Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+base_model: None
+tags:
+- generated_from_trainer
+model-index:
+- name: checkpoints-mistral-300M-FA2
+  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. -->
+
+# checkpoints-mistral-300M-FA2
+
+This model is a fine-tuned version of [None](https://huggingface.co/None) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 8.3607
+
+## 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: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 256
+- total_train_batch_size: 4096
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=0.0001
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 8.361         | 2.87  | 100  | 8.3607          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.87,
+    "eval_loss": 8.360694885253906,
+    "eval_runtime": 47.1861,
+    "eval_samples": 8752,
+    "eval_samples_per_second": 185.478,
+    "eval_steps_per_second": 11.592,
+    "perplexity": 4275.664830790565,
+    "train_loss": 9.417760696411133,
+    "train_runtime": 4915.0289,
+    "train_samples": 142865,
+    "train_samples_per_second": 83.336,
+    "train_steps_per_second": 0.02
+}

checkpoint-100/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "None",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2400,
+  "max_position_embeddings": 2048,
+  "model_type": "mistral",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 6,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 1024,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.35.2"
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452890a4620731fcfd782c43c25f389c33a5f029c8e448d393899400955cd96e
+size 659223584

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4360cc77553db9218f1ae6ad37bb9097a53d68e7f838397cd82dea8807385b88
+size 330481018

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d0e428eaaebbd39500df7b70c85e0c423ad7178fcc03acaa80860c51ef011a
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dd781b5c1688e384631b7f12f7487a26b9d9d620dfb939bff47a96b20bc2b0
+size 1064

checkpoint-100/special_tokens_map.json

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

checkpoint-100/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
+size 1249735

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 50000,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 8.360694885253906,
+  "best_model_checkpoint": "checkpoints-mistral-300M-FA2/checkpoint-100",
+  "epoch": 2.8667413213885777,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 10.9345,
+      "step": 10
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 10.5058,
+      "step": 20
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 9.9277,
+      "step": 30
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 9.5263,
+      "step": 40
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 9.3038,
+      "step": 50
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 9.1594,
+      "step": 60
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 4.2e-05,
+      "loss": 9.0196,
+      "step": 70
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 8.8448,
+      "step": 80
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 8.5947,
+      "step": 90
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 8.361,
+      "step": 100
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 8.360694885253906,
+      "eval_runtime": 47.6223,
+      "eval_samples_per_second": 183.779,
+      "eval_steps_per_second": 11.486,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 3.1758312754538086e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f0266cc4dc9810322a035887955fe4979a6a5741750c465d774c3e155b82e0
+size 4600

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "None",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2400,
+  "max_position_embeddings": 2048,
+  "model_type": "mistral",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 6,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 1024,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.87,
+    "eval_loss": 8.360694885253906,
+    "eval_runtime": 47.1861,
+    "eval_samples": 8752,
+    "eval_samples_per_second": 185.478,
+    "eval_steps_per_second": 11.592,
+    "perplexity": 4275.664830790565
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.35.2"
+}

logs/events.out.tfevents.1706010791.a231f4d877cb.32974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c422e5986608ba0e7b51aa89eb711cba652c43fd63b4ad0f9925b078b42dd82
+size 6330

logs/events.out.tfevents.1706015754.a231f4d877cb.32974.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cd8ae5a0086c7b9bd341b4961ea3bfd36b75b997095dbb1d7ebec07bb0c15f
+size 354

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452890a4620731fcfd782c43c25f389c33a5f029c8e448d393899400955cd96e
+size 659223584

special_tokens_map.json

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

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604cb0c2f073ba13f04739ced6f8310f4f00ab344feea6cb5c4012af3876c684
+size 1249735

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 50000,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.87,
+    "train_loss": 9.417760696411133,
+    "train_runtime": 4915.0289,
+    "train_samples": 142865,
+    "train_samples_per_second": 83.336,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": 8.360694885253906,
+  "best_model_checkpoint": "checkpoints-mistral-300M-FA2/checkpoint-100",
+  "epoch": 2.8667413213885777,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 10.9345,
+      "step": 10
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 10.5058,
+      "step": 20
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 9.9277,
+      "step": 30
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 9.5263,
+      "step": 40
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 9.3038,
+      "step": 50
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 9.1594,
+      "step": 60
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 4.2e-05,
+      "loss": 9.0196,
+      "step": 70
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 8.8448,
+      "step": 80
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 8.5947,
+      "step": 90
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 8.361,
+      "step": 100
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 8.360694885253906,
+      "eval_runtime": 47.6223,
+      "eval_samples_per_second": 183.779,
+      "eval_steps_per_second": 11.486,
+      "step": 100
+    },
+    {
+      "epoch": 2.87,
+      "step": 100,
+      "total_flos": 3.1758312754538086e+17,
+      "train_loss": 9.417760696411133,
+      "train_runtime": 4915.0289,
+      "train_samples_per_second": 83.336,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 3.1758312754538086e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f0266cc4dc9810322a035887955fe4979a6a5741750c465d774c3e155b82e0
+size 4600