upload initial files

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+datasets:
+- RaiBP/openwebtext2-first-30-chunks-ablation-full
+model-index:
+- name: training_full
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# training_full
+
+This model was trained from scratch on the RaiBP/openwebtext2-first-30-chunks-ablation-full dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 1.13.0
+- Datasets 2.16.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.342734659866764,
+    "train_runtime": 177257.4839,
+    "train_samples": 2963032,
+    "train_samples_per_second": 16.716,
+    "train_steps_per_second": 0.261
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./training",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.0.dev0"
+}

runs/events.out.tfevents.1704326138.pytorchRB.4152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a499fe168d4ae5d38f0a56db801e4a933364d4e44a1e5c764c8d56ca285165fd
+size 19569

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.342734659866764,
+    "train_runtime": 177257.4839,
+    "train_samples": 2963032,
+    "train_samples_per_second": 16.716,
+    "train_steps_per_second": 0.261
+}

trainer_state.json

@@ -0,0 +1,582 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999892002807927,
+  "eval_steps": 500,
+  "global_step": 46297,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0025,
+      "loss": 6.1463,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.005,
+      "loss": 4.8574,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.004944808706978387,
+      "loss": 4.2925,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.004889617413956775,
+      "loss": 4.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.004834426120935161,
+      "loss": 3.9071,
+      "step": 2500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.004779234827913549,
+      "loss": 3.8144,
+      "step": 3000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.004724043534891935,
+      "loss": 3.7441,
+      "step": 3500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.004668852241870323,
+      "loss": 3.6878,
+      "step": 4000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00461366094884871,
+      "loss": 3.6526,
+      "step": 4500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0045584696558270965,
+      "loss": 3.6217,
+      "step": 5000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.004503278362805484,
+      "loss": 3.585,
+      "step": 5500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.004448087069783871,
+      "loss": 3.5614,
+      "step": 6000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.004392895776762258,
+      "loss": 3.5374,
+      "step": 6500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.004337704483740645,
+      "loss": 3.5145,
+      "step": 7000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0042825131907190325,
+      "loss": 3.4965,
+      "step": 7500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.004227321897697419,
+      "loss": 3.4809,
+      "step": 8000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.004172130604675806,
+      "loss": 3.4657,
+      "step": 8500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.004116939311654194,
+      "loss": 3.4502,
+      "step": 9000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00406174801863258,
+      "loss": 3.4365,
+      "step": 9500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.004006556725610968,
+      "loss": 3.4281,
+      "step": 10000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.003951365432589355,
+      "loss": 3.4145,
+      "step": 10500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.003896174139567742,
+      "loss": 3.3999,
+      "step": 11000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.003840982846546129,
+      "loss": 3.3951,
+      "step": 11500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0037857915535245163,
+      "loss": 3.3884,
+      "step": 12000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0037306002605029033,
+      "loss": 3.3765,
+      "step": 12500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00367540896748129,
+      "loss": 3.3721,
+      "step": 13000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.003620217674459677,
+      "loss": 3.3632,
+      "step": 13500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0035650263814380645,
+      "loss": 3.3595,
+      "step": 14000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0035098350884164515,
+      "loss": 3.3468,
+      "step": 14500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0034546437953948384,
+      "loss": 3.3418,
+      "step": 15000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0033994525023732258,
+      "loss": 3.3345,
+      "step": 15500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0033442612093516127,
+      "loss": 3.3222,
+      "step": 16000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0032890699163299997,
+      "loss": 3.3208,
+      "step": 16500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0032338786233083866,
+      "loss": 3.3199,
+      "step": 17000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.003178687330286774,
+      "loss": 3.31,
+      "step": 17500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.003123496037265161,
+      "loss": 3.2987,
+      "step": 18000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.003068304744243548,
+      "loss": 3.2946,
+      "step": 18500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0030131134512219357,
+      "loss": 3.2869,
+      "step": 19000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0029579221582003226,
+      "loss": 3.2882,
+      "step": 19500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.002902730865178709,
+      "loss": 3.2788,
+      "step": 20000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.002847539572157097,
+      "loss": 3.2739,
+      "step": 20500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.002792348279135484,
+      "loss": 3.267,
+      "step": 21000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.002737156986113871,
+      "loss": 3.2631,
+      "step": 21500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0026819656930922578,
