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: 7.9175
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 256
+- total_train_batch_size: 256
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.9131        | 0.18  | 100  | 7.9175          |
+
+
+### 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": 0.18,
+    "eval_loss": 7.917535781860352,
+    "eval_runtime": 1151.6067,
+    "eval_samples": 8626,
+    "eval_samples_per_second": 7.49,
+    "eval_steps_per_second": 7.49,
+    "perplexity": 2744.998429631847,
+    "train_loss": 9.09298583984375,
+    "train_runtime": 7786.6651,
+    "train_samples": 141300,
+    "train_samples_per_second": 3.288,
+    "train_steps_per_second": 0.013
+}

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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2400,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "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:b66055765ae3b0a864ddc753d1a641a67569e1ae80a66d0b19e1f1a0ada369fa
+size 1421709600

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daba1416168237d77e9f853c497808bccff33679f71360fe18b9f88fca611f9c
+size 712761466

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5fa02ce1f2057ffdcccd86019817387a38e6b835bf0ecf5d2277b489b598e7
+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": 7.917535781860352,
+  "best_model_checkpoint": "checkpoints-mistral-300M-FA2/checkpoint-100",
+  "epoch": 0.18117480537862704,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 10.9312,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 10.3611,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 9.6675,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 9.2233,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 8.9619,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 8.7956,
+      "step": 60
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.2e-05,
+      "loss": 8.5973,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 8.37,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 8.1088,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 7.9131,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 7.917535781860352,
+      "eval_runtime": 1155.2404,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 7.467,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 4.78084620877824e+16,
+  "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:dc3ee4547859c507ecfdc59d4930ae295891669eabd1de600a6cf8d986345ec3
+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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2400,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "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": 0.18,
+    "eval_loss": 7.917535781860352,
+    "eval_runtime": 1151.6067,
+    "eval_samples": 8626,
+    "eval_samples_per_second": 7.49,
+    "eval_steps_per_second": 7.49,
+    "perplexity": 2744.998429631847
+}

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.1705838367.60c5ea563f1a.8237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2f0be7f93d600290288677b6a254e6b2938b32f55c0e58b73f1eb7dca77965
+size 6329

logs/events.out.tfevents.1705847315.60c5ea563f1a.8237.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c885c4892a5f74cbeb62bf913e6d2cae6a12b9abb3c0f8c27ca3681909123b8
+size 354

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66055765ae3b0a864ddc753d1a641a67569e1ae80a66d0b19e1f1a0ada369fa
+size 1421709600

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": 0.18,
+    "train_loss": 9.09298583984375,
+    "train_runtime": 7786.6651,
+    "train_samples": 141300,
+    "train_samples_per_second": 3.288,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": 7.917535781860352,
+  "best_model_checkpoint": "checkpoints-mistral-300M-FA2/checkpoint-100",
+  "epoch": 0.18117480537862704,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 10.9312,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 10.3611,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 9.6675,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 9.2233,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 8.9619,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 8.7956,
+      "step": 60
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.2e-05,
+      "loss": 8.5973,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 8.37,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 8.1088,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 7.9131,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 7.917535781860352,
+      "eval_runtime": 1155.2404,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 7.467,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "step": 100,
+      "total_flos": 4.78084620877824e+16,
+      "train_loss": 9.09298583984375,
+      "train_runtime": 7786.6651,
+      "train_samples_per_second": 3.288,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 4.78084620877824e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3ee4547859c507ecfdc59d4930ae295891669eabd1de600a6cf8d986345ec3
+size 4600