commit from thisscpdoesnotexist

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: output_gptneo125-2
+  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. -->
+
+# output_gptneo125-2
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.0+cu102
+- Datasets 1.18.3
+- Tokenizers 0.11.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.8555017889734686,
+    "train_runtime": 271.3586,
+    "train_samples": 7441,
+    "train_samples_per_second": 82.264,
+    "train_steps_per_second": 1.293
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "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": "4.17.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30600c4d16ba046409e92acbd9b2b6adfe76d0fb01d9e71c4fd78740a95a402e
+size 551182545

runs/Feb23_22-22-33_tpupytorch/1645654971.4671776/events.out.tfevents.1645654971.tpupytorch.4551.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422c78bf99cf0f073a6a641588a643053e9de87c8415cf2a773e5a464b226915
+size 4761

runs/Feb23_22-22-33_tpupytorch/events.out.tfevents.1645654971.tpupytorch.4551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1489feefc93da28236b43213effd88ebb5f3955a647663c37fc3352cdc5bcbd
+size 4061

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.8555017889734686,
+    "train_runtime": 271.3586,
+    "train_samples": 7441,
+    "train_samples_per_second": 82.264,
+    "train_steps_per_second": 1.293
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 351,
+      "total_flos": 1466939058683904.0,
+      "train_loss": 2.8555017889734686,
+      "train_runtime": 271.3586,
+      "train_samples_per_second": 82.264,
+      "train_steps_per_second": 1.293
+    }
+  ],
+  "max_steps": 351,
+  "num_train_epochs": 3,
+  "total_flos": 1466939058683904.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3d178c047f64c55e460ecc26c3a5a1b6e937c0045397e69b3c4bfffa587797
+size 2991