push model

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: sail/Sailor-0.5B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: vwen-0.5
+ 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. -->
+
+# vwen-0.5
+
+This model is a fine-tuned version of [sail/Sailor-0.5B](https://huggingface.co/sail/Sailor-0.5B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8915
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8915 | 0.11 | 7644 | 1.8915 |
+
+
+### Framework versions
+
+- Transformers 4.39.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 0.11,
+ "train_loss": 1.9877741447859942,
+ "train_runtime": 107245.5846,
+ "train_samples": 1156437,
+ "train_samples_per_second": 10.783,
+ "train_steps_per_second": 0.674
+}

checkpoint-7568/added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

checkpoint-7568/config.json

@@ -0,0 +1,28 @@
+{
+ "_name_or_path": "sail/Sailor-0.5B",
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1024,
+ "initializer_range": 0.02,
+ "intermediate_size": 2816,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 16,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.0",
+ "use_cache": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}

checkpoint-7568/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.39.0"
+}

checkpoint-7568/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cb7261ef90180a443055a42335fb04910cbfffc2a1809d29714b212885a60f
+size 2478313760

checkpoint-7568/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbfa38aec018143e0c1a8d7a237b9b60036764720fe274b572ee6104bb54485
+size 4956808758

checkpoint-7568/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755e14817720c41543c1a422a0b78e32e590221dc68b88ed0640eed88bd5f198
+size 14180

checkpoint-7568/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a380d5509102fb4ef8afb72ca9d9ebb750c25f01d982a83babdee4dab74265b
+size 1064

checkpoint-7568/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-7568/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+ "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
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": null,
+ "chat_template": "{% for message in messages %}{{'<|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": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}

checkpoint-7568/trainer_state.json

@@ -0,0 +1,126 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.1047078223889412,
+ "eval_steps": 500,
+ "global_step": 7568,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "grad_norm": 1.4067256450653076,
+ "learning_rate": 9.930821699849192e-05,
+ "loss": 2.2227,
+ "step": 500
+ },
+ {
+ "epoch": 0.01,
+ "grad_norm": 2.9092910289764404,
+ "learning_rate": 9.861643399698382e-05,
+ "loss": 2.1156,
+ "step": 1000
+ },
+ {
+ "epoch": 0.02,
+ "grad_norm": 1.1342206001281738,
+ "learning_rate": 9.792465099547574e-05,
+ "loss": 2.0774,
+ "step": 1500
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 3.928356409072876,
+ "learning_rate": 9.723286799396766e-05,
+ "loss": 2.0468,
+ "step": 2000
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.9985896944999695,
+ "learning_rate": 9.654108499245957e-05,
+ "loss": 2.0288,
+ "step": 2500
+ },
+ {
+ "epoch": 0.04,
+ "grad_norm": 1.6732710599899292,
+ "learning_rate": 9.584930199095148e-05,
+ "loss": 1.9954,
+ "step": 3000
+ },
+ {
+ "epoch": 0.05,
+ "grad_norm": 0.9810203313827515,
+ "learning_rate": 9.515751898944339e-05,
+ "loss": 1.9757,
+ "step": 3500
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.8682870864868164,
+ "learning_rate": 9.446573598793531e-05,
+ "loss": 1.9651,
+ "step": 4000
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.9405160546302795,
+ "learning_rate": 9.377395298642722e-05,
+ "loss": 1.9498,
+ "step": 4500
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 0.8670147061347961,
+ "learning_rate": 9.308216998491913e-05,
+ "loss": 1.935,
+ "step": 5000
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.9158061146736145,
+ "learning_rate": 9.239038698341104e-05,
+ "loss": 1.9252,
+ "step": 5500
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.8484827280044556,
+ "learning_rate": 9.169860398190296e-05,
+ "loss": 1.9001,
+ "step": 6000
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.8079173564910889,
+ "learning_rate": 9.100682098039488e-05,
+ "loss": 1.9174,
+ "step": 6500
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.8451229929924011,
+ "learning_rate": 9.031503797888679e-05,
+ "loss": 1.8939,
+ "step": 7000
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.7751355171203613,
+ "learning_rate": 8.962325497737871e-05,
+ "loss": 1.8915,
+ "step": 7500
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 72277,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 16,
+ "total_flos": 6.903809319402209e+17,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-7568/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
+size 4920

