Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: llama-fin
+  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. -->
+
+# llama-fin
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2086
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.0634        | 0.1593 | 5000  | 1.6380          |
+| 1.5345        | 0.3185 | 10000 | 1.4842          |
+| 1.4255        | 0.4778 | 15000 | 1.4151          |
+| 1.3929        | 0.6370 | 20000 | 1.3720          |
+| 1.3462        | 0.7963 | 25000 | 1.3367          |
+| 1.3094        | 0.9555 | 30000 | 1.3087          |
+| 1.2835        | 1.1148 | 35000 | 1.2838          |
+| 1.2534        | 1.2740 | 40000 | 1.2605          |
+| 1.2303        | 1.4333 | 45000 | 1.2407          |
+| 1.2187        | 1.5926 | 50000 | 1.2244          |
+| 1.2001        | 1.7518 | 55000 | 1.2133          |
+| 1.1937        | 1.9111 | 60000 | 1.2086          |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.1.0+cu118
+- Datasets 3.5.0
+- Tokenizers 0.21.1

checkpoint-40000/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-40000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-40000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864546b2115d06e4615fc33352ac622e9ad2372f57dcefb0c724e56127bb1e70
+size 111503488

checkpoint-40000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234d26946c38b6ab35294a1fe3ab6e3d77d3b751822980376a5de3a810ff8ff4
+size 223176442

checkpoint-40000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+size 14244

checkpoint-40000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d6bf6fbcda20051d0ed7c9373fc7da2d2e120cb1ffdd71dce90a7adb1c857f
+size 1064

checkpoint-40000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-40000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-40000/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

checkpoint-40000/trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_global_step": null,
+  "best_metric": 1.260542392730713,
+  "best_model_checkpoint": null,
+  "epoch": 1.274047649382087,
+  "eval_steps": 5000,
+  "global_step": 40000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09555357370365651,
+      "grad_norm": 0.6688508987426758,
+      "learning_rate": 0.0002992259870276421,
+      "loss": 3.0634,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15925595617276087,
+      "eval_loss": 1.6379895210266113,
+      "eval_runtime": 36.9077,
+      "eval_samples_per_second": 273.764,
+      "eval_steps_per_second": 8.562,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19110714740731302,
+      "grad_norm": 0.5710486173629761,
+      "learning_rate": 0.00029518136830057303,
+      "loss": 1.6711,
+      "step": 6000
+    },
+    {
+      "epoch": 0.2866607211109696,
+      "grad_norm": 0.5231711864471436,
+      "learning_rate": 0.00028776584441877383,
+      "loss": 1.5345,
+      "step": 9000
+    },
+    {
+      "epoch": 0.31851191234552173,
+      "eval_loss": 1.4841793775558472,
+      "eval_runtime": 36.8712,
+      "eval_samples_per_second": 274.035,
+      "eval_steps_per_second": 8.57,
+      "step": 10000
+    },
+    {
+      "epoch": 0.38221429481462604,
+      "grad_norm": 0.4970897436141968,
+      "learning_rate": 0.00027715159331368833,
+      "loss": 1.4714,
+      "step": 12000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "grad_norm": 0.5002285242080688,
+      "learning_rate": 0.0002635850628193778,
+      "loss": 1.4255,
+      "step": 15000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "eval_loss": 1.4150956869125366,
+      "eval_runtime": 36.8321,
+      "eval_samples_per_second": 274.326,
+      "eval_steps_per_second": 8.579,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5733214422219391,
+      "grad_norm": 0.49311497807502747,
+      "learning_rate": 0.0002473812485038713,
+      "loss": 1.3929,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6370238246910435,
+      "eval_loss": 1.3720492124557495,
+      "eval_runtime": 36.8585,
+      "eval_samples_per_second": 274.13,
+      "eval_steps_per_second": 8.573,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6688750159255956,
+      "grad_norm": 0.5144098401069641,
+      "learning_rate": 0.00022891637991949928,
+      "loss": 1.3669,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7644285896292521,
+      "grad_norm": 0.5176816582679749,
+      "learning_rate": 0.00020861918508708878,
+      "loss": 1.3462,
+      "step": 24000
+    },
+    {
+      "epoch": 0.7962797808638044,
+      "eval_loss": 1.3367421627044678,
+      "eval_runtime": 36.8485,
+      "eval_samples_per_second": 274.204,
+      "eval_steps_per_second": 8.576,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8599821633329087,
+      "grad_norm": 0.5269707441329956,
+      "learning_rate": 0.00018696093604028994,
+      "loss": 1.3283,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "grad_norm": 0.5370417237281799,
+      "learning_rate": 0.0001644445065583549,
+      "loss": 1.3094,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "eval_loss": 1.3087339401245117,
+      "eval_runtime": 36.9277,
+      "eval_samples_per_second": 273.616,
+      "eval_steps_per_second": 8.557,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0510893107402217,
+      "grad_norm": 0.5604170560836792,
+      "learning_rate": 0.00014159269615127048,
+      "loss": 1.2835,
+      "step": 33000
+    },
+    {
+      "epoch": 1.114791693209326,
+      "eval_loss": 1.283848762512207,
+      "eval_runtime": 36.9334,
+      "eval_samples_per_second": 273.573,
+      "eval_steps_per_second": 8.556,
+      "step": 35000
+    },
+    {
+      "epoch": 1.1466428844438783,
+      "grad_norm": 0.5592519044876099,
+      "learning_rate": 0.00011893609139772691,
+      "loss": 1.265,
+      "step": 36000
+    },
+    {
+      "epoch": 1.2421964581475347,
+      "grad_norm": 0.594070315361023,
+      "learning_rate": 9.700074647841136e-05,
+      "loss": 1.2534,
+      "step": 39000
+    },
+    {
+      "epoch": 1.274047649382087,
+      "eval_loss": 1.260542392730713,
+      "eval_runtime": 36.9536,
+      "eval_samples_per_second": 273.424,
+      "eval_steps_per_second": 8.551,
+      "step": 40000
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 62792,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.737039281691034e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dea390da80729e81a7320baa573ab0bba14035962ea3bf179f44ed8e91a0d9
+size 5304

