Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "SmalLmForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "balancing_coef": 0.0001,
+  "bos_token_id": 1,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 0,
+  "expert_size": 576,
+  "gate_noise": false,
+  "head_size": 64,
+  "hidden_size": 960,
+  "high_rotations": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "layer_dropout": 0.1,
+  "low_rotations": 1,
+  "max_seq_len": 1024,
+  "mlp_bias": false,
+  "model_type": "smallm",
+  "moe_bias": false,
+  "moe_period": 2,
+  "no_moe_layers": 10,
+  "noisy_experts": false,
+  "num_attention_heads": 15,
+  "num_hidden_layers": 30,
+  "num_kv_heads": 5,
+  "original_seq_len": 1024,
+  "pad_token_id": 0,
+  "positional_bias_type": "rope",
+  "rms_affine": false,
+  "rms_norm_eps": 1e-06,
+  "rope_base": 100000,
+  "routed_experts": 8,
+  "shared_experts": 1,
+  "sliding_window_attention": true,
+  "sliding_window_context": 1024,
+  "sliding_window_period": 4,
+  "static_residual": false,
+  "token_experts": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "use_moe": false,
+  "vocab_size": 60000
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55222741868110a7178067a82e687d4d08f53b3fb267b8ff795cd2a7d0ac9a6
+size 1410301944

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807c37fe7a39ccde522e11f1ac8c2b945aa3d558fa9ef9e8463fee95772950e4
+size 2820185786

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbc5c949fe22618458235ba3bcce92f8b8993595d1ef5161e2e318f297e8671
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87f7c310f0898821b6ff4df72f4a89fa1b6524a2882b9e3b83cf721a3763459
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|beginoftext|>",
+    "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
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,115 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|beginoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|reserved_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|reserved_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|reserved_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|reserved_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|reserved_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|reserved_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|reserved_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|reserved_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|reserved_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|reserved_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|reserved_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|beginoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.009540050323765458,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00047700251618827287,
+      "grad_norm": 0.7297705411911011,
+      "learning_rate": 0.0001,
+      "loss": 9.0134,
+      "num_input_tokens_seen": 26214400,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009540050323765457,
+      "grad_norm": 0.9636281132698059,
+      "learning_rate": 0.0002,
+      "loss": 7.1965,
+      "num_input_tokens_seen": 52419296,
+      "step": 100
+    },
+    {
+      "epoch": 0.0014310075485648188,
+      "grad_norm": 0.538168728351593,
+      "learning_rate": 0.0003,
+      "loss": 6.2716,
+      "num_input_tokens_seen": 78626240,
+      "step": 150
+    },
+    {
+      "epoch": 0.0019080100647530915,
+      "grad_norm": 0.9969781041145325,
+      "learning_rate": 0.0004,
+      "loss": 5.6452,
+      "num_input_tokens_seen": 104833632,
+      "step": 200
+    },
+    {
+      "epoch": 0.0023850125809413646,
+      "grad_norm": 0.8100546002388,
+      "learning_rate": 0.0005,
+      "loss": 5.2224,
+      "num_input_tokens_seen": 131047584,
+      "step": 250
+    },
+    {
+      "epoch": 0.0028620150971296375,
+      "grad_norm": 0.4632050693035126,
+      "learning_rate": 0.0006,