checkpoint-7584/added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

checkpoint-7584/config.json

@@ -0,0 +1,28 @@
+{
+ "_name_or_path": "sail/Sailor-0.5B",
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1024,
+ "initializer_range": 0.02,
+ "intermediate_size": 2816,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 16,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.0",
+ "use_cache": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}

checkpoint-7584/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.39.0"
+}

checkpoint-7584/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04de49ef60a0904c181f094cd6444f7392b179c603bb3925c6ce25c9c4774201
+size 2478313760

checkpoint-7584/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ccc150c02002f22f424fe60728d31d250a93657ef0c319b190794d4035bb92
+size 4956808758

checkpoint-7584/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755e14817720c41543c1a422a0b78e32e590221dc68b88ed0640eed88bd5f198
+size 14180

checkpoint-7584/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886fd42484078d6089ab68e7e094b4076189120859f226490410821eaefbfe39
+size 1064

checkpoint-7584/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-7584/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+ "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
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": null,
+ "chat_template": "{% for message in messages %}{{'<|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": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}

checkpoint-7584/trainer_state.json

@@ -0,0 +1,126 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.10492919199230048,
+ "eval_steps": 500,
+ "global_step": 7584,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "grad_norm": 1.4067256450653076,
+ "learning_rate": 9.930821699849192e-05,
+ "loss": 2.2227,
+ "step": 500
+ },
+ {
+ "epoch": 0.01,
+ "grad_norm": 2.9092910289764404,
+ "learning_rate": 9.861643399698382e-05,
+ "loss": 2.1156,
+ "step": 1000
+ },
+ {
+ "epoch": 0.02,
+ "grad_norm": 1.1342206001281738,
+ "learning_rate": 9.792465099547574e-05,
+ "loss": 2.0774,
+ "step": 1500
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 3.928356409072876,
+ "learning_rate": 9.723286799396766e-05,
+ "loss": 2.0468,
+ "step": 2000
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.9985896944999695,
+ "learning_rate": 9.654108499245957e-05,
+ "loss": 2.0288,
+ "step": 2500
+ },
+ {
+ "epoch": 0.04,
+ "grad_norm": 1.6732710599899292,
+ "learning_rate": 9.584930199095148e-05,
+ "loss": 1.9954,
+ "step": 3000
+ },
+ {
+ "epoch": 0.05,
+ "grad_norm": 0.9810203313827515,
+ "learning_rate": 9.515751898944339e-05,
+ "loss": 1.9757,
+ "step": 3500
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.8682870864868164,
+ "learning_rate": 9.446573598793531e-05,
+ "loss": 1.9651,
+ "step": 4000
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.9405160546302795,
+ "learning_rate": 9.377395298642722e-05,
+ "loss": 1.9498,
+ "step": 4500
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 0.8670147061347961,
+ "learning_rate": 9.308216998491913e-05,
+ "loss": 1.935,
+ "step": 5000
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.9158061146736145,
+ "learning_rate": 9.239038698341104e-05,
+ "loss": 1.9252,
+ "step": 5500
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.8484827280044556,
+ "learning_rate": 9.169860398190296e-05,
+ "loss": 1.9001,
+ "step": 6000
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.8079173564910889,
+ "learning_rate": 9.100682098039488e-05,
+ "loss": 1.9174,
+ "step": 6500
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.8451229929924011,
+ "learning_rate": 9.031503797888679e-05,
+ "loss": 1.8939,
+ "step": 7000
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.7751355171203613,
+ "learning_rate": 8.962325497737871e-05,
+ "loss": 1.8915,
+ "step": 7500
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 72277,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 16,
+ "total_flos": 6.918405110775153e+17,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-7584/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
+size 4920

