Training in progress, step 1451, checkpoint

checkpoint-1451/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "mnoukhov/SmolLM2-135M-Instruct_tldr-sft",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-1451/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db711e84881c171c81aa2af794e43d3b6f0d286150cb8bb45cf11e0116dfe2ee
+size 269061784

checkpoint-1451/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee663b20ae6ce538b2376e36947e4089c108a7a7c96b790d225eef151c7bd24
+size 538292218

checkpoint-1451/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a6944c405a002fce05f295d08ea6650e2e2ad6dbf5d6da1e9053f7bf7f5827
+size 14244

checkpoint-1451/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3145d99c6ae38f5510a6fff1ad46e7ccc65e49e4d219d1cad4368f1734549219
+size 1064

checkpoint-1451/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1451/tokenizer_config.json

@@ -0,0 +1,158 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "max_length": 580,
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-1451/trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 291,
+  "global_step": 1451,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06891798759476224,
+      "grad_norm": 47.0,
+      "learning_rate": 9.88326321974139e-06,
+      "loss": 0.6874,
+      "step": 100
+    },
+    {
+      "epoch": 0.13783597518952448,
+      "grad_norm": 25.0,
+      "learning_rate": 9.53850386931162e-06,
+      "loss": 0.6895,
+      "step": 200
+    },
+    {
+      "epoch": 0.2005513439007581,
+      "eval_accuracy": 0.569592611154865,
+      "eval_loss": 0.6835629940032959,
+      "eval_runtime": 378.97,
+      "eval_samples_per_second": 221.131,
+      "eval_steps_per_second": 27.643,
+      "step": 291
+    },
+    {
+      "epoch": 0.2067539627842867,
+      "grad_norm": 21.625,
+      "learning_rate": 8.981820387323976e-06,
+      "loss": 0.6849,
+      "step": 300
+    },
+    {
+      "epoch": 0.27567195037904896,
+      "grad_norm": 14.5,
+      "learning_rate": 8.239206948702616e-06,
+      "loss": 0.6902,
+      "step": 400
+    },
+    {
+      "epoch": 0.34458993797381116,
+      "grad_norm": 23.875,
+      "learning_rate": 7.345339674168113e-06,
+      "loss": 0.6849,
+      "step": 500
+    },
+    {
+      "epoch": 0.4011026878015162,
+      "eval_accuracy": 0.5740077802439083,
+      "eval_loss": 0.6811934113502502,
+      "eval_runtime": 377.4685,
+      "eval_samples_per_second": 222.011,
+      "eval_steps_per_second": 27.753,
+      "step": 582
+    },
+    {
+      "epoch": 0.4135079255685734,
+      "grad_norm": 25.125,
+      "learning_rate": 6.341957438763544e-06,
+      "loss": 0.6813,
+      "step": 600
+    },
+    {
+      "epoch": 0.4824259131633356,
+      "grad_norm": 14.875,
+      "learning_rate": 5.275912887100837e-06,
+      "loss": 0.6878,
+      "step": 700
+    },
+    {
+      "epoch": 0.5513439007580979,
+      "grad_norm": 21.25,
+      "learning_rate": 4.1969846626093244e-06,
+      "loss": 0.6902,
+      "step": 800
+    },
+    {
+      "epoch": 0.6016540317022743,
+      "eval_accuracy": 0.5770864657168087,
+      "eval_loss": 0.6811434030532837,
+      "eval_runtime": 379.7091,
+      "eval_samples_per_second": 220.701,
+      "eval_steps_per_second": 27.59,
+      "step": 873
+    },
+    {
+      "epoch": 0.6202618883528601,
+      "grad_norm": 12.125,
+      "learning_rate": 3.155553008111921e-06,
+      "loss": 0.6893,
+      "step": 900
+    },
+    {
+      "epoch": 0.6891798759476223,
+      "grad_norm": 39.5,
+      "learning_rate": 2.2002472748907948e-06,
+      "loss": 0.6849,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7580978635423845,
+      "grad_norm": 21.875,
+      "learning_rate": 1.3756751891294767e-06,
+      "loss": 0.6868,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8022053756030324,
+      "eval_accuracy": 0.5794491778239182,
+      "eval_loss": 0.6808037161827087,
+      "eval_runtime": 378.7407,
+      "eval_samples_per_second": 221.265,
+      "eval_steps_per_second": 27.66,
+      "step": 1164
+    },
+    {
+      "epoch": 0.8270158511371468,
+      "grad_norm": 14.75,
+      "learning_rate": 7.203399069811245e-07,
+      "loss": 0.6872,
+      "step": 1200
+    },
+    {
+      "epoch": 0.895933838731909,
+      "grad_norm": 26.125,
+      "learning_rate": 2.6484212077688697e-07,
+      "loss": 0.6866,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9648518263266712,
+      "grad_norm": 24.75,
+      "learning_rate": 3.045116850732776e-08,
+      "loss": 0.6843,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1451,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 291,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1451/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba979f24668c0cf8441fbd7354957115ac47a09976111fe460aa9f486678a844
+size 5432