Pi3141 commited on
Commit
83b941f
1 Parent(s): 53754c6

Upload 11 files

Browse files
README.md CHANGED
@@ -1,3 +1,111 @@
1
  ---
2
  license: wtfpl
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: wtfpl
3
+ language:
4
+ - en
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - llama
8
+ library_name: adapter-transformers
9
  ---
10
+
11
+ Non-safetensor version: [pi3141/alpaca-7b-native-enhanced-GPTQ](https://huggingface.co/Pi3141/alpaca-7b-native-enhanced-GPTQ)
12
+
13
+ ### About the GPTQ version
14
+ - Quantized to 4-bits 128g using GPTQ-for-LLaMA.
15
+ - Intended for use with Oobabooga Text Generation WebUI.
16
+
17
+ ### Loading model in Oobabooga WebUI
18
+ - Use same parameters as the original model, which can be found in the original repo linked below.
19
+ - Use `AutoGPTQ` loader.
20
+
21
+ ### Information about original model
22
+ *Original repo: [8bit-coder/alpaca-7b-nativeEnhanced](https://huggingface.co/8bit-coder/alpaca-7b-nativeEnhanced)*
23
+ *Alternate: [pi3141/alpaca-7b-native-enhanced](https://huggingface.co/pi3141/alpaca-7b-native-enhanced)*
24
+ Below are information about the original model
25
+
26
+ ---
27
+
28
+ <p align="center"><img src="https://cdn-uploads.huggingface.co/production/uploads/615a1b7a321f65c4da59c3d3/DFHgrYeqJNIchgLrgfZzl.png" height=256></p>
29
+ <h1 align="center">
30
+ Alpaca 7B Native Enhanced
31
+ </h1>
32
+ <p align="center">The Most Advanced Alpaca 7B Model</p>
33
+
34
+ ## 📃 Model Facts
35
+
36
+ - Trained natively on 8x Nvidia A100 40GB GPUs; no LoRA used
37
+ - Trained on the largest & most accurate dataset yet
38
+ - Enhanced Programming Capabilities
39
+ - First Alpaca model to have conversational awareness
40
+
41
+ ## 🚀 Quick Start Guide
42
+
43
+ Step 1. Make sure git-lfs is installed and ready to use ([Guide](https://git-lfs.com/))
44
+
45
+ Step 2. Download and install [text-generation-webui](https://github.com/oobabooga/text-generation-webui) according to the repository's instructions
46
+
47
+ Step 3. Navigate over to one of it's model folders and clone this repository:
48
+
49
+ git clone https://huggingface.co/8bit-coder/alpaca-7b-nativeEnhanced
50
+
51
+ Step 4. Launch the webui, replace "Your name" with "User" and replace the default instruction prompt with:
52
+
53
+ > You are an AI language model designed to assist the User by answering their questions, offering advice, and engaging in casual conversation in a friendly, helpful, and informative manner. You respond clearly, coherently, and you consider the conversation history.
54
+ >
55
+ > User: Hey, how's it going?
56
+ >
57
+ > Assistant: Hey there! I'm doing great, thank you. What can I help you with today? Let's have a fun chat!
58
+
59
+ Step 5. Change the settings to match this screenshot:
60
+ ![Settings](https://cdn-uploads.huggingface.co/production/uploads/615a1b7a321f65c4da59c3d3/m8s2o52xN2I6MDy0sZ5rZ.png)
61
+
62
+ ## 📚 Training
63
+
64
+ #### We used 8x Nvidia A100 40GB GPUs for training this model. Training time took ~3 hours and resulting loss was 0.4761 over 3 epochs. The command used for training is as follows
65
+
66
+ > **torchrun --nproc_per_node=8 --master_port=3045 ./stanford_alpaca/train.py --model_name_or_path ./llama-7b-hf --data_path ./alpaca-7b-nativeEnhanced/training_files/alpaca-megaset-fixed.json --fp16 True --output_dir ./output_7b --num_train_epochs 3 --per_device_train_batch_size 2 --per_device_eval_batch_size 2 --gradient_accumulation_steps 16 --evaluation_strategy "no" --save_strategy "steps" --save_steps 200 --learning_rate 2e-5 --weight_decay 0. --warmup_ratio 0.03 --lr_scheduler_type "cosine" --logging_steps 1 --fsdp "full_shard auto_wrap" --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' --tf32 True**
67
+
68
+ There's a folder in this repository called training_files. **full-training-instructions.txt** is the full list of commands from start to finish of training, to converting the model all the way to 4 bit quantized ggml. **It is not recommended to quantize this model down to 4 bits. The instructions are included purely for informational purposes.**
69
+
70
+ In addition, the training instructions file is built specifically for rented cloud computing. This means that by following the commands in the file, anyone should be able to train a similar model.
71
+
72
+ ### Common errors while training
73
+
74
+ - CUDA Out of Memory error
75
+ - This is because your GPUs do not have a minimum of 40GB of vram. The weakest GPU that we've been able to successfully train on has been Nvidia A100 40GB. Even with 8 of these, the vram usage was almost always right up at the limit. If you have 40GB GPUs and are still running into this error, try halving the **per_device_train_batch_size** and **per_device_eval_batch_size** and doubling the **gradient_accumulation_steps**. If you have more than 40GB of vram per GPU and wish to train faster, the opposite applies.
76
+
77
+ - LLaMATokenizer error
78
+ - This happens because you forgot to fix tokenizer_config.json in the llama-7b-hf directory. The fix is to rename **LLaMATokenizer** to **LlamaTokenizer** in that file.
79
+
80
+ - RuntimeError: CUDA error: invalid device ordinal
81
+ - This error occurs when your **nproc_per_node** is set to a number greater than how many GPUs you have installed in your system. You can check how many GPUs you have installed by running **nvidia-smi**.
82
+
83
+ - torchrun is not recognized
84
+ - This error occurs when you have a python version older than 3.10. Follow the instructions in the training instructions file to install miniconda and get python 3.10 set up. Circumventing this error by running python -m torch.distributed.run will **not work**. Many of the dependencies require python 3.10 and will fatally error out at the start of training.
85
+
86
+ - KeyError
87
+ - This happens when your JSON training data is broken in some way. Try running the dataset_validator.py in the training_files folder to find the broken key.
88
+
89
+ ## 📝 Notes
90
+
91
+ - The main version of this model is in the hugging face transformers data type. The other one (.pth) format is provided **purely for experimental use with llama.cpp** and is not guaranteed to have conversational awareness.
92
+ - This model exhibits weird behavior when quantized to 4 bits. This might be due to the complexity of the model. We recommend the smallest quantization to be 8 bits, but this is untested.
93
+ - This model is slightly **underfitted**. We observed that training the model with a smaller gradient accumulation size benefitted the response quality.
94
+
95
+ - This model appears to have full conversational awareness. This means that provided you're running the model in the same configuration we detailed in the Quick Start Guide, you should be able to hold very detailed conversation with the AI without issues. There is a limit to it's memory, and it's 2048 tokens. Beyond that, it'll forget details and will need to be reminded.
96
+
97
+ ## 🔧 Dataset
98
+
99
+ The dataset used for training this model is made from [AlpacaDataCleaned](https://github.com/gururise/AlpacaDataCleaned) and [codealpaca](https://github.com/sahil280114/codealpaca). We combined these datasets for the following reasons:
100
+
101
+ 1. Increased accuracy since the original stanford_alpaca dataset had many errors.
102
+ 2. Better knowledge in programming
103
+ 3. More training data
104
+
105
+ We had an issue with the latest AlpacaDataCleaned dataset where at around 90k lines in, one of the keys has a typo. The key is "instruction:" instead of "instruction". We have fixed this error in the provided megaset but if you plan on grabbing directly from AlpacaDataCleaned, make sure to fix this error. Otherwise, the training script will fail due to a KeyError.
106
+
107
+ ## 👨‍💻 Credits
108
+
109
+ Credits go to [Meta](https://github.com/facebookresearch/llama) for creating the foundational LLaMA models and [Stanford](https://github.com/tatsu-lab/stanford_alpaca) for the instructions on how to train. For the dataset, credits go to [AlpacaDataCleaned](https://github.com/gururise/AlpacaDataCleaned) and [codealpaca](https://github.com/sahil280114/codealpaca). Credits also go to [chavinlo](https://huggingface.co/chavinlo/alpaca-native) for creating the original Alpaca 7B Native model, the inspiration behind this model.
