Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- llama1b_fw10b_0401/checkpoint-4000/config.json +37 -0
- llama1b_fw10b_0401/checkpoint-4000/data_index.npy +3 -0
- llama1b_fw10b_0401/checkpoint-4000/generation_config.json +9 -0
- llama1b_fw10b_0401/checkpoint-4000/model.safetensors +3 -0
- llama1b_fw10b_0401/checkpoint-4000/special_tokens_map.json +16 -0
- llama1b_fw10b_0401/checkpoint-4000/tokenizer.json +3 -0
- llama1b_fw10b_0401/checkpoint-4000/tokenizer_config.json +2065 -0
- llama1b_fw10b_0401/checkpoint-4000/trainer_state.json +2833 -0
- llama1b_fw10b_0401/checkpoint-4000/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -46,3 +46,4 @@ qwen05b_30b_0326/checkpoint-114000/tokenizer.json filter=lfs diff=lfs merge=lfs
|
|
| 46 |
qwen15b_30b_0325/checkpoint-96000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
llama8b_10b_0405/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
llama1b_10b/checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 46 |
qwen15b_30b_0325/checkpoint-96000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
llama8b_10b_0405/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
llama1b_10b/checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
llama1b_fw10b_0401/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
llama1b_fw10b_0401/checkpoint-4000/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 16,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": {
|
| 24 |
+
"factor": 32.0,
|
| 25 |
+
"high_freq_factor": 4.0,
|
| 26 |
+
"low_freq_factor": 1.0,
|
| 27 |
+
"original_max_position_embeddings": 8192,
|
| 28 |
+
"rope_type": "llama3"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 500000.0,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.49.0",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"vocab_size": 128256,
|
| 36 |
+
"w_bits": 2
|
| 37 |
+
}
|
llama1b_fw10b_0401/checkpoint-4000/data_index.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f41b1ac79886656ce6276c34b948e301306ea308886773820f616db791d9fde
|
| 3 |
+
size 136
|
llama1b_fw10b_0401/checkpoint-4000/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "4.49.0"
|
| 9 |
+
}
|
llama1b_fw10b_0401/checkpoint-4000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d14f65a72e9b2169b9653e123d5a716329a6434f6a44a65205a8e37ce8947d
|
| 3 |
+
size 2472412832
|
llama1b_fw10b_0401/checkpoint-4000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
+
}
|
llama1b_fw10b_0401/checkpoint-4000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
llama1b_fw10b_0401/checkpoint-4000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"128000": {
|
| 6 |
+
"content": "<|begin_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"128001": {
|
| 14 |
+
"content": "<|end_of_text|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"128002": {
|
| 22 |
+
"content": "<|reserved_special_token_0|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"128003": {
|
| 30 |
+
"content": "<|reserved_special_token_1|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"128004": {
|
| 38 |
+
"content": "<|finetune_right_pad_id|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"128005": {
|
| 46 |
+
"content": "<|reserved_special_token_2|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"128006": {
|
| 54 |
+
"content": "<|start_header_id|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"128007": {
|
| 62 |
+
"content": "<|end_header_id|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"128008": {
|
| 70 |
+
"content": "<|eom_id|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"128009": {
|
| 78 |
+
"content": "<|eot_id|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"128010": {
|
| 86 |
+
"content": "<|python_tag|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"128011": {
|
| 94 |
+
"content": "<|reserved_special_token_3|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"128012": {
|
| 102 |
+
"content": "<|reserved_special_token_4|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"128013": {
|
| 110 |
+
"content": "<|reserved_special_token_5|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"128014": {
|
| 118 |
+
"content": "<|reserved_special_token_6|>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"128015": {
|
| 126 |
+
"content": "<|reserved_special_token_7|>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"128016": {
|
| 134 |
+
"content": "<|reserved_special_token_8|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"128017": {
|
| 142 |
+
"content": "<|reserved_special_token_9|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"128018": {
|
| 150 |
+
"content": "<|reserved_special_token_10|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"128019": {
|
| 158 |
+
"content": "<|reserved_special_token_11|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"128020": {
|
| 166 |
+
"content": "<|reserved_special_token_12|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"128021": {
|
| 174 |
+
"content": "<|reserved_special_token_13|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"128022": {
|
| 182 |
+
"content": "<|reserved_special_token_14|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"128023": {
|
| 190 |
+
"content": "<|reserved_special_token_15|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"128024": {
|
| 198 |
+
"content": "<|reserved_special_token_16|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"128025": {
|
| 206 |
+
"content": "<|reserved_special_token_17|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"128026": {
|
| 214 |
+
"content": "<|reserved_special_token_18|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"128027": {
|
| 222 |
+
"content": "<|reserved_special_token_19|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"128028": {
|
| 230 |
+
"content": "<|reserved_special_token_20|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"128029": {
|
| 238 |
+
"content": "<|reserved_special_token_21|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"128030": {
|
| 246 |
+
