upload initial files

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+datasets:
+- RaiBP/openwebtext2-first-30-chunks-english-only-examples
+model-index:
+- name: training_nen
+  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_nen
+
+This model was trained from scratch on the RaiBP/openwebtext2-first-30-chunks-english-only-examples 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": 3.391347985035243,
+    "train_runtime": 175663.9283,
+    "train_samples": 2944169,
+    "train_samples_per_second": 16.76,
+    "train_steps_per_second": 0.262
+}

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.1704577514.pytorchRB.11761.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735fc90bbed117de2f99d0b4afd3e2d368da330ce0152cebed4f6731acb51784
+size 19566

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": 3.391347985035243,
+    "train_runtime": 175663.9283,
+    "train_samples": 2944169,
+    "train_samples_per_second": 16.76,
+    "train_steps_per_second": 0.262
+}

trainer_state.json

@@ -0,0 +1,582 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999836966268321,
+  "eval_steps": 500,
+  "global_step": 46002,
+  "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": 6.1489,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.005,
+      "loss": 4.849,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.004944446913470513,
+      "loss": 4.3185,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.004888893826941025,
+      "loss": 4.0835,
+      "step": 2000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.004833340740411538,
+      "loss": 3.9459,
+      "step": 2500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0047777876538820496,
+      "loss": 3.8551,
+      "step": 3000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.004722234567352562,
+      "loss": 3.7909,
+      "step": 3500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.004666681480823075,
+      "loss": 3.7385,
+      "step": 4000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.004611128394293587,
+      "loss": 3.6979,
+      "step": 4500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.004555575307764099,
+      "loss": 3.6587,
+      "step": 5000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0045000222212346125,
+      "loss": 3.6335,
+      "step": 5500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.004444469134705124,
+      "loss": 3.6055,
+      "step": 6000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.004388916048175637,
+      "loss": 3.582,
+      "step": 6500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.004333362961646149,
+      "loss": 3.5627,
+      "step": 7000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.004277809875116662,
+      "loss": 3.5455,
+      "step": 7500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.004222256788587174,
+      "loss": 3.5307,
+      "step": 8000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.004166703702057686,
+      "loss": 3.5155,
+      "step": 8500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.004111150615528199,
+      "loss": 3.5015,
+      "step": 9000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.004055597528998711,
+      "loss": 3.4861,
+      "step": 9500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.004000044442469224,
+      "loss": 3.4746,
+      "step": 10000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.003944491355939736,
+      "loss": 3.4666,
+      "step": 10500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0038889382694102487,
+      "loss": 3.4558,
+      "step": 11000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.003833385182880761,
+      "loss": 3.4457,
+      "step": 11500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0037778320963512734,
+      "loss": 3.4388,
+      "step": 12000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0037222790098217855,
+      "loss": 3.4297,
+      "step": 12500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0036667259232922985,
+      "loss": 3.4141,
+      "step": 13000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0036111728367628107,
+      "loss": 3.4104,
+      "step": 13500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0035556197502333233,
+      "loss": 3.4001,
+      "step": 14000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0035000666637038354,
+      "loss": 3.3922,
+      "step": 14500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.003444513577174348,
+      "loss": 3.3842,
+      "step": 15000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00338896049064486,
+      "loss": 3.3775,
+      "step": 15500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0033334074041153727,
+      "loss": 3.3712,
+      "step": 16000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.003277854317585885,
+      "loss": 3.3677,
+      "step": 16500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0032223012310563974,
+      "loss": 3.3633,
+      "step": 17000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0031667481445269096,
+      "loss": 3.3547,
+      "step": 17500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0031111950579974226,
+      "loss": 3.3504,
+      "step": 18000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0030556419714679347,
+      "loss": 3.3417,
+      "step": 18500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0030000888849384473,
+      "loss": 3.3381,
+      "step": 19000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00294453579840896,
+      "loss": 3.3331,
+      "step": 19500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.002888982711879472,
+      "loss": 3.3252,
+      "step": 20000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0028334296253499846,
+      "loss": 3.3194,
+      "step": 20500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0027778765388204968,
+      "loss": 3.3189,
+      "step": 21000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0027223234522910093,
+      "loss": 3.3097,
+      "step": 21500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0026667703657615215,
+      "loss": 3.3074,