checkpoint-45000/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-45000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-45000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d4c55a0d3b55d3c33a3e7c772c42da53586fbbc31295bd20ba9d213a57bb1e
+size 111503488

checkpoint-45000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7636c39ee46f24ef0e7e6f60d06533989a5e1d760ef77d995331baaa945925
+size 223176442

checkpoint-45000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
+size 14244

checkpoint-45000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400f89ab81606f66afc30799e6e50a56917758a20d3c6664119029c6a34c6ad9
+size 1064

checkpoint-45000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-45000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-45000/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

checkpoint-45000/trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_global_step": null,
+  "best_metric": 1.2406779527664185,
+  "best_model_checkpoint": null,
+  "epoch": 1.4333036055548478,
+  "eval_steps": 5000,
+  "global_step": 45000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09555357370365651,
+      "grad_norm": 0.6688508987426758,
+      "learning_rate": 0.0002992259870276421,
+      "loss": 3.0634,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15925595617276087,
+      "eval_loss": 1.6379895210266113,
+      "eval_runtime": 36.9077,
+      "eval_samples_per_second": 273.764,
+      "eval_steps_per_second": 8.562,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19110714740731302,
+      "grad_norm": 0.5710486173629761,
+      "learning_rate": 0.00029518136830057303,
+      "loss": 1.6711,
+      "step": 6000
+    },
+    {
+      "epoch": 0.2866607211109696,
+      "grad_norm": 0.5231711864471436,
+      "learning_rate": 0.00028776584441877383,
+      "loss": 1.5345,
+      "step": 9000
+    },
+    {
+      "epoch": 0.31851191234552173,
+      "eval_loss": 1.4841793775558472,
+      "eval_runtime": 36.8712,
+      "eval_samples_per_second": 274.035,
+      "eval_steps_per_second": 8.57,
+      "step": 10000
+    },
+    {
+      "epoch": 0.38221429481462604,
+      "grad_norm": 0.4970897436141968,
+      "learning_rate": 0.00027715159331368833,
+      "loss": 1.4714,
+      "step": 12000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "grad_norm": 0.5002285242080688,
+      "learning_rate": 0.0002635850628193778,
+      "loss": 1.4255,
+      "step": 15000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "eval_loss": 1.4150956869125366,
+      "eval_runtime": 36.8321,
+      "eval_samples_per_second": 274.326,
+      "eval_steps_per_second": 8.579,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5733214422219391,
+      "grad_norm": 0.49311497807502747,
+      "learning_rate": 0.0002473812485038713,
+      "loss": 1.3929,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6370238246910435,
+      "eval_loss": 1.3720492124557495,
+      "eval_runtime": 36.8585,
+      "eval_samples_per_second": 274.13,
+      "eval_steps_per_second": 8.573,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6688750159255956,
+      "grad_norm": 0.5144098401069641,
+      "learning_rate": 0.00022891637991949928,
+      "loss": 1.3669,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7644285896292521,
+      "grad_norm": 0.5176816582679749,
+      "learning_rate": 0.00020861918508708878,
+      "loss": 1.3462,
+      "step": 24000
+    },
+    {