"content": "<|reserved_special_token_22|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"128031": {
|
| 254 |
+
"content": "<|reserved_special_token_23|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"128032": {
|
| 262 |
+
"content": "<|reserved_special_token_24|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"128033": {
|
| 270 |
+
"content": "<|reserved_special_token_25|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"128034": {
|
| 278 |
+
"content": "<|reserved_special_token_26|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"128035": {
|
| 286 |
+
"content": "<|reserved_special_token_27|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"128036": {
|
| 294 |
+
"content": "<|reserved_special_token_28|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"128037": {
|
| 302 |
+
"content": "<|reserved_special_token_29|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"128038": {
|
| 310 |
+
"content": "<|reserved_special_token_30|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"128039": {
|
| 318 |
+
"content": "<|reserved_special_token_31|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"128040": {
|
| 326 |
+
"content": "<|reserved_special_token_32|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"128041": {
|
| 334 |
+
"content": "<|reserved_special_token_33|>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"128042": {
|
| 342 |
+
"content": "<|reserved_special_token_34|>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"128043": {
|
| 350 |
+
"content": "<|reserved_special_token_35|>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"128044": {
|
| 358 |
+
"content": "<|reserved_special_token_36|>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"128045": {
|
| 366 |
+
"content": "<|reserved_special_token_37|>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"128046": {
|
| 374 |
+
"content": "<|reserved_special_token_38|>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"128047": {
|
| 382 |
+
"content": "<|reserved_special_token_39|>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"128048": {
|
| 390 |
+
"content": "<|reserved_special_token_40|>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"128049": {
|
| 398 |
+
"content": "<|reserved_special_token_41|>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"128050": {
|
| 406 |
+
"content": "<|reserved_special_token_42|>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"128051": {
|
| 414 |
+
"content": "<|reserved_special_token_43|>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"128052": {
|
| 422 |
+
"content": "<|reserved_special_token_44|>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"128053": {
|
| 430 |
+
"content": "<|reserved_special_token_45|>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"128054": {
|
| 438 |
+
"content": "<|reserved_special_token_46|>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"128055": {
|
| 446 |
+
"content": "<|reserved_special_token_47|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"128056": {
|
| 454 |
+
"content": "<|reserved_special_token_48|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"128057": {
|
| 462 |
+
"content": "<|reserved_special_token_49|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"128058": {
|
| 470 |
+
"content": "<|reserved_special_token_50|>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"128059": {
|
| 478 |
+
"content": "<|reserved_special_token_51|>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"128060": {
|
| 486 |
+
"content": "<|reserved_special_token_52|>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"128061": {
|
| 494 |
+
"content": "<|reserved_special_token_53|>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"128062": {
|
| 502 |
+
"content": "<|reserved_special_token_54|>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"128063": {
|
| 510 |
+
"content": "<|reserved_special_token_55|>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"128064": {
|
| 518 |
+
"content": "<|reserved_special_token_56|>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"128065": {
|
| 526 |
+
"content": "<|reserved_special_token_57|>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"128066": {
|
| 534 |
+
"content": "<|reserved_special_token_58|>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"128067": {
|
| 542 |
+
"content": "<|reserved_special_token_59|>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"128068": {
|
| 550 |
+
"content": "<|reserved_special_token_60|>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"128069": {
|
| 558 |
+
"content": "<|reserved_special_token_61|>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"128070": {
|
| 566 |
+
"content": "<|reserved_special_token_62|>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"128071": {
|
| 574 |
+
"content": "<|reserved_special_token_63|>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"128072": {
|
| 582 |
+
"content": "<|reserved_special_token_64|>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"128073": {
|
| 590 |
+
"content": "<|reserved_special_token_65|>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"128074": {
|
| 598 |
+
"content": "<|reserved_special_token_66|>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"128075": {
|
| 606 |
+
"content": "<|reserved_special_token_67|>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"128076": {
|
| 614 |
+
"content": "<|reserved_special_token_68|>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"128077": {
|
| 622 |
+
"content": "<|reserved_special_token_69|>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"128078": {
|
| 630 |
+
"content": "<|reserved_special_token_70|>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"128079": {
|
| 638 |
+
"content": "<|reserved_special_token_71|>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"128080": {
|
| 646 |
+
"content": "<|reserved_special_token_72|>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"128081": {
|
| 654 |
+