checkpoint-7600/added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

checkpoint-7600/config.json

@@ -0,0 +1,28 @@
+{
+ "_name_or_path": "sail/Sailor-0.5B",
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1024,
+ "initializer_range": 0.02,
+ "intermediate_size": 2816,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 16,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.0",
+ "use_cache": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}

checkpoint-7600/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.39.0"
+}

checkpoint-7600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11146d20de778d3cd004f0fb0fd9a9b35b43eeda4d30329a8ec6859c867f380c
+size 2478313760

checkpoint-7600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9bc20ea9a5f27c524b6c3aa458b2685618ce1dc14cc8eab8564ff0095e52fc
+size 4956808758

checkpoint-7600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a41ab52e23892da54d70091e14df8f1b6941c11a68eef43ba6478fda827b6f4
+size 14244

checkpoint-7600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4763ef45d4c6c771b85175f8a79b7d11b80434eb92b755c683851b559cf22273
+size 1064

checkpoint-7600/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-7600/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+ "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
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": null,
+ "chat_template": "{% for message in messages %}{{'<|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": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}

checkpoint-7600/trainer_state.json

@@ -0,0 +1,126 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.10515056159565978,
+ "eval_steps": 500,
+ "global_step": 7600,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "grad_norm": 1.4067256450653076,
+ "learning_rate": 9.930821699849192e-05,
+ "loss": 2.2227,
+ "step": 500
+ },
+ {
+ "epoch": 0.01,
+ "grad_norm": 2.9092910289764404,
+ "learning_rate": 9.861643399698382e-05,
+ "loss": 2.1156,
+ "step": 1000
+ },
+ {
+ "epoch": 0.02,
+ "grad_norm": 1.1342206001281738,
+ "learning_rate": 9.792465099547574e-05,
+ "loss": 2.0774,
+ "step": 1500
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 3.928356409072876,
+ "learning_rate": 9.723286799396766e-05,
+ "loss": 2.0468,
+ "step": 2000
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.9985896944999695,
+ "learning_rate": 9.654108499245957e-05,
+ "loss": 2.0288,
+ "step": 2500
+ },
+ {
+ "epoch": 0.04,
+ "grad_norm": 1.6732710599899292,
+ "learning_rate": 9.584930199095148e-05,
+ "loss": 1.9954,
+ "step": 3000
+ },
+ {
+ "epoch": 0.05,
+ "grad_norm": 0.9810203313827515,
+ "learning_rate": 9.515751898944339e-05,
+ "loss": 1.9757,
+ "step": 3500
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.8682870864868164,
+ "learning_rate": 9.446573598793531e-05,
+ "loss": 1.9651,
+ "step": 4000
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.9405160546302795,
+ "learning_rate": 9.377395298642722e-05,
+ "loss": 1.9498,
+ "step": 4500
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 0.8670147061347961,
+ "learning_rate": 9.308216998491913e-05,
+ "loss": 1.935,
+ "step": 5000
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.9158061146736145,
+ "learning_rate": 9.239038698341104e-05,
+ "loss": 1.9252,
+ "step": 5500
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.8484827280044556,
+ "learning_rate": 9.169860398190296e-05,
+ "loss": 1.9001,
+ "step": 6000
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.8079173564910889,
+ "learning_rate": 9.100682098039488e-05,
+ "loss": 1.9174,
+ "step": 6500
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.8451229929924011,
+ "learning_rate": 9.031503797888679e-05,
+ "loss": 1.8939,
+ "step": 7000
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.7751355171203613,
+ "learning_rate": 8.962325497737871e-05,
+ "loss": 1.8915,
+ "step": 7500
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 72277,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 16,
+ "total_flos": 6.933000902148096e+17,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-7600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
+size 4920

checkpoint-7616/added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

checkpoint-7616/config.json

@@ -0,0 +1,28 @@
+{
+ "_name_or_path": "sail/Sailor-0.5B",
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1024,
+ "initializer_range": 0.02,
+ "intermediate_size": 2816,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 16,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.0",
+ "use_cache": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}

checkpoint-7616/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.39.0"
+}

checkpoint-7616/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937917280f9f64041d30fe11a7882da25ed0ecdee59fb7b1843952ded485414b
+size 2478313760