Training in progress, step 1000

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: belie-gen-l1-7b-v2
+  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. -->
+
+# belie-gen-l1-7b-v2
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 10000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.17.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.15,
+    "train_loss": 0.6717062408447265,
+    "train_runtime": 2130.1373,
+    "train_samples": 897,
+    "train_samples_per_second": 4.695,
+    "train_steps_per_second": 4.695
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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_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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "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": "4.39.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2b967722cc70cecbacdf1a9d714ee33f80d2f6a3b3003a3086661250f2673c
+size 497774208

runs/Feb21_15-03-48_52e53dc2f2d6/events.out.tfevents.1708527838.52e53dc2f2d6.2349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8310930c4adee7340491e20034596b68372629cecba914ae85527752924b3546
+size 9392

runs/Feb21_16-05-32_52e53dc2f2d6/events.out.tfevents.1708531548.52e53dc2f2d6.2773.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d088d3cf7e88c3a07c97b799b8bf223cec6e4d7953e541ceabfa3fc74b3c6f
+size 4184

runs/Feb21_16-07-41_52e53dc2f2d6/events.out.tfevents.1708531664.52e53dc2f2d6.2833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a9034bacf1c54cbb1513ee6f3619457c42262e2be36170db449b2ac6e21153
+size 5237

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": 11.15,
+    "train_loss": 0.6717062408447265,
+    "train_runtime": 2130.1373,
+    "train_samples": 897,
+    "train_samples_per_second": 4.695,
+    "train_steps_per_second": 4.695
+}

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.148272017837236,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.136017322540283,
+      "learning_rate": 4.75e-05,
+      "loss": 1.4862,
+      "step": 500
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 3.5059304237365723,
+      "learning_rate": 4.5e-05,
+      "loss": 1.2182,
+      "step": 1000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.1735312938690186,
+      "learning_rate": 4.25e-05,
+      "loss": 1.0549,
+      "step": 1500
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 3.1064469814300537,
+      "learning_rate": 4e-05,
+      "loss": 0.9527,
+      "step": 2000
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.8415098190307617,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.8717,
+      "step": 2500
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 2.4496607780456543,
+      "learning_rate": 3.5e-05,
+      "loss": 0.783,
+      "step": 3000
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 2.9042794704437256,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.7372,
+      "step": 3500
+    },
+    {
+      "epoch": 4.46,
+      "grad_norm": 2.628190517425537,
+      "learning_rate": 3e-05,
+      "loss": 0.6509,
+      "step": 4000
+    },
+    {
+      "epoch": 5.02,
+      "grad_norm": 2.9309325218200684,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.6398,
+      "step": 4500
+    },
+    {
+      "epoch": 5.57,
+      "grad_norm": 2.357445240020752,
+      "learning_rate": 2.5e-05,
+      "loss": 0.56,
+      "step": 5000
+    },
+    {
+      "epoch": 6.13,
+      "grad_norm": 2.1420226097106934,
+      "learning_rate": 2.25e-05,
+      "loss": 0.5543,
+      "step": 5500
+    },
+    {
+      "epoch": 6.69,
+      "grad_norm": 2.6394078731536865,
+      "learning_rate": 2e-05,
+      "loss": 0.5104,
+      "step": 6000
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 2.395305633544922,
+      "learning_rate": 1.75e-05,
+      "loss": 0.4832,
+      "step": 6500
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 2.048461675643921,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4705,
+      "step": 7000
+    },
+    {
+      "epoch": 8.36,
+      "grad_norm": 2.379493236541748,
+      "learning_rate": 1.25e-05,
+      "loss": 0.442,
+      "step": 7500
+    },
+    {
+      "epoch": 8.92,
+      "grad_norm": 2.170802116394043,
+      "learning_rate": 1e-05,
+      "loss": 0.4264,
+      "step": 8000
+    },
+    {
+      "epoch": 9.48,
+      "grad_norm": 2.277756690979004,
+      "learning_rate": 7.5e-06,
+      "loss": 0.405,
+      "step": 8500
+    },
+    {
+      "epoch": 10.03,
+      "grad_norm": 2.3412973880767822,
+      "learning_rate": 5e-06,
+      "loss": 0.4069,
+      "step": 9000
+    },
+    {
+      "epoch": 10.59,
+      "grad_norm": 2.220499038696289,
+      "learning_rate": 2.5e-06,
+      "loss": 0.3937,
+      "step": 9500
+    },
+    {
+      "epoch": 11.15,
+      "grad_norm": 2.1124320030212402,
+      "learning_rate": 0.0,
+      "loss": 0.3872,
+      "step": 10000
+    },
+    {
+      "epoch": 11.15,
+      "step": 10000,
+      "total_flos": 5225840640000000.0,
+      "train_loss": 0.6717062408447265,
+      "train_runtime": 2130.1373,
+      "train_samples_per_second": 4.695,
+      "train_steps_per_second": 4.695
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 1000,
+  "total_flos": 5225840640000000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb61092570b7d8e04b17ecc72c4885d59d221bb701f17e1d74e03054ed3006a
+size 4920