End of training

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+base_model: JasperV13/Fhamator-30000
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Fhamator-SFT
+  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. -->
+
+# Fhamator-SFT
+
+This model is a fine-tuned version of [JasperV13/Fhamator-30000](https://huggingface.co/JasperV13/Fhamator-30000) on an unknown dataset.
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "JasperV13/Fhamator-30000",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "repetition_penalty": 3.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 64001
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46235a1ccf587b9ef1f5d397e5764facfaf51f970362266ed4d4a403013abb0
+size 539995776

runs/Sep07_10-27-30_d6bdffe743a9/events.out.tfevents.1725704874.d6bdffe743a9.219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58e16a0d4bd87b6dd9d873932022db57a5198f2d769e9139c7aa32dcd6185f0
+size 5613

runs/Sep07_10-29-18_d6bdffe743a9/events.out.tfevents.1725704964.d6bdffe743a9.219.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f508addf921c204ed0c65721f087248d4038045a08effed2cb3ef076b26791e
+size 5613

runs/Sep07_10-29-49_d6bdffe743a9/events.out.tfevents.1725705026.d6bdffe743a9.219.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526f3c940d8f52c281b9b79003fe512c3ed7e5f5d4d6e2dd23e963c145471e3b
+size 5611

runs/Sep07_10-30-44_d6bdffe743a9/events.out.tfevents.1725705057.d6bdffe743a9.219.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac961a9cb84069649a61ac97991b914a3a39e774596fb2ff22c789981e79d230
+size 5823

runs/Sep07_10-38-48_d6bdffe743a9/events.out.tfevents.1725705537.d6bdffe743a9.219.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00135b1745742ab60cbe638b771f1268eafee152ac9f5b363f3887d5e78b9921
+size 8518

runs/Sep07_10-41-16_d6bdffe743a9/events.out.tfevents.1725705683.d6bdffe743a9.219.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb7617d5ec9f0b58b7ea777bacc8078e67363fd3c482eeec42cb514fb8dbcd2
+size 10839

runs/Sep07_10-46-11_d6bdffe743a9/events.out.tfevents.1725705985.d6bdffe743a9.219.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5303682ef73a189c27baf69f33f82f70a389ebf358ecd0e82dfc5b62a561fa
+size 28073

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3955ecf38b77ab3ea98e3ce1c16711cbaa94cee682003c26c4ff8b801aa16eb0
+size 5432