ {
+ "epoch": 0.0004890075683090088,
+ "grad_norm": 10.497812271118164,
+ "learning_rate": 6e-06,
+ "loss": 23.8844,
+ "step": 60
+ },
+ {
+ "epoch": 0.0007335113524635132,
+ "grad_norm": 6.692718029022217,
+ "learning_rate": 9e-06,
+ "loss": 11.7198,
+ "step": 90
+ },
+ {
+ "epoch": 0.0009780151366180175,
+ "grad_norm": 9.11446475982666,
+ "learning_rate": 1.2e-05,
+ "loss": 10.3199,
+ "step": 120
+ },
+ {
+ "epoch": 0.001222518920772522,
+ "grad_norm": 16.92243766784668,
+ "learning_rate": 1.5e-05,
+ "loss": 9.5338,
+ "step": 150
+ },
+ {
+ "epoch": 0.0014670227049270264,
+ "grad_norm": 12.929216384887695,
+ "learning_rate": 1.8e-05,
+ "loss": 8.9114,
+ "step": 180
+ },
+ {
+ "epoch": 0.0017115264890815308,
+ "grad_norm": 8.830116271972656,
+ "learning_rate": 2.1e-05,
+ "loss": 8.3867,
+ "step": 210
+ },
+ {
+ "epoch": 0.001956030273236035,
+ "grad_norm": 7.348124980926514,
+ "learning_rate": 2.4e-05,
+ "loss": 8.0113,
+ "step": 240
+ },
+ {
+ "epoch": 0.0022005340573905395,
+ "grad_norm": 12.751787185668945,
+ "learning_rate": 2.7000000000000002e-05,
+ "loss": 7.6093,
+ "step": 270
+ },
+ {
+ "epoch": 0.002445037841545044,
+ "grad_norm": 15.10444164276123,
+ "learning_rate": 3e-05,
+ "loss": 7.3484,
+ "step": 300
+ },
+ {
+ "epoch": 0.0026895416256995483,
+ "grad_norm": 6.653383731842041,
+ "learning_rate": 3.3e-05,
+ "loss": 7.2105,
+ "step": 330
+ },
+ {
+ "epoch": 0.0029340454098540527,
+ "grad_norm": 6.986039161682129,
+ "learning_rate": 3.6e-05,
+ "loss": 7.0228,
+ "step": 360
+ },
+ {
+ "epoch": 0.003178549194008557,
+ "grad_norm": 6.230088710784912,
+ "learning_rate": 3.9000000000000006e-05,
+ "loss": 6.8948,
+ "step": 390
+ },
+ {
+ "epoch": 0.0034230529781630616,
+ "grad_norm": 8.170981407165527,
+ "learning_rate": 4.2e-05,
+ "loss": 6.6965,
+ "step": 420
+ },
+ {
+ "epoch": 0.0036675567623175656,
+ "grad_norm": 5.6345930099487305,
+ "learning_rate": 4.5e-05,
+ "loss": 6.5988,
+ "step": 450
+ },
+ {
+ "epoch": 0.00391206054647207,
+ "grad_norm": 5.156513214111328,
+ "learning_rate": 4.8e-05,
+ "loss": 6.4795,
+ "step": 480
+ },
+ {
+ "epoch": 0.0041565643306265745,
+ "grad_norm": 5.4964189529418945,
+ "learning_rate": 4.999999990869806e-05,
+ "loss": 6.333,
+ "step": 510
+ },
+ {
+ "epoch": 0.004401068114781079,
+ "grad_norm": 3.67378306388855,
+ "learning_rate": 4.999999853916893e-05,
+ "loss": 6.2208,
+ "step": 540
+ },
+ {
+ "epoch": 0.004645571898935583,
+ "grad_norm": 8.507222175598145,
+ "learning_rate": 4.9999995526204936e-05,
+ "loss": 6.1097,
+ "step": 570
+ },
+ {
+ "epoch": 0.004890075683090088,
+ "grad_norm": 3.756618022918701,
+ "learning_rate": 4.999999086980628e-05,
+ "loss": 5.9886,
+ "step": 600
+ },
+ {
+ "epoch": 0.005134579467244592,
+ "grad_norm": 3.8149781227111816,
+ "learning_rate": 4.999998456997326e-05,
+ "loss": 5.8779,
+ "step": 630
+ },
+ {
+ "epoch": 0.005379083251399097,
+ "grad_norm": 3.840543270111084,
+ "learning_rate": 4.999997662670628e-05,
+ "loss": 5.805,
+ "step": 660
+ },
+ {
+ "epoch": 0.005623587035553601,
+ "grad_norm": 3.4208931922912598,
+ "learning_rate": 4.999996704000589e-05,
+ "loss": 5.6992,
+ "step": 690
+ },
+ {
+ "epoch": 0.0058680908197081055,
+ "grad_norm": 3.2975683212280273,
+ "learning_rate": 4.99999558098727e-05,
+ "loss": 5.6531,
+ "step": 720
+ },
+ {
+ "epoch": 0.00611259460386261,
+ "grad_norm": 4.05631160736084,
+ "learning_rate": 4.9999942936307445e-05,
+ "loss": 5.554,
+ "step": 750
+ },
+ {
+ "epoch": 0.006357098388017114,
+ "grad_norm": 3.1539864540100098,
+ "learning_rate": 4.9999928419310994e-05,
+ "loss": 5.4931,
+ "step": 780
+ },
+ {
+ "epoch": 0.006601602172171619,
+ "grad_norm": 4.811732292175293,
+ "learning_rate": 4.999991225888427e-05,
+ "loss": 5.4204,
+ "step": 810
+ },
+ {
+ "epoch": 0.006846105956326123,
+ "grad_norm": 2.9593210220336914,
+ "learning_rate": 4.999989445502837e-05,
+ "loss": 5.3687,
+ "step": 840
+ },
+ {
+ "epoch": 0.007090609740480627,
+ "grad_norm": 3.942239284515381,
+ "learning_rate": 4.9999875007744436e-05,
+ "loss": 5.3238,
+ "step": 870
+ },
+ {
+ "epoch": 0.007335113524635131,
+ "grad_norm": 2.29752254486084,
+ "learning_rate": 4.9999853917033756e-05,
+ "loss": 5.2423,
+ "step": 900
+ },
+ {
+ "epoch": 0.007579617308789636,
+ "grad_norm": 2.243770122528076,
+ "learning_rate": 4.999983118289773e-05,
+ "loss": 5.2384,
+ "step": 930
+ },
+ {
+ "epoch": 0.00782412109294414,
+ "grad_norm": 2.5572686195373535,
+ "learning_rate": 4.999980680533782e-05,
+ "loss": 5.1761,
+ "step": 960
+ },
+ {
+ "epoch": 0.008068624877098645,
+ "grad_norm": 2.4739913940429688,
+ "learning_rate": 4.999978078435567e-05,
+ "loss": 5.1215,
+ "step": 990
+ },
+ {
+ "epoch": 0.008313128661253149,
+ "grad_norm": 1.6927807331085205,
+ "learning_rate": 4.999975311995295e-05,
+ "loss": 5.1264,
+ "step": 1020
+ },
+ {
+ "epoch": 0.008557632445407654,
+ "grad_norm": 2.3166885375976562,
+ "learning_rate": 4.99997238121315e-05,
+ "loss": 5.0469,