+      "epoch": 0.7962797808638044,
+      "eval_loss": 1.3367421627044678,
+      "eval_runtime": 36.8485,
+      "eval_samples_per_second": 274.204,
+      "eval_steps_per_second": 8.576,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8599821633329087,
+      "grad_norm": 0.5269707441329956,
+      "learning_rate": 0.00018696093604028994,
+      "loss": 1.3283,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "grad_norm": 0.5370417237281799,
+      "learning_rate": 0.0001644445065583549,
+      "loss": 1.3094,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "eval_loss": 1.3087339401245117,
+      "eval_runtime": 36.9277,
+      "eval_samples_per_second": 273.616,
+      "eval_steps_per_second": 8.557,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0510893107402217,
+      "grad_norm": 0.5604170560836792,
+      "learning_rate": 0.00014159269615127048,
+      "loss": 1.2835,
+      "step": 33000
+    },
+    {
+      "epoch": 1.114791693209326,
+      "eval_loss": 1.283848762512207,
+      "eval_runtime": 36.9334,
+      "eval_samples_per_second": 273.573,
+      "eval_steps_per_second": 8.556,
+      "step": 35000
+    },
+    {
+      "epoch": 1.1466428844438783,
+      "grad_norm": 0.5592519044876099,
+      "learning_rate": 0.00011893609139772691,
+      "loss": 1.265,
+      "step": 36000
+    },
+    {
+      "epoch": 1.2421964581475347,
+      "grad_norm": 0.594070315361023,
+      "learning_rate": 9.700074647841136e-05,
+      "loss": 1.2534,
+      "step": 39000
+    },
+    {
+      "epoch": 1.274047649382087,
+      "eval_loss": 1.260542392730713,
+      "eval_runtime": 36.9536,
+      "eval_samples_per_second": 273.424,
+      "eval_steps_per_second": 8.551,
+      "step": 40000
+    },
+    {
+      "epoch": 1.3377500318511912,
+      "grad_norm": 0.6026796102523804,
+      "learning_rate": 7.629596894514561e-05,
+      "loss": 1.2422,
+      "step": 42000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "grad_norm": 0.5905404090881348,
+      "learning_rate": 5.7302494322958876e-05,
+      "loss": 1.2303,
+      "step": 45000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "eval_loss": 1.2406779527664185,
+      "eval_runtime": 37.226,
+      "eval_samples_per_second": 271.423,
+      "eval_steps_per_second": 8.489,
+      "step": 45000
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 62792,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.704174480923034e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-45000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dea390da80729e81a7320baa573ab0bba14035962ea3bf179f44ed8e91a0d9
+size 5304

checkpoint-50000/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-50000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-50000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3af2ad45fd40654c1497f7418106a41af852323d15342d41f60ca689dd4f34b
+size 111503488

checkpoint-50000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacbc08856cfb789a10c5f977dab052508daf0d5646680a7da3ba398d825fd49
+size 223176442

checkpoint-50000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
+size 14244

checkpoint-50000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabec674ef0d60462518cf5c37f7fc011a2a644ee516e6b0525d88cbd7ebabd0
+size 1064

checkpoint-50000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-50000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-50000/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