"content": "<|reserved_special_token_73|>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"128082": {
|
| 662 |
+
"content": "<|reserved_special_token_74|>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"128083": {
|
| 670 |
+
"content": "<|reserved_special_token_75|>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"128084": {
|
| 678 |
+
"content": "<|reserved_special_token_76|>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"128085": {
|
| 686 |
+
"content": "<|reserved_special_token_77|>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"128086": {
|
| 694 |
+
"content": "<|reserved_special_token_78|>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"128087": {
|
| 702 |
+
"content": "<|reserved_special_token_79|>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"128088": {
|
| 710 |
+
"content": "<|reserved_special_token_80|>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"128089": {
|
| 718 |
+
"content": "<|reserved_special_token_81|>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"128090": {
|
| 726 |
+
"content": "<|reserved_special_token_82|>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"128091": {
|
| 734 |
+
"content": "<|reserved_special_token_83|>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"128092": {
|
| 742 |
+
"content": "<|reserved_special_token_84|>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"128093": {
|
| 750 |
+
"content": "<|reserved_special_token_85|>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"128094": {
|
| 758 |
+
"content": "<|reserved_special_token_86|>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"128095": {
|
| 766 |
+
"content": "<|reserved_special_token_87|>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
},
|
| 773 |
+
"128096": {
|
| 774 |
+
"content": "<|reserved_special_token_88|>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": true
|
| 780 |
+
},
|
| 781 |
+
"128097": {
|
| 782 |
+
"content": "<|reserved_special_token_89|>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
"128098": {
|
| 790 |
+
"content": "<|reserved_special_token_90|>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": true
|
| 796 |
+
},
|
| 797 |
+
"128099": {
|
| 798 |
+
"content": "<|reserved_special_token_91|>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": true
|
| 804 |
+
},
|
| 805 |
+
"128100": {
|
| 806 |
+
"content": "<|reserved_special_token_92|>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": true
|
| 812 |
+
},
|
| 813 |
+
"128101": {
|
| 814 |
+
"content": "<|reserved_special_token_93|>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
"128102": {
|
| 822 |
+
"content": "<|reserved_special_token_94|>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": true
|
| 828 |
+
},
|
| 829 |
+
"128103": {
|
| 830 |
+
"content": "<|reserved_special_token_95|>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": true
|
| 836 |
+
},
|
| 837 |
+
"128104": {
|
| 838 |
+
"content": "<|reserved_special_token_96|>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": true
|
| 844 |
+
},
|
| 845 |
+
"128105": {
|
| 846 |
+
"content": "<|reserved_special_token_97|>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": true
|
| 852 |
+
},
|
| 853 |
+
"128106": {
|
| 854 |
+
"content": "<|reserved_special_token_98|>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"128107": {
|
| 862 |
+
"content": "<|reserved_special_token_99|>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"128108": {
|
| 870 |
+
"content": "<|reserved_special_token_100|>",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": true
|
| 876 |
+
},
|
| 877 |
+
"128109": {
|
| 878 |
+
"content": "<|reserved_special_token_101|>",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": true
|
| 884 |
+
},
|
| 885 |
+
"128110": {
|
| 886 |
+
"content": "<|reserved_special_token_102|>",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": true
|
| 892 |
+
},
|
| 893 |
+
"128111": {
|
| 894 |
+
"content": "<|reserved_special_token_103|>",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": true
|
| 900 |
+
},
|
| 901 |
+
"128112": {
|
| 902 |
+
"content": "<|reserved_special_token_104|>",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": true
|
| 908 |
+
},
|
| 909 |
+
"128113": {
|
| 910 |
+
"content": "<|reserved_special_token_105|>",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": true
|
| 916 |
+
},
|
| 917 |
+
"128114": {
|
| 918 |
+
"content": "<|reserved_special_token_106|>",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": true
|
| 924 |
+
},
|
| 925 |
+
"128115": {
|
| 926 |
+
"content": "<|reserved_special_token_107|>",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": true
|
| 932 |
+
},
|
| 933 |
+
"128116": {
|
| 934 |
+
"content": "<|reserved_special_token_108|>",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": true
|
| 940 |
+
},
|
| 941 |
+
"128117": {
|
| 942 |
+
"content": "<|reserved_special_token_109|>",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": true
|
| 948 |
+
},
|
| 949 |
+
"128118": {
|
| 950 |
+
"content": "<|reserved_special_token_110|>",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": true
|
| 956 |
+
},
|
| 957 |
+
"128119": {
|
| 958 |
+
"content": "<|reserved_special_token_111|>",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": true
|
| 964 |
+
},
|
| 965 |
+
"128120": {
|
| 966 |
+
"content": "<|reserved_special_token_112|>",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": true
|
| 972 |
+
},
|
| 973 |
+
"128121": {
|
| 974 |
+
"content": "<|reserved_special_token_113|>",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": true
|
| 980 |
+
},
|
| 981 |
+
"128122": {
|
| 982 |
+
"content": "<|reserved_special_token_114|>",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": true
|
| 988 |
+
},
|
| 989 |
+
"128123": {
|
| 990 |
+
"content": "<|reserved_special_token_115|>",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": true
|
| 996 |
+
},
|
| 997 |
+
"128124": {
|
| 998 |
+
"content": "<|reserved_special_token_116|>",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": true
