Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: sail/Sailor2-8B-Chat
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Sailor2-8B-Chat_sft_sg_values
+  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. -->
+
+# Sailor2-8B-Chat_sft_sg_values
+
+This model is a fine-tuned version of [sail/Sailor2-8B-Chat](https://huggingface.co/sail/Sailor2-8B-Chat) on the sft_sg_values dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1354
+
+## 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-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4422        | 0.1869 | 250  | 0.2675          |
+| 0.1727        | 0.3738 | 500  | 0.1680          |
+| 0.1475        | 0.5607 | 750  | 0.1457          |
+| 0.1284        | 0.7477 | 1000 | 0.1373          |
+| 0.1066        | 0.9346 | 1250 | 0.1348          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sail/Sailor2-8B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a50954e7d10823ddad02acd56b66afe51371b166cdcd0b67da99e5c22e46332
+size 92333848

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9996261682242991,
+    "eval_loss": 0.13543763756752014,
+    "eval_runtime": 29.1007,
+    "eval_samples_per_second": 17.182,
+    "eval_steps_per_second": 8.591,
+    "total_flos": 9.834180665971507e+16,
+    "train_loss": 0.32745340464270284,
+    "train_runtime": 2094.2749,
+    "train_samples_per_second": 5.109,
+    "train_steps_per_second": 0.638
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9996261682242991,
+    "eval_loss": 0.13543763756752014,
+    "eval_runtime": 29.1007,
+    "eval_samples_per_second": 17.182,
+    "eval_steps_per_second": 8.591
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bf42f9364aa867b8c9b839e53c829979092b99b8fab5e8dc932d83f965e815
+size 11421995

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are an AI assistant named Sailor2, created by Sea AI Lab. As an AI assistant, you can answer questions in English, Chinese, and Southeast Asian languages such as Burmese, Cebuano, Ilocano, Indonesian, Javanese, Khmer, Lao, Malay, Sundanese, Tagalog, Thai, Vietnamese, and Waray. Your responses should be friendly, unbiased, informative, detailed, and faithful.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 3848,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9996261682242991,
+    "total_flos": 9.834180665971507e+16,
+    "train_loss": 0.32745340464270284,
+    "train_runtime": 2094.2749,
+    "train_samples_per_second": 5.109,
+    "train_steps_per_second": 0.638
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 74, "total_steps": 1462, "loss": 2.027, "lr": 4.965986394557823e-07, "epoch": 0.05060694135749701, "percentage": 5.06, "elapsed_time": "0:01:44", "remaining_time": "0:32:44"}
+{"current_steps": 148, "total_steps": 1462, "loss": 1.3623, "lr": 1e-06, "epoch": 0.10121388271499401, "percentage": 10.12, "elapsed_time": "0:03:30", "remaining_time": "0:31:06"}
+{"current_steps": 222, "total_steps": 1462, "loss": 0.3715, "lr": 9.437262357414448e-07, "epoch": 0.15182082407249103, "percentage": 15.18, "elapsed_time": "0:05:17", "remaining_time": "0:29:34"}
+{"current_steps": 250, "total_steps": 1462, "eval_loss": 0.2821245491504669, "epoch": 0.17096939647803044, "percentage": 17.1, "elapsed_time": "0:06:27", "remaining_time": "0:31:19"}
+{"current_steps": 296, "total_steps": 1462, "loss": 0.2479, "lr": 8.874524714828897e-07, "epoch": 0.20242776542998803, "percentage": 20.25, "elapsed_time": "0:07:33", "remaining_time": "0:29:45"}
+{"current_steps": 370, "total_steps": 1462, "loss": 0.2056, "lr": 8.311787072243346e-07, "epoch": 0.253034706787485, "percentage": 25.31, "elapsed_time": "0:09:18", "remaining_time": "0:27:28"}
+{"current_steps": 444, "total_steps": 1462, "loss": 0.1642, "lr": 7.749049429657795e-07, "epoch": 0.30364164814498207, "percentage": 30.37, "elapsed_time": "0:11:04", "remaining_time": "0:25:23"}
+{"current_steps": 500, "total_steps": 1462, "eval_loss": 0.17338356375694275, "epoch": 0.3419387929560609, "percentage": 34.2, "elapsed_time": "0:12:53", "remaining_time": "0:24:48"}