checkpoint-50000/trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_global_step": null,
+  "best_metric": 1.2243584394454956,
+  "best_model_checkpoint": null,
+  "epoch": 1.5925595617276085,
+  "eval_steps": 5000,
+  "global_step": 50000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09555357370365651,
+      "grad_norm": 0.6688508987426758,
+      "learning_rate": 0.0002992259870276421,
+      "loss": 3.0634,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15925595617276087,
+      "eval_loss": 1.6379895210266113,
+      "eval_runtime": 36.9077,
+      "eval_samples_per_second": 273.764,
+      "eval_steps_per_second": 8.562,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19110714740731302,
+      "grad_norm": 0.5710486173629761,
+      "learning_rate": 0.00029518136830057303,
+      "loss": 1.6711,
+      "step": 6000
+    },
+    {
+      "epoch": 0.2866607211109696,
+      "grad_norm": 0.5231711864471436,
+      "learning_rate": 0.00028776584441877383,
+      "loss": 1.5345,
+      "step": 9000
+    },
+    {
+      "epoch": 0.31851191234552173,
+      "eval_loss": 1.4841793775558472,
+      "eval_runtime": 36.8712,
+      "eval_samples_per_second": 274.035,
+      "eval_steps_per_second": 8.57,
+      "step": 10000
+    },
+    {
+      "epoch": 0.38221429481462604,
+      "grad_norm": 0.4970897436141968,
+      "learning_rate": 0.00027715159331368833,
+      "loss": 1.4714,
+      "step": 12000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "grad_norm": 0.5002285242080688,
+      "learning_rate": 0.0002635850628193778,
+      "loss": 1.4255,
+      "step": 15000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "eval_loss": 1.4150956869125366,
+      "eval_runtime": 36.8321,
+      "eval_samples_per_second": 274.326,
+      "eval_steps_per_second": 8.579,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5733214422219391,
+      "grad_norm": 0.49311497807502747,
+      "learning_rate": 0.0002473812485038713,
+      "loss": 1.3929,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6370238246910435,
+      "eval_loss": 1.3720492124557495,
+      "eval_runtime": 36.8585,
+      "eval_samples_per_second": 274.13,
+      "eval_steps_per_second": 8.573,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6688750159255956,
+      "grad_norm": 0.5144098401069641,
+      "learning_rate": 0.00022891637991949928,
+      "loss": 1.3669,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7644285896292521,
+      "grad_norm": 0.5176816582679749,
+      "learning_rate": 0.00020861918508708878,
+      "loss": 1.3462,
+      "step": 24000
+    },
+    {
+      "epoch": 0.7962797808638044,
+      "eval_loss": 1.3367421627044678,
+      "eval_runtime": 36.8485,
+      "eval_samples_per_second": 274.204,
+      "eval_steps_per_second": 8.576,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8599821633329087,
+      "grad_norm": 0.5269707441329956,
+      "learning_rate": 0.00018696093604028994,
+      "loss": 1.3283,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "grad_norm": 0.5370417237281799,
+      "learning_rate": 0.0001644445065583549,
+      "loss": 1.3094,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "eval_loss": 1.3087339401245117,
+      "eval_runtime": 36.9277,
+      "eval_samples_per_second": 273.616,
+      "eval_steps_per_second": 8.557,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0510893107402217,
+      "grad_norm": 0.5604170560836792,
+      "learning_rate": 0.00014159269615127048,
+      "loss": 1.2835,
+      "step": 33000
+    },
+    {
+      "epoch": 1.114791693209326,
+      "eval_loss": 1.283848762512207,
+      "eval_runtime": 36.9334,
+      "eval_samples_per_second": 273.573,
+      "eval_steps_per_second": 8.556,
+      "step": 35000
+    },
+    {
+      "epoch": 1.1466428844438783,
+      "grad_norm": 0.5592519044876099,
+      "learning_rate": 0.00011893609139772691,
+      "loss": 1.265,
+      "step": 36000
+    },
+    {
+      "epoch": 1.2421964581475347,
+      "grad_norm": 0.594070315361023,
+      "learning_rate": 9.700074647841136e-05,
+      "loss": 1.2534,
+      "step": 39000
+    },
+    {
+      "epoch": 1.274047649382087,
+      "eval_loss": 1.260542392730713,
+      "eval_runtime": 36.9536,
+      "eval_samples_per_second": 273.424,
+      "eval_steps_per_second": 8.551,
+      "step": 40000
+    },
+    {
+      "epoch": 1.3377500318511912,
+      "grad_norm": 0.6026796102523804,
+      "learning_rate": 7.629596894514561e-05,
+      "loss": 1.2422,
+      "step": 42000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "grad_norm": 0.5905404090881348,
+      "learning_rate": 5.7302494322958876e-05,
+      "loss": 1.2303,
+      "step": 45000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "eval_loss": 1.2406779527664185,
+      "eval_runtime": 37.226,
+      "eval_samples_per_second": 271.423,
+      "eval_steps_per_second": 8.489,
+      "step": 45000
+    },
+    {
+      "epoch": 1.5288571792585044,
+      "grad_norm": 0.6186478137969971,
+      "learning_rate": 4.046132411403847e-05,
+      "loss": 1.2187,
+      "step": 48000
+    },
+    {
+      "epoch": 1.5925595617276085,
+      "eval_loss": 1.2243584394454956,
+      "eval_runtime": 37.1965,
+      "eval_samples_per_second": 271.639,
+      "eval_steps_per_second": 8.495,
+      "step": 50000
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 62792,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.671309680155034e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dea390da80729e81a7320baa573ab0bba14035962ea3bf179f44ed8e91a0d9
+size 5304

