Upload folder using huggingface_hub

base/52_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

base/52_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a97cb08d916ebfb21dd2d4492fced0c458046c75939b90b285289e665cfd4b1
+size 791751704

base/52_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.3407124401055334e+17,
+    "train_loss": 0.7801467624616452,
+    "train_runtime": 253.8178,
+    "train_samples": 2958,
+    "train_samples_per_second": 34.962,
+    "train_steps_per_second": 1.099
+}

base/52_128_e3_3e-5/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}

base/52_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<reponame>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

base/52_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<reponame>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

base/52_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.3407124401055334e+17,
+    "train_loss": 0.7801467624616452,
+    "train_runtime": 253.8178,
+    "train_samples": 2958,
+    "train_samples_per_second": 34.962,
+    "train_steps_per_second": 1.099
+}

base/52_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,428 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 279,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 0.6785212755203247,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.9306,
+      "step": 5
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.5165809988975525,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 1.9604,
+      "step": 10
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.5334264636039734,
+      "learning_rate": 1.5e-05,
+      "loss": 1.8873,
+      "step": 15
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.5095286965370178,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 1.8741,
+      "step": 20
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.5062769651412964,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.8019,
+      "step": 25
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.502143144607544,
+      "learning_rate": 2.999882508108334e-05,
+      "loss": 1.7686,
+      "step": 30
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.5365138053894043,
+      "learning_rate": 2.995772224185354e-05,
+      "loss": 1.7151,
+      "step": 35
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.73558109998703,
+      "learning_rate": 2.9858057385153234e-05,
+      "loss": 1.6193,
+      "step": 40
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.6831375360488892,
+      "learning_rate": 2.9700220715786658e-05,
+      "loss": 1.5976,
+      "step": 45
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.6852832436561584,
+      "learning_rate": 2.948483019106306e-05,
+      "loss": 1.5359,
+      "step": 50
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.7376053929328918,
+      "learning_rate": 2.9212729101389083e-05,
+      "loss": 1.4666,
+      "step": 55
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.976175844669342,
+      "learning_rate": 2.8884982768643927e-05,
+      "loss": 1.3475,
+      "step": 60
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.9649496078491211,
+      "learning_rate": 2.8502874375263646e-05,
+      "loss": 1.2856,
+      "step": 65
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 1.0865520238876343,
+      "learning_rate": 2.806789994036445e-05,
+      "loss": 1.2644,
+      "step": 70
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.313912034034729,
+      "learning_rate": 2.7581762462574335e-05,
+      "loss": 1.1697,
+      "step": 75
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 1.1698577404022217,
+      "learning_rate": 2.7046365252504835e-05,
+      "loss": 1.1434,
+      "step": 80
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 1.2489899396896362,
+      "learning_rate": 2.6463804480967445e-05,
+      "loss": 1.0282,
+      "step": 85
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 1.4168100357055664,
+      "learning_rate": 2.5836360972109643e-05,
+      "loss": 0.9807,
+      "step": 90
+    },
+    {
+      "epoch": 1.0216216216216216,
+      "grad_norm": 1.4763374328613281,
+      "learning_rate": 2.5166491273601802e-05,
+      "loss": 0.9239,
+      "step": 95
+    },
+    {
+      "epoch": 1.0756756756756758,
+      "grad_norm": 1.6701091527938843,
+      "learning_rate": 2.445681803883678e-05,
+      "loss": 0.8151,
+      "step": 100
+    },
+    {
+      "epoch": 1.1297297297297297,
+      "grad_norm": 1.6311923265457153,
+      "learning_rate": 2.371011975879742e-05,
+      "loss": 0.8152,
+      "step": 105
+    },
+    {
+      "epoch": 1.1837837837837837,
+      "grad_norm": 1.7697092294692993,
+      "learning_rate": 2.292931988379344e-05,
+      "loss": 0.751,
+      "step": 110
+    },
+    {
+      "epoch": 1.2378378378378379,
+      "grad_norm": 1.7223427295684814,
+      "learning_rate": 2.211747537765808e-05,
+      "loss": 0.7145,
+      "step": 115
+    },
+    {
+      "epoch": 1.291891891891892,
+      "grad_norm": 1.9200992584228516,
+      "learning_rate": 2.1277764749216613e-05,
+      "loss": 0.7398,
+      "step": 120
+    },
+    {
+      "epoch": 1.345945945945946,
+      "grad_norm": 2.0339231491088867,
+      "learning_rate": 2.0413475607885617e-05,
+      "loss": 0.6419,
+      "step": 125
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.7481001615524292,
+      "learning_rate": 1.9527991792124977e-05,
+      "loss": 0.6498,
+      "step": 130
+    },
+    {
+      "epoch": 1.454054054054054,
+      "grad_norm": 1.8370639085769653,
+      "learning_rate": 1.862478012113684e-05,
