initial training

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+base_model: vicgalle/gpt2-open-instruct-v1
+tags:
+- generated_from_trainer
+datasets:
+- gsm8k
+model-index:
+- name: gpt2-open-instruct-v1-gsm8k
+  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. -->
+
+# gpt2-open-instruct-v1-gsm8k
+
+This model is a fine-tuned version of [vicgalle/gpt2-open-instruct-v1](https://huggingface.co/vicgalle/gpt2-open-instruct-v1) on the gsm8k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4454
+
+## 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: 0.0005
+- train_batch_size: 6
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.6943        | 1.0   | 1246 | 2.5155          |
+| 2.62          | 2.0   | 2492 | 2.4769          |
+| 2.5851        | 3.0   | 3738 | 2.4575          |
+| 2.5692        | 4.0   | 4984 | 2.4492          |
+| 2.5485        | 5.0   | 6230 | 2.4454          |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.13.1
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

checkpoint-4984/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

checkpoint-4984/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "vicgalle/gpt2-open-instruct-v1",
+  "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": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 50260
+}

checkpoint-4984/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.31.0",
+  "use_cache": false
+}

checkpoint-4984/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318971244dfffc95173117a6525c3f6e9f9948288811a51c2788fbb0fc427275
+size 2291

checkpoint-4984/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d70adf85a6993424510eeeaf760d3facdb64140786afdab235c554af03bf01e
+size 497816413

checkpoint-4984/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76feedbbe7df4e3995eb129b79413d6acc81d558e18412dfb3ca00225be0c886
+size 14575

checkpoint-4984/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ceb9870ffb08bc8fbbb3b8fb254f8045dec405b8ca6a1772347b4db7641feb0
+size 563

checkpoint-4984/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-4984/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "max_seq_length": 512,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

checkpoint-4984/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 2.4491631984710693,
+  "best_model_checkpoint": "gpt2-open-instruct-v1-gsm8k/checkpoint-4984",
+  "epoch": 4.0,
+  "global_step": 4984,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00934910277324633,
+      "loss": 2.9068,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.008533442088091354,
+      "loss": 2.6943,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5155069828033447,
+      "eval_runtime": 22.9749,
+      "eval_samples_per_second": 57.41,
+      "eval_steps_per_second": 57.41,
+      "step": 1246
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.007719412724306688,
+      "loss": 2.6507,
+      "step": 1500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.006903752039151713,
+      "loss": 2.62,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.4768738746643066,
+      "eval_runtime": 22.6896,
+      "eval_samples_per_second": 58.132,
+      "eval_steps_per_second": 58.132,
+      "step": 2492
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.006088091353996738,
+      "loss": 2.6066,
+      "step": 2500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.005272430668841762,
+      "loss": 2.5892,
+      "step": 3000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.004456769983686787,
+      "loss": 2.5851,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.4574520587921143,
+      "eval_runtime": 22.9332,
+      "eval_samples_per_second": 57.515,
+      "eval_steps_per_second": 57.515,
+      "step": 3738
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.0036427406199021207,
+      "loss": 2.5574,
+      "step": 4000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0028270799347471453,
+      "loss": 2.5692,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.4491631984710693,
+      "eval_runtime": 22.7775,
+      "eval_samples_per_second": 57.908,
+      "eval_steps_per_second": 57.908,
+      "step": 4984
+    }
+  ],
+  "max_steps": 6230,
+  "num_train_epochs": 5,
+  "total_flos": 3295072161792000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4984/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd44df1d17d716db8d85f6c86f061584611315664462a60a46b9ceb8331de89
+size 3963

checkpoint-6230/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

checkpoint-6230/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "vicgalle/gpt2-open-instruct-v1",
+  "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": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 50260
+}

checkpoint-6230/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.31.0",
+  "use_cache": false
+}

checkpoint-6230/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f677d070f6bb6cde72da19c977758b81933a889ce85e82afb9f208e22c9b38c9
+size 2291

checkpoint-6230/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a465e6267a176635c584180cf6fc0d931332074e5f265644e0e21469f228a2dd
+size 497816413

checkpoint-6230/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38625868d66fb830b6c44973a821e372af7fedc34777fd7f89f92300a25d9fe
+size 14575

checkpoint-6230/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ea958f7352f0890043b0bb3bbc372808bc3a972fe88a1fd8c718fd2193e955
+size 563

checkpoint-6230/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-6230/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "max_seq_length": 512,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

checkpoint-6230/trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": 2.445409059524536,
+  "best_model_checkpoint": "gpt2-open-instruct-v1-gsm8k/checkpoint-6230",
+  "epoch": 5.0,
+  "global_step": 6230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00934910277324633,
+      "loss": 2.9068,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.008533442088091354,
+      "loss": 2.6943,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5155069828033447,
+      "eval_runtime": 22.9749,
+      "eval_samples_per_second": 57.41,
+      "eval_steps_per_second": 57.41,
+      "step": 1246
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.007719412724306688,
+      "loss": 2.6507,
+      "step": 1500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.006903752039151713,
+      "loss": 2.62,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.4768738746643066,
+      "eval_runtime": 22.6896,
+      "eval_samples_per_second": 58.132,
+      "eval_steps_per_second": 58.132,
+      "step": 2492
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.006088091353996738,
+      "loss": 2.6066,
+      "step": 2500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.005272430668841762,
+      "loss": 2.5892,
+      "step": 3000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.004456769983686787,
+      "loss": 2.5851,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.4574520587921143,
+      "eval_runtime": 22.9332,
+      "eval_samples_per_second": 57.515,
+      "eval_steps_per_second": 57.515,
+      "step": 3738
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.0036427406199021207,
+      "loss": 2.5574,
+      "step": 4000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0028270799347471453,
+      "loss": 2.5692,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.4491631984710693,
+      "eval_runtime": 22.7775,
+      "eval_samples_per_second": 57.908,
+      "eval_steps_per_second": 57.908,
+      "step": 4984
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.0020114192495921694,
+      "loss": 2.552,
+      "step": 5000
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.0011957585644371941,
+      "loss": 2.5497,
+      "step": 5500
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 0.00038009787928221857,
+      "loss": 2.5485,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.445409059524536,
+      "eval_runtime": 23.0868,
+      "eval_samples_per_second": 57.132,
+      "eval_steps_per_second": 57.132,
+      "step": 6230
+    }
+  ],
+  "max_steps": 6230,
+  "num_train_epochs": 5,
+  "total_flos": 4118840202240000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6230/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd44df1d17d716db8d85f6c86f061584611315664462a60a46b9ceb8331de89
+size 3963

logs/events.out.tfevents.1689879201.2b534bb86dca.2620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d7f112a653984632fa0a39623c142cb592f08c2757157e6068d62ce72471f3
+size 7958

logs/events.out.tfevents.1689880376.2b534bb86dca.2620.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7509ac7f1d44b3ec215e2a985f916fe2a588ba10558614344a9835521564d22a
+size 359

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "max_seq_length": 512,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}