Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,49 @@
+{
+  "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,
+  "moe_type": "default",
+  "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:a1a922d0fb93138543d9c71953a8b445e82ac2e882b91763888dc16d89db4b7c
+size 301235464

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8be7d83ae49acf07fcfaf3d23973b18bf764184f77831e50ea1b03c4a6bb9d
+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": 0.006726498874152251,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00033632494370761253,
+      "grad_norm": 1.274348497390747,
+      "learning_rate": 0.0001,
+      "loss": 9.9462,
+      "num_input_tokens_seen": 13107200,
+      "step": 50
+    },
+    {
+      "epoch": 0.0006726498874152251,
+      "grad_norm": 0.3978561758995056,
+      "learning_rate": 0.0002,
+      "loss": 8.361,
+      "num_input_tokens_seen": 26214400,
+      "step": 100
+    },
+    {
+      "epoch": 0.0010089748311228376,
+      "grad_norm": 0.41306379437446594,
+      "learning_rate": 0.0003,
+      "loss": 7.6593,
+      "num_input_tokens_seen": 39321600,
+      "step": 150
+    },
+    {
+      "epoch": 0.0013452997748304501,
+      "grad_norm": 0.3370315134525299,
+      "learning_rate": 0.0004,
+      "loss": 7.1018,
+      "num_input_tokens_seen": 52428800,
+      "step": 200
+    },
+    {
+      "epoch": 0.0016816247185380627,
+      "grad_norm": 0.6396230459213257,
+      "learning_rate": 0.0005,
+      "loss": 6.6331,
+      "num_input_tokens_seen": 65536000,
+      "step": 250
+    },
+    {
+      "epoch": 0.002017949662245675,
+      "grad_norm": 0.5036832690238953,
+      "learning_rate": 0.0006,
+      "loss": 6.2646,
+      "num_input_tokens_seen": 78643200,
+      "step": 300
+    },
+    {
+      "epoch": 0.002354274605953288,
+      "grad_norm": 0.4829367399215698,
+      "learning_rate": 0.0007,
+      "loss": 5.9656,
+      "num_input_tokens_seen": 91750400,
+      "step": 350
+    },
+    {
+      "epoch": 0.0026905995496609002,
+      "grad_norm": 0.6319091320037842,
+      "learning_rate": 0.0008,
+      "loss": 5.7098,
+      "num_input_tokens_seen": 104857600,
+      "step": 400
+    },
+    {
+      "epoch": 0.003026924493368513,
+      "grad_norm": 0.8607974648475647,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 5.5012,
+      "num_input_tokens_seen": 117964800,
+      "step": 450
+    },
+    {
+      "epoch": 0.0033632494370761253,
+      "grad_norm": 0.4290812611579895,
+      "learning_rate": 0.001,
+      "loss": 5.3179,
+      "num_input_tokens_seen": 131072000,
+      "step": 500
+    },
+    {
+      "epoch": 0.0033632494370761253,
+      "eval_loss": 5.179312705993652,
+      "eval_runtime": 100.6159,
+      "eval_samples_per_second": 49.694,
+      "eval_steps_per_second": 12.423,
+      "num_input_tokens_seen": 131072000,
+      "step": 500
+    },
+    {
+      "epoch": 0.003699574380783738,
+      "grad_norm": 0.407632052898407,
+      "learning_rate": 0.001,
+      "loss": 5.1431,
+      "num_input_tokens_seen": 144179200,
+      "step": 550
+    },
+    {
+      "epoch": 0.00403589932449135,
+      "grad_norm": 0.31742918491363525,
+      "learning_rate": 0.001,
+      "loss": 4.9611,
+      "num_input_tokens_seen": 157286400,
+      "step": 600
+    },
+    {
+      "epoch": 0.004372224268198963,
+      "grad_norm": 0.3897629678249359,
+      "learning_rate": 0.001,
+      "loss": 4.8043,
+      "num_input_tokens_seen": 170393600,
+      "step": 650
+    },
+    {
+      "epoch": 0.004708549211906576,
+      "grad_norm": 0.41930389404296875,
+      "learning_rate": 0.001,
+      "loss": 4.6617,
+      "num_input_tokens_seen": 183500800,
+      "step": 700
+    },
+    {
+      "epoch": 0.005044874155614189,
+      "grad_norm": 0.4283705949783325,
+      "learning_rate": 0.001,
+      "loss": 4.5535,
+      "num_input_tokens_seen": 196608000,
+      "step": 750
+    },
+    {
+      "epoch": 0.0053811990993218005,
+      "grad_norm": 0.3931107521057129,
+      "learning_rate": 0.001,
+      "loss": 4.4556,
+      "num_input_tokens_seen": 209715200,
+      "step": 800
+    },
+    {
+      "epoch": 0.005717524043029413,
+      "grad_norm": 0.3258611857891083,
+      "learning_rate": 0.001,
+      "loss": 4.3808,
+      "num_input_tokens_seen": 222822400,
+      "step": 850
+    },
+    {
+      "epoch": 0.006053848986737026,
+      "grad_norm": 0.3562588095664978,
+      "learning_rate": 0.001,
+      "loss": 4.3136,
+      "num_input_tokens_seen": 235929600,
+      "step": 900
+    },
+    {
+      "epoch": 0.006390173930444639,
+      "grad_norm": 0.3626460134983063,
+      "learning_rate": 0.001,
+      "loss": 4.2557,
+      "num_input_tokens_seen": 249036800,
+      "step": 950
+    },
+    {
+      "epoch": 0.006726498874152251,
+      "grad_norm": 0.4001849293708801,
+      "learning_rate": 0.001,
+      "loss": 4.208,
+      "num_input_tokens_seen": 262144000,
+      "step": 1000
+    },
+    {
+      "epoch": 0.006726498874152251,
+      "eval_loss": 4.108783721923828,
+      "eval_runtime": 101.5418,
+      "eval_samples_per_second": 49.241,
+      "eval_steps_per_second": 12.31,
+      "num_input_tokens_seen": 262144000,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 50000,
+  "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:d6d2cbedeb75b9254fdded4264191ece35eac9f755fa3f4e7a861e2389e2ec8b
+size 6008