110
+
111
+ Lastly, credits go to the homies that stayed up all night again and again: 8bit, π, chug, Taddy, yoyodapro, Symax, and most importantly: stablediffusion for the beautiful artwork
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
alpaca-7b-native-enhanced-4bit-128g-gptq.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbea16c7a99400445764bb5137a76012f207c56eca942b80b42912f0e4ab343
3
+ size 3893986936
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./llama-7b-hf",
3
+ "architectures": ["LlamaForCausalLM"],
4
+ "bos_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "hidden_act": "silu",
7
+ "hidden_size": 4096,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 11008,
10
+ "max_sequence_length": 2048,
11
+ "model_type": "llama",
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 32,
14
+ "pad_token_id": -1,
15
+ "rms_norm_eps": 1e-6,
16
+ "tie_word_embeddings": false,
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.28.0.dev0",
19
+ "use_cache": true,
20
+ "vocab_size": 32001,
21
+ "quantization_config": {
22
+ "bits": 4,
23
+ "group_size": 128,
24
+ "damp_percent": 0.01,
25
+ "desc_act": false,
26
+ "sym": true,
27
+ "true_sequential": true,
28
+ "model_name_or_path": null,
29
+ "model_file_base_name": "model",
30
+ "quant_method": "gptq"
31
+ }
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.0.dev0"
7
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953703424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "</s>"
6
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "",
3
+ "eos_token": "",
4
+ "model_max_length": 512,
5
+ "padding_side": "right",
6
+ "special_tokens_map_file": "./llama-7b-hf/special_tokens_map.json",
7
+ "tokenizer_class": "LlamaTokenizer",
8
+ "unk_token": ""
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,2545 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.995319812792512,
5
+ "global_step": 420,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0,
13
+ "loss": 1.4861,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.0,
19
+ "loss": 1.4901,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.5384615384615387e-06,
25
+ "loss": 1.4646,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 3.0769230769230774e-06,
31
+ "loss": 1.44,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 4.615384615384616e-06,
37
+ "loss": 1.4355,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 6.153846153846155e-06,
43
+ "loss": 1.1764,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 7.692307692307694e-06,
49
+ "loss": 1.0584,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 9.230769230769232e-06,
55
+ "loss": 1.0187,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 1.076923076923077e-05,
61
+ "loss": 1.0039,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.07,
66
+ "learning_rate": 1.230769230769231e-05,
67
+ "loss": 0.9911,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.08,
72
+ "learning_rate": 1.3846153846153847e-05,
73
+ "loss": 0.972,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.09,
78
+ "learning_rate": 1.5384615384615387e-05,
79
+ "loss": 0.9573,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.09,
84
+ "learning_rate": 1.6923076923076924e-05,
85
+ "loss": 0.9277,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.1,
90
+ "learning_rate": 1.8461538461538465e-05,
91
+ "loss": 0.8686,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.11,
96
+ "learning_rate": 2e-05,
97
+ "loss": 0.9066,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.11,
102
+ "learning_rate": 1.9999702094326033e-05,
103
+ "loss": 0.9442,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.12,
108
+ "learning_rate": 1.9998808395053687e-05,
109
+ "loss": 0.8849,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.13,
114
+ "learning_rate": 1.999731895543058e-05,
115
+ "loss": 0.8767,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.14,
120
+ "learning_rate": 1.9995233864199213e-05,
121
+ "loss": 0.9332,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.14,
126
+ "learning_rate": 1.9992553245591694e-05,
127
+ "loss": 0.9058,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.15,
132
+ "learning_rate": 1.9989277259322314e-05,
133
+ "loss": 0.9563,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.16,
138
+ "learning_rate": 1.998540610057806e-05,
139
+ "loss": 0.9188,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.16,
144
+ "learning_rate": 1.9980940000006956e-05,
145
+ "loss": 0.9445,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.17,
150
+ "learning_rate": 1.997587922370434e-05,
151
+ "loss": 0.8958,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.18,
156
+ "learning_rate": 1.997022407319702e-05,
157
+ "loss": 0.8969,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.19,
162
+ "learning_rate": 1.9963974885425267e-05,
163
+ "loss": 0.9201,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.19,
168
+ "learning_rate": 1.9957132032722787e-05,
169
+ "loss": 0.8686,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.2,
174
+ "learning_rate": 1.9949695922794508e-05,
175
+ "loss": 0.8845,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.21,
180
+ "learning_rate": 1.99416669986923e-05,
181
+ "loss": 0.9125,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.21,
186
+ "learning_rate": 1.9933045738788564e-05,
187
+ "loss": 0.9097,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.22,
192
+ "learning_rate": 1.992383265674776e-05,
193
+ "loss": 0.886,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.23,
198
+ "learning_rate": 1.991402830149576e-05,
199
+ "loss": 0.9274,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.24,
204
+ "learning_rate": 1.9903633257187186e-05,
205
+ "loss": 0.9153,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.24,
210
+ "learning_rate": 1.9892648143170565e-05,
211
+ "loss": 0.9458,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.25,
216
+ "learning_rate": 1.9881073613951464e-05,
217
+ "loss": 0.9064,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.26,
222
+ "learning_rate": 1.986891035915346e-05,
223
+ "loss": 0.8758,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.26,
228
+ "learning_rate": 1.9856159103477085e-05,
229
+ "loss": 0.8764,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.27,
234
+ "learning_rate": 1.984282060665662e-05,
235
+ "loss": 0.9475,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.28,
240
+ "learning_rate": 1.9828895663414838e-05,
241
+ "loss": 0.883,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.29,
246
+ "learning_rate": 1.9814385103415662e-05,
247
+ "loss": 0.8835,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.29,
252
+ "learning_rate": 1.9799289791214725e-05,
253
+ "loss": 0.8706,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.3,
258
+ "learning_rate": 1.9783610626207855e-05,
259
+ "loss": 0.923,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.31,
264
+ "learning_rate": 1.9767348542577496e-05,
265
+ "loss": 0.8666,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.31,
270
+ "learning_rate": 1.9750504509237046e-05,
271
+ "loss": 0.882,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.32,
276
+ "learning_rate": 1.9733079529773123e-05,
277
+ "loss": 0.8919,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.33,
282
+ "learning_rate": 1.9715074642385785e-05,
283
+ "loss": 0.911,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.34,
288
+ "learning_rate": 1.9696490919826647e-05,
289
+ "loss": 0.9278,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.34,
294
+ "learning_rate": 1.967732946933499e-05,
295
+ "loss": 0.8796,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.35,
300
+ "learning_rate": 1.965759143257178e-05,
301
+ "loss": 0.9192,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.36,
306
+ "learning_rate": 1.9637277985551643e-05,
307
+ "loss": 0.8925,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.36,
312
+ "learning_rate": 1.9616390338572805e-05,
313
+ "loss": 0.9026,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.37,
