Newly created GPT for Estonian, base version.

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt4est-s
+  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. -->
+
+# gpt4est-s
+
+This model is a ...
+
+It achieves the following results on the evaluation set:
+- Loss: 3.9846
+
+## 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: 0.0003
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- 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 4.13.0.dev0
+- Pytorch 1.10.0+cu102
+- Datasets 1.15.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.9845974445343018,
+    "eval_runtime": 1425.6748,
+    "eval_samples": 32253,
+    "eval_samples_per_second": 22.623,
+    "eval_steps_per_second": 3.771,
+    "perplexity": 53.7636422730289,
+    "train_loss": 0.7859680134460877,
+    "train_runtime": 210975.8843,
+    "train_samples": 3196485,
+    "train_samples_per_second": 45.453,
+    "train_steps_per_second": 7.575
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/gpfs/space/home/fishel/gptest/models/gpt4est-s/checkpoint-1290000",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 54321
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.9845974445343018,
+    "eval_runtime": 1425.6748,
+    "eval_samples": 32253,
+    "eval_samples_per_second": 22.623,
+    "eval_steps_per_second": 3.771,
+    "perplexity": 53.7636422730289
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<bos>", "eos_token": "<eos>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": "/gpfs/space/home/fishel/gptest/models/tokmdl/special_tokens_map.json", "name_or_path": "/gpfs/space/home/fishel/gptest/models/tokmdl", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7859680134460877,
+    "train_runtime": 210975.8843,
+    "train_samples": 3196485,
+    "train_samples_per_second": 45.453,
+    "train_steps_per_second": 7.575
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96f4e174ade0eed47afbe8e0c52c321608d8cbf35fa4157520aa283865c9782
+size 2863