+ "step": 1050
+ },
+ {
+ "epoch": 0.008802136229562158,
+ "grad_norm": 1.69430410861969,
+ "learning_rate": 4.999969286089325e-05,
+ "loss": 5.005,
+ "step": 1080
+ },
+ {
+ "epoch": 0.009046640013716663,
+ "grad_norm": 2.0859012603759766,
+ "learning_rate": 4.9999660266240235e-05,
+ "loss": 4.9693,
+ "step": 1110
+ },
+ {
+ "epoch": 0.009291143797871167,
+ "grad_norm": 1.7291619777679443,
+ "learning_rate": 4.9999626028174585e-05,
+ "loss": 4.9352,
+ "step": 1140
+ },
+ {
+ "epoch": 0.00953564758202567,
+ "grad_norm": 1.5966330766677856,
+ "learning_rate": 4.999959014669856e-05,
+ "loss": 4.87,
+ "step": 1170
+ },
+ {
+ "epoch": 0.009780151366180176,
+ "grad_norm": 1.9011143445968628,
+ "learning_rate": 4.9999552621814513e-05,
+ "loss": 4.8772,
+ "step": 1200
+ },
+ {
+ "epoch": 0.010024655150334679,
+ "grad_norm": 1.701004981994629,
+ "learning_rate": 4.9999513453524917e-05,
+ "loss": 4.8484,
+ "step": 1230
+ },
+ {
+ "epoch": 0.010269158934489184,
+ "grad_norm": 2.171808958053589,
+ "learning_rate": 4.9999472641832336e-05,
+ "loss": 4.8233,
+ "step": 1260
+ },
+ {
+ "epoch": 0.010513662718643688,
+ "grad_norm": 1.4896094799041748,
+ "learning_rate": 4.999943018673946e-05,
+ "loss": 4.7921,
+ "step": 1290
+ },
+ {
+ "epoch": 0.010758166502798193,
+ "grad_norm": 2.112971544265747,
+ "learning_rate": 4.999938608824909e-05,
+ "loss": 4.7908,
+ "step": 1320
+ },
+ {
+ "epoch": 0.011002670286952697,
+ "grad_norm": 1.7113062143325806,
+ "learning_rate": 4.999934034636411e-05,
+ "loss": 4.7186,
+ "step": 1350
+ },
+ {
+ "epoch": 0.011247174071107202,
+ "grad_norm": 2.099663019180298,
+ "learning_rate": 4.999929296108753e-05,
+ "loss": 4.7112,
+ "step": 1380
+ },
+ {
+ "epoch": 0.011491677855261706,
+ "grad_norm": 1.40205979347229,
+ "learning_rate": 4.9999243932422466e-05,
+ "loss": 4.6701,
+ "step": 1410
+ },
+ {
+ "epoch": 0.011736181639416211,
+ "grad_norm": 1.53098726272583,
+ "learning_rate": 4.999919326037215e-05,
+ "loss": 4.6786,
+ "step": 1440
+ },
+ {
+ "epoch": 0.011980685423570715,
+ "grad_norm": 1.7461609840393066,
+ "learning_rate": 4.99991409449399e-05,
+ "loss": 4.6614,
+ "step": 1470
+ },
+ {
+ "epoch": 0.01222518920772522,
+ "grad_norm": 1.6045819520950317,
+ "learning_rate": 4.999908698612916e-05,
+ "loss": 4.6233,
+ "step": 1500
+ },
+ {
+ "epoch": 0.012469692991879723,
+ "grad_norm": 1.351077675819397,
+ "learning_rate": 4.9999031383943486e-05,
+ "loss": 4.626,
+ "step": 1530
+ },
+ {
+ "epoch": 0.012714196776034229,
+ "grad_norm": 1.4363055229187012,
+ "learning_rate": 4.999897413838651e-05,
+ "loss": 4.5781,
+ "step": 1560
+ },
+ {
+ "epoch": 0.012958700560188732,
+ "grad_norm": 1.1321336030960083,
+ "learning_rate": 4.999891524946202e-05,
+ "loss": 4.5492,
+ "step": 1590
+ },
+ {
+ "epoch": 0.013203204344343238,
+ "grad_norm": 1.2755215167999268,
+ "learning_rate": 4.999885471717387e-05,
+ "loss": 4.5444,
+ "step": 1620
+ },
+ {
+ "epoch": 0.013447708128497741,
+ "grad_norm": 1.471504807472229,
+ "learning_rate": 4.999879254152605e-05,
+ "loss": 4.5247,
+ "step": 1650
+ },
+ {
+ "epoch": 0.013692211912652246,
+ "grad_norm": 1.3664900064468384,
+ "learning_rate": 4.999872872252265e-05,
+ "loss": 4.5158,
+ "step": 1680
+ },
+ {
+ "epoch": 0.01393671569680675,
+ "grad_norm": 1.360611915588379,
+ "learning_rate": 4.999866326016785e-05,
+ "loss": 4.498,
+ "step": 1710
+ },
+ {
+ "epoch": 0.014181219480961254,
+ "grad_norm": 1.43533456325531,
+ "learning_rate": 4.999859615446596e-05,
+ "loss": 4.5035,
+ "step": 1740
+ },
+ {
+ "epoch": 0.014425723265115759,
+ "grad_norm": 1.4639947414398193,
+ "learning_rate": 4.99985274054214e-05,
+ "loss": 4.4533,
+ "step": 1770
+ },
+ {
+ "epoch": 0.014670227049270262,
+ "grad_norm": 1.438585638999939,
+ "learning_rate": 4.999845701303868e-05,
+ "loss": 4.4484,
+ "step": 1800
+ },
+ {
+ "epoch": 0.014914730833424768,
+ "grad_norm": 1.1868066787719727,
+ "learning_rate": 4.999838497732243e-05,
+ "loss": 4.4516,
+ "step": 1830
+ },
+ {
+ "epoch": 0.015159234617579271,
+ "grad_norm": 1.1804672479629517,
+ "learning_rate": 4.999831129827739e-05,
+ "loss": 4.4378,
+ "step": 1860
+ },
+ {
+ "epoch": 0.015403738401733777,
+ "grad_norm": 1.127652645111084,
+ "learning_rate": 4.9998235975908394e-05,
+ "loss": 4.4,
+ "step": 1890
+ },
+ {
+ "epoch": 0.01564824218588828,
+ "grad_norm": 1.2617137432098389,
+ "learning_rate": 4.99981590102204e-05,
+ "loss": 4.3802,
+ "step": 1920
+ },
+ {
+ "epoch": 0.015892745970042785,
+ "grad_norm": 1.4249097108840942,
+ "learning_rate": 4.9998080401218464e-05,
+ "loss": 4.3689,
+ "step": 1950
+ },
+ {
+ "epoch": 0.01613724975419729,
+ "grad_norm": 1.0717036724090576,
+ "learning_rate": 4.999800014890777e-05,
+ "loss": 4.3645,
+ "step": 1980
+ },
+ {
+ "epoch": 0.016381753538351793,
+ "grad_norm": 1.414404273033142,
+ "learning_rate": 4.9997918253293555e-05,
+ "loss": 4.343,
+ "step": 2010
+ },
+ {
+ "epoch": 0.016626257322506298,
