Upload 8 files

config.json

@@ -0,0 +1,43 @@
+{
+ "_name_or_path": "data/further_pretraining/xlnet-large-cased/checkpoint-42354",
+ "architectures": [
+ "XLNetLMHeadModel"
+ ],
+ "attn_type": "bi",
+ "bi_data": false,
+ "bos_token_id": 1,
+ "clamp_len": -1,
+ "d_head": 64,
+ "d_inner": 4096,
+ "d_model": 1024,
+ "dropout": 0.1,
+ "end_n_top": 5,
+ "eos_token_id": 2,
+ "ff_activation": "gelu",
+ "initializer_range": 0.02,
+ "layer_norm_eps": 1e-12,
+ "mem_len": null,
+ "model_type": "xlnet",
+ "n_head": 16,
+ "n_layer": 24,
+ "pad_token_id": 5,
+ "reuse_len": null,
+ "same_length": false,
+ "start_n_top": 5,
+ "summary_activation": "tanh",
+ "summary_last_dropout": 0.1,
+ "summary_type": "last",
+ "summary_use_proj": true,
+ "task_specific_params": {
+ "text-generation": {
+ "do_sample": true,
+ "max_length": 250
+ }
+ },
+ "torch_dtype": "float32",
+ "transformers_version": "4.37.2",
+ "untie_r": true,
+ "use_mems_eval": true,
+ "use_mems_train": false,
+ "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "pad_token_id": 5,
+ "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ba3e8d38edc5e430a564acb7229761dc5ac70ee5c86a32505a01ef3f6ea834
+size 1441248632

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed847e330aa92c74b3f96f0fa64708c1d1aca4ce37bc60622abbea3539ad308c
+size 2882752227

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9baa22c0a5f56036cc8b7a2f34fc4ae033a88859cc813c28d7171e45feb7c0d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ddc11590b44292b46c83821a904f319a165e36d3b4d30a50f0bd644c35745a
+size 1064

trainer_state.json

@@ -0,0 +1,83 @@
+{
+ "best_metric": 0.00019271760538686067,
+ "best_model_checkpoint": "data/further_pretraining/xlnet-large-cased/checkpoint-4706",
+ "epoch": 1.0,
+ "eval_steps": 500,
+ "global_step": 4706,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.11,
+ "learning_rate": 2.6812579685507864e-05,
+ "loss": 0.0002,
+ "step": 500
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 2.3625159371015725e-05,
+ "loss": 0.0001,
+ "step": 1000
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 2.043773905652359e-05,
+ "loss": 0.0001,
+ "step": 1500
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 1.7250318742031452e-05,
+ "loss": 0.0077,
+ "step": 2000
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 1.4062898427539311e-05,
+ "loss": 0.0006,
+ "step": 2500
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 1.0875478113047175e-05,
+ "loss": 0.0006,
+ "step": 3000
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 7.688057798555037e-06,
+ "loss": 0.0,
+ "step": 3500
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 4.500637484062899e-06,
+ "loss": 0.0003,
+ "step": 4000
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 1.3132171695707608e-06,
+ "loss": 0.0,
+ "step": 4500
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 0.00019271760538686067,
+ "eval_runtime": 829.7336,
+ "eval_samples_per_second": 90.73,
+ "eval_steps_per_second": 5.672,
+ "step": 4706
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 4706,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 500,
+ "total_flos": 1.89368250236928e+16,
+ "train_batch_size": 16,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5138dad5d0f337f45af836663cb38b59f101b69dad77ac7e70b54b4025dd87c
+size 4728