318
+ "learning_rate": 1.9594929736144978e-05,
319
+ "loss": 0.8203,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.38,
324
+ "learning_rate": 1.95728974569152e-05,
325
+ "loss": 0.8867,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.39,
330
+ "learning_rate": 1.9550294813591685e-05,
331
+ "loss": 0.8783,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.39,
336
+ "learning_rate": 1.9527123152865562e-05,
337
+ "loss": 0.897,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.4,
342
+ "learning_rate": 1.950338385533067e-05,
343
+ "loss": 0.8365,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.41,
348
+ "learning_rate": 1.9479078335401297e-05,
349
+ "loss": 0.8951,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.41,
354
+ "learning_rate": 1.9454208041227905e-05,
355
+ "loss": 0.8633,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.42,
360
+ "learning_rate": 1.9428774454610845e-05,
361
+ "loss": 0.9022,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.43,
366
+ "learning_rate": 1.940277909091206e-05,
367
+ "loss": 0.885,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.44,
372
+ "learning_rate": 1.937622349896483e-05,
373
+ "loss": 0.8765,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.44,
378
+ "learning_rate": 1.9349109260981455e-05,
379
+ "loss": 0.8465,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.45,
384
+ "learning_rate": 1.9321437992458996e-05,
385
+ "loss": 0.8642,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.46,
390
+ "learning_rate": 1.929321134208304e-05,
391
+ "loss": 0.8872,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.46,
396
+ "learning_rate": 1.9264430991629447e-05,
397
+ "loss": 0.9043,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.47,
402
+ "learning_rate": 1.9235098655864156e-05,
403
+ "loss": 0.9398,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.48,
408
+ "learning_rate": 1.920521608244102e-05,
409
+ "loss": 0.9099,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.48,
414
+ "learning_rate": 1.9174785051797668e-05,
415
+ "loss": 0.8736,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.49,
420
+ "learning_rate": 1.9143807377049443e-05,
421
+ "loss": 0.7984,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.5,
426
+ "learning_rate": 1.911228490388136e-05,
427
+ "loss": 0.8401,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.51,
432
+ "learning_rate": 1.9080219510438137e-05,
433
+ "loss": 0.8782,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.51,
438
+ "learning_rate": 1.9047613107212314e-05,
439
+ "loss": 0.8569,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.52,
444
+ "learning_rate": 1.9014467636930387e-05,
445
+ "loss": 0.8467,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.53,
450
+ "learning_rate": 1.8980785074437095e-05,
451
+ "loss": 0.8492,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.53,
456
+ "learning_rate": 1.8946567426577724e-05,
457
+ "loss": 0.8786,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.54,
462
+ "learning_rate": 1.8911816732078577e-05,
463
+ "loss": 0.8782,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.55,
468
+ "learning_rate": 1.8876535061425454e-05,
469
+ "loss": 0.8979,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.56,
474
+ "learning_rate": 1.884072451674034e-05,
475
+ "loss": 0.906,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.56,
480
+ "learning_rate": 1.880438723165612e-05,
481
+ "loss": 0.9005,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.57,
486
+ "learning_rate": 1.8767525371189473e-05,
487
+ "loss": 0.828,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.58,
492
+ "learning_rate": 1.8730141131611882e-05,
493
+ "loss": 0.8725,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.58,
498
+ "learning_rate": 1.869223674031876e-05,
499
+ "loss": 0.8478,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.59,
504
+ "learning_rate": 1.865381445569676e-05,
505
+ "loss": 0.8932,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.6,
510
+ "learning_rate": 1.861487656698919e-05,
511
+ "loss": 0.8847,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.61,
516
+ "learning_rate": 1.8575425394159653e-05,
517
+ "loss": 0.9109,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.61,
522
+ "learning_rate": 1.8535463287753797e-05,
523
+ "loss": 0.8571,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.62,
528
+ "learning_rate": 1.849499262875927e-05,
529
+ "loss": 0.8681,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.63,
534
+ "learning_rate": 1.845401582846385e-05,
535
+ "loss": 0.8969,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.63,
540
+ "learning_rate": 1.8412535328311813e-05,
541
+ "loss": 0.8889,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.64,
546
+ "learning_rate": 1.8370553599758424e-05,
547
+ "loss": 0.8971,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.65,
552
+ "learning_rate": 1.8328073144122708e-05,
553
+ "loss": 0.8818,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.66,
558
+ "learning_rate": 1.8285096492438424e-05,
559
+ "loss": 0.8723,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.66,
564
+ "learning_rate": 1.8241626205303245e-05,
565
+ "loss": 0.8822,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.67,
570
+ "learning_rate": 1.8197664872726206e-05,
571
+ "loss": 0.852,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.68,
576
+ "learning_rate": 1.8153215113973398e-05,
577
+ "loss": 0.8946,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.68,
582
+ "learning_rate": 1.810827957741188e-05,
583
+ "loss": 0.8812,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.69,
588
+ "learning_rate": 1.8062860940351916e-05,
589
+ "loss": 0.8572,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.7,
594
+ "learning_rate": 1.8016961908887444e-05,
595
+ "loss": 0.8703,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.71,
600
+ "learning_rate": 1.7970585217734843e-05,
601
+ "loss": 0.8565,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.71,
606
+ "learning_rate": 1.792373363007e-05,
607
+ "loss": 0.8724,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.72,
612
+ "learning_rate": 1.7876409937363677e-05,
613
+ "loss": 0.8421,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.73,
618
+ "learning_rate": 1.7828616959215185e-05,
619
+ "loss": 0.8504,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.73,
624
+ "learning_rate": 1.7780357543184396e-05,
625
+ "loss": 0.8842,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.74,
630
+ "learning_rate": 1.7731634564622087e-05,
631
+ "loss": 0.8467,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.75,
636
+ "learning_rate": 1.768245092649861e-05,
637
+ "loss": 0.893,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.76,
642
+ "learning_rate": 1.763280955923093e-05,
643
+ "loss": 0.8401,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.76,
648
+ "learning_rate": 1.7582713420508052e-05,
649
+ "loss": 0.8824,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.77,
654
+ "learning_rate": 1.7532165495114765e-05,
655
+ "loss": 0.8969,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.78,
660
+ "learning_rate": 1.748116879475383e-05,
661
+ "loss": 0.8517,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.78,
666
+ "learning_rate": 1.7429726357866516e-05,
667
+ "loss": 0.9263,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.79,
672
+ "learning_rate": 1.7377841249451596e-05,
673
+ "loss": 0.8942,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.8,
678
+ "learning_rate": 1.7325516560882706e-05,
679
+ "loss": 0.8849,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.81,
684
+ "learning_rate": 1.727275540972417e-05,
685
+ "loss": 0.8786,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.81,
690
+ "learning_rate": 1.7219560939545246e-05,
691
+ "loss": 0.8361,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.82,
696
+ "learning_rate": 1.7165936319732833e-05,
697