+      "step": 22000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0026112172792320345,
+      "loss": 3.3042,
+      "step": 22500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0025556641927025467,
+      "loss": 3.2946,
+      "step": 23000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0025001111061730592,
+      "loss": 3.2915,
+      "step": 23500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0024445580196435714,
+      "loss": 3.2863,
+      "step": 24000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.002389004933114084,
+      "loss": 3.2838,
+      "step": 24500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0023334518465845965,
+      "loss": 3.2779,
+      "step": 25000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0022778987600551087,
+      "loss": 3.2719,
+      "step": 25500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0022223456735256213,
+      "loss": 3.2683,
+      "step": 26000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0021667925869961334,
+      "loss": 3.2655,
+      "step": 26500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.002111239500466646,
+      "loss": 3.2607,
+      "step": 27000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0020556864139371586,
+      "loss": 3.2536,
+      "step": 27500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0020001333274076707,
+      "loss": 3.2529,
+      "step": 28000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0019445802408781833,
+      "loss": 3.2472,
+      "step": 28500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0018890271543486957,
+      "loss": 3.2371,
+      "step": 29000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.001833474067819208,
+      "loss": 3.2356,
+      "step": 29500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0017779209812897204,
+      "loss": 3.235,
+      "step": 30000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0017223678947602327,
+      "loss": 3.2278,
+      "step": 30500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0016668148082307453,
+      "loss": 3.2242,
+      "step": 31000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0016112617217012577,
+      "loss": 3.2187,
+      "step": 31500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0015557086351717703,
+      "loss": 3.2166,
+      "step": 32000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0015001555486422826,
+      "loss": 3.2124,
+      "step": 32500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0014446024621127952,
+      "loss": 3.2056,
+      "step": 33000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0013890493755833076,
+      "loss": 3.2004,
+      "step": 33500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00133349628905382,
+      "loss": 3.1971,
+      "step": 34000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0012779432025243323,
+      "loss": 3.1939,
+      "step": 34500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0012223901159948447,
+      "loss": 3.1899,
+      "step": 35000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0011668370294653572,
+      "loss": 3.1844,
+      "step": 35500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0011112839429358696,
+      "loss": 3.1825,
+      "step": 36000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.001055730856406382,
+      "loss": 3.1777,
+      "step": 36500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0010001777698768943,
+      "loss": 3.1737,
+      "step": 37000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0009446246833474068,
+      "loss": 3.1702,
+      "step": 37500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0008890715968179192,
+      "loss": 3.1652,
+      "step": 38000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0008335185102884317,
+      "loss": 3.1591,
+      "step": 38500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0007779654237589441,
+      "loss": 3.156,
+      "step": 39000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0007224123372294565,
+      "loss": 3.1518,
+      "step": 39500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0006668592506999689,
+      "loss": 3.1452,
+      "step": 40000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0006113061641704813,
+      "loss": 3.1406,
+      "step": 40500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0005557530776409938,
+      "loss": 3.1359,
+      "step": 41000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0005001999911115062,
+      "loss": 3.135,
+      "step": 41500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0004446469045820186,
+      "loss": 3.1247,
+      "step": 42000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.000389093818052531,
+      "loss": 3.1266,
+      "step": 42500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00033354073152304343,
+      "loss": 3.1242,
+      "step": 43000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00027798764499355585,
+      "loss": 3.12,
+      "step": 43500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00022243455846406826,
+      "loss": 3.119,
+      "step": 44000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001668814719345807,
+      "loss": 3.1099,
+      "step": 44500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001113283854050931,
+      "loss": 3.1032,
+      "step": 45000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.577529887560553e-05,
+      "loss": 3.1045,
+      "step": 45500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.222123461179503e-07,
+      "loss": 3.1027,
+      "step": 46000
+    },
+    {
+      "epoch": 1.0,
+      "step": 46002,
+      "total_flos": 1.538554399872254e+18,
+      "train_loss": 3.391347985035243,
+      "train_runtime": 175663.9283,
+      "train_samples_per_second": 16.76,
+      "train_steps_per_second": 0.262
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 46002,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "total_flos": 1.538554399872254e+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 sha256:50f69e0dfecf25900229cfd973e84e5af05b574c025f3e4b20e2c92cfb0ac3b5
+size 4219