model

README.md

@@ -0,0 +1,67 @@
+---
+license: other
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: opt-model
+  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. -->
+
+# opt-model
+
+This model is a fine-tuned version of [facebook/opt-13b](https://huggingface.co/facebook/opt-13b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3965
+- Accuracy: 0.5020
+
+## 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: 24
+- eval_batch_size: 24
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 72
+- total_eval_batch_size: 72
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.6363        | 1.0   | 3    | 3.2090          | 0.4082   |
+| 2.8168        | 2.0   | 6    | 2.4805          | 0.4874   |
+| 2.3529        | 3.0   | 9    | 2.4219          | 0.4915   |
+| 2.1842        | 4.0   | 12   | 2.4023          | 0.4991   |
+| 2.0765        | 5.0   | 15   | 2.3965          | 0.5020   |
+
+
+### Framework versions
+
+- Transformers 4.20.1
+- Pytorch 1.12.0+cu102
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,29 @@
+{
+    "before_init_mem_cpu": 19409301504,
+    "before_init_mem_gpu": 514785792,
+    "epoch": 5.0,
+    "eval_accuracy": 0.5020384866275277,
+    "eval_loss": 2.396484375,
+    "eval_mem_cpu_alloc_delta": 1241088,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 13894116352,
+    "eval_runtime": 7.6383,
+    "eval_samples": 24,
+    "eval_samples_per_second": 3.142,
+    "eval_steps_per_second": 0.131,
+    "init_mem_cpu_alloc_delta": 20480,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 0,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 10.984491067549964,
+    "train_loss": 2.6133464177449546,
+    "train_mem_cpu_alloc_delta": 87850864640,
+    "train_mem_cpu_peaked_delta": 4164583424,
+    "train_mem_gpu_alloc_delta": -456804352,
+    "train_mem_gpu_peaked_delta": 13894116352,
+    "train_runtime": 736.506,
+    "train_samples": 165,
+    "train_samples_per_second": 1.12,
+    "train_steps_per_second": 0.02
+}

checkpoint-2/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "facebook/opt-13b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 20480,
+  "hidden_size": 5120,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "output_projection": true,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 5120
+}

checkpoint-2/global_step2/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57b140e0944cc8b63af3723b415db6069ef6be3d49df869329c6981b28f2dff
+size 250361

checkpoint-2/global_step2/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03aee2c6dbe6a211808185f77ae3bdae79004aabc33bdcc7fbabab08ba53dac8
+size 19496779776

checkpoint-2/global_step2/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b5e09f6f315cbda85befc546cba246c7d39dca55510eae78c0479aeb514d2d
+size 250361

checkpoint-2/global_step2/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0928b3add3e1426b289c7ea63bb131e7ea4616db7a4490d10239913eab160cc4
+size 18584686592

checkpoint-2/global_step2/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585a2b848e9d1373ef33676865ea87839fcddc069e49d350308683dae28a634c
+size 250361

checkpoint-2/global_step2/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c5edb967b0d4f9eb1be96837b40f187d364dfc201154afc5f9da155e8c6712
+size 19108249600

checkpoint-2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761bc42254196f751d37cf2c3dd1128f531d990acd84e2a6dbb270c1085d7ead
+size 25707087165

checkpoint-2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "name_or_path": "facebook/opt-13b",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c70db082549e01237f6482f16e9f3aa714da3c1bc6c9967f9370f573a4dc62
+size 4335

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "facebook/opt-13b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 20480,
+  "hidden_size": 5120,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "output_projection": true,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 5120
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5020384866275277,
+    "eval_loss": 2.396484375,
+    "eval_mem_cpu_alloc_delta": 1241088,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 13894116352,
+    "eval_runtime": 7.6383,
+    "eval_samples": 24,
+    "eval_samples_per_second": 3.142,
+    "eval_steps_per_second": 0.131,
+    "perplexity": 10.984491067549964
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb0640265cd6ca8c05efaaee690c15cefa365e2b9372f4cec62588e86bb4d1e
+size 25707087165

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "name_or_path": "facebook/opt-13b",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,18 @@
+{
+    "before_init_mem_cpu": 19409301504,
+    "before_init_mem_gpu": 514785792,
+    "epoch": 5.0,
+    "init_mem_cpu_alloc_delta": 20480,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 0,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_loss": 2.6133464177449546,
+    "train_mem_cpu_alloc_delta": 87850864640,
+    "train_mem_cpu_peaked_delta": 4164583424,
+    "train_mem_gpu_alloc_delta": -456804352,
+    "train_mem_gpu_peaked_delta": 13894116352,
+    "train_runtime": 736.506,
+    "train_samples": 165,
+    "train_samples_per_second": 1.12,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 3.6363,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.40818656229615136,
+      "eval_loss": 3.208984375,
+      "eval_runtime": 9.2632,
+      "eval_samples_per_second": 2.591,
+      "eval_steps_per_second": 0.108,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 2.8168,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4873613829093281,
+      "eval_loss": 2.48046875,
+      "eval_runtime": 7.2903,
+      "eval_samples_per_second": 3.292,
+      "eval_steps_per_second": 0.137,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.3529,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.49151989562948467,
+      "eval_loss": 2.421875,
+      "eval_runtime": 7.8557,
+      "eval_samples_per_second": 3.055,
+      "eval_steps_per_second": 0.127,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.1842,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4991030658838878,
+      "eval_loss": 2.40234375,
+      "eval_runtime": 7.3477,
+      "eval_samples_per_second": 3.266,
+      "eval_steps_per_second": 0.136,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.0765,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5020384866275277,
+      "eval_loss": 2.396484375,
+      "eval_runtime": 7.3064,
+      "eval_samples_per_second": 3.285,
+      "eval_steps_per_second": 0.137,
+      "step": 15
+    },
+    {
+      "before_init_mem_cpu": 19409301504,
+      "before_init_mem_gpu": 514785792,
+      "epoch": 5.0,
+      "init_mem_cpu_alloc_delta": 20480,
+      "init_mem_cpu_peaked_delta": 0,
+      "init_mem_gpu_alloc_delta": 0,
+      "init_mem_gpu_peaked_delta": 0,
+      "step": 15,
+      "total_flos": 6182393610240.0,
+      "train_loss": 2.6133464177449546,
+      "train_mem_cpu_alloc_delta": 87850864640,
+      "train_mem_cpu_peaked_delta": 4164583424,
+      "train_mem_gpu_alloc_delta": -456804352,
+      "train_mem_gpu_peaked_delta": 13894116352,
+      "train_runtime": 736.506,
+      "train_samples_per_second": 1.12,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "max_steps": 15,
+  "num_train_epochs": 5,
+  "total_flos": 6182393610240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76845b569c4dd3b62f36428c000bf88337c8a3be024d00a72965e01f994db56d
+size 4335