|
| 1004 |
+
},
|
| 1005 |
+
"128125": {
|
| 1006 |
+
"content": "<|reserved_special_token_117|>",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": true
|
| 1012 |
+
},
|
| 1013 |
+
"128126": {
|
| 1014 |
+
"content": "<|reserved_special_token_118|>",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": true
|
| 1020 |
+
},
|
| 1021 |
+
"128127": {
|
| 1022 |
+
"content": "<|reserved_special_token_119|>",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": true
|
| 1028 |
+
},
|
| 1029 |
+
"128128": {
|
| 1030 |
+
"content": "<|reserved_special_token_120|>",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": true
|
| 1036 |
+
},
|
| 1037 |
+
"128129": {
|
| 1038 |
+
"content": "<|reserved_special_token_121|>",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": true
|
| 1044 |
+
},
|
| 1045 |
+
"128130": {
|
| 1046 |
+
"content": "<|reserved_special_token_122|>",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": true
|
| 1052 |
+
},
|
| 1053 |
+
"128131": {
|
| 1054 |
+
"content": "<|reserved_special_token_123|>",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": true
|
| 1060 |
+
},
|
| 1061 |
+
"128132": {
|
| 1062 |
+
"content": "<|reserved_special_token_124|>",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": true
|
| 1068 |
+
},
|
| 1069 |
+
"128133": {
|
| 1070 |
+
"content": "<|reserved_special_token_125|>",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": true
|
| 1076 |
+
},
|
| 1077 |
+
"128134": {
|
| 1078 |
+
"content": "<|reserved_special_token_126|>",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": true
|
| 1084 |
+
},
|
| 1085 |
+
"128135": {
|
| 1086 |
+
"content": "<|reserved_special_token_127|>",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": true
|
| 1092 |
+
},
|
| 1093 |
+
"128136": {
|
| 1094 |
+
"content": "<|reserved_special_token_128|>",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": true
|
| 1100 |
+
},
|
| 1101 |
+
"128137": {
|
| 1102 |
+
"content": "<|reserved_special_token_129|>",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": true
|
| 1108 |
+
},
|
| 1109 |
+
"128138": {
|
| 1110 |
+
"content": "<|reserved_special_token_130|>",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": true
|
| 1116 |
+
},
|
| 1117 |
+
"128139": {
|
| 1118 |
+
"content": "<|reserved_special_token_131|>",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": true
|
| 1124 |
+
},
|
| 1125 |
+
"128140": {
|
| 1126 |
+
"content": "<|reserved_special_token_132|>",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": true
|
| 1132 |
+
},
|
| 1133 |
+
"128141": {
|
| 1134 |
+
"content": "<|reserved_special_token_133|>",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": true
|
| 1140 |
+
},
|
| 1141 |
+
"128142": {
|
| 1142 |
+
"content": "<|reserved_special_token_134|>",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": true
|
| 1148 |
+
},
|
| 1149 |
+
"128143": {
|
| 1150 |
+
"content": "<|reserved_special_token_135|>",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": true
|
| 1156 |
+
},
|
| 1157 |
+
"128144": {
|
| 1158 |
+
"content": "<|reserved_special_token_136|>",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": true
|
| 1164 |
+
},
|
| 1165 |
+
"128145": {
|
| 1166 |
+
"content": "<|reserved_special_token_137|>",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": true
|
| 1172 |
+
},
|
| 1173 |
+
"128146": {
|
| 1174 |
+
"content": "<|reserved_special_token_138|>",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": true
|
| 1180 |
+
},
|
| 1181 |
+
"128147": {
|
| 1182 |
+
"content": "<|reserved_special_token_139|>",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": true
|
| 1188 |
+
},
|
| 1189 |
+
"128148": {
|
| 1190 |
+
"content": "<|reserved_special_token_140|>",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": true
|
| 1196 |
+
},
|
| 1197 |
+
"128149": {
|
| 1198 |
+
"content": "<|reserved_special_token_141|>",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": true
|
| 1204 |
+
},
|
| 1205 |
+
"128150": {
|
| 1206 |
+
"content": "<|reserved_special_token_142|>",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": true
|
| 1212 |
+
},
|
| 1213 |
+
"128151": {
|
| 1214 |
+
"content": "<|reserved_special_token_143|>",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": true
|
| 1220 |
+
},
|
| 1221 |
+
"128152": {
|
| 1222 |
+
"content": "<|reserved_special_token_144|>",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": true
|
| 1228 |
+
},
|
| 1229 |
+
"128153": {
|
| 1230 |
+
"content": "<|reserved_special_token_145|>",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": true
|
| 1236 |
+
},
|
| 1237 |
+
"128154": {
|
| 1238 |
+
"content": "<|reserved_special_token_146|>",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": true
|
| 1244 |
+
},
|
| 1245 |
+
"128155": {
|
| 1246 |
+
"content": "<|reserved_special_token_147|>",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": true
|
| 1252 |
+
},
|
| 1253 |
+
"128156": {
|
| 1254 |
+
"content": "<|reserved_special_token_148|>",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": true
|
| 1260 |
+
},
|
| 1261 |
+
"128157": {
|
| 1262 |
+
"content": "<|reserved_special_token_149|>",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": true
|
| 1268 |
+
},
|
| 1269 |
+
"128158": {
|
| 1270 |
+
"content": "<|reserved_special_token_150|>",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": true
|
| 1276 |
+
},
|
| 1277 |
+
"128159": {
|
| 1278 |
+
"content": "<|reserved_special_token_151|>",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": true
|
| 1284 |
+
},
|
| 1285 |
+
"128160": {
|
| 1286 |
+
"content": "<|reserved_special_token_152|>",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": true
|
| 1292 |
+
},
|
| 1293 |
+
"128161": {
|
| 1294 |
+
"content": "<|reserved_special_token_153|>",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": true
|
| 1300 |
+
},
|
| 1301 |
+
"128162": {
|
| 1302 |
+