checkpoint-55000/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-55000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-55000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bd10caf84bff659cebdee378fa4ec0baa3854af5ac028859034e0977760b97
+size 111503488

checkpoint-55000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58810b8f3ab1618999d680aad83e4453f866f49df92c46bdbccb7dd22fb9b79e
+size 223176442

checkpoint-55000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7682299c566684ea51cf26f0c86b6ffaa3c0bc63cbdf84674b29a2c62ac72143
+size 14244

checkpoint-55000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5ed0cd7a0667e74d3cccf18cf9c8e09dedf9bcbe1c5d32ff54dcd38e07805f
+size 1064

checkpoint-55000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-55000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-55000/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

checkpoint-55000/trainer_state.json

@@ -0,0 +1,248 @@
+{
+  "best_global_step": null,
+  "best_metric": 1.2133299112319946,
+  "best_model_checkpoint": null,
+  "epoch": 1.7518155179003694,
+  "eval_steps": 5000,
+  "global_step": 55000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09555357370365651,
+      "grad_norm": 0.6688508987426758,
+      "learning_rate": 0.0002992259870276421,
+      "loss": 3.0634,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15925595617276087,
+      "eval_loss": 1.6379895210266113,
+      "eval_runtime": 36.9077,
+      "eval_samples_per_second": 273.764,
+      "eval_steps_per_second": 8.562,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19110714740731302,
+      "grad_norm": 0.5710486173629761,
+      "learning_rate": 0.00029518136830057303,
+      "loss": 1.6711,
+      "step": 6000
+    },
+    {
+      "epoch": 0.2866607211109696,
+      "grad_norm": 0.5231711864471436,
+      "learning_rate": 0.00028776584441877383,
+      "loss": 1.5345,
+      "step": 9000
+    },
+    {
+      "epoch": 0.31851191234552173,
+      "eval_loss": 1.4841793775558472,
+      "eval_runtime": 36.8712,
+      "eval_samples_per_second": 274.035,
+      "eval_steps_per_second": 8.57,
+      "step": 10000
+    },
+    {
+      "epoch": 0.38221429481462604,
+      "grad_norm": 0.4970897436141968,
+      "learning_rate": 0.00027715159331368833,
+      "loss": 1.4714,
+      "step": 12000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "grad_norm": 0.5002285242080688,
+      "learning_rate": 0.0002635850628193778,
+      "loss": 1.4255,
+      "step": 15000
+    },
+    {
+      "epoch": 0.47776786851828257,
+      "eval_loss": 1.4150956869125366,
+      "eval_runtime": 36.8321,
+      "eval_samples_per_second": 274.326,
+      "eval_steps_per_second": 8.579,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5733214422219391,
+      "grad_norm": 0.49311497807502747,
+      "learning_rate": 0.0002473812485038713,
+      "loss": 1.3929,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6370238246910435,
+      "eval_loss": 1.3720492124557495,
+      "eval_runtime": 36.8585,
+      "eval_samples_per_second": 274.13,
+      "eval_steps_per_second": 8.573,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6688750159255956,
+      "grad_norm": 0.5144098401069641,
+      "learning_rate": 0.00022891637991949928,
+      "loss": 1.3669,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7644285896292521,
+      "grad_norm": 0.5176816582679749,
+      "learning_rate": 0.00020861918508708878,
+      "loss": 1.3462,
+      "step": 24000
+    },
+    {
+      "epoch": 0.7962797808638044,
+      "eval_loss": 1.3367421627044678,
+      "eval_runtime": 36.8485,
+      "eval_samples_per_second": 274.204,
+      "eval_steps_per_second": 8.576,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8599821633329087,
+      "grad_norm": 0.5269707441329956,