+ "grad_norm": 1.1941649913787842,
+ "learning_rate": 4.999783471438124e-05,
+ "loss": 4.3271,
+ "step": 2040
+ },
+ {
+ "epoch": 0.016870761106660803,
+ "grad_norm": 1.0737369060516357,
+ "learning_rate": 4.999774953217631e-05,
+ "loss": 4.3223,
+ "step": 2070
+ },
+ {
+ "epoch": 0.01711526489081531,
+ "grad_norm": 1.2367453575134277,
+ "learning_rate": 4.9997662706684345e-05,
+ "loss": 4.3106,
+ "step": 2100
+ },
+ {
+ "epoch": 0.01735976867496981,
+ "grad_norm": 1.0919674634933472,
+ "learning_rate": 4.999757423791107e-05,
+ "loss": 4.2916,
+ "step": 2130
+ },
+ {
+ "epoch": 0.017604272459124316,
+ "grad_norm": 1.2348527908325195,
+ "learning_rate": 4.9997484125862306e-05,
+ "loss": 4.2935,
+ "step": 2160
+ },
+ {
+ "epoch": 0.01784877624327882,
+ "grad_norm": 1.173093318939209,
+ "learning_rate": 4.999739237054395e-05,
+ "loss": 4.2761,
+ "step": 2190
+ },
+ {
+ "epoch": 0.018093280027433326,
+ "grad_norm": 1.1982988119125366,
+ "learning_rate": 4.9997298971962065e-05,
+ "loss": 4.2619,
+ "step": 2220
+ },
+ {
+ "epoch": 0.018337783811587828,
+ "grad_norm": 1.4401408433914185,
+ "learning_rate": 4.999720393012277e-05,
+ "loss": 4.2672,
+ "step": 2250
+ },
+ {
+ "epoch": 0.018582287595742333,
+ "grad_norm": 1.0311753749847412,
+ "learning_rate": 4.999710724503233e-05,
+ "loss": 4.2272,
+ "step": 2280
+ },
+ {
+ "epoch": 0.01882679137989684,
+ "grad_norm": 1.4242304563522339,
+ "learning_rate": 4.9997008916697075e-05,
+ "loss": 4.2415,
+ "step": 2310
+ },
+ {
+ "epoch": 0.01907129516405134,
+ "grad_norm": 1.039548397064209,
+ "learning_rate": 4.999690894512349e-05,
+ "loss": 4.2086,
+ "step": 2340
+ },
+ {
+ "epoch": 0.019315798948205846,
+ "grad_norm": 1.1213486194610596,
+ "learning_rate": 4.999680733031814e-05,
+ "loss": 4.2043,
+ "step": 2370
+ },
+ {
+ "epoch": 0.01956030273236035,
+ "grad_norm": 1.0591011047363281,
+ "learning_rate": 4.9996704072287716e-05,
+ "loss": 4.1894,
+ "step": 2400
+ },
+ {
+ "epoch": 0.019804806516514856,
+ "grad_norm": 1.0503829717636108,
+ "learning_rate": 4.9996599171038984e-05,
+ "loss": 4.184,
+ "step": 2430
+ },
+ {
+ "epoch": 0.020049310300669358,
+ "grad_norm": 1.068516492843628,
+ "learning_rate": 4.999649262657886e-05,
+ "loss": 4.1918,
+ "step": 2460
+ },
+ {
+ "epoch": 0.020293814084823864,
+ "grad_norm": 0.9620047211647034,
+ "learning_rate": 4.999638443891434e-05,
+ "loss": 4.182,
+ "step": 2490
+ },
+ {
+ "epoch": 0.02053831786897837,
+ "grad_norm": 0.9728343486785889,
+ "learning_rate": 4.999627460805253e-05,
+ "loss": 4.1746,
+ "step": 2520
+ },
+ {
+ "epoch": 0.020782821653132874,
+ "grad_norm": 0.990840494632721,
+ "learning_rate": 4.999616313400066e-05,
+ "loss": 4.1339,
+ "step": 2550
+ },
+ {
+ "epoch": 0.021027325437287376,
+ "grad_norm": 1.0678601264953613,
+ "learning_rate": 4.999605001676605e-05,
+ "loss": 4.1548,
+ "step": 2580
+ },
+ {
+ "epoch": 0.02127182922144188,
+ "grad_norm": 1.1837236881256104,
+ "learning_rate": 4.9995935256356144e-05,
+ "loss": 4.1508,
+ "step": 2610
+ },
+ {
+ "epoch": 0.021516333005596387,
+ "grad_norm": 1.0381749868392944,
+ "learning_rate": 4.9995818852778476e-05,
+ "loss": 4.0977,
+ "step": 2640
+ },
+ {
+ "epoch": 0.021760836789750892,
+ "grad_norm": 0.9649094343185425,
+ "learning_rate": 4.999570080604071e-05,
+ "loss": 4.1405,
+ "step": 2670
+ },
+ {
+ "epoch": 0.022005340573905394,
+ "grad_norm": 1.1858196258544922,
+ "learning_rate": 4.99955811161506e-05,
+ "loss": 4.1242,
+ "step": 2700
+ },
+ {
+ "epoch": 0.0222498443580599,
+ "grad_norm": 1.035134196281433,
+ "learning_rate": 4.9995459783116004e-05,
+ "loss": 4.1042,
+ "step": 2730
+ },
+ {
+ "epoch": 0.022494348142214404,
+ "grad_norm": 1.0874470472335815,
+ "learning_rate": 4.999533680694493e-05,
+ "loss": 4.0951,
+ "step": 2760
+ },
+ {
+ "epoch": 0.02273885192636891,
+ "grad_norm": 1.5923190116882324,
+ "learning_rate": 4.9995212187645416e-05,
+ "loss": 4.1031,
+ "step": 2790
+ },
+ {
+ "epoch": 0.02298335571052341,
+ "grad_norm": 0.935354471206665,
+ "learning_rate": 4.9995085925225693e-05,
+ "loss": 4.0804,
+ "step": 2820
+ },
+ {
+ "epoch": 0.023227859494677917,
+ "grad_norm": 1.6059459447860718,
+ "learning_rate": 4.999495801969404e-05,
+ "loss": 4.0703,
+ "step": 2850
+ },
+ {
+ "epoch": 0.023472363278832422,
+ "grad_norm": 1.1116045713424683,
+ "learning_rate": 4.9994828471058876e-05,
+ "loss": 4.0579,
+ "step": 2880
+ },
+ {
+ "epoch": 0.023716867062986924,
+ "grad_norm": 1.0068392753601074,
+ "learning_rate": 4.9994697279328714e-05,
+ "loss": 4.0635,
+ "step": 2910
+ },
+ {
+ "epoch": 0.02396137084714143,
+ "grad_norm": 0.9715657234191895,
+ "learning_rate": 4.9994564444512176e-05,
+ "loss": 4.068,
+ "step": 2940
+ },
+ {
+ "epoch": 0.024205874631295934,
+ "grad_norm": 1.1550418138504028,
+ "learning_rate": 4.9994429966618e-05,
+ "loss": 4.0416,
+ "step": 2970
+ },
+ {
+ "epoch": 0.02445037841545044,
+ "grad_norm": 1.1463241577148438,
+ "learning_rate": 4.999429384565502e-05,
