Training in progress, step 2000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "HybridFourierLM"
+  ],
+  "bos_token_id": 0,
+  "dropout": 0.05,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "latent_dim": 768,
+  "layer_types": [
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax"
+  ],
+  "model_type": "hybrid_fourier_lm",
+  "num_layers": 12,
+  "num_modes": 64,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "time_scale": 128.0,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 50277
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.12.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5705e7af05b27ed5ad80eeb0dae22c64e16bff581aaf95045a9a3c2b27d7f21
+size 734275920

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9ff05a88f38ae15dcd4e979b30ea6e420ba8aa2182c4adeee6f99722b56a5e
+size 1468687243

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac82640fafcec4ed8ce64644dd9dc382f3c142b4db92d38741fbda9a0d9aa763
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b31fd960caa060732c4a15ecd9d246ac0b9616bb6fb26ea726c7f67997fc86
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af82b03ee66a3766dd3122ac1bd62daf83a9a7fc283f1df0579a5c40ddfef85e
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03e28169c2c00e7fe490c6e4aa7935441cb75b55aeeb2e3bed7d76862fc0206
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0140d9aef0aa9f9eff1f556146a51b440b5ca7bd8c9b6043e06890735ba840
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5362ad2368a4ee2c667be0d3d1a656244a24515027b86ba737e31a78d06f0d5
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983aeb93e8b1ee3cd8c0ae6e23e1979775495cab73d44b292da46ee36a3343a5
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75816da70d512d83fb7557d7a5c717448c64bfd6d870f6115bed5b80d2a1e9f
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97205df308aacb47c267cc39a5798ea630f3942b814c426e195523287df99abf
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 5.65625,
+      "learning_rate": 6.6e-05,
+      "loss": 73.6,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 3.375,
+      "learning_rate": 9.999976160274871e-05,
+      "loss": 57.8,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.999779565902032e-05,
+      "loss": 53.08,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 5.0,
+      "learning_rate": 9.999384399149714e-05,
+      "loss": 51.56,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.5,
+      "learning_rate": 9.998790675712448e-05,
+      "loss": 50.32,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 5.5,
+      "learning_rate": 9.99799841917069e-05,
+      "loss": 48.76,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 6.65625,
+      "learning_rate": 9.997007660989881e-05,
+      "loss": 47.36,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 10.8125,
+      "learning_rate": 9.995818440519196e-05,
+      "loss": 47.32,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.994430804989984e-05,
+      "loss": 46.28,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 17.625,
+      "learning_rate": 9.992844809513897e-05,
+      "loss": 46.84,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 46.71875,
+      "eval_runtime": 9.8626,
+      "eval_samples_per_second": 0.406,
+      "eval_steps_per_second": 0.101,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 406.0,
+      "learning_rate": 9.991060517080687e-05,
+      "loss": 47.04,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 278.0,
+      "learning_rate": 9.989077998555717e-05,
+      "loss": 47.24,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 300.0,
+      "learning_rate": 9.986897332677145e-05,
+      "loss": 47.44,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 132.0,
+      "learning_rate": 9.984518606052792e-05,
+      "loss": 46.84,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 336.0,
+      "learning_rate": 9.9819419131567e-05,
+      "loss": 47.36,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 161.0,
+      "learning_rate": 9.979167356325394e-05,
+      "loss": 48.16,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 400.0,
+      "learning_rate": 9.976195045753797e-05,
+      "loss": 48.08,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 372.0,
+      "learning_rate": 9.973025099490876e-05,
+      "loss": 48.12,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 209.0,
+      "learning_rate": 9.969657643434932e-05,
+      "loss": 48.92,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1192.0,
+      "learning_rate": 9.966092811328614e-05,
+      "loss": 47.6,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 47.21875,
+      "eval_runtime": 0.2475,
+      "eval_samples_per_second": 16.161,
+      "eval_steps_per_second": 4.04,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.424901537792e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018db098c009b077a596bcd57ca4359ea322e874799c144a100d3d03ea3ce145
+size 5201