Initial model upload

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "state-spaces/mamba-790m-hf",
+  "architectures": [
+    "MambaForTokenClassification"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "d_model": 2048,
+  "eos_token_id": 0,
+  "expand": 2,
+  "fused_add_norm": true,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-ORG",
+    "2": "B-PER",
+    "3": "I-LOC",
+    "4": "I-ORG",
+    "5": "I-PER",
+    "6": "O"
+  },
+  "initializer_range": 0.1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 1,
+    "B-PER": 2,
+    "I-LOC": 3,
+    "I-ORG": 4,
+    "I-PER": 5,
+    "O": 6
+  },
+  "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,
+  "ssm_cfg": {},
+  "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": 96,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mambapy": false,
+  "vocab_size": 50280
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b9f7e4b391e554121a51dbcf2d43a7ed0b26697b9ffcbf1f28c13559574b46
+size 3172911676

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3ccb4bfb280203037002c7655683ca3fd2e1d5827616be03eb404c9b506c5d
+size 6346131398

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e54933b0aa06f60e61a06b56be70340a551730f0d5eedbba895ff36d2379784
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9197244c5ee8fd84c23cb5387dd7cd4b0d34bb7720142963e9ea404ddb17646d
+size 1064

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 13.113007545471191,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 4.1143,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.43995586037635803,
+      "eval_runtime": 32.4764,
+      "eval_samples_per_second": 1.971,
+      "eval_steps_per_second": 0.062,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 20.936077117919922,
+      "learning_rate": 4.2e-05,
+      "loss": 2.1269,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.379876971244812,
+      "eval_runtime": 32.4094,
+      "eval_samples_per_second": 1.975,
+      "eval_steps_per_second": 0.062,
+      "step": 200
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 16.75326156616211,
+      "learning_rate": 3.8e-05,
+      "loss": 1.8978,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.2993869483470917,
+      "eval_runtime": 32.9835,
+      "eval_samples_per_second": 1.94,
+      "eval_steps_per_second": 0.061,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 21.65208625793457,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.8537,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.30614784359931946,
+      "eval_runtime": 32.9509,
+      "eval_samples_per_second": 1.942,
+      "eval_steps_per_second": 0.061,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.365196228027344,
+      "learning_rate": 3e-05,
+      "loss": 1.6485,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.3090161383152008,
+      "eval_runtime": 32.2891,
+      "eval_samples_per_second": 1.982,
+      "eval_steps_per_second": 0.062,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 12.13517951965332,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.7569,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.265519380569458,
+      "eval_runtime": 33.1283,
+      "eval_samples_per_second": 1.932,
+      "eval_steps_per_second": 0.06,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 11.330101013183594,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.6369,
+      "step": 700
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.27068448066711426,
+      "eval_runtime": 32.3816,
+      "eval_samples_per_second": 1.976,
+      "eval_steps_per_second": 0.062,
+      "step": 700
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 10.912799835205078,
+      "learning_rate": 1.8e-05,
+      "loss": 1.6069,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.26618537306785583,
+      "eval_runtime": 32.4233,
+      "eval_samples_per_second": 1.974,
+      "eval_steps_per_second": 0.062,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 10.115180015563965,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.5865,
+      "step": 900
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.2548241913318634,
+      "eval_runtime": 32.7391,
+      "eval_samples_per_second": 1.955,
+      "eval_steps_per_second": 0.061,
+      "step": 900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.854705810546875,
+      "learning_rate": 1e-05,
+      "loss": 1.6823,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.253208190202713,
+      "eval_runtime": 33.3194,
+      "eval_samples_per_second": 1.921,
+      "eval_steps_per_second": 0.06,
+      "step": 1000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 15.417906761169434,
+      "learning_rate": 6e-06,
+      "loss": 1.4823,
+      "step": 1100
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.2543775737285614,
+      "eval_runtime": 32.6584,
+      "eval_samples_per_second": 1.96,
+      "eval_steps_per_second": 0.061,
+      "step": 1100
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 10.001874923706055,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.6394,
+      "step": 1200
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.25032997131347656,
+      "eval_runtime": 36.1677,
+      "eval_samples_per_second": 1.77,
+      "eval_steps_per_second": 0.055,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1804900566516192.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8e5aac368155674d30ef5e3f0d8903af3baa95f7826c71f0cffd62e5910a52
+size 5176