+{"current_steps": 518, "total_steps": 1462, "loss": 0.1423, "lr": 7.186311787072243e-07, "epoch": 0.35424858950247906, "percentage": 35.43, "elapsed_time": "0:13:19", "remaining_time": "0:24:16"}
+{"current_steps": 592, "total_steps": 1462, "loss": 0.1511, "lr": 6.623574144486692e-07, "epoch": 0.40485553085997605, "percentage": 40.49, "elapsed_time": "0:15:05", "remaining_time": "0:22:10"}
+{"current_steps": 666, "total_steps": 1462, "loss": 0.1454, "lr": 6.060836501901141e-07, "epoch": 0.45546247221747305, "percentage": 45.55, "elapsed_time": "0:16:52", "remaining_time": "0:20:09"}
+{"current_steps": 740, "total_steps": 1462, "loss": 0.1431, "lr": 5.498098859315589e-07, "epoch": 0.50606941357497, "percentage": 50.62, "elapsed_time": "0:18:38", "remaining_time": "0:18:11"}
+{"current_steps": 750, "total_steps": 1462, "eval_loss": 0.15121176838874817, "epoch": 0.5129081894340913, "percentage": 51.3, "elapsed_time": "0:19:22", "remaining_time": "0:18:23"}
+{"current_steps": 814, "total_steps": 1462, "loss": 0.1339, "lr": 4.935361216730038e-07, "epoch": 0.5566763549324671, "percentage": 55.68, "elapsed_time": "0:20:54", "remaining_time": "0:16:39"}
+{"current_steps": 888, "total_steps": 1462, "loss": 0.1281, "lr": 4.372623574144487e-07, "epoch": 0.6072832962899641, "percentage": 60.74, "elapsed_time": "0:22:42", "remaining_time": "0:14:40"}
+{"current_steps": 962, "total_steps": 1462, "loss": 0.1257, "lr": 3.8098859315589356e-07, "epoch": 0.6578902376474611, "percentage": 65.8, "elapsed_time": "0:24:28", "remaining_time": "0:12:43"}
+{"current_steps": 1000, "total_steps": 1462, "eval_loss": 0.14153704047203064, "epoch": 0.6838775859121218, "percentage": 68.4, "elapsed_time": "0:25:52", "remaining_time": "0:11:57"}
+{"current_steps": 1036, "total_steps": 1462, "loss": 0.1332, "lr": 3.247148288973384e-07, "epoch": 0.7084971790049581, "percentage": 70.86, "elapsed_time": "0:26:43", "remaining_time": "0:10:59"}
+{"current_steps": 1110, "total_steps": 1462, "loss": 0.1174, "lr": 2.6844106463878326e-07, "epoch": 0.7591041203624551, "percentage": 75.92, "elapsed_time": "0:28:28", "remaining_time": "0:09:01"}
+{"current_steps": 1184, "total_steps": 1462, "loss": 0.1281, "lr": 2.1216730038022811e-07, "epoch": 0.8097110617199521, "percentage": 80.98, "elapsed_time": "0:30:12", "remaining_time": "0:07:05"}
+{"current_steps": 1250, "total_steps": 1462, "eval_loss": 0.13589061796665192, "epoch": 0.8548469823901521, "percentage": 85.5, "elapsed_time": "0:32:16", "remaining_time": "0:05:28"}
+{"current_steps": 1258, "total_steps": 1462, "loss": 0.1097, "lr": 1.55893536121673e-07, "epoch": 0.8603180030774491, "percentage": 86.05, "elapsed_time": "0:32:27", "remaining_time": "0:05:15"}
+{"current_steps": 1332, "total_steps": 1462, "loss": 0.1246, "lr": 9.961977186311786e-08, "epoch": 0.9109249444349461, "percentage": 91.11, "elapsed_time": "0:34:16", "remaining_time": "0:03:20"}
+{"current_steps": 1406, "total_steps": 1462, "loss": 0.1079, "lr": 4.3346007604562734e-08, "epoch": 0.9615318857924432, "percentage": 96.17, "elapsed_time": "0:36:02", "remaining_time": "0:01:26"}
+{"current_steps": 1462, "total_steps": 1462, "epoch": 0.999829030603522, "percentage": 100.0, "elapsed_time": "0:37:25", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996261682242991,
+  "eval_steps": 250,
+  "global_step": 1337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05009345794392523,
+      "grad_norm": 28.664648056030273,
+      "learning_rate": 4.925373134328357e-07,
+      "loss": 2.0415,
+      "step": 67
+    },
+    {
+      "epoch": 0.10018691588785046,
+      "grad_norm": 15.266758918762207,
+      "learning_rate": 9.925373134328357e-07,
+      "loss": 1.5231,
+      "step": 134
+    },
+    {
+      "epoch": 0.1502803738317757,
+      "grad_norm": 3.644252061843872,
+      "learning_rate": 9.451371571072319e-07,
+      "loss": 0.4422,
+      "step": 201
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "eval_loss": 0.26753509044647217,
+      "eval_runtime": 29.4536,
+      "eval_samples_per_second": 16.976,
+      "eval_steps_per_second": 8.488,
+      "step": 250
+    },
+    {
+      "epoch": 0.20037383177570092,
+      "grad_norm": 2.716437339782715,
+      "learning_rate": 8.894430590191188e-07,