"content": "<|reserved_special_token_154|>",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": true
|
| 1308 |
+
},
|
| 1309 |
+
"128163": {
|
| 1310 |
+
"content": "<|reserved_special_token_155|>",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": true
|
| 1316 |
+
},
|
| 1317 |
+
"128164": {
|
| 1318 |
+
"content": "<|reserved_special_token_156|>",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": true
|
| 1324 |
+
},
|
| 1325 |
+
"128165": {
|
| 1326 |
+
"content": "<|reserved_special_token_157|>",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": true
|
| 1332 |
+
},
|
| 1333 |
+
"128166": {
|
| 1334 |
+
"content": "<|reserved_special_token_158|>",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": true
|
| 1340 |
+
},
|
| 1341 |
+
"128167": {
|
| 1342 |
+
"content": "<|reserved_special_token_159|>",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": true
|
| 1348 |
+
},
|
| 1349 |
+
"128168": {
|
| 1350 |
+
"content": "<|reserved_special_token_160|>",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": true
|
| 1356 |
+
},
|
| 1357 |
+
"128169": {
|
| 1358 |
+
"content": "<|reserved_special_token_161|>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": true
|
| 1364 |
+
},
|
| 1365 |
+
"128170": {
|
| 1366 |
+
"content": "<|reserved_special_token_162|>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": true
|
| 1372 |
+
},
|
| 1373 |
+
"128171": {
|
| 1374 |
+
"content": "<|reserved_special_token_163|>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": true
|
| 1380 |
+
},
|
| 1381 |
+
"128172": {
|
| 1382 |
+
"content": "<|reserved_special_token_164|>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": true
|
| 1388 |
+
},
|
| 1389 |
+
"128173": {
|
| 1390 |
+
"content": "<|reserved_special_token_165|>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": true
|
| 1396 |
+
},
|
| 1397 |
+
"128174": {
|
| 1398 |
+
"content": "<|reserved_special_token_166|>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": true
|
| 1404 |
+
},
|
| 1405 |
+
"128175": {
|
| 1406 |
+
"content": "<|reserved_special_token_167|>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": true
|
| 1412 |
+
},
|
| 1413 |
+
"128176": {
|
| 1414 |
+
"content": "<|reserved_special_token_168|>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": true
|
| 1420 |
+
},
|
| 1421 |
+
"128177": {
|
| 1422 |
+
"content": "<|reserved_special_token_169|>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": true
|
| 1428 |
+
},
|
| 1429 |
+
"128178": {
|
| 1430 |
+
"content": "<|reserved_special_token_170|>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": true
|
| 1436 |
+
},
|
| 1437 |
+
"128179": {
|
| 1438 |
+
"content": "<|reserved_special_token_171|>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": true
|
| 1444 |
+
},
|
| 1445 |
+
"128180": {
|
| 1446 |
+
"content": "<|reserved_special_token_172|>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": true
|
| 1452 |
+
},
|
| 1453 |
+
"128181": {
|
| 1454 |
+
"content": "<|reserved_special_token_173|>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": true
|
| 1460 |
+
},
|
| 1461 |
+
"128182": {
|
| 1462 |
+
"content": "<|reserved_special_token_174|>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": true
|
| 1468 |
+
},
|
| 1469 |
+
"128183": {
|
| 1470 |
+
"content": "<|reserved_special_token_175|>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": true
|
| 1476 |
+
},
|
| 1477 |
+
"128184": {
|
| 1478 |
+
"content": "<|reserved_special_token_176|>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": true
|
| 1484 |
+
},
|
| 1485 |
+
"128185": {
|
| 1486 |
+
"content": "<|reserved_special_token_177|>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": true
|
| 1492 |
+
},
|
| 1493 |
+
"128186": {
|
| 1494 |
+
"content": "<|reserved_special_token_178|>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": true
|
| 1500 |
+
},
|
| 1501 |
+
"128187": {
|
| 1502 |
+
"content": "<|reserved_special_token_179|>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": true
|
| 1508 |
+
},
|
| 1509 |
+
"128188": {
|
| 1510 |
+
"content": "<|reserved_special_token_180|>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": true
|
| 1516 |
+
},
|
| 1517 |
+
"128189": {
|
| 1518 |
+
"content": "<|reserved_special_token_181|>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": true
|
| 1524 |
+
},
|
| 1525 |
+
"128190": {
|
| 1526 |
+
"content": "<|reserved_special_token_182|>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": true
|
| 1532 |
+
},
|
| 1533 |
+
"128191": {
|
| 1534 |
+
"content": "<|reserved_special_token_183|>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": true
|
| 1540 |
+
},
|
| 1541 |
+
"128192": {
|
| 1542 |
+
"content": "<|reserved_special_token_184|>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": true
|
| 1548 |
+
},
|
| 1549 |
+
"128193": {
|
| 1550 |
+
"content": "<|reserved_special_token_185|>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": true
|
| 1556 |
+
},
|
| 1557 |
+
"128194": {
|
| 1558 |
+
"content": "<|reserved_special_token_186|>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": true
|
| 1564 |
+
},
|
| 1565 |
+
"128195": {
|
| 1566 |
+
"content": "<|reserved_special_token_187|>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": true
|
| 1572 |
+
},
|
| 1573 |
+
"128196": {
|
| 1574 |
+
"content": "<|reserved_special_token_188|>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": true
|
| 1580 |
+
},
|
| 1581 |
+
"128197": {
|
| 1582 |
+
"content": "<|reserved_special_token_189|>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": true
|
| 1588 |
+
},
|
| 1589 |
+
"128198": {
|
| 1590 |
+
"content": "<|reserved_special_token_190|>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": true
|
| 1596 |
+
},
|
| 1597 |
+
"128199": {
|
| 1598 |
+
"content": "<|reserved_special_token_191|>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": true
|
| 1604 |
+
},
|
| 1605 |
+
"128200": {
|
| 1606 |
+
"content": "<|reserved_special_token_192|>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": true
