Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.5377466023936e+16,
+    "train_loss": 5.757713494451266,
+    "train_runtime": 5411.3319,
+    "train_samples": 97123,
+    "train_samples_per_second": 17.948,
+    "train_steps_per_second": 2.244
+}

checkpoint-10000/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./gpt2/config.json",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-10000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.1"
+}

checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac5051c5733efec770dd14dc85b0511539f257ae3ec666430834d19ed6b958a
+size 497774208

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2a10dd40cc005c6f61574bc63727ddeb4d91f57ece5df84fc3c772b392ec90
+size 995642298

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86265bc3b5bdd99cf8b09c33ce545311a548aa60acf41313375be0f2221b884c
+size 14244

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95c05e607b1866ea12ab07e69e308cf16182f4b085df3507b86b2f6e88c8eed
+size 1064

checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8236553825879253,
+  "eval_steps": 1000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08236553825879252,
+      "grad_norm": 2.806833267211914,
+      "learning_rate": 1.835268923482415e-05,
+      "loss": 7.3233,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16473107651758503,
+      "grad_norm": 2.414405345916748,
+      "learning_rate": 1.67053784696483e-05,
+      "loss": 6.428,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24709661477637757,
+      "grad_norm": 2.7336931228637695,
+      "learning_rate": 1.505806770447245e-05,
+      "loss": 6.121,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32946215303517007,
+      "grad_norm": 2.707063674926758,
+      "learning_rate": 1.3410756939296599e-05,
+      "loss": 5.8761,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4118276912939626,
+      "grad_norm": 2.918213129043579,
+      "learning_rate": 1.176344617412075e-05,
+      "loss": 5.7252,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49419322955275513,
+      "grad_norm": 2.722219944000244,
+      "learning_rate": 1.0116135408944898e-05,
+      "loss": 5.5951,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5765587678115477,
+      "grad_norm": 3.1989521980285645,
+      "learning_rate": 8.470471954534224e-06,
+      "loss": 5.4935,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6589243060703401,
+      "grad_norm": 3.0108842849731445,
+      "learning_rate": 6.823161189358373e-06,
+      "loss": 5.4158,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7412898443291327,
+      "grad_norm": 2.9963932037353516,
+      "learning_rate": 5.177497734947698e-06,
+      "loss": 5.3553,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8236553825879253,
+      "grad_norm": 3.4173614978790283,
+      "learning_rate": 3.530186969771848e-06,
+      "loss": 5.2982,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 12141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.090336256e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ef3c13c88151db8e45a0b5710a309567ce4c7d0ec21fe92d39500047d43726
+size 5368

checkpoint-12141/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./gpt2/config.json",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-12141/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.1"
+}

checkpoint-12141/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484497fd81aa8274235e37459d5194c43f2e078e52b81d56bb57a29edf21817b
+size 497774208

checkpoint-12141/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d14857c0b728b89df20385d432fcf48f6840795e77e21dd167987a60ec3a7c
+size 995642298

checkpoint-12141/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0622c513c9f4497e3c3c3583048de7eb5a3c8c797f78f267464f88929b3e30b9
+size 14244

checkpoint-12141/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec524885c31fa20b26ef6f9fff97de491dba4aad844145b65ae384ff09dbddb
+size 1064