+ "loss": 4.0224,
+ "step": 3000
+ },
+ {
+ "epoch": 0.02469488219960494,
+ "grad_norm": 0.9614786505699158,
+ "learning_rate": 4.999415608163217e-05,
+ "loss": 4.0092,
+ "step": 3030
+ },
+ {
+ "epoch": 0.024939385983759447,
+ "grad_norm": 1.0928614139556885,
+ "learning_rate": 4.999401667455854e-05,
+ "loss": 4.0083,
+ "step": 3060
+ },
+ {
+ "epoch": 0.025183889767913952,
+ "grad_norm": 1.0884851217269897,
+ "learning_rate": 4.9993875624443274e-05,
+ "loss": 4.0251,
+ "step": 3090
+ },
+ {
+ "epoch": 0.025428393552068457,
+ "grad_norm": 1.0158635377883911,
+ "learning_rate": 4.9993732931295646e-05,
+ "loss": 3.9629,
+ "step": 3120
+ },
+ {
+ "epoch": 0.02567289733622296,
+ "grad_norm": 1.0032926797866821,
+ "learning_rate": 4.999358859512503e-05,
+ "loss": 4.0015,
+ "step": 3150
+ },
+ {
+ "epoch": 0.025917401120377465,
+ "grad_norm": 0.9303460121154785,
+ "learning_rate": 4.9993442615940936e-05,
+ "loss": 4.0066,
+ "step": 3180
+ },
+ {
+ "epoch": 0.02616190490453197,
+ "grad_norm": 1.0750280618667603,
+ "learning_rate": 4.999329499375292e-05,
+ "loss": 3.9937,
+ "step": 3210
+ },
+ {
+ "epoch": 0.026406408688686475,
+ "grad_norm": 1.2123857736587524,
+ "learning_rate": 4.999314572857074e-05,
+ "loss": 3.9891,
+ "step": 3240
+ },
+ {
+ "epoch": 0.026650912472840977,
+ "grad_norm": 0.988030731678009,
+ "learning_rate": 4.9992994820404174e-05,
+ "loss": 3.9779,
+ "step": 3270
+ },
+ {
+ "epoch": 0.026895416256995482,
+ "grad_norm": 1.0025092363357544,
+ "learning_rate": 4.999284226926314e-05,
+ "loss": 3.9684,
+ "step": 3300
+ },
+ {
+ "epoch": 0.027139920041149988,
+ "grad_norm": 0.9497402310371399,
+ "learning_rate": 4.999268807515768e-05,
+ "loss": 3.9542,
+ "step": 3330
+ },
+ {
+ "epoch": 0.027384423825304493,
+ "grad_norm": 0.9898300766944885,
+ "learning_rate": 4.999253223809792e-05,
+ "loss": 3.9462,
+ "step": 3360
+ },
+ {
+ "epoch": 0.027628927609458995,
+ "grad_norm": 0.8951054215431213,
+ "learning_rate": 4.999237475809411e-05,
+ "loss": 3.9535,
+ "step": 3390
+ },
+ {
+ "epoch": 0.0278734313936135,
+ "grad_norm": 1.1410372257232666,
+ "learning_rate": 4.99922156351566e-05,
+ "loss": 3.9701,
+ "step": 3420
+ },
+ {
+ "epoch": 0.028117935177768005,
+ "grad_norm": 0.9642576575279236,
+ "learning_rate": 4.999205486929586e-05,
+ "loss": 3.9532,
+ "step": 3450
+ },
+ {
+ "epoch": 0.028362438961922507,
+ "grad_norm": 0.9304039478302002,
+ "learning_rate": 4.999189246052245e-05,
+ "loss": 3.9335,
+ "step": 3480
+ },
+ {
+ "epoch": 0.028606942746077012,
+ "grad_norm": 0.9684301614761353,
+ "learning_rate": 4.999172840884704e-05,
+ "loss": 3.9289,
+ "step": 3510
+ },
+ {
+ "epoch": 0.028851446530231518,
+ "grad_norm": 0.9566449522972107,
+ "learning_rate": 4.999156271428043e-05,
+ "loss": 3.92,
+ "step": 3540
+ },
+ {
+ "epoch": 0.029095950314386023,
+ "grad_norm": 0.9796332120895386,
+ "learning_rate": 4.9991395376833496e-05,
+ "loss": 3.9173,
+ "step": 3570
+ },
+ {
+ "epoch": 0.029340454098540525,
+ "grad_norm": 0.939052164554596,
+ "learning_rate": 4.999122639651725e-05,
+ "loss": 3.8938,
+ "step": 3600
+ },
+ {
+ "epoch": 0.02958495788269503,
+ "grad_norm": 0.8773409724235535,
+ "learning_rate": 4.9991055773342795e-05,
+ "loss": 3.9225,
+ "step": 3630
+ },
+ {
+ "epoch": 0.029829461666849535,
+ "grad_norm": 0.9443736672401428,
+ "learning_rate": 4.9990883507321354e-05,
+ "loss": 3.8889,
+ "step": 3660
+ },
+ {
+ "epoch": 0.03007396545100404,
+ "grad_norm": 0.9129781723022461,
+ "learning_rate": 4.999070959846424e-05,
+ "loss": 3.894,
+ "step": 3690
+ },
+ {
+ "epoch": 0.030318469235158543,
+ "grad_norm": 0.988441526889801,
+ "learning_rate": 4.999053404678289e-05,
+ "loss": 3.8968,
+ "step": 3720
+ },
+ {
+ "epoch": 0.030562973019313048,
+ "grad_norm": 1.0134508609771729,
+ "learning_rate": 4.999035685228884e-05,
+ "loss": 3.873,
+ "step": 3750
+ },
+ {
+ "epoch": 0.030807476803467553,
+ "grad_norm": 0.9853084087371826,
+ "learning_rate": 4.999017801499375e-05,
+ "loss": 3.8921,
+ "step": 3780
+ },
+ {
+ "epoch": 0.03105198058762206,
+ "grad_norm": 1.0263316631317139,
+ "learning_rate": 4.998999753490937e-05,
+ "loss": 3.8691,
+ "step": 3810
+ },
+ {
+ "epoch": 0.03129648437177656,
+ "grad_norm": 1.2496927976608276,
+ "learning_rate": 4.998981541204757e-05,
+ "loss": 3.8631,
+ "step": 3840
+ },
+ {
+ "epoch": 0.031540988155931066,
+ "grad_norm": 1.2647733688354492,
+ "learning_rate": 4.998963164642031e-05,
+ "loss": 3.8676,
+ "step": 3870
+ },
+ {
+ "epoch": 0.03178549194008557,
+ "grad_norm": 0.8532811403274536,
+ "learning_rate": 4.9989446238039676e-05,
+ "loss": 3.8196,
+ "step": 3900
+ },
+ {
+ "epoch": 0.032029995724240076,
+ "grad_norm": 0.9394932985305786,
+ "learning_rate": 4.998925918691786e-05,
+ "loss": 3.8464,
+ "step": 3930
+ },
+ {
+ "epoch": 0.03227449950839458,
+ "grad_norm": 0.9216808676719666,
+ "learning_rate": 4.998907049306715e-05,
+ "loss": 3.8294,
+ "step": 3960
