Upload 14 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "/content/gdrive/MyDrive/models/rugpt3medium_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "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": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4266cd054220cc53309bb83ffba492f70a3ab86cebbfe64e377edf99fe149102
+size 1524265245

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f3d36f8ec43bdfda7b5df324a1333e430713d00e92668b639e5897f4386fe5
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a76e1d5ee5e123156bce49bffc71b75a50bbf7e3af0baea5664e7d88a87bbdf
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc1e5dbf804a348d919f0e7078c7ea5a61c36246037e84246d3d732c19988c3
+size 627

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 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.60555255092843,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9774652965566973e-05,
+      "loss": 2.8362,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.9549756625202815e-05,
+      "loss": 2.8099,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9324409590769786e-05,
+      "loss": 2.8307,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.909951325040563e-05,
+      "loss": 2.7755,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.88741662159726e-05,
+      "loss": 2.7973,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.864881918153957e-05,
+      "loss": 2.7982,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.842347214710655e-05,
+      "loss": 2.7681,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.819812511267352e-05,
+      "loss": 2.7785,
+      "step": 4000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.79727780782405e-05,
+      "loss": 2.7593,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.774743104380747e-05,
+      "loss": 2.7396,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.752208400937444e-05,
+      "loss": 2.7515,
+      "step": 5500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.7296736974941416e-05,
+      "loss": 2.5096,
+      "step": 6000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.707138994050839e-05,
+      "loss": 2.4782,
+      "step": 6500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.684604290607536e-05,
+      "loss": 2.5025,
+      "step": 7000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.66211465657112e-05,
+      "loss": 2.5009,
+      "step": 7500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.639579953127817e-05,
+      "loss": 2.4875,
+      "step": 8000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.617045249684514e-05,
+      "loss": 2.5066,
+      "step": 8500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.594510546241212e-05,
+      "loss": 2.5209,
+      "step": 9000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.571975842797909e-05,
+      "loss": 2.5225,
+      "step": 9500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.549441139354607e-05,
+      "loss": 2.5228,
+      "step": 10000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.526906435911303e-05,
+      "loss": 2.5173,
+      "step": 10500
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.5044168018748875e-05,
+      "loss": 2.5319,
+      "step": 11000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.481882098431585e-05,
+      "loss": 2.2928,
+      "step": 11500
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.459347394988282e-05,
+      "loss": 2.2681,
+      "step": 12000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 4.4368126915449795e-05,
+      "loss": 2.2761,
+      "step": 12500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.4142779881016766e-05,
+      "loss": 2.2751,
+      "step": 13000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 4.391788354065261e-05,
+      "loss": 2.2932,
+      "step": 13500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.369253650621958e-05,
+      "loss": 2.2924,
+      "step": 14000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.346718947178655e-05,
+      "loss": 2.2908,
+      "step": 14500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.324184243735353e-05,
+      "loss": 2.3225,
+      "step": 15000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 4.30164954029205e-05,
+      "loss": 2.3189,
+      "step": 15500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.279114836848747e-05,
+      "loss": 2.3191,
+      "step": 16000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.256580133405445e-05,
+      "loss": 2.3243,
+      "step": 16500
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.234090499369028e-05,
+      "loss": 2.1313,
+      "step": 17000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.211555795925726e-05,
+      "loss": 2.0608,
+      "step": 17500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 4.189021092482423e-05,
+      "loss": 2.0668,
+      "step": 18000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 4.16648638903912e-05,
+      "loss": 2.0977,
+      "step": 18500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 4.143951685595818e-05,
+      "loss": 2.0911,
+      "step": 19000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 4.121416982152515e-05,
+      "loss": 2.1224,
+      "step": 19500
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 4.098882278709212e-05,
+      "loss": 2.1214,
+      "step": 20000
+    }
+  ],
+  "max_steps": 110940,
+  "num_train_epochs": 20,
+  "total_flos": 3.714802778112e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c2fcda5e210d0236fd4a93dadbcecf1f8991fb6b833bbc3d3fc27c2f43ff14
+size 3643