Uploaded 1.31B tokens trained checkpoint of USPTO model

config.json

@@ -0,0 +1,31 @@
+{
+  "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_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "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": "4.28.1",
+  "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": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220ad86dae3c0f981b9c75fe3f4553eda59c4d674a265fb2afb2f63a67ad9712
+size 411891141

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef0835117dfa2d0c3db7c0d37ac082aa311504a959788a0dd30e3f401443963
+size 214330013

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cc321735b16afb265febc9b58a858689648ca16d15e424c9b8548eaa0f9207
+size 21665

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7549ad274089a9ad60efe6de271569cab8c04edb13f588f2f4bfaed55ef14be8
+size 627

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.823427587890625,
+    "train_runtime": 29054.993,
+    "train_samples": 20000,
+    "train_samples_per_second": 44.054,
+    "train_steps_per_second": 0.688
+}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.875e-05,
+      "loss": 6.4755,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.75e-05,
+      "loss": 5.3883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6250000000000006e-05,
+      "loss": 5.0866,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5e-05,
+      "loss": 4.8098,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.375e-05,
+      "loss": 4.5874,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.25e-05,
+      "loss": 4.431,
+      "step": 3000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.125e-05,
+      "loss": 4.2697,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4e-05,
+      "loss": 4.1265,
+      "step": 4000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.875e-05,
+      "loss": 3.9942,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 3.9671,
+      "step": 5000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.625e-05,
+      "loss": 3.8442,
+      "step": 5500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.5e-05,
+      "loss": 3.7388,
+      "step": 6000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.375000000000001e-05,
+      "loss": 3.6739,
+      "step": 6500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 3.6045,
+      "step": 7000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.125e-05,
+      "loss": 3.5164,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3e-05,
+      "loss": 3.6107,
+      "step": 8000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.8749999999999997e-05,
+      "loss": 3.586,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 3.5452,
+      "step": 9000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.625e-05,
+      "loss": 3.512,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5e-05,
+      "loss": 3.4694,
+      "step": 10000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.375e-05,
+      "loss": 3.3509,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.25e-05,
+      "loss": 3.3117,
+      "step": 11000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.125e-05,
+      "loss": 3.2709,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2e-05,
+      "loss": 3.2705,
+      "step": 12000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.2726,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.75e-05,
+      "loss": 3.2576,
+      "step": 13000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 2.973,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5e-05,
+      "loss": 2.8429,
+      "step": 14000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.3750000000000002e-05,
+      "loss": 2.7647,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.25e-05,
+      "loss": 2.7949,
+      "step": 15000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.125e-05,
+      "loss": 2.808,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 2.807,
+      "step": 16000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.75e-06,
+      "loss": 2.7749,
+      "step": 16500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.5e-06,
+      "loss": 2.8158,
+      "step": 17000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.25e-06,
+      "loss": 2.7586,
+      "step": 17500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5e-06,
+      "loss": 2.7598,
+      "step": 18000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.75e-06,
+      "loss": 2.7767,
+      "step": 18500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.5e-06,
+      "loss": 2.7294,
+      "step": 19000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.25e-06,
+      "loss": 2.737,
+      "step": 19500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 2.7474,
+      "step": 20000
+    }
+  ],
+  "max_steps": 20000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.9833890537472e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e309872293e031866f471f1dbaff34a19e38f1fd3785b6a45e5666f0aec69a8
+size 3643