+ "loss": 0.8518,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.83,
702
+ "learning_rate": 1.711188474530263e-05,
703
+ "loss": 0.8686,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.83,
708
+ "learning_rate": 1.7057409436708783e-05,
709
+ "loss": 0.8457,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.84,
714
+ "learning_rate": 1.700251363965199e-05,
715
+ "loss": 0.8331,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.85,
720
+ "learning_rate": 1.6947200624886145e-05,
721
+ "loss": 0.8336,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.86,
726
+ "learning_rate": 1.6891473688023425e-05,
727
+ "loss": 0.8896,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.86,
732
+ "learning_rate": 1.6835336149337976e-05,
733
+ "loss": 0.8698,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.87,
738
+ "learning_rate": 1.677879135356805e-05,
739
+ "loss": 0.8493,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.88,
744
+ "learning_rate": 1.6721842669716752e-05,
745
+ "loss": 0.8637,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.88,
750
+ "learning_rate": 1.666449349085129e-05,
751
+ "loss": 0.8614,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.89,
756
+ "learning_rate": 1.6606747233900816e-05,
757
+ "loss": 0.8878,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.9,
762
+ "learning_rate": 1.6548607339452853e-05,
763
+ "loss": 0.8685,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.91,
768
+ "learning_rate": 1.6490077271548287e-05,
769
+ "loss": 0.8429,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.91,
774
+ "learning_rate": 1.6431160517474986e-05,
775
+ "loss": 0.8828,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.92,
780
+ "learning_rate": 1.637186058756001e-05,
781
+ "loss": 0.8589,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.93,
786
+ "learning_rate": 1.6312181014960483e-05,
787
+ "loss": 0.864,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.93,
792
+ "learning_rate": 1.6252125355453058e-05,
793
+ "loss": 0.8906,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.94,
798
+ "learning_rate": 1.619169718722209e-05,
799
+ "loss": 0.854,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.95,
804
+ "learning_rate": 1.6130900110646404e-05,
805
+ "loss": 0.9064,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.96,
810
+ "learning_rate": 1.6069737748084823e-05,
811
+ "loss": 0.9017,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.96,
816
+ "learning_rate": 1.600821374366031e-05,
817
+ "loss": 0.8955,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.97,
822
+ "learning_rate": 1.594633176304287e-05,
823
+ "loss": 0.8569,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.98,
828
+ "learning_rate": 1.5884095493231123e-05,
829
+ "loss": 0.8699,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.98,
834
+ "learning_rate": 1.582150864233266e-05,
835
+ "loss": 0.8945,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.99,
840
+ "learning_rate": 1.5758574939343073e-05,
841
+ "loss": 0.8861,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 1.0,
846
+ "learning_rate": 1.569529813392381e-05,
847
+ "loss": 0.8806,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 1.01,
852
+ "learning_rate": 1.5631681996178735e-05,
853
+ "loss": 0.7215,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 1.01,
858
+ "learning_rate": 1.5567730316429536e-05,
859
+ "loss": 0.6521,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 1.02,
864
+ "learning_rate": 1.5503446904989856e-05,
865
+ "loss": 0.6706,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 1.03,
870
+ "learning_rate": 1.54388355919383e-05,
871
+ "loss": 0.6824,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 1.03,
876
+ "learning_rate": 1.537390022689022e-05,
877
+ "loss": 0.6543,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 1.04,
882
+ "learning_rate": 1.530864467876836e-05,
883
+ "loss": 0.6559,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 1.05,
888
+ "learning_rate": 1.5243072835572319e-05,
889
+ "loss": 0.6764,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 1.06,
894
+ "learning_rate": 1.5177188604146929e-05,
895
+ "loss": 0.6662,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 1.06,
900
+ "learning_rate": 1.5110995909949465e-05,
901
+ "loss": 0.6668,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 1.07,
906
+ "learning_rate": 1.504449869681576e-05,
907
+ "loss": 0.6746,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 1.08,
912
+ "learning_rate": 1.4977700926725231e-05,
913
+ "loss": 0.6726,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 1.08,
918
+ "learning_rate": 1.4910606579564827e-05,
919
+ "loss": 0.6261,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 1.09,
924
+ "learning_rate": 1.4843219652891889e-05,
925
+ "loss": 0.6561,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 1.1,
930
+ "learning_rate": 1.4775544161695975e-05,
931
+ "loss": 0.6725,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 1.11,
936
+ "learning_rate": 1.4707584138159652e-05,
937
+ "loss": 0.6421,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 1.11,
942
+ "learning_rate": 1.4639343631418239e-05,
943
+ "loss": 0.6568,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 1.12,
948
+ "learning_rate": 1.457082670731857e-05,
949
+ "loss": 0.6381,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 1.13,
954
+ "learning_rate": 1.4502037448176734e-05,
955
+ "loss": 0.6663,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 1.13,
960
+ "learning_rate": 1.4432979952534853e-05,
961
+ "loss": 0.6344,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 1.14,
966
+ "learning_rate": 1.4363658334916883e-05,
967
+ "loss": 0.6778,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 1.15,
972
+ "learning_rate": 1.4294076725583463e-05,
973
+ "loss": 0.6412,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 1.16,
978
+ "learning_rate": 1.4224239270285847e-05,
979
+ "loss": 0.6905,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 1.16,
984
+ "learning_rate": 1.4154150130018867e-05,
985
+ "loss": 0.6732,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 1.17,
990
+ "learning_rate": 1.4083813480773036e-05,
991
+ "loss": 0.6823,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 1.18,
996
+ "learning_rate": 1.4013233513285734e-05,
997
+ "loss": 0.6621,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 1.18,
1002
+ "learning_rate": 1.394241443279152e-05,
1003
+ "loss": 0.6802,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 1.19,
1008
+ "learning_rate": 1.3871360458771575e-05,
1009
+ "loss": 0.6327,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 1.2,
1014
+ "learning_rate": 1.38000758247023e-05,
1015
+ "loss": 0.6688,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 1.21,
1020
+ "learning_rate": 1.3728564777803089e-05,
1021
+ "loss": 0.6781,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 1.21,
1026
+ "learning_rate": 1.3656831578783263e-05,
1027
+ "loss": 0.6387,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 1.22,
1032
+ "learning_rate": 1.3584880501588225e-05,
1033
+ "loss": 0.6211,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 1.23,
1038
+ "learning_rate": 1.35127158331448e-05,
1039
+ "loss": 0.6674,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 1.23,
1044
+ "learning_rate": 1.3440341873105834e-05,
1045
+ "loss": 0.664,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 1.24,
1050
+ "learning_rate": 1.3367762933593989e-05,
1051
+ "loss": 0.6374,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 1.25,
1056
+ "learning_rate": 1.3294983338944842e-05,
1057
+ "loss": 0.7106,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 1.26,
1062
+ "learning_rate": 1.3222007425449234e-05,
1063
+ "loss": 0.6743,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 1.26,
1068
+ "learning_rate": 1.314883954109491e-05,
1069
+ "loss": 0.6266,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 1.27,
1074
+ "learning_rate": 1.3075484045307443e-05,
1075