checkpoint-12141/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-12141/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-12141/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 12141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08236553825879252,
+      "grad_norm": 2.806833267211914,
+      "learning_rate": 1.835268923482415e-05,
+      "loss": 7.3233,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16473107651758503,
+      "grad_norm": 2.414405345916748,
+      "learning_rate": 1.67053784696483e-05,
+      "loss": 6.428,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24709661477637757,
+      "grad_norm": 2.7336931228637695,
+      "learning_rate": 1.505806770447245e-05,
+      "loss": 6.121,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32946215303517007,
+      "grad_norm": 2.707063674926758,
+      "learning_rate": 1.3410756939296599e-05,
+      "loss": 5.8761,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4118276912939626,
+      "grad_norm": 2.918213129043579,
+      "learning_rate": 1.176344617412075e-05,
+      "loss": 5.7252,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49419322955275513,
+      "grad_norm": 2.722219944000244,
+      "learning_rate": 1.0116135408944898e-05,
+      "loss": 5.5951,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5765587678115477,
+      "grad_norm": 3.1989521980285645,
+      "learning_rate": 8.470471954534224e-06,
+      "loss": 5.4935,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6589243060703401,
+      "grad_norm": 3.0108842849731445,
+      "learning_rate": 6.823161189358373e-06,
+      "loss": 5.4158,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7412898443291327,
+      "grad_norm": 2.9963932037353516,
+      "learning_rate": 5.177497734947698e-06,
+      "loss": 5.3553,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8236553825879253,
+      "grad_norm": 3.4173614978790283,
+      "learning_rate": 3.530186969771848e-06,
+      "loss": 5.2982,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9060209208467177,
+      "grad_norm": 2.9771502017974854,
+      "learning_rate": 1.884523515361173e-06,
+      "loss": 5.2726,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9883864591055103,
+      "grad_norm": 3.5910282135009766,
+      "learning_rate": 2.3721275018532246e-07,
+      "loss": 5.2688,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 12141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5377466023936e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12141/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ef3c13c88151db8e45a0b5710a309567ce4c7d0ec21fe92d39500047d43726
+size 5368

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./gpt2/config.json",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "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": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484497fd81aa8274235e37459d5194c43f2e078e52b81d56bb57a29edf21817b
+size 497774208

runs/Dec30_04-43-15_52a4379daf8e/events.out.tfevents.1735533808.52a4379daf8e.1729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22217bff33d82cf46396d0c1dc825c4e1def6d4721b3e11c72cc291af78674cf
+size 8089

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.5377466023936e+16,
+    "train_loss": 5.757713494451266,
+    "train_runtime": 5411.3319,
+    "train_samples": 97123,
+    "train_samples_per_second": 17.948,
+    "train_steps_per_second": 2.244
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 12141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08236553825879252,
+      "grad_norm": 2.806833267211914,
+      "learning_rate": 1.835268923482415e-05,
+      "loss": 7.3233,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16473107651758503,
+      "grad_norm": 2.414405345916748,
+      "learning_rate": 1.67053784696483e-05,
+      "loss": 6.428,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24709661477637757,
+      "grad_norm": 2.7336931228637695,
+      "learning_rate": 1.505806770447245e-05,
+      "loss": 6.121,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32946215303517007,
+      "grad_norm": 2.707063674926758,
+      "learning_rate": 1.3410756939296599e-05,
+      "loss": 5.8761,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4118276912939626,
+      "grad_norm": 2.918213129043579,
+      "learning_rate": 1.176344617412075e-05,
+      "loss": 5.7252,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49419322955275513,
+      "grad_norm": 2.722219944000244,
+      "learning_rate": 1.0116135408944898e-05,
+      "loss": 5.5951,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5765587678115477,
+      "grad_norm": 3.1989521980285645,
+      "learning_rate": 8.470471954534224e-06,
+      "loss": 5.4935,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6589243060703401,
+      "grad_norm": 3.0108842849731445,
+      "learning_rate": 6.823161189358373e-06,
+      "loss": 5.4158,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7412898443291327,
+      "grad_norm": 2.9963932037353516,
+      "learning_rate": 5.177497734947698e-06,
+      "loss": 5.3553,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8236553825879253,
+      "grad_norm": 3.4173614978790283,
+      "learning_rate": 3.530186969771848e-06,
+      "loss": 5.2982,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9060209208467177,
+      "grad_norm": 2.9771502017974854,
+      "learning_rate": 1.884523515361173e-06,
+      "loss": 5.2726,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9883864591055103,
+      "grad_norm": 3.5910282135009766,
+      "learning_rate": 2.3721275018532246e-07,
+      "loss": 5.2688,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0,
+      "step": 12141,
+      "total_flos": 2.5377466023936e+16,
+      "train_loss": 5.757713494451266,
+      "train_runtime": 5411.3319,
+      "train_samples_per_second": 17.948,
+      "train_steps_per_second": 2.244
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 12141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5377466023936e+16,
+  "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 sha256:36ef3c13c88151db8e45a0b5710a309567ce4c7d0ec21fe92d39500047d43726
+size 5368