+      "learning_rate": 0.00018696093604028994,
+      "loss": 1.3283,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "grad_norm": 0.5370417237281799,
+      "learning_rate": 0.0001644445065583549,
+      "loss": 1.3094,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9555357370365651,
+      "eval_loss": 1.3087339401245117,
+      "eval_runtime": 36.9277,
+      "eval_samples_per_second": 273.616,
+      "eval_steps_per_second": 8.557,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0510893107402217,
+      "grad_norm": 0.5604170560836792,
+      "learning_rate": 0.00014159269615127048,
+      "loss": 1.2835,
+      "step": 33000
+    },
+    {
+      "epoch": 1.114791693209326,
+      "eval_loss": 1.283848762512207,
+      "eval_runtime": 36.9334,
+      "eval_samples_per_second": 273.573,
+      "eval_steps_per_second": 8.556,
+      "step": 35000
+    },
+    {
+      "epoch": 1.1466428844438783,
+      "grad_norm": 0.5592519044876099,
+      "learning_rate": 0.00011893609139772691,
+      "loss": 1.265,
+      "step": 36000
+    },
+    {
+      "epoch": 1.2421964581475347,
+      "grad_norm": 0.594070315361023,
+      "learning_rate": 9.700074647841136e-05,
+      "loss": 1.2534,
+      "step": 39000
+    },
+    {
+      "epoch": 1.274047649382087,
+      "eval_loss": 1.260542392730713,
+      "eval_runtime": 36.9536,
+      "eval_samples_per_second": 273.424,
+      "eval_steps_per_second": 8.551,
+      "step": 40000
+    },
+    {
+      "epoch": 1.3377500318511912,
+      "grad_norm": 0.6026796102523804,
+      "learning_rate": 7.629596894514561e-05,
+      "loss": 1.2422,
+      "step": 42000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "grad_norm": 0.5905404090881348,
+      "learning_rate": 5.7302494322958876e-05,
+      "loss": 1.2303,
+      "step": 45000
+    },
+    {
+      "epoch": 1.4333036055548478,
+      "eval_loss": 1.2406779527664185,
+      "eval_runtime": 37.226,
+      "eval_samples_per_second": 271.423,
+      "eval_steps_per_second": 8.489,
+      "step": 45000
+    },
+    {
+      "epoch": 1.5288571792585044,
+      "grad_norm": 0.6186478137969971,
+      "learning_rate": 4.046132411403847e-05,
+      "loss": 1.2187,
+      "step": 48000
+    },
+    {
+      "epoch": 1.5925595617276085,
+      "eval_loss": 1.2243584394454956,
+      "eval_runtime": 37.1965,
+      "eval_samples_per_second": 271.639,
+      "eval_steps_per_second": 8.495,
+      "step": 50000
+    },
+    {
+      "epoch": 1.6244107529621608,
+      "grad_norm": 0.6473325490951538,
+      "learning_rate": 2.6163486369252473e-05,
+      "loss": 1.2095,
+      "step": 51000
+    },
+    {
+      "epoch": 1.7199643266658173,
+      "grad_norm": 0.6508156061172485,
+      "learning_rate": 1.4740956572229152e-05,
+      "loss": 1.2001,
+      "step": 54000
+    },
+    {
+      "epoch": 1.7518155179003694,
+      "eval_loss": 1.2133299112319946,
+      "eval_runtime": 37.1949,
+      "eval_samples_per_second": 271.65,
+      "eval_steps_per_second": 8.496,
+      "step": 55000
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 62792,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0638444879387034e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-55000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dea390da80729e81a7320baa573ab0bba14035962ea3bf179f44ed8e91a0d9
+size 5304

checkpoint-60000/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-60000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-60000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f921a0b25c62636ee1d1e72fc061257ac5bcc99ec5bd898868cd14c91f8727
+size 111503488

checkpoint-60000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1f9eb7a33e964435001f70d9707e54243644755a6ae28777b129bd5bf911ce
+size 223176442

checkpoint-60000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
+size 14244