|
| 1612 |
+
},
|
| 1613 |
+
"128201": {
|
| 1614 |
+
"content": "<|reserved_special_token_193|>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": true
|
| 1620 |
+
},
|
| 1621 |
+
"128202": {
|
| 1622 |
+
"content": "<|reserved_special_token_194|>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": true
|
| 1628 |
+
},
|
| 1629 |
+
"128203": {
|
| 1630 |
+
"content": "<|reserved_special_token_195|>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": true
|
| 1636 |
+
},
|
| 1637 |
+
"128204": {
|
| 1638 |
+
"content": "<|reserved_special_token_196|>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": true
|
| 1644 |
+
},
|
| 1645 |
+
"128205": {
|
| 1646 |
+
"content": "<|reserved_special_token_197|>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": true
|
| 1652 |
+
},
|
| 1653 |
+
"128206": {
|
| 1654 |
+
"content": "<|reserved_special_token_198|>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": true
|
| 1660 |
+
},
|
| 1661 |
+
"128207": {
|
| 1662 |
+
"content": "<|reserved_special_token_199|>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": true
|
| 1668 |
+
},
|
| 1669 |
+
"128208": {
|
| 1670 |
+
"content": "<|reserved_special_token_200|>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": true
|
| 1676 |
+
},
|
| 1677 |
+
"128209": {
|
| 1678 |
+
"content": "<|reserved_special_token_201|>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": true
|
| 1684 |
+
},
|
| 1685 |
+
"128210": {
|
| 1686 |
+
"content": "<|reserved_special_token_202|>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": true
|
| 1692 |
+
},
|
| 1693 |
+
"128211": {
|
| 1694 |
+
"content": "<|reserved_special_token_203|>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": true
|
| 1700 |
+
},
|
| 1701 |
+
"128212": {
|
| 1702 |
+
"content": "<|reserved_special_token_204|>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": true
|
| 1708 |
+
},
|
| 1709 |
+
"128213": {
|
| 1710 |
+
"content": "<|reserved_special_token_205|>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": true
|
| 1716 |
+
},
|
| 1717 |
+
"128214": {
|
| 1718 |
+
"content": "<|reserved_special_token_206|>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": true
|
| 1724 |
+
},
|
| 1725 |
+
"128215": {
|
| 1726 |
+
"content": "<|reserved_special_token_207|>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": true
|
| 1732 |
+
},
|
| 1733 |
+
"128216": {
|
| 1734 |
+
"content": "<|reserved_special_token_208|>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": true
|
| 1740 |
+
},
|
| 1741 |
+
"128217": {
|
| 1742 |
+
"content": "<|reserved_special_token_209|>",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": true
|
| 1748 |
+
},
|
| 1749 |
+
"128218": {
|
| 1750 |
+
"content": "<|reserved_special_token_210|>",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": true
|
| 1756 |
+
},
|
| 1757 |
+
"128219": {
|
| 1758 |
+
"content": "<|reserved_special_token_211|>",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": true
|
| 1764 |
+
},
|
| 1765 |
+
"128220": {
|
| 1766 |
+
"content": "<|reserved_special_token_212|>",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": true
|
| 1772 |
+
},
|
| 1773 |
+
"128221": {
|
| 1774 |
+
"content": "<|reserved_special_token_213|>",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": true
|
| 1780 |
+
},
|
| 1781 |
+
"128222": {
|
| 1782 |
+
"content": "<|reserved_special_token_214|>",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": true
|
| 1788 |
+
},
|
| 1789 |
+
"128223": {
|
| 1790 |
+
"content": "<|reserved_special_token_215|>",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": true
|
| 1796 |
+
},
|
| 1797 |
+
"128224": {
|
| 1798 |
+
"content": "<|reserved_special_token_216|>",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": true
|
| 1804 |
+
},
|
| 1805 |
+
"128225": {
|
| 1806 |
+
"content": "<|reserved_special_token_217|>",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": true
|
| 1812 |
+
},
|
| 1813 |
+
"128226": {
|
| 1814 |
+
"content": "<|reserved_special_token_218|>",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": true
|
| 1820 |
+
},
|
| 1821 |
+
"128227": {
|
| 1822 |
+
"content": "<|reserved_special_token_219|>",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": true
|
| 1828 |
+
},
|
| 1829 |
+
"128228": {
|
| 1830 |
+
"content": "<|reserved_special_token_220|>",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": true
|
| 1836 |
+
},
|
| 1837 |
+
"128229": {
|
| 1838 |
+
"content": "<|reserved_special_token_221|>",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": true
|
| 1844 |
+
},
|
| 1845 |
+
"128230": {
|
| 1846 |
+
"content": "<|reserved_special_token_222|>",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": true
|
| 1852 |
+
},
|
| 1853 |
+
"128231": {
|
| 1854 |
+
"content": "<|reserved_special_token_223|>",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": true
|
| 1860 |
+
},
|
| 1861 |
+
"128232": {
|
| 1862 |
+
"content": "<|reserved_special_token_224|>",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": true
|
| 1868 |
+
},
|
| 1869 |
+
"128233": {
|
| 1870 |
+
"content": "<|reserved_special_token_225|>",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": true
|
| 1876 |
+
},
|
| 1877 |
+
"128234": {
|
| 1878 |
+
"content": "<|reserved_special_token_226|>",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": true
|
| 1884 |
+
},
|
| 1885 |
+
"128235": {
|
| 1886 |
+
"content": "<|reserved_special_token_227|>",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": true
|
| 1892 |
+
},
|
| 1893 |
+
"128236": {
|
| 1894 |
+
"content": "<|reserved_special_token_228|>",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": true
|
| 1900 |
+
},
|
| 1901 |
+
"128237": {
|
| 1902 |
+
"content": "<|reserved_special_token_229|>",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": true
|
| 1908 |
+
},
|
| 1909 |
+
"128238": {
|
| 1910 |
+
"content": "<|reserved_special_token_230|>",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": true