+      "loss": 4.8733,
+      "num_input_tokens_seen": 157260544,
+      "step": 300
+    },
+    {
+      "epoch": 0.0033390176133179105,
+      "grad_norm": 2.2721216678619385,
+      "learning_rate": 0.0007,
+      "loss": 4.5928,
+      "num_input_tokens_seen": 183472896,
+      "step": 350
+    },
+    {
+      "epoch": 0.003816020129506183,
+      "grad_norm": 0.244660422205925,
+      "learning_rate": 0.0008,
+      "loss": 4.4136,
+      "num_input_tokens_seen": 209685664,
+      "step": 400
+    },
+    {
+      "epoch": 0.004293022645694456,
+      "grad_norm": 0.3138381540775299,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 4.0552,
+      "num_input_tokens_seen": 235896448,
+      "step": 450
+    },
+    {
+      "epoch": 0.004770025161882729,
+      "grad_norm": 0.27429279685020447,
+      "learning_rate": 0.001,
+      "loss": 3.8584,
+      "num_input_tokens_seen": 262104320,
+      "step": 500
+    },
+    {
+      "epoch": 0.004770025161882729,
+      "eval_loss": 3.676422357559204,
+      "eval_runtime": 80.6607,
+      "eval_samples_per_second": 61.988,
+      "eval_steps_per_second": 15.497,
+      "num_input_tokens_seen": 262104320,
+      "step": 500
+    },
+    {
+      "epoch": 0.005247027678071002,
+      "grad_norm": 0.20896735787391663,
+      "learning_rate": 0.001,
+      "loss": 3.6992,
+      "num_input_tokens_seen": 288318720,
+      "step": 550
+    },
+    {
+      "epoch": 0.005724030194259275,
+      "grad_norm": 0.1993994414806366,
+      "learning_rate": 0.001,
+      "loss": 3.5839,
+      "num_input_tokens_seen": 314519904,
+      "step": 600
+    },
+    {
+      "epoch": 0.0062010327104475476,
+      "grad_norm": 0.21841953694820404,
+      "learning_rate": 0.001,
+      "loss": 3.472,
+      "num_input_tokens_seen": 340725984,
+      "step": 650
+    },
+    {
+      "epoch": 0.006678035226635821,
+      "grad_norm": 0.17900177836418152,
+      "learning_rate": 0.001,
+      "loss": 3.3972,
+      "num_input_tokens_seen": 366937216,
+      "step": 700
+    },
+    {
+      "epoch": 0.007155037742824093,
+      "grad_norm": 0.1761142611503601,
+      "learning_rate": 0.001,
+      "loss": 3.3383,
+      "num_input_tokens_seen": 393150592,
+      "step": 750
+    },
+    {
+      "epoch": 0.007632040259012366,
+      "grad_norm": 0.19628353416919708,
+      "learning_rate": 0.001,
+      "loss": 3.2933,
+      "num_input_tokens_seen": 419364992,
+      "step": 800
+    },
+    {
+      "epoch": 0.008109042775200638,
+      "grad_norm": 0.18105614185333252,
+      "learning_rate": 0.001,
+      "loss": 3.2451,
+      "num_input_tokens_seen": 445578432,
+      "step": 850
+    },
+    {
+      "epoch": 0.008586045291388912,
+      "grad_norm": 0.15662750601768494,
+      "learning_rate": 0.001,
+      "loss": 3.2089,
+      "num_input_tokens_seen": 471790144,
+      "step": 900
+    },
+    {
+      "epoch": 0.009063047807577185,
+      "grad_norm": 0.16136744618415833,
+      "learning_rate": 0.001,
+      "loss": 3.1683,
+      "num_input_tokens_seen": 498004544,
+      "step": 950
+    },
+    {
+      "epoch": 0.009540050323765458,
+      "grad_norm": 0.16362419724464417,
+      "learning_rate": 0.001,
+      "loss": 3.1457,
+      "num_input_tokens_seen": 524218944,
+      "step": 1000
+    },
+    {
+      "epoch": 0.009540050323765458,
+      "eval_loss": 3.0411295890808105,
+      "eval_runtime": 80.4796,
+      "eval_samples_per_second": 62.128,
+      "eval_steps_per_second": 15.532,
+      "num_input_tokens_seen": 524218944,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 70000,
+  "num_input_tokens_seen": 524218944,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.277719133446144e+17,
+  "train_batch_size": 32,
+  "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:f10f259b6c564b291bae58bd100079895e4b771948be7bd645c7d55385933964
+size 6008