+ },
+ {
+ "epoch": 0.03251900329254909,
+ "grad_norm": 0.9735797047615051,
+ "learning_rate": 4.998888015649996e-05,
+ "loss": 3.8412,
+ "step": 3990
+ },
+ {
+ "epoch": 0.032763507076703585,
+ "grad_norm": 0.9803655743598938,
+ "learning_rate": 4.99886881772288e-05,
+ "loss": 3.834,
+ "step": 4020
+ },
+ {
+ "epoch": 0.03300801086085809,
+ "grad_norm": 0.8677938580513,
+ "learning_rate": 4.998849455526628e-05,
+ "loss": 3.8325,
+ "step": 4050
+ },
+ {
+ "epoch": 0.033252514645012596,
+ "grad_norm": 1.0530720949172974,
+ "learning_rate": 4.998829929062515e-05,
+ "loss": 3.8125,
+ "step": 4080
+ },
+ {
+ "epoch": 0.0334970184291671,
+ "grad_norm": 0.9517835378646851,
+ "learning_rate": 4.998810238331822e-05,
+ "loss": 3.8079,
+ "step": 4110
+ },
+ {
+ "epoch": 0.033741522213321606,
+ "grad_norm": 0.9056320190429688,
+ "learning_rate": 4.998790383335845e-05,
+ "loss": 3.8023,
+ "step": 4140
+ },
+ {
+ "epoch": 0.03398602599747611,
+ "grad_norm": 1.042631983757019,
+ "learning_rate": 4.9987703640758894e-05,
+ "loss": 3.8089,
+ "step": 4170
+ },
+ {
+ "epoch": 0.03423052978163062,
+ "grad_norm": 1.003548502922058,
+ "learning_rate": 4.99875018055327e-05,
+ "loss": 3.8088,
+ "step": 4200
+ },
+ {
+ "epoch": 0.034475033565785115,
+ "grad_norm": 0.9754064083099365,
+ "learning_rate": 4.998729832769315e-05,
+ "loss": 3.7969,
+ "step": 4230
+ },
+ {
+ "epoch": 0.03471953734993962,
+ "grad_norm": 0.9784180521965027,
+ "learning_rate": 4.998709320725361e-05,
+ "loss": 3.8066,
+ "step": 4260
+ },
+ {
+ "epoch": 0.034964041134094126,
+ "grad_norm": 0.9522731900215149,
+ "learning_rate": 4.998688644422756e-05,
+ "loss": 3.8062,
+ "step": 4290
+ },
+ {
+ "epoch": 0.03520854491824863,
+ "grad_norm": 1.0362435579299927,
+ "learning_rate": 4.998667803862861e-05,
+ "loss": 3.8007,
+ "step": 4320
+ },
+ {
+ "epoch": 0.03545304870240314,
+ "grad_norm": 0.899608850479126,
+ "learning_rate": 4.9986467990470445e-05,
+ "loss": 3.8013,
+ "step": 4350
+ },
+ {
+ "epoch": 0.03569755248655764,
+ "grad_norm": 0.9725902676582336,
+ "learning_rate": 4.998625629976688e-05,
+ "loss": 3.7688,
+ "step": 4380
+ },
+ {
+ "epoch": 0.03594205627071215,
+ "grad_norm": 0.9904030561447144,
+ "learning_rate": 4.998604296653182e-05,
+ "loss": 3.7503,
+ "step": 4410
+ },
+ {
+ "epoch": 0.03618656005486665,
+ "grad_norm": 0.9177742004394531,
+ "learning_rate": 4.99858279907793e-05,
+ "loss": 3.7664,
+ "step": 4440
+ },
+ {
+ "epoch": 0.03643106383902115,
+ "grad_norm": 0.964356005191803,
+ "learning_rate": 4.998561137252346e-05,
+ "loss": 3.7574,
+ "step": 4470
+ },
+ {
+ "epoch": 0.036675567623175656,
+ "grad_norm": 1.0006535053253174,
+ "learning_rate": 4.9985393111778525e-05,
+ "loss": 3.7616,
+ "step": 4500
+ },
+ {
+ "epoch": 0.03692007140733016,
+ "grad_norm": 0.9334198236465454,
+ "learning_rate": 4.998517320855884e-05,
+ "loss": 3.776,
+ "step": 4530
+ },
+ {
+ "epoch": 0.03716457519148467,
+ "grad_norm": 0.9192038774490356,
+ "learning_rate": 4.998495166287887e-05,
+ "loss": 3.7552,
+ "step": 4560
+ },
+ {
+ "epoch": 0.03740907897563917,
+ "grad_norm": 0.9278284311294556,
+ "learning_rate": 4.998472847475318e-05,
+ "loss": 3.7508,
+ "step": 4590
+ },
+ {
+ "epoch": 0.03765358275979368,
+ "grad_norm": 0.870951771736145,
+ "learning_rate": 4.998450364419643e-05,
+ "loss": 3.7419,
+ "step": 4620
+ },
+ {
+ "epoch": 0.03789808654394818,
+ "grad_norm": 0.8986937403678894,
+ "learning_rate": 4.998427717122342e-05,
+ "loss": 3.7285,
+ "step": 4650
+ },
+ {
+ "epoch": 0.03814259032810268,
+ "grad_norm": 0.8922073841094971,
+ "learning_rate": 4.9984049055849024e-05,
+ "loss": 3.7252,
+ "step": 4680
+ },
+ {
+ "epoch": 0.038387094112257186,
+ "grad_norm": 0.8716844916343689,
+ "learning_rate": 4.9983819298088234e-05,
+ "loss": 3.7243,
+ "step": 4710
+ },
+ {
+ "epoch": 0.03863159789641169,
+ "grad_norm": 0.9074581861495972,
+ "learning_rate": 4.9983587897956166e-05,
+ "loss": 3.7254,
+ "step": 4740
+ },
+ {
+ "epoch": 0.0388761016805662,
+ "grad_norm": 0.8903953433036804,
+ "learning_rate": 4.998335485546802e-05,
+ "loss": 3.7363,
+ "step": 4770
+ },
+ {
+ "epoch": 0.0391206054647207,
+ "grad_norm": 1.0858160257339478,
+ "learning_rate": 4.998312017063912e-05,
+ "loss": 3.708,
+ "step": 4800
+ },
+ {
+ "epoch": 0.03936510924887521,
+ "grad_norm": 1.1008403301239014,
+ "learning_rate": 4.9982883843484895e-05,
+ "loss": 3.727,
+ "step": 4830
+ },
+ {
+ "epoch": 0.03960961303302971,
+ "grad_norm": 0.9895632863044739,
+ "learning_rate": 4.998264587402088e-05,
+ "loss": 3.7383,
+ "step": 4860
+ },
+ {
+ "epoch": 0.03985411681718422,
+ "grad_norm": 1.0174016952514648,
+ "learning_rate": 4.9982406262262726e-05,
+ "loss": 3.6967,
+ "step": 4890
+ },
+ {
+ "epoch": 0.040098620601338716,
+ "grad_norm": 0.9164692163467407,
+ "learning_rate": 4.9982165008226175e-05,
+ "loss": 3.7038,
+ "step": 4920
+ },
+ {
+ "epoch": 0.04034312438549322,
+ "grad_norm": 0.8442469835281372,