|
| 1916 |
+
},
|
| 1917 |
+
"128239": {
|
| 1918 |
+
"content": "<|reserved_special_token_231|>",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": true
|
| 1924 |
+
},
|
| 1925 |
+
"128240": {
|
| 1926 |
+
"content": "<|reserved_special_token_232|>",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": true
|
| 1932 |
+
},
|
| 1933 |
+
"128241": {
|
| 1934 |
+
"content": "<|reserved_special_token_233|>",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": true
|
| 1940 |
+
},
|
| 1941 |
+
"128242": {
|
| 1942 |
+
"content": "<|reserved_special_token_234|>",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": true
|
| 1948 |
+
},
|
| 1949 |
+
"128243": {
|
| 1950 |
+
"content": "<|reserved_special_token_235|>",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": true
|
| 1956 |
+
},
|
| 1957 |
+
"128244": {
|
| 1958 |
+
"content": "<|reserved_special_token_236|>",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": true
|
| 1964 |
+
},
|
| 1965 |
+
"128245": {
|
| 1966 |
+
"content": "<|reserved_special_token_237|>",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": true
|
| 1972 |
+
},
|
| 1973 |
+
"128246": {
|
| 1974 |
+
"content": "<|reserved_special_token_238|>",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": true
|
| 1980 |
+
},
|
| 1981 |
+
"128247": {
|
| 1982 |
+
"content": "<|reserved_special_token_239|>",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": true
|
| 1988 |
+
},
|
| 1989 |
+
"128248": {
|
| 1990 |
+
"content": "<|reserved_special_token_240|>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": true
|
| 1996 |
+
},
|
| 1997 |
+
"128249": {
|
| 1998 |
+
"content": "<|reserved_special_token_241|>",
|
| 1999 |
+
"lstrip": false,
|
| 2000 |
+
"normalized": false,
|
| 2001 |
+
"rstrip": false,
|
| 2002 |
+
"single_word": false,
|
| 2003 |
+
"special": true
|
| 2004 |
+
},
|
| 2005 |
+
"128250": {
|
| 2006 |
+
"content": "<|reserved_special_token_242|>",
|
| 2007 |
+
"lstrip": false,
|
| 2008 |
+
"normalized": false,
|
| 2009 |
+
"rstrip": false,
|
| 2010 |
+
"single_word": false,
|
| 2011 |
+
"special": true
|
| 2012 |
+
},
|
| 2013 |
+
"128251": {
|
| 2014 |
+
"content": "<|reserved_special_token_243|>",
|
| 2015 |
+
"lstrip": false,
|
| 2016 |
+
"normalized": false,
|
| 2017 |
+
"rstrip": false,
|
| 2018 |
+
"single_word": false,
|
| 2019 |
+
"special": true
|
| 2020 |
+
},
|
| 2021 |
+
"128252": {
|
| 2022 |
+
"content": "<|reserved_special_token_244|>",
|
| 2023 |
+
"lstrip": false,
|
| 2024 |
+
"normalized": false,
|
| 2025 |
+
"rstrip": false,
|
| 2026 |
+
"single_word": false,
|
| 2027 |
+
"special": true
|
| 2028 |
+
},
|
| 2029 |
+
"128253": {
|
| 2030 |
+
"content": "<|reserved_special_token_245|>",
|
| 2031 |
+
"lstrip": false,
|
| 2032 |
+
"normalized": false,
|
| 2033 |
+
"rstrip": false,
|
| 2034 |
+
"single_word": false,
|
| 2035 |
+
"special": true
|
| 2036 |
+
},
|
| 2037 |
+
"128254": {
|
| 2038 |
+
"content": "<|reserved_special_token_246|>",
|
| 2039 |
+
"lstrip": false,
|
| 2040 |
+
"normalized": false,
|
| 2041 |
+
"rstrip": false,
|
| 2042 |
+
"single_word": false,
|
| 2043 |
+
"special": true
|
| 2044 |
+
},
|
| 2045 |
+
"128255": {
|
| 2046 |
+
"content": "<|reserved_special_token_247|>",
|
| 2047 |
+
"lstrip": false,
|
| 2048 |
+
"normalized": false,
|
| 2049 |
+
"rstrip": false,
|
| 2050 |
+
"single_word": false,
|
| 2051 |
+
"special": true
|
| 2052 |
+
}
|
| 2053 |
+
},
|
| 2054 |
+
"bos_token": "<|begin_of_text|>",
|
| 2055 |
+
"clean_up_tokenization_spaces": true,
|
| 2056 |
+
"eos_token": "<|end_of_text|>",
|
| 2057 |
+
"extra_special_tokens": {},
|
| 2058 |
+
"model_input_names": [
|
| 2059 |
+
"input_ids",
|
| 2060 |
+
"attention_mask"
|
| 2061 |
+
],
|
| 2062 |
+
"model_max_length": 2048,
|
| 2063 |
+
"padding_side": "right",
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2065 |
+
}
|
llama1b_fw10b_0401/checkpoint-4000/trainer_state.json
ADDED
|
@@ -0,0 +1,2833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1,
|
| 5 |
+
"eval_steps": 2000.0,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025,
|
| 13 |
+
"grad_norm": 6.78125,
|
| 14 |
+
"learning_rate": 1.9999996915748784e-05,
|
| 15 |
+
"loss": 9.0811,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005,
|
| 20 |
+
"grad_norm": 2.859375,
|
| 21 |
+
"learning_rate": 1.9999987662997034e-05,
|
| 22 |
+
"loss": 7.9734,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00075,
|
| 27 |
+
"grad_norm": 8.125,
|
| 28 |
+
"learning_rate": 1.9999972241750466e-05,
|
| 29 |
+
"loss": 7.8417,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.001,
|
| 34 |
+
"grad_norm": 6.40625,
|
| 35 |
+
"learning_rate": 1.9999950652018585e-05,
|
| 36 |
+
"loss": 7.4662,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.00125,
|
| 41 |
+
"grad_norm": 10.625,
|
| 42 |
+
"learning_rate": 1.9999922893814707e-05,
|
| 43 |
+
"loss": 7.1123,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015,
|
| 48 |
+
"grad_norm": 9.6875,
|
| 49 |
+
"learning_rate": 1.9999888967155963e-05,
|
| 50 |
+
"loss": 6.8197,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.00175,
|
| 55 |
+
"grad_norm": 8.1875,
|
| 56 |
+
"learning_rate": 1.999984887206327e-05,
|
| 57 |
+
"loss": 6.5134,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.002,
|
| 62 |
+
"grad_norm": 10.6875,
|
| 63 |
+
"learning_rate": 1.999980260856137e-05,
|
| 64 |
+
"loss": 6.2623,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.00225,
|
| 69 |
+
"grad_norm": 10.375,
|
| 70 |
+
"learning_rate": 1.9999750176678802e-05,
|
| 71 |
+
"loss": 6.0482,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025,
|
| 76 |
+
"grad_norm": 6.5,
|
| 77 |
+
"learning_rate": 1.99996915764479e-05,
|
| 78 |
+
"loss": 5.8435,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.00275,
|
| 83 |
+
"grad_norm": 6.9375,
|
| 84 |
+
"learning_rate": 1.9999626807904814e-05,
|
| 85 |
+
"loss": 5.6339,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.003,
|
| 90 |
+
"grad_norm": 6.84375,
|
