Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./result/pythia-410m/checkpoint-91500",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6f54b3613eae4e61a4e56387835e202ed8d60c74a79788ec635dedaf088ba0
+size 3242843909

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f03a0059d2a96c6d05b7450177af030d9dd586c995b7d280897ed1facc04640
+size 1722122365

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e1aabc544c60122ce261dbdc9173745974f4484ccd8761dacb22f948424c9a
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf76056583d41842871336602e548b8352166ec739e85623f056fff67204eb95
+size 627

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "./result/pythia-410m/checkpoint-91500",
+  "special_tokens_map_file": "./result/pythia-410m/checkpoint-91500/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 21.278782894736842,
+  "global_step": 103500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.588973502853666e-06,
+      "loss": 0.6499,
+      "step": 5000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.177782529317917e-06,
+      "loss": 0.5129,
+      "step": 10000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 8.766591555782168e-06,
+      "loss": 0.4726,
+      "step": 15000
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 8.355400582246419e-06,
+      "loss": 0.4026,
+      "step": 20000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 7.94420960871067e-06,
+      "loss": 0.3312,
+      "step": 25000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 7.533018635174921e-06,
+      "loss": 0.2952,
+      "step": 30000
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 7.121827661639172e-06,
+      "loss": 0.229,
+      "step": 35000
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 6.710636688103423e-06,
+      "loss": 0.1724,
+      "step": 40000
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 6.2994457145676745e-06,
+      "loss": 0.1658,
+      "step": 45000
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 5.888254741031926e-06,
+      "loss": 0.1506,
+      "step": 50000
+    },
+    {
+      "epoch": 11.31,
+      "learning_rate": 5.477063767496177e-06,
+      "loss": 0.1034,
+      "step": 55000
+    },
+    {
+      "epoch": 12.34,
+      "learning_rate": 5.065872793960427e-06,
+      "loss": 0.0735,
+      "step": 60000
+    },
+    {
+      "epoch": 13.36,
+      "learning_rate": 4.654681820424679e-06,
+      "loss": 0.0548,
+      "step": 65000
+    },
+    {
+      "epoch": 14.39,
+      "learning_rate": 4.24349084688893e-06,
+      "loss": 0.0437,
+      "step": 70000
+    },
+    {
+      "epoch": 15.42,
+      "learning_rate": 3.83229987335318e-06,
+      "loss": 0.0721,
+      "step": 75000
+    },
+    {
+      "epoch": 16.45,
+      "learning_rate": 3.421108899817431e-06,
+      "loss": 0.0555,
+      "step": 80000
+    },
+    {
+      "epoch": 17.48,
+      "learning_rate": 3.0099179262816823e-06,
+      "loss": 0.041,
+      "step": 85000
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 2.5987269527459334e-06,
+      "loss": 0.034,
+      "step": 90000
+    },
+    {
+      "epoch": 19.53,
+      "learning_rate": 2.187535979210185e-06,
+      "loss": 0.0392,
+      "step": 95000
+    },
+    {
+      "epoch": 20.56,
+      "learning_rate": 1.7763450056744355e-06,
+      "loss": 0.035,
+      "step": 100000
+    }
+  ],
+  "max_steps": 121600,
+  "num_train_epochs": 25,
+  "total_flos": 8.999206543215821e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2d37e17ddee0cc36fea1deab8a0dff7f3a98469319127fb8b9b9fe1a503337
+size 3259