+ "learning_rate": 4.998192211192708e-05,
+ "loss": 3.7045,
+ "step": 4950
+ },
+ {
+ "epoch": 0.04058762816964773,
+ "grad_norm": 0.9134944677352905,
+ "learning_rate": 4.9981677573381423e-05,
+ "loss": 3.6909,
+ "step": 4980
+ },
+ {
+ "epoch": 0.04083213195380223,
+ "grad_norm": 0.9397178292274475,
+ "learning_rate": 4.9981431392605274e-05,
+ "loss": 3.7087,
+ "step": 5010
+ },
+ {
+ "epoch": 0.04107663573795674,
+ "grad_norm": 1.1442530155181885,
+ "learning_rate": 4.998118356961481e-05,
+ "loss": 3.6804,
+ "step": 5040
+ },
+ {
+ "epoch": 0.04132113952211124,
+ "grad_norm": 0.8651236891746521,
+ "learning_rate": 4.998093410442632e-05,
+ "loss": 3.668,
+ "step": 5070
+ },
+ {
+ "epoch": 0.04156564330626575,
+ "grad_norm": 1.0404279232025146,
+ "learning_rate": 4.998068299705623e-05,
+ "loss": 3.673,
+ "step": 5100
+ },
+ {
+ "epoch": 0.041810147090420254,
+ "grad_norm": 0.9545896053314209,
+ "learning_rate": 4.9980430247521014e-05,
+ "loss": 3.6635,
+ "step": 5130
+ },
+ {
+ "epoch": 0.04205465087457475,
+ "grad_norm": 0.9344103932380676,
+ "learning_rate": 4.998017585583731e-05,
+ "loss": 3.6834,
+ "step": 5160
+ },
+ {
+ "epoch": 0.04229915465872926,
+ "grad_norm": 1.0414049625396729,
+ "learning_rate": 4.9979919822021824e-05,
+ "loss": 3.6868,
+ "step": 5190
+ },
+ {
+ "epoch": 0.04254365844288376,
+ "grad_norm": 0.9391636252403259,
+ "learning_rate": 4.99796621460914e-05,
+ "loss": 3.6671,
+ "step": 5220
+ },
+ {
+ "epoch": 0.04278816222703827,
+ "grad_norm": 0.8789961934089661,
+ "learning_rate": 4.9979402828062963e-05,
+ "loss": 3.6575,
+ "step": 5250
+ },
+ {
+ "epoch": 0.04303266601119277,
+ "grad_norm": 0.8953958749771118,
+ "learning_rate": 4.997914186795358e-05,
+ "loss": 3.6741,
+ "step": 5280
+ },
+ {
+ "epoch": 0.04327716979534728,
+ "grad_norm": 0.8470034003257751,
+ "learning_rate": 4.9978879265780385e-05,
+ "loss": 3.6517,
+ "step": 5310
+ },
+ {
+ "epoch": 0.043521673579501784,
+ "grad_norm": 0.8863801956176758,
+ "learning_rate": 4.997861502156066e-05,
+ "loss": 3.6667,
+ "step": 5340
+ },
+ {
+ "epoch": 0.04376617736365628,
+ "grad_norm": 0.9392006993293762,
+ "learning_rate": 4.997834913531176e-05,
+ "loss": 3.6278,
+ "step": 5370
+ },
+ {
+ "epoch": 0.04401068114781079,
+ "grad_norm": 0.8935637474060059,
+ "learning_rate": 4.9978081607051176e-05,
+ "loss": 3.6656,
+ "step": 5400
+ },
+ {
+ "epoch": 0.04425518493196529,
+ "grad_norm": 0.9051403403282166,
+ "learning_rate": 4.997781243679648e-05,
+ "loss": 3.6439,
+ "step": 5430
+ },
+ {
+ "epoch": 0.0444996887161198,
+ "grad_norm": 0.9147741794586182,
+ "learning_rate": 4.9977541624565374e-05,
+ "loss": 3.6362,
+ "step": 5460
+ },
+ {
+ "epoch": 0.0447441925002743,
+ "grad_norm": 0.8926962614059448,
+ "learning_rate": 4.9977269170375665e-05,
+ "loss": 3.6179,
+ "step": 5490
+ },
+ {
+ "epoch": 0.04498869628442881,
+ "grad_norm": 0.9078648686408997,
+ "learning_rate": 4.997699507424526e-05,
+ "loss": 3.6323,
+ "step": 5520
+ },
+ {
+ "epoch": 0.045233200068583314,
+ "grad_norm": 0.8844118118286133,
+ "learning_rate": 4.997671933619218e-05,
+ "loss": 3.6219,
+ "step": 5550
+ },
+ {
+ "epoch": 0.04547770385273782,
+ "grad_norm": 0.9098038077354431,
+ "learning_rate": 4.9976441956234546e-05,
+ "loss": 3.6341,
+ "step": 5580
+ },
+ {
+ "epoch": 0.04572220763689232,
+ "grad_norm": 0.8704332709312439,
+ "learning_rate": 4.99761629343906e-05,
+ "loss": 3.6038,
+ "step": 5610
+ },
+ {
+ "epoch": 0.04596671142104682,
+ "grad_norm": 0.9353320002555847,
+ "learning_rate": 4.9975882270678676e-05,
+ "loss": 3.6171,
+ "step": 5640
+ },
+ {
+ "epoch": 0.04621121520520133,
+ "grad_norm": 1.0025008916854858,
+ "learning_rate": 4.997559996511723e-05,
+ "loss": 3.6084,
+ "step": 5670
+ },
+ {
+ "epoch": 0.04645571898935583,
+ "grad_norm": 0.8339236974716187,
+ "learning_rate": 4.997531601772481e-05,
+ "loss": 3.6271,
+ "step": 5700
+ },
+ {
+ "epoch": 0.04670022277351034,
+ "grad_norm": 0.8991410136222839,
+ "learning_rate": 4.9975030428520084e-05,
+ "loss": 3.5897,
+ "step": 5730
+ },
+ {
+ "epoch": 0.046944726557664844,
+ "grad_norm": 0.8854517936706543,
+ "learning_rate": 4.997474319752184e-05,
+ "loss": 3.603,
+ "step": 5760
+ },
+ {
+ "epoch": 0.04718923034181935,
+ "grad_norm": 0.9445385932922363,
+ "learning_rate": 4.997445432474895e-05,
+ "loss": 3.6084,
+ "step": 5790
+ },
+ {
+ "epoch": 0.04743373412597385,
+ "grad_norm": 0.871096134185791,
+ "learning_rate": 4.9974163810220406e-05,
+ "loss": 3.5892,
+ "step": 5820
+ },
+ {
+ "epoch": 0.04767823791012835,
+ "grad_norm": 0.8828051686286926,
+ "learning_rate": 4.99738716539553e-05,
+ "loss": 3.6075,
+ "step": 5850
+ },
+ {
+ "epoch": 0.04792274169428286,
+ "grad_norm": 0.8362672328948975,
+ "learning_rate": 4.997357785597284e-05,
+ "loss": 3.5772,
+ "step": 5880
+ },
+ {
+ "epoch": 0.048167245478437364,
+ "grad_norm": 0.9075796008110046,
+ "learning_rate": 4.997328241629234e-05,
+ "loss": 3.5881,
+ "step": 5910