+      "loss": 0.2826,
+      "step": 268
+    },
+    {
+      "epoch": 0.2504672897196262,
+      "grad_norm": 2.4839746952056885,
+      "learning_rate": 8.337489609310058e-07,
+      "loss": 0.2107,
+      "step": 335
+    },
+    {
+      "epoch": 0.3005607476635514,
+      "grad_norm": 1.4838812351226807,
+      "learning_rate": 7.780548628428927e-07,
+      "loss": 0.1864,
+      "step": 402
+    },
+    {
+      "epoch": 0.3506542056074766,
+      "grad_norm": 1.873056411743164,
+      "learning_rate": 7.223607647547797e-07,
+      "loss": 0.1727,
+      "step": 469
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "eval_loss": 0.16795502603054047,
+      "eval_runtime": 29.4488,
+      "eval_samples_per_second": 16.979,
+      "eval_steps_per_second": 8.489,
+      "step": 500
+    },
+    {
+      "epoch": 0.40074766355140184,
+      "grad_norm": 1.8321393728256226,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 0.1551,
+      "step": 536
+    },
+    {
+      "epoch": 0.4508411214953271,
+      "grad_norm": 2.681673049926758,
+      "learning_rate": 6.109725685785536e-07,
+      "loss": 0.148,
+      "step": 603
+    },
+    {
+      "epoch": 0.5009345794392523,
+      "grad_norm": 2.600128650665283,
+      "learning_rate": 5.552784704904405e-07,
+      "loss": 0.1521,
+      "step": 670
+    },
+    {
+      "epoch": 0.5510280373831775,
+      "grad_norm": 3.1303086280822754,
+      "learning_rate": 4.995843724023275e-07,
+      "loss": 0.1475,
+      "step": 737
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "eval_loss": 0.14567767083644867,
+      "eval_runtime": 29.4447,
+      "eval_samples_per_second": 16.981,
+      "eval_steps_per_second": 8.49,
+      "step": 750
+    },
+    {
+      "epoch": 0.6011214953271028,
+      "grad_norm": 2.5121614933013916,
+      "learning_rate": 4.438902743142144e-07,
+      "loss": 0.1327,
+      "step": 804
+    },
+    {
+      "epoch": 0.6512149532710281,
+      "grad_norm": 2.2810795307159424,
+      "learning_rate": 3.881961762261014e-07,
+      "loss": 0.1394,
+      "step": 871
+    },
+    {
+      "epoch": 0.7013084112149532,
+      "grad_norm": 2.4329702854156494,
+      "learning_rate": 3.3250207813798835e-07,
+      "loss": 0.1284,
+      "step": 938
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "eval_loss": 0.13731907308101654,
+      "eval_runtime": 29.4402,
+      "eval_samples_per_second": 16.984,
+      "eval_steps_per_second": 8.492,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7514018691588785,
+      "grad_norm": 2.148538112640381,
+      "learning_rate": 2.7680798004987534e-07,
+      "loss": 0.1065,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8014953271028037,
+      "grad_norm": 2.3607959747314453,
+      "learning_rate": 2.2111388196176226e-07,
+      "loss": 0.1167,
+      "step": 1072
+    },
+    {
+      "epoch": 0.851588785046729,
+      "grad_norm": 4.869778633117676,
+      "learning_rate": 1.6541978387364923e-07,
+      "loss": 0.1278,
+      "step": 1139
+    },
+    {
+      "epoch": 0.9016822429906542,
+      "grad_norm": 1.291765570640564,
+      "learning_rate": 1.0972568578553615e-07,
+      "loss": 0.1066,
+      "step": 1206
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "eval_loss": 0.13475529849529266,
+      "eval_runtime": 29.4487,
+      "eval_samples_per_second": 16.979,
+      "eval_steps_per_second": 8.489,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9517757009345794,
+      "grad_norm": 2.3237946033477783,
+      "learning_rate": 5.403158769742311e-08,
+      "loss": 0.108,
+      "step": 1273
+    },
+    {
+      "epoch": 0.9996261682242991,
+      "step": 1337,
+      "total_flos": 9.834180665971507e+16,
+      "train_loss": 0.32745340464270284,
+      "train_runtime": 2094.2749,
+      "train_samples_per_second": 5.109,
+      "train_steps_per_second": 0.638
+    }
+  ],
+  "logging_steps": 67,
+  "max_steps": 1337,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.834180665971507e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0c0638d94d81e788e7e1448592b5bdba33d802af43b5b7749e92f56c41047f
+size 5752