+ "loss": 0.6409,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 1.28,
1080
+ "learning_rate": 1.3001945308690514e-05,
1081
+ "loss": 0.696,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 1.28,
1086
+ "learning_rate": 1.2928227712765504e-05,
1087
+ "loss": 0.6427,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 1.29,
1092
+ "learning_rate": 1.2854335649710436e-05,
1093
+ "loss": 0.687,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 1.3,
1098
+ "learning_rate": 1.2780273522098276e-05,
1099
+ "loss": 0.624,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 1.31,
1104
+ "learning_rate": 1.2706045742634637e-05,
1105
+ "loss": 0.6444,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 1.31,
1110
+ "learning_rate": 1.2631656733894842e-05,
1111
+ "loss": 0.64,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 1.32,
1116
+ "learning_rate": 1.2557110928060456e-05,
1117
+ "loss": 0.6345,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 1.33,
1122
+ "learning_rate": 1.2482412766655183e-05,
1123
+ "loss": 0.6863,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 1.33,
1128
+ "learning_rate": 1.2407566700280247e-05,
1129
+ "loss": 0.6546,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 1.34,
1134
+ "learning_rate": 1.2332577188349217e-05,
1135
+ "loss": 0.6767,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 1.35,
1140
+ "learning_rate": 1.2257448698822314e-05,
1141
+ "loss": 0.6265,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 1.36,
1146
+ "learning_rate": 1.2182185707940196e-05,
1147
+ "loss": 0.6039,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 1.36,
1152
+ "learning_rate": 1.2106792699957264e-05,
1153
+ "loss": 0.6537,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 1.37,
1158
+ "learning_rate": 1.2031274166874498e-05,
1159
+ "loss": 0.671,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 1.38,
1164
+ "learning_rate": 1.1955634608171792e-05,
1165
+ "loss": 0.6542,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 1.38,
1170
+ "learning_rate": 1.187987853053989e-05,
1171
+ "loss": 0.6243,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 1.39,
1176
+ "learning_rate": 1.1804010447611862e-05,
1177
+ "loss": 0.6399,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 1.4,
1182
+ "learning_rate": 1.1728034879694185e-05,
1183
+ "loss": 0.6114,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 1.4,
1188
+ "learning_rate": 1.1651956353497418e-05,
1189
+ "loss": 0.6876,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 1.41,
1194
+ "learning_rate": 1.1575779401866475e-05,
1195
+ "loss": 0.6567,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 1.42,
1200
+ "learning_rate": 1.1499508563510587e-05,
1201
+ "loss": 0.6602,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 1.43,
1206
+ "learning_rate": 1.1423148382732854e-05,
1207
+ "loss": 0.6618,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 1.43,
1212
+ "learning_rate": 1.1346703409159495e-05,
1213
+ "loss": 0.6235,
1214
+ "step": 201
1215
+ },
1216
+ {
1217
+ "epoch": 1.44,
1218
+ "learning_rate": 1.1270178197468788e-05,
1219
+ "loss": 0.6743,
1220
+ "step": 202
1221
+ },
1222
+ {
1223
+ "epoch": 1.45,
1224
+ "learning_rate": 1.1193577307119687e-05,
1225
+ "loss": 0.676,
1226
+ "step": 203
1227
+ },
1228
+ {
1229
+ "epoch": 1.45,
1230
+ "learning_rate": 1.1116905302080163e-05,
1231
+ "loss": 0.6091,
1232
+ "step": 204
1233
+ },
1234
+ {
1235
+ "epoch": 1.46,
1236
+ "learning_rate": 1.1040166750555288e-05,
1237
+ "loss": 0.6412,
1238
+ "step": 205
1239
+ },
1240
+ {
1241
+ "epoch": 1.47,
1242
+ "learning_rate": 1.0963366224715035e-05,
1243
+ "loss": 0.6593,
1244
+ "step": 206
1245
+ },
1246
+ {
1247
+ "epoch": 1.48,
1248
+ "learning_rate": 1.0886508300421892e-05,
1249
+ "loss": 0.6369,
1250
+ "step": 207
1251
+ },
1252
+ {
1253
+ "epoch": 1.48,
1254
+ "learning_rate": 1.080959755695821e-05,
1255
+ "loss": 0.7025,
1256
+ "step": 208
1257
+ },
1258
+ {
1259
+ "epoch": 1.49,
1260
+ "learning_rate": 1.0732638576753355e-05,
1261
+ "loss": 0.6387,
1262
+ "step": 209
1263
+ },
1264
+ {
1265
+ "epoch": 1.5,
1266
+ "learning_rate": 1.0655635945110705e-05,
1267
+ "loss": 0.6821,
1268
+ "step": 210
1269
+ },
1270
+ {
1271
+ "epoch": 1.5,
1272
+ "learning_rate": 1.0578594249934433e-05,
1273
+ "loss": 0.673,
1274
+ "step": 211
1275
+ },
1276
+ {
1277
+ "epoch": 1.51,
1278
+ "learning_rate": 1.0501518081456164e-05,
1279
+ "loss": 0.6481,
1280
+ "step": 212
1281
+ },
1282
+ {
1283
+ "epoch": 1.52,
1284
+ "learning_rate": 1.0424412031961485e-05,
1285
+ "loss": 0.6704,
1286
+ "step": 213
1287
+ },
1288
+ {
1289
+ "epoch": 1.53,
1290
+ "learning_rate": 1.0347280695516319e-05,
1291
+ "loss": 0.6656,
1292
+ "step": 214
1293
+ },
1294
+ {
1295
+ "epoch": 1.53,
1296
+ "learning_rate": 1.0270128667693225e-05,
1297
+ "loss": 0.644,
1298
+ "step": 215
1299
+ },
1300
+ {
1301
+ "epoch": 1.54,
1302
+ "learning_rate": 1.0192960545297568e-05,
1303
+ "loss": 0.6596,
1304
+ "step": 216
1305
+ },
1306
+ {
1307
+ "epoch": 1.55,
1308
+ "learning_rate": 1.011578092609365e-05,
1309
+ "loss": 0.6377,
1310
+ "step": 217
1311
+ },
1312
+ {
1313
+ "epoch": 1.55,
1314
+ "learning_rate": 1.0038594408530768e-05,
1315
+ "loss": 0.6317,
1316
+ "step": 218
1317
+ },
1318
+ {
1319
+ "epoch": 1.56,
1320
+ "learning_rate": 9.96140559146923e-06,
1321
+ "loss": 0.6491,
1322
+ "step": 219
1323
+ },
1324
+ {
1325
+ "epoch": 1.57,
1326
+ "learning_rate": 9.884219073906353e-06,
1327
+ "loss": 0.6474,
1328
+ "step": 220
1329
+ },
1330
+ {
1331
+ "epoch": 1.58,
1332
+ "learning_rate": 9.807039454702436e-06,
1333
+ "loss": 0.6897,
1334
+ "step": 221
1335
+ },
1336
+ {
1337
+ "epoch": 1.58,
1338
+ "learning_rate": 9.729871332306775e-06,
1339
+ "loss": 0.6109,
1340
+ "step": 222
1341
+ },
1342
+ {
1343
+ "epoch": 1.59,
1344
+ "learning_rate": 9.652719304483683e-06,
1345
+ "loss": 0.6783,
1346
+ "step": 223
1347
+ },
1348
+ {
1349
+ "epoch": 1.6,
1350
+ "learning_rate": 9.57558796803852e-06,
1351
+ "loss": 0.6471,
1352
+ "step": 224
1353
+ },
1354
+ {
1355
+ "epoch": 1.6,
1356
+ "learning_rate": 9.498481918543836e-06,
1357
+ "loss": 0.6259,
1358
+ "step": 225
1359
+ },
1360
+ {
1361
+ "epoch": 1.61,
1362
+ "learning_rate": 9.42140575006557e-06,
1363
+ "loss": 0.6444,
1364
+ "step": 226
1365
+ },
1366
+ {
1367
+ "epoch": 1.62,
1368
+ "learning_rate": 9.344364054889298e-06,
1369
+ "loss": 0.6624,
1370
+ "step": 227
1371
+ },
1372
+ {
1373
+ "epoch": 1.63,
1374
+ "learning_rate": 9.267361423246645e-06,
1375
+ "loss": 0.6863,
1376
+ "step": 228
1377
+ },
1378
+ {
1379
+ "epoch": 1.63,
1380
+ "learning_rate": 9.190402443041792e-06,
1381
+ "loss": 0.643,
1382
+ "step": 229
1383
+ },
1384
+ {
1385
+ "epoch": 1.64,
1386
+ "learning_rate": 9.11349169957811e-06,
1387
+ "loss": 0.6617,
1388
+ "step": 230
1389
+ },
1390
+ {
1391
+ "epoch": 1.65,
1392
+ "learning_rate": 9.036633775284968e-06,
1393
+ "loss": 0.6689,
1394
+ "step": 231
1395
+ },
1396
+ {
1397
+ "epoch": 1.65,
1398
+ "learning_rate": 8.959833249444715e-06,
1399
+ "loss": 0.6269,
1400
+ "step": 232
1401
+ },
1402
+ {
1403
+ "epoch": 1.66,
1404
+ "learning_rate": 8.883094697919839e-06,
1405
+ "loss": 0.6601,
1406
+ "step": 233
1407
+ },
1408
+ {
1409
+ "epoch": 1.67,
1410
+ "learning_rate": 8.806422692880318e-06,
1411
+ "loss": 0.6672,
1412
+ "step": 234
1413
+ },
1414
+ {
1415
+ "epoch": 1.68,
1416
+ "learning_rate": 8.729821802531213e-06,
1417
+ "loss": 0.6126,
1418
+ "step": 235
1419
+ },
1420
+ {
1421
+ "epoch": 1.68,
1422
+ "learning_rate": 8.653296590840509e-06,
1423
+ "loss": 0.6506,
1424
+ "step": 236
1425
+ },
1426
+ {
1427
+ "epoch": 1.69,
1428
+ "learning_rate": 8.576851617267151e-06,
1429
+ "loss": 0.6503,
1430
+ "step": 237
1431
+ },
1432
+ {
1433
+ "epoch": 1.7,
1434
+ "learning_rate": 8.500491436489413e-06,
1435
+ "loss": 0.6969,
1436
+ "step": 238
1437
+ },
1438
+ {
1439
+ "epoch": 1.7,
1440
+ "learning_rate": 8.424220598133526e-06,
1441
+ "loss": 0.6609,
1442
+ "step": 239
1443
+ },
1444
+ {
1445
+ "epoch": 1.71,
1446
+ "learning_rate": 8.348043646502588e-06,