+      "loss": 0.5914,
+      "step": 135
+    },
+    {
+      "epoch": 1.5081081081081082,
+      "grad_norm": 1.9454028606414795,
+      "learning_rate": 1.770737682168091e-05,
+      "loss": 0.5612,
+      "step": 140
+    },
+    {
+      "epoch": 1.5621621621621622,
+      "grad_norm": 2.057041645050049,
+      "learning_rate": 1.6779373683147424e-05,
+      "loss": 0.5542,
+      "step": 145
+    },
+    {
+      "epoch": 1.6162162162162161,
+      "grad_norm": 1.9461379051208496,
+      "learning_rate": 1.5844403995092943e-05,
+      "loss": 0.5502,
+      "step": 150
+    },
+    {
+      "epoch": 1.6702702702702703,
+      "grad_norm": 1.807660698890686,
+      "learning_rate": 1.4906128322296054e-05,
+      "loss": 0.5301,
+      "step": 155
+    },
+    {
+      "epoch": 1.7243243243243245,
+      "grad_norm": 1.9510632753372192,
+      "learning_rate": 1.3968220173025866e-05,
+      "loss": 0.4716,
+      "step": 160
+    },
+    {
+      "epoch": 1.7783783783783784,
+      "grad_norm": 1.7930570840835571,
+      "learning_rate": 1.303435161663459e-05,
+      "loss": 0.4719,
+      "step": 165
+    },
+    {
+      "epoch": 1.8324324324324324,
+      "grad_norm": 2.0223488807678223,
+      "learning_rate": 1.2108178906783734e-05,
+      "loss": 0.4589,
+      "step": 170
+    },
+    {
+      "epoch": 1.8864864864864865,
+      "grad_norm": 1.8874939680099487,
+      "learning_rate": 1.119332816659137e-05,
+      "loss": 0.4204,
+      "step": 175
+    },
+    {
+      "epoch": 1.9405405405405407,
+      "grad_norm": 2.061260223388672,
+      "learning_rate": 1.0293381191745638e-05,
+      "loss": 0.416,
+      "step": 180
+    },
+    {
+      "epoch": 1.9945945945945946,
+      "grad_norm": 1.8097596168518066,
+      "learning_rate": 9.411861427167567e-06,
+      "loss": 0.4104,
+      "step": 185
+    },
+    {
+      "epoch": 2.0432432432432432,
+      "grad_norm": 2.0580127239227295,
+      "learning_rate": 8.552220172127148e-06,
+      "loss": 0.323,
+      "step": 190
+    },
+    {
+      "epoch": 2.097297297297297,
+      "grad_norm": 1.7233787775039673,
+      "learning_rate": 7.717823067821737e-06,
+      "loss": 0.2843,
+      "step": 195
+    },
+    {
+      "epoch": 2.1513513513513516,
+      "grad_norm": 1.961771845817566,
+      "learning_rate": 6.911936920320457e-06,
+      "loss": 0.2987,
+      "step": 200
+    },
+    {
+      "epoch": 2.2054054054054055,
+      "grad_norm": 1.6951320171356201,
+      "learning_rate": 6.137716910464735e-06,
+      "loss": 0.2813,
+      "step": 205
+    },
+    {
+      "epoch": 2.2594594594594595,
+      "grad_norm": 1.9422856569290161,
+      "learning_rate": 5.398194240800684e-06,
+      "loss": 0.2696,
+      "step": 210
+    },
+    {
+      "epoch": 2.3135135135135134,
+      "grad_norm": 1.5580745935440063,
+      "learning_rate": 4.696264267907346e-06,
+      "loss": 0.2934,
+      "step": 215
+    },
+    {
+      "epoch": 2.3675675675675674,
+      "grad_norm": 2.1355059146881104,
+      "learning_rate": 4.034675166585079e-06,
+      "loss": 0.2452,
+      "step": 220
+    },
+    {
+      "epoch": 2.4216216216216218,
+      "grad_norm": 1.7997058629989624,
+      "learning_rate": 3.4160171702854287e-06,
+      "loss": 0.2584,
+      "step": 225
+    },
+    {
+      "epoch": 2.4756756756756757,
+      "grad_norm": 1.5523905754089355,
+      "learning_rate": 2.8427124299082374e-06,
+      "loss": 0.2387,
+      "step": 230
+    },
+    {
+      "epoch": 2.5297297297297296,
+      "grad_norm": 1.4123568534851074,
+      "learning_rate": 2.3170055306703516e-06,
+      "loss": 0.2421,
+      "step": 235
+    },
+    {
+      "epoch": 2.583783783783784,
+      "grad_norm": 1.677291989326477,
+      "learning_rate": 1.8409547041741437e-06,
+      "loss": 0.2335,
+      "step": 240
+    },
+    {
+      "epoch": 2.637837837837838,
+      "grad_norm": 1.4620577096939087,
+      "learning_rate": 1.416423770081941e-06,
+      "loss": 0.2145,
+      "step": 245
+    },
+    {
+      "epoch": 2.691891891891892,
+      "grad_norm": 1.4463541507720947,
+      "learning_rate": 1.0450748389462183e-06,
+      "loss": 0.2318,
+      "step": 250
+    },
+    {
+      "epoch": 2.745945945945946,
+      "grad_norm": 1.2982896566390991,
+      "learning_rate": 7.283618047650808e-07,
+      "loss": 0.2283,
+      "step": 255
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.3607592582702637,
+      "learning_rate": 4.675246527408872e-07,
+      "loss": 0.215,
+      "step": 260
+    },
+    {
+      "epoch": 2.854054054054054,
+      "grad_norm": 1.4905956983566284,
+      "learning_rate": 2.635846045280277e-07,
+      "loss": 0.2345,
+      "step": 265
+    },
+    {
+      "epoch": 2.908108108108108,
+      "grad_norm": 1.372031569480896,
+      "learning_rate": 1.1734011997709626e-07,
+      "loss": 0.2151,
+      "step": 270
+    },
+    {
+      "epoch": 2.962162162162162,
+      "grad_norm": 1.4231053590774536,
+      "learning_rate": 2.9363771029242705e-08,
+      "loss": 0.2205,
+      "step": 275
+    },
+    {
+      "epoch": 3.0,
+      "step": 279,
+      "total_flos": 5.3407124401055334e+17,
+      "train_loss": 0.7801467624616452,
+      "train_runtime": 253.8178,
+      "train_samples_per_second": 34.962,
+      "train_steps_per_second": 1.099
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 279,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.3407124401055334e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

base/52_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e475f950f442b51f4c1b72a3230f19888409c44fc51d326c04a0208f929b81
+size 8017