+ },
+ {
+ "epoch": 0.04841174926259187,
+ "grad_norm": 0.9475303888320923,
+ "learning_rate": 4.997298533493323e-05,
+ "loss": 3.5963,
+ "step": 5940
+ },
+ {
+ "epoch": 0.048656253046746374,
+ "grad_norm": 0.807908296585083,
+ "learning_rate": 4.997268661191503e-05,
+ "loss": 3.5776,
+ "step": 5970
+ },
+ {
+ "epoch": 0.04890075683090088,
+ "grad_norm": 0.9100547432899475,
+ "learning_rate": 4.9972386247257385e-05,
+ "loss": 3.5924,
+ "step": 6000
+ },
+ {
+ "epoch": 0.049145260615055385,
+ "grad_norm": 0.79295814037323,
+ "learning_rate": 4.9972084240980025e-05,
+ "loss": 3.5603,
+ "step": 6030
+ },
+ {
+ "epoch": 0.04938976439920988,
+ "grad_norm": 0.8548495173454285,
+ "learning_rate": 4.997178059310281e-05,
+ "loss": 3.5624,
+ "step": 6060
+ },
+ {
+ "epoch": 0.04963426818336439,
+ "grad_norm": 0.8862835168838501,
+ "learning_rate": 4.997147530364571e-05,
+ "loss": 3.5738,
+ "step": 6090
+ },
+ {
+ "epoch": 0.049878771967518894,
+ "grad_norm": 1.0974136590957642,
+ "learning_rate": 4.9971168372628793e-05,
+ "loss": 3.5549,
+ "step": 6120
+ },
+ {
+ "epoch": 0.0501232757516734,
+ "grad_norm": 0.9224910140037537,
+ "learning_rate": 4.997085980007222e-05,
+ "loss": 3.5632,
+ "step": 6150
+ },
+ {
+ "epoch": 0.050367779535827904,
+ "grad_norm": 0.8416465520858765,
+ "learning_rate": 4.99705495859963e-05,
+ "loss": 3.5605,
+ "step": 6180
+ },
+ {
+ "epoch": 0.05061228331998241,
+ "grad_norm": 0.9750398993492126,
+ "learning_rate": 4.99702377304214e-05,
+ "loss": 3.5652,
+ "step": 6210
+ },
+ {
+ "epoch": 0.050856787104136915,
+ "grad_norm": 1.0585671663284302,
+ "learning_rate": 4.9969924233368036e-05,
+ "loss": 3.5605,
+ "step": 6240
+ },
+ {
+ "epoch": 0.05110129088829142,
+ "grad_norm": 1.0180178880691528,
+ "learning_rate": 4.996960909485681e-05,
+ "loss": 3.5543,
+ "step": 6270
+ },
+ {
+ "epoch": 0.05134579467244592,
+ "grad_norm": 0.8081057667732239,
+ "learning_rate": 4.9969292314908446e-05,
+ "loss": 3.5551,
+ "step": 6300
+ },
+ {
+ "epoch": 0.051590298456600424,
+ "grad_norm": 0.8196061253547668,
+ "learning_rate": 4.996897389354376e-05,
+ "loss": 3.5566,
+ "step": 6330
+ },
+ {
+ "epoch": 0.05183480224075493,
+ "grad_norm": 0.9229000806808472,
+ "learning_rate": 4.9968653830783684e-05,
+ "loss": 3.5439,
+ "step": 6360
+ },
+ {
+ "epoch": 0.052079306024909434,
+ "grad_norm": 0.8422220945358276,
+ "learning_rate": 4.996833212664927e-05,
+ "loss": 3.5413,
+ "step": 6390
+ },
+ {
+ "epoch": 0.05232380980906394,
+ "grad_norm": 0.9290680885314941,
+ "learning_rate": 4.996800878116166e-05,
+ "loss": 3.5245,
+ "step": 6420
+ },
+ {
+ "epoch": 0.052568313593218445,
+ "grad_norm": 0.7990279793739319,
+ "learning_rate": 4.99676837943421e-05,
+ "loss": 3.5519,
+ "step": 6450
+ },
+ {
+ "epoch": 0.05281281737737295,
+ "grad_norm": 0.8968884348869324,
+ "learning_rate": 4.996735716621196e-05,
+ "loss": 3.5306,
+ "step": 6480
+ },
+ {
+ "epoch": 0.05305732116152745,
+ "grad_norm": 0.8280816674232483,
+ "learning_rate": 4.996702889679272e-05,
+ "loss": 3.5407,
+ "step": 6510
+ },
+ {
+ "epoch": 0.053301824945681954,
+ "grad_norm": 0.9637565612792969,
+ "learning_rate": 4.996669898610595e-05,
+ "loss": 3.5361,
+ "step": 6540
+ },
+ {
+ "epoch": 0.05354632872983646,
+ "grad_norm": 0.8355570435523987,
+ "learning_rate": 4.996636743417334e-05,
+ "loss": 3.5215,
+ "step": 6570
+ },
+ {
+ "epoch": 0.053790832513990965,
+ "grad_norm": 0.7987068295478821,
+ "learning_rate": 4.996603424101669e-05,
+ "loss": 3.5135,
+ "step": 6600
+ },
+ {
+ "epoch": 0.05403533629814547,
+ "grad_norm": 0.8417894840240479,
+ "learning_rate": 4.996569940665789e-05,
+ "loss": 3.5254,
+ "step": 6630
+ },
+ {
+ "epoch": 0.054279840082299975,
+ "grad_norm": 0.8814358115196228,
+ "learning_rate": 4.996536293111896e-05,
+ "loss": 3.5091,
+ "step": 6660
+ },
+ {
+ "epoch": 0.05452434386645448,
+ "grad_norm": 0.8625611662864685,
+ "learning_rate": 4.996502481442202e-05,
+ "loss": 3.5207,
+ "step": 6690
+ },
+ {
+ "epoch": 0.054768847650608986,
+ "grad_norm": 0.8265979886054993,
+ "learning_rate": 4.9964685056589314e-05,
+ "loss": 3.5011,
+ "step": 6720
+ },
+ {
+ "epoch": 0.055013351434763484,
+ "grad_norm": 0.8092629313468933,
+ "learning_rate": 4.996434365764314e-05,
+ "loss": 3.4897,
+ "step": 6750
+ },
+ {
+ "epoch": 0.05525785521891799,
+ "grad_norm": 0.917871356010437,
+ "learning_rate": 4.996400061760597e-05,
+ "loss": 3.5188,
+ "step": 6780
+ },
+ {
+ "epoch": 0.055502359003072495,
+ "grad_norm": 0.8477138876914978,
+ "learning_rate": 4.996365593650033e-05,
+ "loss": 3.5142,
+ "step": 6810
+ },
+ {
+ "epoch": 0.055746862787227,
+ "grad_norm": 0.7970532178878784,
+ "learning_rate": 4.99633096143489e-05,
+ "loss": 3.5112,
+ "step": 6840
+ },
+ {
+ "epoch": 0.055991366571381505,
+ "grad_norm": 0.8973976969718933,
+ "learning_rate": 4.9962961651174436e-05,
+ "loss": 3.5156,
+ "step": 6870
+ },
+ {
+ "epoch": 0.05623587035553601,