1447
+ "loss": 0.648,
1448
+ "step": 240
1449
+ },
1450
+ {
1451
+ "epoch": 1.72,
1452
+ "learning_rate": 8.271965120305815e-06,
1453
+ "loss": 0.7073,
1454
+ "step": 241
1455
+ },
1456
+ {
1457
+ "epoch": 1.73,
1458
+ "learning_rate": 8.19598955238814e-06,
1459
+ "loss": 0.6661,
1460
+ "step": 242
1461
+ },
1462
+ {
1463
+ "epoch": 1.73,
1464
+ "learning_rate": 8.120121469460114e-06,
1465
+ "loss": 0.727,
1466
+ "step": 243
1467
+ },
1468
+ {
1469
+ "epoch": 1.74,
1470
+ "learning_rate": 8.04436539182821e-06,
1471
+ "loss": 0.6866,
1472
+ "step": 244
1473
+ },
1474
+ {
1475
+ "epoch": 1.75,
1476
+ "learning_rate": 7.968725833125505e-06,
1477
+ "loss": 0.6556,
1478
+ "step": 245
1479
+ },
1480
+ {
1481
+ "epoch": 1.75,
1482
+ "learning_rate": 7.89320730004274e-06,
1483
+ "loss": 0.6132,
1484
+ "step": 246
1485
+ },
1486
+ {
1487
+ "epoch": 1.76,
1488
+ "learning_rate": 7.81781429205981e-06,
1489
+ "loss": 0.6601,
1490
+ "step": 247
1491
+ },
1492
+ {
1493
+ "epoch": 1.77,
1494
+ "learning_rate": 7.74255130117769e-06,
1495
+ "loss": 0.6627,
1496
+ "step": 248
1497
+ },
1498
+ {
1499
+ "epoch": 1.78,
1500
+ "learning_rate": 7.667422811650786e-06,
1501
+ "loss": 0.6766,
1502
+ "step": 249
1503
+ },
1504
+ {
1505
+ "epoch": 1.78,
1506
+ "learning_rate": 7.592433299719757e-06,
1507
+ "loss": 0.6407,
1508
+ "step": 250
1509
+ },
1510
+ {
1511
+ "epoch": 1.79,
1512
+ "learning_rate": 7.51758723334482e-06,
1513
+ "loss": 0.6199,
1514
+ "step": 251
1515
+ },
1516
+ {
1517
+ "epoch": 1.8,
1518
+ "learning_rate": 7.442889071939548e-06,
1519
+ "loss": 0.665,
1520
+ "step": 252
1521
+ },
1522
+ {
1523
+ "epoch": 1.8,
1524
+ "learning_rate": 7.368343266105162e-06,
1525
+ "loss": 0.671,
1526
+ "step": 253
1527
+ },
1528
+ {
1529
+ "epoch": 1.81,
1530
+ "learning_rate": 7.293954257365368e-06,
1531
+ "loss": 0.6747,
1532
+ "step": 254
1533
+ },
1534
+ {
1535
+ "epoch": 1.82,
1536
+ "learning_rate": 7.2197264779017275e-06,
1537
+ "loss": 0.6633,
1538
+ "step": 255
1539
+ },
1540
+ {
1541
+ "epoch": 1.83,
1542
+ "learning_rate": 7.145664350289566e-06,
1543
+ "loss": 0.6527,
1544
+ "step": 256
1545
+ },
1546
+ {
1547
+ "epoch": 1.83,
1548
+ "learning_rate": 7.071772287234497e-06,
1549
+ "loss": 0.6978,
1550
+ "step": 257
1551
+ },
1552
+ {
1553
+ "epoch": 1.84,
1554
+ "learning_rate": 6.998054691309489e-06,
1555
+ "loss": 0.6754,
1556
+ "step": 258
1557
+ },
1558
+ {
1559
+ "epoch": 1.85,
1560
+ "learning_rate": 6.924515954692563e-06,
1561
+ "loss": 0.66,
1562
+ "step": 259
1563
+ },
1564
+ {
1565
+ "epoch": 1.85,
1566
+ "learning_rate": 6.851160458905093e-06,
1567
+ "loss": 0.6229,
1568
+ "step": 260
1569
+ },
1570
+ {
1571
+ "epoch": 1.86,
1572
+ "learning_rate": 6.777992574550767e-06,
1573
+ "loss": 0.6619,
1574
+ "step": 261
1575
+ },
1576
+ {
1577
+ "epoch": 1.87,
1578
+ "learning_rate": 6.705016661055162e-06,
1579
+ "loss": 0.6291,
1580
+ "step": 262
1581
+ },
1582
+ {
1583
+ "epoch": 1.88,
1584
+ "learning_rate": 6.632237066406014e-06,
1585
+ "loss": 0.6353,
1586
+ "step": 263
1587
+ },
1588
+ {
1589
+ "epoch": 1.88,
1590
+ "learning_rate": 6.559658126894169e-06,
1591
+ "loss": 0.6533,
1592
+ "step": 264
1593
+ },
1594
+ {
1595
+ "epoch": 1.89,
1596
+ "learning_rate": 6.487284166855203e-06,
1597
+ "loss": 0.6381,
1598
+ "step": 265
1599
+ },
1600
+ {
1601
+ "epoch": 1.9,
1602
+ "learning_rate": 6.4151194984117774e-06,
1603
+ "loss": 0.6156,
1604
+ "step": 266
1605
+ },
1606
+ {
1607
+ "epoch": 1.9,
1608
+ "learning_rate": 6.343168421216741e-06,
1609
+ "loss": 0.6582,
1610
+ "step": 267
1611
+ },
1612
+ {
1613
+ "epoch": 1.91,
1614
+ "learning_rate": 6.2714352221969155e-06,
1615
+ "loss": 0.6862,
1616
+ "step": 268
1617
+ },
1618
+ {
1619
+ "epoch": 1.92,
1620
+ "learning_rate": 6.199924175297701e-06,
1621
+ "loss": 0.6487,
1622
+ "step": 269
1623
+ },
1624
+ {
1625
+ "epoch": 1.93,
1626
+ "learning_rate": 6.128639541228427e-06,
1627
+ "loss": 0.6534,
1628
+ "step": 270
1629
+ },
1630
+ {
1631
+ "epoch": 1.93,
1632
+ "learning_rate": 6.057585567208484e-06,
1633
+ "loss": 0.6827,
1634
+ "step": 271
1635
+ },
1636
+ {
1637
+ "epoch": 1.94,
1638
+ "learning_rate": 5.986766486714268e-06,
1639
+ "loss": 0.6595,
1640
+ "step": 272
1641
+ },
1642
+ {
1643
+ "epoch": 1.95,
1644
+ "learning_rate": 5.916186519226966e-06,
1645
+ "loss": 0.6754,
1646
+ "step": 273
1647
+ },
1648
+ {
1649
+ "epoch": 1.95,
1650
+ "learning_rate": 5.845849869981137e-06,
1651
+ "loss": 0.6635,
1652
+ "step": 274
1653
+ },
1654
+ {
1655
+ "epoch": 1.96,
1656
+ "learning_rate": 5.775760729714155e-06,
1657
+ "loss": 0.6604,
1658
+ "step": 275
1659
+ },
1660
+ {
1661
+ "epoch": 1.97,
1662
+ "learning_rate": 5.705923274416536e-06,
1663
+ "loss": 0.6956,
1664
+ "step": 276
1665
+ },
1666
+ {
1667
+ "epoch": 1.98,
1668
+ "learning_rate": 5.636341665083121e-06,
1669
+ "loss": 0.6262,
1670
+ "step": 277
1671
+ },
1672
+ {
1673
+ "epoch": 1.98,
1674
+ "learning_rate": 5.5670200474651505e-06,
1675
+ "loss": 0.6186,
1676
+ "step": 278
1677
+ },
1678
+ {
1679
+ "epoch": 1.99,
1680
+ "learning_rate": 5.497962551823266e-06,
1681
+ "loss": 0.6558,
1682
+ "step": 279
1683
+ },
1684
+ {
1685
+ "epoch": 2.0,
1686
+ "learning_rate": 5.429173292681433e-06,
1687
+ "loss": 0.7025,
1688
+ "step": 280
1689
+ },
1690
+ {
1691
+ "epoch": 2.0,
1692
+ "learning_rate": 5.3606563685817646e-06,
1693
+ "loss": 0.5535,
1694
+ "step": 281
1695
+ },
1696
+ {
1697
+ "epoch": 2.01,
1698
+ "learning_rate": 5.29241586184035e-06,
1699
+ "loss": 0.5372,
1700
+ "step": 282
1701
+ },
1702
+ {
1703
+ "epoch": 2.02,
1704
+ "learning_rate": 5.224455838304028e-06,
1705
+ "loss": 0.5183,
1706
+ "step": 283
1707
+ },
1708
+ {
1709
+ "epoch": 2.03,
1710
+ "learning_rate": 5.1567803471081164e-06,
1711
+ "loss": 0.5192,
1712
+ "step": 284
1713
+ },
1714
+ {
1715
+ "epoch": 2.03,
1716
+ "learning_rate": 5.089393420435176e-06,
1717
+ "loss": 0.5072,
1718
+ "step": 285
1719
+ },
1720
+ {
1721
+ "epoch": 2.04,
1722
+ "learning_rate": 5.022299073274769e-06,
1723
+ "loss": 0.5038,
1724
+ "step": 286
1725
+ },
1726
+ {
1727
+ "epoch": 2.05,
1728
+ "learning_rate": 4.9555013031842445e-06,
1729
+ "loss": 0.5133,
1730
+ "step": 287
1731
+ },
1732
+ {
1733
+ "epoch": 2.05,
1734
+ "learning_rate": 4.889004090050536e-06,
1735
+ "loss": 0.483,
1736
+ "step": 288
1737
+ },
1738
+ {
1739
+ "epoch": 2.06,
1740
+ "learning_rate": 4.822811395853073e-06,
1741
+ "loss": 0.478,
1742
+ "step": 289
1743
+ },
1744
+ {
1745
+ "epoch": 2.07,
1746
+ "learning_rate": 4.756927164427685e-06,
1747
+ "loss": 0.491,
1748
+ "step": 290
1749
+ },
1750
+ {
1751
+ "epoch": 2.08,
1752
+ "learning_rate": 4.691355321231645e-06,
1753
+ "loss": 0.5153,
1754
+ "step": 291
1755
+ },
1756
+ {
1757
+ "epoch": 2.08,
1758
+ "learning_rate": 4.62609977310978e-06,
1759
+ "loss": 0.5066,
1760
+ "step": 292
1761
+ },
1762
+ {
1763
+ "epoch": 2.09,
1764
+ "learning_rate": 4.561164408061703e-06,
1765
+ "loss": 0.495,
1766
+ "step": 293
1767
+ },
1768
+ {
1769
+ "epoch": 2.1,
1770
+ "learning_rate": 4.496553095010147e-06,
1771
+ "loss": 0.5069,
1772
+ "step": 294
1773
+ },
1774
+ {
1775
+ "epoch": 2.1,
1776
+ "learning_rate": 4.432269683570469e-06,
1777
+ "loss": 0.4724,
1778
+ "step": 295
1779
+ },
1780
+ {
1781
+ "epoch": 2.11,
1782
+ "learning_rate": 4.368318003821266e-06,
1783
+ "loss": 0.4922,
1784
+ "step": 296
1785
+ },
1786
+ {
1787
+ "epoch": 2.12,
1788
+ "learning_rate": 4.304701866076194e-06,
1789
+ "loss": 0.495,
1790
+ "step": 297
1791
+ },
1792
+ {
1793
+ "epoch": 2.13,
1794
+ "learning_rate": 4.241425060656927e-06,
1795
+ "loss": 0.5082,
1796
+ "step": 298
1797
+ },
1798
+ {
1799
+ "epoch": 2.13,
1800
+ "learning_rate": 4.178491357667342e-06,
1801
+ "loss": 0.4689,
1802
+ "step": 299
1803
+ },
1804
+ {
1805
+ "epoch": 2.14,
1806
+ "learning_rate": 4.11590450676888e-06,
1807
+ "loss": 0.4802,
1808
+ "step": 300
1809
+ },
1810
+ {
1811
+ "epoch": 2.15,
1812
+ "learning_rate": 4.053668236957135e-06,
1813
+ "loss": 0.4662,
1814
+ "step": 301
1815
+ },
1816
+ {
1817
+ "epoch": 2.15,
1818
