Training in progress, step 20, 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": true,
+  "time_scale": 128.0,
+  "transformers_version": "5.13.0",
+  "use_cache": false,
+  "vocab_size": 50277
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109a1ff562e60b4a3659de3f31e49413def647fff60dd801ec9ed38b39374255
+size 579824888

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cdb8b10ce287047c72839d766120849b2d9aacf931ff44a1b8510116bdc7e6
+size 1159794763

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a81ce99965f5650998c3fdf0932f734f4f0b6b9b4f4bc0d128c8b5f65e9ca4
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ad50ba85de2f08235ac51873a9e6e650ceaf5d93913d1c853bc575c8052ec1
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0004,
+  "eval_steps": 10,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002,
+      "eval_accuracy": 0.043638611041376174,
+      "eval_loss": 9.762117385864258,
+      "eval_runtime": 6.9234,
+      "eval_samples_per_second": 280.355,
+      "eval_steps_per_second": 17.621,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004,
+      "eval_accuracy": 0.06910715419957232,
+      "eval_loss": 8.825312614440918,
+      "eval_runtime": 6.4973,
+      "eval_samples_per_second": 298.738,
+      "eval_steps_per_second": 18.777,
+      "step": 20
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 783992173363200.0,
+  "train_batch_size": 120,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873e1a4204ced4196d959a031f55bc9264b3965e59e7590a3c6d11d44d86d0dc
+size 5265