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": 512,
+  "high_rotations": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "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": 8,
+  "num_hidden_layers": 20,
+  "num_kv_heads": 2,
+  "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 sha256:5a649d90ab58037b762c45c79d904b4609178104849f032f757c05b10a265354
+size 301235464

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7122412a0e10c14ba45ded3790e3026711348bb363aa2d497afa0327fc5196
+size 602335994

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31bc35ff4d19e4ab9d14669a2cbe270c59e5f1338e54885237240d73daac524
+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": 0.004770025161882729,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00023850125809413643,
+      "grad_norm": 1.5476292371749878,
+      "learning_rate": 0.0001,
+      "loss": 9.8285,
+      "num_input_tokens_seen": 13107200,
+      "step": 50
+    },
+    {
+      "epoch": 0.00047700251618827287,
+      "grad_norm": 0.47720426321029663,
+      "learning_rate": 0.0002,
+      "loss": 7.964,
+      "num_input_tokens_seen": 26214400,
+      "step": 100
+    },
+    {
+      "epoch": 0.0007155037742824094,
+      "grad_norm": 0.8443030714988708,
+      "learning_rate": 0.0003,
+      "loss": 7.0452,
+      "num_input_tokens_seen": 39321600,
+      "step": 150
+    },
+    {
+      "epoch": 0.0009540050323765457,
+      "grad_norm": 0.5895723104476929,
+      "learning_rate": 0.0004,
+      "loss": 6.355,
+      "num_input_tokens_seen": 52428800,
+      "step": 200
+    },
+    {
+      "epoch": 0.0011925062904706823,
+      "grad_norm": 0.8343789577484131,
+      "learning_rate": 0.0005,
+      "loss": 5.8716,
+      "num_input_tokens_seen": 65536000,
+      "step": 250
+    },
+    {
+      "epoch": 0.0014310075485648188,
+      "grad_norm": 0.5747953057289124,
+      "learning_rate": 0.0006,
+      "loss": 5.5086,
+      "num_input_tokens_seen": 78643200,
+      "step": 300
+    },
+    {
+      "epoch": 0.0016695088066589552,
+      "grad_norm": 0.8383421301841736,
+      "learning_rate": 0.0007,
+      "loss": 5.2217,
+      "num_input_tokens_seen": 91750400,
+      "step": 350
+    },
+    {
+      "epoch": 0.0019080100647530915,
+      "grad_norm": 0.5696113109588623,
+      "learning_rate": 0.0008,
+      "loss": 4.9683,
+      "num_input_tokens_seen": 104857600,
+      "step": 400
+    },
+    {
+      "epoch": 0.002146511322847228,
+      "grad_norm": 0.5431691408157349,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 4.7629,
+      "num_input_tokens_seen": 117964800,
+      "step": 450
+    },
+    {
+      "epoch": 0.0023850125809413646,
+      "grad_norm": 0.4571855664253235,
+      "learning_rate": 0.001,
+      "loss": 4.5284,
+      "num_input_tokens_seen": 131072000,
+      "step": 500
+    },
+    {
+      "epoch": 0.0023850125809413646,
+      "eval_loss": 4.309167385101318,
+      "eval_runtime": 53.3891,
+      "eval_samples_per_second": 93.652,
+      "eval_steps_per_second": 23.413,
+      "num_input_tokens_seen": 131072000,
+      "step": 500
+    },
+    {
+      "epoch": 0.002623513839035501,
+      "grad_norm": 0.43464773893356323,
+      "learning_rate": 0.001,
+      "loss": 4.3379,
+      "num_input_tokens_seen": 144179200,
+      "step": 550
+    },
+    {
+      "epoch": 0.0028620150971296375,
+      "grad_norm": 0.49611660838127136,
+      "learning_rate": 0.001,
+      "loss": 4.1712,
+      "num_input_tokens_seen": 157286400,
+      "step": 600
+    },
+    {
+      "epoch": 0.0031005163552237738,
+      "grad_norm": 0.4060957729816437,
+      "learning_rate": 0.001,
+      "loss": 4.0436,
+      "num_input_tokens_seen": 170393600,
+      "step": 650
+    },
+    {
+      "epoch": 0.0033390176133179105,
+      "grad_norm": 0.37300577759742737,
+      "learning_rate": 0.001,
+      "loss": 3.9582,
+      "num_input_tokens_seen": 183500800,
+      "step": 700
+    },
+    {
+      "epoch": 0.0035775188714120467,
+      "grad_norm": 0.4117021858692169,
+      "learning_rate": 0.001,
+      "loss": 3.8674,
+      "num_input_tokens_seen": 196608000,
+      "step": 750
+    },
+    {
+      "epoch": 0.003816020129506183,
+      "grad_norm": 0.3335980772972107,
+      "learning_rate": 0.001,
+      "loss": 3.8031,
+      "num_input_tokens_seen": 209715200,
+      "step": 800
+    },
+    {
+      "epoch": 0.004054521387600319,
+      "grad_norm": 0.35943159461021423,
+      "learning_rate": 0.001,
+      "loss": 3.7534,
+      "num_input_tokens_seen": 222822400,
+      "step": 850
+    },
+    {
+      "epoch": 0.004293022645694456,
+      "grad_norm": 0.40000948309898376,
+      "learning_rate": 0.001,
+      "loss": 3.6867,
+      "num_input_tokens_seen": 235929600,
+      "step": 900
+    },
+    {
+      "epoch": 0.0045315239037885926,
+      "grad_norm": 0.3165877163410187,
+      "learning_rate": 0.001,
+      "loss": 3.6565,
+      "num_input_tokens_seen": 249036800,
+      "step": 950
+    },
+    {
+      "epoch": 0.004770025161882729,
+      "grad_norm": 0.3687070906162262,
+      "learning_rate": 0.001,
+      "loss": 3.6005,
+      "num_input_tokens_seen": 262144000,
+      "step": 1000
+    },
+    {
+      "epoch": 0.004770025161882729,
+      "eval_loss": 3.4853296279907227,
+      "eval_runtime": 52.477,
+      "eval_samples_per_second": 95.28,
+      "eval_steps_per_second": 23.82,
+      "num_input_tokens_seen": 262144000,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 70000,
+  "num_input_tokens_seen": 262144000,
+  "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": 7.012607852544e+16,
+  "train_batch_size": 64,
+  "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:e2b62c5934cfe883a6c45537c72c0d7d5838e653daab02b21938129bf7a81627
+size 6008