+ "learning_rate": 3.991786256339692e-06,
1819
+ "loss": 0.529,
1820
+ "step": 302
1821
+ },
1822
+ {
1823
+ "epoch": 2.16,
1824
+ "learning_rate": 3.930262251915181e-06,
1825
+ "loss": 0.5224,
1826
+ "step": 303
1827
+ },
1828
+ {
1829
+ "epoch": 2.17,
1830
+ "learning_rate": 3.869099889353597e-06,
1831
+ "loss": 0.5176,
1832
+ "step": 304
1833
+ },
1834
+ {
1835
+ "epoch": 2.18,
1836
+ "learning_rate": 3.8083028127779143e-06,
1837
+ "loss": 0.5094,
1838
+ "step": 305
1839
+ },
1840
+ {
1841
+ "epoch": 2.18,
1842
+ "learning_rate": 3.7478746445469415e-06,
1843
+ "loss": 0.4926,
1844
+ "step": 306
1845
+ },
1846
+ {
1847
+ "epoch": 2.19,
1848
+ "learning_rate": 3.6878189850395186e-06,
1849
+ "loss": 0.4941,
1850
+ "step": 307
1851
+ },
1852
+ {
1853
+ "epoch": 2.2,
1854
+ "learning_rate": 3.628139412439993e-06,
1855
+ "loss": 0.5487,
1856
+ "step": 308
1857
+ },
1858
+ {
1859
+ "epoch": 2.2,
1860
+ "learning_rate": 3.5688394825250193e-06,
1861
+ "loss": 0.5081,
1862
+ "step": 309
1863
+ },
1864
+ {
1865
+ "epoch": 2.21,
1866
+ "learning_rate": 3.5099227284517145e-06,
1867
+ "loss": 0.4889,
1868
+ "step": 310
1869
+ },
1870
+ {
1871
+ "epoch": 2.22,
1872
+ "learning_rate": 3.4513926605471504e-06,
1873
+ "loss": 0.4938,
1874
+ "step": 311
1875
+ },
1876
+ {
1877
+ "epoch": 2.23,
1878
+ "learning_rate": 3.3932527660991877e-06,
1879
+ "loss": 0.4837,
1880
+ "step": 312
1881
+ },
1882
+ {
1883
+ "epoch": 2.23,
1884
+ "learning_rate": 3.335506509148716e-06,
1885
+ "loss": 0.4979,
1886
+ "step": 313
1887
+ },
1888
+ {
1889
+ "epoch": 2.24,
1890
+ "learning_rate": 3.2781573302832493e-06,
1891
+ "loss": 0.4936,
1892
+ "step": 314
1893
+ },
1894
+ {
1895
+ "epoch": 2.25,
1896
+ "learning_rate": 3.221208646431949e-06,
1897
+ "loss": 0.4766,
1898
+ "step": 315
1899
+ },
1900
+ {
1901
+ "epoch": 2.25,
1902
+ "learning_rate": 3.1646638506620265e-06,
1903
+ "loss": 0.5223,
1904
+ "step": 316
1905
+ },
1906
+ {
1907
+ "epoch": 2.26,
1908
+ "learning_rate": 3.108526311976574e-06,
1909
+ "loss": 0.498,
1910
+ "step": 317
1911
+ },
1912
+ {
1913
+ "epoch": 2.27,
1914
+ "learning_rate": 3.0527993751138575e-06,
1915
+ "loss": 0.4948,
1916
+ "step": 318
1917
+ },
1918
+ {
1919
+ "epoch": 2.28,
1920
+ "learning_rate": 2.997486360348011e-06,
1921
+ "loss": 0.4607,
1922
+ "step": 319
1923
+ },
1924
+ {
1925
+ "epoch": 2.28,
1926
+ "learning_rate": 2.942590563291219e-06,
1927
+ "loss": 0.5286,
1928
+ "step": 320
1929
+ },
1930
+ {
1931
+ "epoch": 2.29,
1932
+ "learning_rate": 2.888115254697371e-06,
1933
+ "loss": 0.5225,
1934
+ "step": 321
1935
+ },
1936
+ {
1937
+ "epoch": 2.3,
1938
+ "learning_rate": 2.8340636802671716e-06,
1939
+ "loss": 0.4547,
1940
+ "step": 322
1941
+ },
1942
+ {
1943
+ "epoch": 2.3,
1944
+ "learning_rate": 2.780439060454756e-06,
1945
+ "loss": 0.4879,
1946
+ "step": 323
1947
+ },
1948
+ {
1949
+ "epoch": 2.31,
1950
+ "learning_rate": 2.727244590275834e-06,
1951
+ "loss": 0.5063,
1952
+ "step": 324
1953
+ },
1954
+ {
1955
+ "epoch": 2.32,
1956
+ "learning_rate": 2.674483439117296e-06,
1957
+ "loss": 0.5119,
1958
+ "step": 325
1959
+ },
1960
+ {
1961
+ "epoch": 2.32,
1962
+ "learning_rate": 2.622158750548407e-06,
1963
+ "loss": 0.5264,
1964
+ "step": 326
1965
+ },
1966
+ {
1967
+ "epoch": 2.33,
1968
+ "learning_rate": 2.5702736421334853e-06,
1969
+ "loss": 0.5035,
1970
+ "step": 327
1971
+ },
1972
+ {
1973
+ "epoch": 2.34,
1974
+ "learning_rate": 2.518831205246174e-06,
1975
+ "loss": 0.5364,
1976
+ "step": 328
1977
+ },
1978
+ {
1979
+ "epoch": 2.35,
1980
+ "learning_rate": 2.4678345048852326e-06,
1981
+ "loss": 0.4828,
1982
+ "step": 329
1983
+ },
1984
+ {
1985
+ "epoch": 2.35,
1986
+ "learning_rate": 2.4172865794919477e-06,
1987
+ "loss": 0.4919,
1988
+ "step": 330
1989
+ },
1990
+ {
1991
+ "epoch": 2.36,
1992
+ "learning_rate": 2.3671904407690704e-06,
1993
+ "loss": 0.5037,
1994
+ "step": 331
1995
+ },
1996
+ {
1997
+ "epoch": 2.37,
1998
+ "learning_rate": 2.317549073501396e-06,
1999
+ "loss": 0.5387,
2000
+ "step": 332
2001
+ },
2002
+ {
2003
+ "epoch": 2.37,
2004
+ "learning_rate": 2.268365435377915e-06,
2005
+ "loss": 0.4866,
2006
+ "step": 333
2007
+ },
2008
+ {
2009
+ "epoch": 2.38,
2010
+ "learning_rate": 2.2196424568156073e-06,
2011
+ "loss": 0.5168,
2012
+ "step": 334
2013
+ },
2014
+ {
2015
+ "epoch": 2.39,
2016
+ "learning_rate": 2.171383040784819e-06,
2017
+ "loss": 0.5497,
2018
+ "step": 335
2019
+ },
2020
+ {
2021
+ "epoch": 2.4,
2022
+ "learning_rate": 2.123590062636328e-06,
2023
+ "loss": 0.4872,
2024
+ "step": 336
2025
+ },
2026
+ {
2027
+ "epoch": 2.4,
2028
+ "learning_rate": 2.076266369930002e-06,
2029
+ "loss": 0.4733,
2030
+ "step": 337
2031
+ },
2032
+ {
2033
+ "epoch": 2.41,
2034
+ "learning_rate": 2.02941478226516e-06,
2035
+ "loss": 0.4585,
2036
+ "step": 338
2037
+ },
2038
+ {
2039
+ "epoch": 2.42,
2040
+ "learning_rate": 1.983038091112558e-06,
2041
+ "loss": 0.5143,
2042
+ "step": 339
2043
+ },
2044
+ {
2045
+ "epoch": 2.42,
2046
+ "learning_rate": 1.9371390596480865e-06,
2047
+ "loss": 0.5329,
2048
+ "step": 340
2049
+ },
2050
+ {
2051
+ "epoch": 2.43,
2052
+ "learning_rate": 1.8917204225881236e-06,
2053
+ "loss": 0.4934,
2054
+ "step": 341
2055
+ },
2056
+ {
2057
+ "epoch": 2.44,
2058
+ "learning_rate": 1.8467848860266047e-06,
2059
+ "loss": 0.5128,
2060
+ "step": 342
2061
+ },
2062
+ {
2063
+ "epoch": 2.45,
2064
+ "learning_rate": 1.8023351272737955e-06,
2065
+ "loss": 0.5159,
2066
+ "step": 343
2067
+ },
2068
+ {
2069
+ "epoch": 2.45,
2070
+ "learning_rate": 1.7583737946967606e-06,
2071
+ "loss": 0.5194,
2072
+ "step": 344
2073
+ },
2074
+ {
2075
+ "epoch": 2.46,
2076
+ "learning_rate": 1.7149035075615795e-06,
2077
+ "loss": 0.5457,
2078
+ "step": 345
2079
+ },
2080
+ {
2081
+ "epoch": 2.47,
2082
+ "learning_rate": 1.6719268558772927e-06,
2083
+ "loss": 0.4861,
2084
+ "step": 346
2085
+ },
2086
+ {
2087
+ "epoch": 2.47,
2088
+ "learning_rate": 1.6294464002415789e-06,
2089
+ "loss": 0.4779,
2090
+ "step": 347
2091
+ },
2092
+ {
2093
+ "epoch": 2.48,
2094
+ "learning_rate": 1.587464671688187e-06,
2095
+ "loss": 0.4923,
2096
+ "step": 348
2097
+ },
2098
+ {
2099
+ "epoch": 2.49,
2100
+ "learning_rate": 1.54598417153615e-06,
2101
+ "loss": 0.4961,
2102
+ "step": 349
2103
+ },
2104
+ {
2105
+ "epoch": 2.5,
2106
+ "learning_rate": 1.5050073712407354e-06,
2107
+ "loss": 0.5059,
2108
+ "step": 350
2109
+ },
2110
+ {
2111
+ "epoch": 2.5,
2112
+ "learning_rate": 1.464536712246205e-06,
2113
+ "loss": 0.504,
2114
+ "step": 351
2115
+ },
2116
+ {
2117
+ "epoch": 2.51,
2118
+ "learning_rate": 1.4245746058403464e-06,
2119
+ "loss": 0.489,
2120
+ "step": 352
2121
+ },
2122
+ {
2123
+ "epoch": 2.52,
2124
+ "learning_rate": 1.385123433010812e-06,
2125
+ "loss": 0.4703,
2126
+ "step": 353
2127
+ },
2128
+ {
2129
+ "epoch": 2.52,
2130
+ "learning_rate": 1.3461855443032456e-06,
2131
+ "loss": 0.5223,
2132
+ "step": 354
2133
+ },
2134
+ {
2135
+ "epoch": 2.53,
2136
+ "learning_rate": 1.3077632596812407e-06,
2137
+ "loss": 0.4904,
2138
+ "step": 355
2139
+ },
2140
+ {
2141
+ "epoch": 2.54,
2142
+ "learning_rate": 1.2698588683881185e-06,
2143
+ "loss": 0.4623,
2144
+ "step": 356
2145
+ },
2146
+ {
2147
+ "epoch": 2.55,
2148
+ "learning_rate": 1.2324746288105272e-06,
2149
+ "loss": 0.5149,
2150
+ "step": 357
2151
+ },
2152
+ {
2153
+ "epoch": 2.55,
2154
+ "learning_rate": 1.1956127683438822e-06,
2155
+ "loss": 0.4923,
2156
+ "step": 358
2157
+ },
2158
+ {
2159
+ "epoch": 2.56,
2160
+ "learning_rate": 1.1592754832596632e-06,
2161
+ "loss": 0.5164,
2162
+ "step": 359
2163
+ },
2164
+ {
2165
+ "epoch": 2.57,
2166
+ "learning_rate": 1.1234649385745488e-06,
2167
+ "loss": 0.5093,
2168
+ "step": 360
2169
+ },
2170
+ {
2171
+ "epoch": 2.57,
2172
+ "learning_rate": 1.0881832679214276e-06,
2173
+ "loss": 0.4929,
2174
+ "step": 361
2175
+ },
2176
+ {
2177
+ "epoch": 2.58,
2178
+ "learning_rate": 1.0534325734222773e-06,
2179
+ "loss": 0.5419,
2180
+ "step": 362
2181
+ },
2182
+ {
2183
+ "epoch": 2.59,
2184
+ "learning_rate": 1.0192149255629114e-06,
2185
+ "loss": 0.5164,