+ "grad_norm": 0.962066113948822,
+ "learning_rate": 4.9962612046999827e-05,
+ "loss": 3.4848,
+ "step": 6900
+ },
+ {
+ "epoch": 0.056480374139690516,
+ "grad_norm": 0.9020524621009827,
+ "learning_rate": 4.996226080184803e-05,
+ "loss": 3.503,
+ "step": 6930
+ },
+ {
+ "epoch": 0.056724877923845014,
+ "grad_norm": 0.8064045906066895,
+ "learning_rate": 4.996190791574215e-05,
+ "loss": 3.4982,
+ "step": 6960
+ },
+ {
+ "epoch": 0.05696938170799952,
+ "grad_norm": 0.8507282733917236,
+ "learning_rate": 4.996155338870538e-05,
+ "loss": 3.4713,
+ "step": 6990
+ },
+ {
+ "epoch": 0.057213885492154025,
+ "grad_norm": 0.8574703931808472,
+ "learning_rate": 4.9961197220761035e-05,
+ "loss": 3.4924,
+ "step": 7020
+ },
+ {
+ "epoch": 0.05745838927630853,
+ "grad_norm": 0.8214017152786255,
+ "learning_rate": 4.996083941193252e-05,
+ "loss": 3.4773,
+ "step": 7050
+ },
+ {
+ "epoch": 0.057702893060463036,
+ "grad_norm": 0.8267714977264404,
+ "learning_rate": 4.9960479962243367e-05,
+ "loss": 3.4836,
+ "step": 7080
+ },
+ {
+ "epoch": 0.05794739684461754,
+ "grad_norm": 0.8415769934654236,
+ "learning_rate": 4.996011887171719e-05,
+ "loss": 3.4871,
+ "step": 7110
+ },
+ {
+ "epoch": 0.058191900628772046,
+ "grad_norm": 0.9093459248542786,
+ "learning_rate": 4.995975614037773e-05,
+ "loss": 3.4777,
+ "step": 7140
+ },
+ {
+ "epoch": 0.05843640441292655,
+ "grad_norm": 0.865168571472168,
+ "learning_rate": 4.995939176824883e-05,
+ "loss": 3.4798,
+ "step": 7170
+ },
+ {
+ "epoch": 0.05868090819708105,
+ "grad_norm": 0.8812352418899536,
+ "learning_rate": 4.995902575535446e-05,
+ "loss": 3.4634,
+ "step": 7200
+ },
+ {
+ "epoch": 0.058925411981235555,
+ "grad_norm": 0.8318623900413513,
+ "learning_rate": 4.995865810171866e-05,
+ "loss": 3.4691,
+ "step": 7230
+ },
+ {
+ "epoch": 0.05916991576539006,
+ "grad_norm": 0.8475897312164307,
+ "learning_rate": 4.995828880736561e-05,
+ "loss": 3.4894,
+ "step": 7260
+ },
+ {
+ "epoch": 0.059414419549544566,
+ "grad_norm": 0.8317278027534485,
+ "learning_rate": 4.995791787231958e-05,
+ "loss": 3.4597,
+ "step": 7290
+ },
+ {
+ "epoch": 0.05965892333369907,
+ "grad_norm": 0.8189125657081604,
+ "learning_rate": 4.9957545296604965e-05,
+ "loss": 3.4495,
+ "step": 7320
+ },
+ {
+ "epoch": 0.059903427117853576,
+ "grad_norm": 0.8047211766242981,
+ "learning_rate": 4.9957171080246245e-05,
+ "loss": 3.4865,
+ "step": 7350
+ },
+ {
+ "epoch": 0.06014793090200808,
+ "grad_norm": 0.8353013396263123,
+ "learning_rate": 4.995679522326803e-05,
+ "loss": 3.4671,
+ "step": 7380
+ },
+ {
+ "epoch": 0.06039243468616259,
+ "grad_norm": 0.7747114300727844,
+ "learning_rate": 4.995641772569502e-05,
+ "loss": 3.4423,
+ "step": 7410
+ },
+ {
+ "epoch": 0.060636938470317085,
+ "grad_norm": 0.792785108089447,
+ "learning_rate": 4.995603858755203e-05,
+ "loss": 3.448,
+ "step": 7440
+ },
+ {
+ "epoch": 0.06088144225447159,
+ "grad_norm": 0.9009000658988953,
+ "learning_rate": 4.9955657808863985e-05,
+ "loss": 3.4471,
+ "step": 7470
+ },
+ {
+ "epoch": 0.061125946038626096,
+ "grad_norm": 0.8719607591629028,
+ "learning_rate": 4.995527538965593e-05,
+ "loss": 3.4512,
+ "step": 7500
+ },
+ {
+ "epoch": 0.0613704498227806,
+ "grad_norm": 0.840308666229248,
+ "learning_rate": 4.995489132995298e-05,
+ "loss": 3.4576,
+ "step": 7530
+ },
+ {
+ "epoch": 0.061614953606935106,
+ "grad_norm": 0.8216726779937744,
+ "learning_rate": 4.99545056297804e-05,
+ "loss": 3.4369,
+ "step": 7560
+ },
+ {
+ "epoch": 0.06185945739108961,
+ "grad_norm": 0.7841954827308655,
+ "learning_rate": 4.995411828916354e-05,
+ "loss": 3.4338,
+ "step": 7590
+ },
+ {
+ "epoch": 0.06210396117524412,
+ "grad_norm": 0.7832449674606323,
+ "learning_rate": 4.9953729308127874e-05,
+ "loss": 3.431,
+ "step": 7620
+ },
+ {
+ "epoch": 0.062348464959398615,
+ "grad_norm": 0.821207582950592,
+ "learning_rate": 4.995333868669895e-05,
+ "loss": 3.44,
+ "step": 7650
+ },
+ {
+ "epoch": 0.06259296874355312,
+ "grad_norm": 0.7705381512641907,
+ "learning_rate": 4.995294642490246e-05,
+ "loss": 3.4479,
+ "step": 7680
+ },
+ {
+ "epoch": 0.06283747252770763,
+ "grad_norm": 0.7850989699363708,
+ "learning_rate": 4.995255252276418e-05,
+ "loss": 3.4276,
+ "step": 7710
+ },
+ {
+ "epoch": 0.06308197631186213,
+ "grad_norm": 0.7798038721084595,
+ "learning_rate": 4.9952156980310016e-05,
+ "loss": 3.4376,
+ "step": 7740
+ },
+ {
+ "epoch": 0.06332648009601663,
+ "grad_norm": 0.8357362151145935,
+ "learning_rate": 4.9951759797565965e-05,
+ "loss": 3.4408,
+ "step": 7770
+ },
+ {
+ "epoch": 0.06357098388017114,
+ "grad_norm": 0.8627969622612,
+ "learning_rate": 4.995136097455815e-05,
+ "loss": 3.4328,
+ "step": 7800
+ }
+ ],
+ "logging_steps": 30,
+ "max_steps": 368091,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 100,
+ "total_flos": 7.58996998815744e+18,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd09cf647966b7aa9734641f3c430c3c948068505081b7e0375830487e6a3632
+size 4984