+      "loss": 3.26,
+      "step": 22000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.002626774400070645,
+      "loss": 3.2565,
+      "step": 22500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.002571583107049032,
+      "loss": 3.243,
+      "step": 23000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.002516391814027419,
+      "loss": 3.2469,
+      "step": 23500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.002461200521005806,
+      "loss": 3.2408,
+      "step": 24000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0024060092279841933,
+      "loss": 3.2296,
+      "step": 24500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0023508179349625803,
+      "loss": 3.2367,
+      "step": 25000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0022956266419409672,
+      "loss": 3.2261,
+      "step": 25500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0022404353489193546,
+      "loss": 3.2252,
+      "step": 26000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0021852440558977415,
+      "loss": 3.2202,
+      "step": 26500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.002130052762876129,
+      "loss": 3.2141,
+      "step": 27000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.002074861469854516,
+      "loss": 3.2018,
+      "step": 27500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.002019670176832903,
+      "loss": 3.206,
+      "step": 28000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00196447888381129,
+      "loss": 3.1959,
+      "step": 28500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.001909287590789677,
+      "loss": 3.1896,
+      "step": 29000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0018540962977680643,
+      "loss": 3.1903,
+      "step": 29500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0017989050047464512,
+      "loss": 3.1911,
+      "step": 30000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0017437137117248384,
+      "loss": 3.1755,
+      "step": 30500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0016885224187032255,
+      "loss": 3.1731,
+      "step": 31000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0016333311256816125,
+      "loss": 3.1638,
+      "step": 31500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0015781398326599996,
+      "loss": 3.1666,
+      "step": 32000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0015229485396383866,
+      "loss": 3.1628,
+      "step": 32500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0014677572466167737,
+      "loss": 3.1549,
+      "step": 33000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.001412565953595161,
+      "loss": 3.1544,
+      "step": 33500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0013573746605735479,
+      "loss": 3.1452,
+      "step": 34000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.001302183367551935,
+      "loss": 3.1516,
+      "step": 34500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0012469920745303222,
+      "loss": 3.138,
+      "step": 35000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0011918007815087093,
+      "loss": 3.1318,
+      "step": 35500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0011366094884870963,
+      "loss": 3.1302,
+      "step": 36000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0010814181954654834,
+      "loss": 3.1262,
+      "step": 36500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0010262269024438704,
+      "loss": 3.1229,
+      "step": 37000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0009710356094222576,
+      "loss": 3.1205,
+      "step": 37500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0009158443164006447,
+      "loss": 3.1195,
+      "step": 38000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0008606530233790317,
+      "loss": 3.1108,
+      "step": 38500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0008054617303574188,
+      "loss": 3.0978,
+      "step": 39000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0007502704373358058,
+      "loss": 3.1015,
+      "step": 39500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0006950791443141929,
+      "loss": 3.0981,
+      "step": 40000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0006398878512925802,
+      "loss": 3.0908,
+      "step": 40500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0005846965582709672,
+      "loss": 3.0911,
+      "step": 41000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0005295052652493543,
+      "loss": 3.087,
+      "step": 41500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0004743139722277413,
+      "loss": 3.0817,
+      "step": 42000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0004191226792061285,
+      "loss": 3.0753,
+      "step": 42500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00036393138618451553,
+      "loss": 3.0719,
+      "step": 43000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00030874009316290263,
+      "loss": 3.0713,
+      "step": 43500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00025354880014128974,
+      "loss": 3.0591,
+      "step": 44000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001983575071196768,
+      "loss": 3.0564,
+      "step": 44500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001431662140980639,
+      "loss": 3.0586,
+      "step": 45000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.797492107645099e-05,
+      "loss": 3.0503,
+      "step": 45500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.278362805483807e-05,
+      "loss": 3.0476,
+      "step": 46000
+    },
+    {
+      "epoch": 1.0,
+      "step": 46297,
+      "total_flos": 1.5484207870676828e+18,
+      "train_loss": 3.342734659866764,
+      "train_runtime": 177257.4839,
+      "train_samples_per_second": 16.716,
+      "train_steps_per_second": 0.261
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 46297,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "total_flos": 1.5484207870676828e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a700fa06932e8b6453db02c249385bf1f2905676fbf3fd7307b65df17c9ae9
+size 4219