2186
+ "step": 363
2187
+ },
2188
+ {
2189
+ "epoch": 2.6,
2190
+ "learning_rate": 9.855323630696146e-07,
2191
+ "loss": 0.4707,
2192
+ "step": 364
2193
+ },
2194
+ {
2195
+ "epoch": 2.6,
2196
+ "learning_rate": 9.523868927876889e-07,
2197
+ "loss": 0.4744,
2198
+ "step": 365
2199
+ },
2200
+ {
2201
+ "epoch": 2.61,
2202
+ "learning_rate": 9.197804895618623e-07,
2203
+ "loss": 0.4753,
2204
+ "step": 366
2205
+ },
2206
+ {
2207
+ "epoch": 2.62,
2208
+ "learning_rate": 8.87715096118642e-07,
2209
+ "loss": 0.4882,
2210
+ "step": 367
2211
+ },
2212
+ {
2213
+ "epoch": 2.62,
2214
+ "learning_rate": 8.561926229505601e-07,
2215
+ "loss": 0.4818,
2216
+ "step": 368
2217
+ },
2218
+ {
2219
+ "epoch": 2.63,
2220
+ "learning_rate": 8.252149482023363e-07,
2221
+ "loss": 0.4743,
2222
+ "step": 369
2223
+ },
2224
+ {
2225
+ "epoch": 2.64,
2226
+ "learning_rate": 7.947839175589845e-07,
2227
+ "loss": 0.4877,
2228
+ "step": 370
2229
+ },
2230
+ {
2231
+ "epoch": 2.65,
2232
+ "learning_rate": 7.649013441358466e-07,
2233
+ "loss": 0.5093,
2234
+ "step": 371
2235
+ },
2236
+ {
2237
+ "epoch": 2.65,
2238
+ "learning_rate": 7.355690083705547e-07,
2239
+ "loss": 0.4711,
2240
+ "step": 372
2241
+ },
2242
+ {
2243
+ "epoch": 2.66,
2244
+ "learning_rate": 7.067886579169625e-07,
2245
+ "loss": 0.477,
2246
+ "step": 373
2247
+ },
2248
+ {
2249
+ "epoch": 2.67,
2250
+ "learning_rate": 6.78562007541006e-07,
2251
+ "loss": 0.4992,
2252
+ "step": 374
2253
+ },
2254
+ {
2255
+ "epoch": 2.67,
2256
+ "learning_rate": 6.508907390185504e-07,
2257
+ "loss": 0.4993,
2258
+ "step": 375
2259
+ },
2260
+ {
2261
+ "epoch": 2.68,
2262
+ "learning_rate": 6.237765010351715e-07,
2263
+ "loss": 0.466,
2264
+ "step": 376
2265
+ },
2266
+ {
2267
+ "epoch": 2.69,
2268
+ "learning_rate": 5.972209090879389e-07,
2269
+ "loss": 0.4727,
2270
+ "step": 377
2271
+ },
2272
+ {
2273
+ "epoch": 2.7,
2274
+ "learning_rate": 5.71225545389158e-07,
2275
+ "loss": 0.4927,
2276
+ "step": 378
2277
+ },
2278
+ {
2279
+ "epoch": 2.7,
2280
+ "learning_rate": 5.457919587720961e-07,
2281
+ "loss": 0.5099,
2282
+ "step": 379
2283
+ },
2284
+ {
2285
+ "epoch": 2.71,
2286
+ "learning_rate": 5.209216645987036e-07,
2287
+ "loss": 0.5217,
2288
+ "step": 380
2289
+ },
2290
+ {
2291
+ "epoch": 2.72,
2292
+ "learning_rate": 4.966161446693329e-07,
2293
+ "loss": 0.5118,
2294
+ "step": 381
2295
+ },
2296
+ {
2297
+ "epoch": 2.72,
2298
+ "learning_rate": 4.728768471344425e-07,
2299
+ "loss": 0.5118,
2300
+ "step": 382
2301
+ },
2302
+ {
2303
+ "epoch": 2.73,
2304
+ "learning_rate": 4.4970518640831687e-07,
2305
+ "loss": 0.5028,
2306
+ "step": 383
2307
+ },
2308
+ {
2309
+ "epoch": 2.74,
2310
+ "learning_rate": 4.271025430847986e-07,
2311
+ "loss": 0.4986,
2312
+ "step": 384
2313
+ },
2314
+ {
2315
+ "epoch": 2.75,
2316
+ "learning_rate": 4.0507026385502747e-07,
2317
+ "loss": 0.4744,
2318
+ "step": 385
2319
+ },
2320
+ {
2321
+ "epoch": 2.75,
2322
+ "learning_rate": 3.836096614271989e-07,
2323
+ "loss": 0.4928,
2324
+ "step": 386
2325
+ },
2326
+ {
2327
+ "epoch": 2.76,
2328
+ "learning_rate": 3.6272201444836006e-07,
2329
+ "loss": 0.467,
2330
+ "step": 387
2331
+ },
2332
+ {
2333
+ "epoch": 2.77,
2334
+ "learning_rate": 3.424085674282229e-07,
2335
+ "loss": 0.4756,
2336
+ "step": 388
2337
+ },
2338
+ {
2339
+ "epoch": 2.77,
2340
+ "learning_rate": 3.226705306650113e-07,
2341
+ "loss": 0.5302,
2342
+ "step": 389
2343
+ },
2344
+ {
2345
+ "epoch": 2.78,
2346
+ "learning_rate": 3.0350908017335423e-07,
2347
+ "loss": 0.4687,
2348
+ "step": 390
2349
+ },
2350
+ {
2351
+ "epoch": 2.79,
2352
+ "learning_rate": 2.8492535761421635e-07,
2353
+ "loss": 0.4699,
2354
+ "step": 391
2355
+ },
2356
+ {
2357
+ "epoch": 2.8,
2358
+ "learning_rate": 2.6692047022687684e-07,
2359
+ "loss": 0.472,
2360
+ "step": 392
2361
+ },
2362
+ {
2363
+ "epoch": 2.8,
2364
+ "learning_rate": 2.494954907629565e-07,
2365
+ "loss": 0.5102,
2366
+ "step": 393
2367
+ },
2368
+ {
2369
+ "epoch": 2.81,
2370
+ "learning_rate": 2.3265145742250694e-07,
2371
+ "loss": 0.4985,
2372
+ "step": 394
2373
+ },
2374
+ {
2375
+ "epoch": 2.82,
2376
+ "learning_rate": 2.1638937379214852e-07,
2377
+ "loss": 0.4999,
2378
+ "step": 395
2379
+ },
2380
+ {
2381
+ "epoch": 2.82,
2382
+ "learning_rate": 2.0071020878527857e-07,
2383
+ "loss": 0.4821,
2384
+ "step": 396
2385
+ },
2386
+ {
2387
+ "epoch": 2.83,
2388
+ "learning_rate": 1.8561489658433963e-07,
2389
+ "loss": 0.5049,
2390
+ "step": 397
2391
+ },
2392
+ {
2393
+ "epoch": 2.84,
2394
+ "learning_rate": 1.711043365851639e-07,
2395
+ "loss": 0.4672,
2396
+ "step": 398
2397
+ },
2398
+ {
2399
+ "epoch": 2.85,
2400
+ "learning_rate": 1.5717939334338184e-07,
2401
+ "loss": 0.5159,
2402
+ "step": 399
2403
+ },
2404
+ {
2405
+ "epoch": 2.85,
2406
+ "learning_rate": 1.4384089652291544e-07,
2407
+ "loss": 0.4481,
2408
+ "step": 400
2409
+ },
2410
+ {
2411
+ "epoch": 2.86,
2412
+ "learning_rate": 1.310896408465401e-07,
2413
+ "loss": 0.4825,
2414
+ "step": 401
2415
+ },
2416
+ {
2417
+ "epoch": 2.87,
2418
+ "learning_rate": 1.1892638604853901e-07,
2419
+ "loss": 0.4974,
2420
+ "step": 402
2421
+ },
2422
+ {
2423
+ "epoch": 2.87,
2424
+ "learning_rate": 1.0735185682943628e-07,
2425
+ "loss": 0.5136,
2426
+ "step": 403
2427
+ },
2428
+ {
2429
+ "epoch": 2.88,
2430
+ "learning_rate": 9.636674281281788e-08,
2431
+ "loss": 0.4991,
2432
+ "step": 404
2433
+ },
2434
+ {
2435
+ "epoch": 2.89,
2436
+ "learning_rate": 8.597169850424136e-08,
2437
+ "loss": 0.4636,
2438
+ "step": 405
2439
+ },
2440
+ {
2441
+ "epoch": 2.9,
2442
+ "learning_rate": 7.616734325224473e-08,
2443
+ "loss": 0.5009,
2444
+ "step": 406
2445
+ },
2446
+ {
2447
+ "epoch": 2.9,
2448
+ "learning_rate": 6.69542612114371e-08,
2449
+ "loss": 0.4814,
2450
+ "step": 407
2451
+ },
2452
+ {
2453
+ "epoch": 2.91,
2454
+ "learning_rate": 5.833300130770436e-08,
2455
+ "loss": 0.4765,
2456
+ "step": 408
2457
+ },
2458
+ {
2459
+ "epoch": 2.92,
2460
+ "learning_rate": 5.030407720549413e-08,
2461
+ "loss": 0.4909,
2462
+ "step": 409
2463
+ },
2464
+ {
2465
+ "epoch": 2.92,
2466
+ "learning_rate": 4.286796727721476e-08,
2467
+ "loss": 0.4783,
2468
+ "step": 410
2469
+ },
2470
+ {
2471
+ "epoch": 2.93,
2472
+ "learning_rate": 3.602511457473479e-08,
2473
+ "loss": 0.493,
2474
+ "step": 411
2475
+ },
2476
+ {
2477
+ "epoch": 2.94,
2478
+ "learning_rate": 2.9775926802984022e-08,
2479
+ "loss": 0.4648,
2480
+ "step": 412
2481
+ },
2482
+ {
2483
+ "epoch": 2.95,
2484
+ "learning_rate": 2.4120776295659675e-08,
2485
+ "loss": 0.4917,
2486
+ "step": 413
2487
+ },
2488
+ {
2489
+ "epoch": 2.95,
2490
+ "learning_rate": 1.905999999304853e-08,
2491
+ "loss": 0.4844,
2492
+ "step": 414
2493
+ },
2494
+ {
2495
+ "epoch": 2.96,
2496
+ "learning_rate": 1.4593899421943003e-08,
2497
+ "loss": 0.4925,
2498
+ "step": 415
2499
+ },
2500
+ {
2501
+ "epoch": 2.97,
2502
+ "learning_rate": 1.0722740677685529e-08,
2503
+ "loss": 0.4803,
2504
+ "step": 416
2505
+ },
2506
+ {
2507
+ "epoch": 2.97,
2508
+ "learning_rate": 7.4467544083067776e-09,
2509
+ "loss": 0.4579,
2510
+ "step": 417
2511
+ },
2512
+ {
2513
+ "epoch": 2.98,
2514
+ "learning_rate": 4.766135800785554e-09,
2515
+ "loss": 0.4739,
2516
+ "step": 418
2517
+ },
2518
+ {
2519
+ "epoch": 2.99,
2520
+ "learning_rate": 2.68104456942031e-09,
2521
+ "loss": 0.5126,
2522
+ "step": 419
2523
+ },
2524
+ {
2525
+ "epoch": 3.0,
2526
+ "learning_rate": 1.1916049463134293e-09,
2527
+ "loss": 0.4761,
2528
+ "step": 420
2529
+ },
2530
+ {
2531
+ "epoch": 3.0,
2532
+ "step": 420,
2533
+ "total_flos": 1.7711353317818368e+17,
2534
+ "train_loss": 0.6881538674944923,
2535
+ "train_runtime": 11850.5144,
2536
+ "train_samples_per_second": 18.172,
2537
+ "train_steps_per_second": 0.035
2538
+ }
2539
+ ],
2540
+ "max_steps": 420,
2541
+ "num_train_epochs": 3,
2542
+ "total_flos": 1.7711353317818368e+17,
2543
+ "trial_name": null,
2544
+ "trial_params": null
2545
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d393098e52facaab695c8a5a28ff25d2c56b92016e757bdb1c154c1835d15399
3
+ size 3707