| 91 |
+
"learning_rate": 1.99995558710895e-05,
|
| 92 |
+
"loss": 5.505,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.00325,
|
| 97 |
+
"grad_norm": 6.71875,
|
| 98 |
+
"learning_rate": 1.9999478766045712e-05,
|
| 99 |
+
"loss": 5.3947,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0035,
|
| 104 |
+
"grad_norm": 6.71875,
|
| 105 |
+
"learning_rate": 1.9999395492821018e-05,
|
| 106 |
+
"loss": 5.285,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.00375,
|
| 111 |
+
"grad_norm": 4.9375,
|
| 112 |
+
"learning_rate": 1.9999306051466772e-05,
|
| 113 |
+
"loss": 5.1586,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004,
|
| 118 |
+
"grad_norm": 5.125,
|
| 119 |
+
"learning_rate": 1.9999210442038164e-05,
|
| 120 |
+
"loss": 5.0601,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.00425,
|
| 125 |
+
"grad_norm": 3.4375,
|
| 126 |
+
"learning_rate": 1.9999108664594158e-05,
|
| 127 |
+
"loss": 5.0024,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0045,
|
| 132 |
+
"grad_norm": 4.21875,
|
| 133 |
+
"learning_rate": 1.9999000719197538e-05,
|
| 134 |
+
"loss": 4.9013,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.00475,
|
| 139 |
+
"grad_norm": 4.25,
|
| 140 |
+
"learning_rate": 1.9998886605914893e-05,
|
| 141 |
+
"loss": 4.8314,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005,
|
| 146 |
+
"grad_norm": 4.15625,
|
| 147 |
+
"learning_rate": 1.9998766324816606e-05,
|
| 148 |
+
"loss": 4.7311,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.00525,
|
| 153 |
+
"grad_norm": 3.71875,
|
| 154 |
+
"learning_rate": 1.9998639875976885e-05,
|
| 155 |
+
"loss": 4.7051,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0055,
|
| 160 |
+
"grad_norm": 4.0625,
|
| 161 |
+
"learning_rate": 1.999850725947372e-05,
|
| 162 |
+
"loss": 4.6402,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.00575,
|
| 167 |
+
"grad_norm": 5.1875,
|
| 168 |
+
"learning_rate": 1.9998368475388918e-05,
|
| 169 |
+
"loss": 4.5561,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.006,
|
| 174 |
+
"grad_norm": 5.5,
|
| 175 |
+
"learning_rate": 1.9998223523808092e-05,
|
| 176 |
+
"loss": 4.4706,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00625,
|
| 181 |
+
"grad_norm": 3.265625,
|
| 182 |
+
"learning_rate": 1.9998072404820648e-05,
|
| 183 |
+
"loss": 4.4615,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.0065,
|
| 188 |
+
"grad_norm": 3.71875,
|
| 189 |
+
"learning_rate": 1.9997915118519813e-05,
|
| 190 |
+
"loss": 4.4033,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.00675,
|
| 195 |
+
"grad_norm": 3.78125,
|
| 196 |
+
"learning_rate": 1.9997751665002602e-05,
|
| 197 |
+
"loss": 4.3937,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007,
|
| 202 |
+
"grad_norm": 3.53125,
|
| 203 |
+
"learning_rate": 1.9997582044369843e-05,
|
| 204 |
+
"loss": 4.3302,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.00725,
|
| 209 |
+
"grad_norm": 2.6875,
|
| 210 |
+
"learning_rate": 1.9997406256726165e-05,
|
| 211 |
+
"loss": 4.3236,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.0075,
|
| 216 |
+
"grad_norm": 2.671875,
|
| 217 |
+
"learning_rate": 1.9997224302180008e-05,
|
| 218 |
+
"loss": 4.2641,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.00775,
|
| 223 |
+
"grad_norm": 3.625,
|
| 224 |
+
"learning_rate": 1.9997036180843605e-05,
|
| 225 |
+
"loss": 4.2173,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008,
|
| 230 |
+
"grad_norm": 2.40625,
|
| 231 |
+
"learning_rate": 1.9996841892833e-05,
|
| 232 |
+
"loss": 4.2156,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.00825,
|
| 237 |
+
"grad_norm": 2.546875,
|
| 238 |
+
"learning_rate": 1.9996641438268047e-05,
|
| 239 |
+
"loss": 4.1677,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0085,
|
| 244 |
+
"grad_norm": 2.6875,
|
| 245 |
+
"learning_rate": 1.999643481727238e-05,
|
| 246 |
+
"loss": 4.1629,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.00875,
|
| 251 |
+
"grad_norm": 2.5625,
|
| 252 |
+
"learning_rate": 1.999622202997347e-05,
|
| 253 |
+
"loss": 4.1344,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.009,
|
| 258 |
+
"grad_norm": 3.015625,
|
| 259 |
+
"learning_rate": 1.9996003076502567e-05,
|
| 260 |
+
"loss": 4.1396,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00925,
|
| 265 |
+
"grad_norm": 2.71875,
|
| 266 |
+
"learning_rate": 1.9995777956994734e-05,
|
| 267 |
+
"loss": 4.1204,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0095,
|
| 272 |
+
"grad_norm": 2.71875,
|
| 273 |
+
"learning_rate": 1.9995546671588833e-05,
|
| 274 |
+
"loss": 4.0905,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.00975,
|
| 279 |
+
"grad_norm": 2.3125,
|
| 280 |
+
"learning_rate": 1.999530922042754e-05,
|
| 281 |
+
"loss": 4.0777,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.01,
|
| 286 |
+
"grad_norm": 2.03125,
|
| 287 |
+
"learning_rate": 1.9995065603657317e-05,
|
| 288 |
+
"loss": 4.052,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.01025,
|
| 293 |
+
"grad_norm": 2.21875,
|
| 294 |
+
"learning_rate": 1.9994815821428447e-05,
|
| 295 |
+
"loss": 4.0851,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.0105,
|
| 300 |
+
"grad_norm": 2.328125,
|
| 301 |
+
"learning_rate": 1.9994559873895003e-05,
|
| 302 |
+
"loss": 4.0553,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01075,
|
| 307 |
+
"grad_norm": 2.34375,
|
| 308 |
+
"learning_rate": 1.999429776121487e-05,
|
| 309 |
+
"loss": 4.0086,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011,
|
| 314 |
+
"grad_norm": 1.9375,
|
| 315 |
+
"learning_rate": 1.9994029483549732e-05,
|
| 316 |
+
"loss": 3.988,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.01125,
|
| 321 |
+
"grad_norm": 2.3125,
|
| 322 |
+
"learning_rate": 1.999375504106507e-05,
|
| 323 |
+
"loss": 3.9964,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.0115,
|
| 328 |
+
"grad_norm": 2.0,
|
| 329 |
+
"learning_rate": 1.9993474433930184e-05,
|
| 330 |
+
"loss": 3.9426,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.01175,
|
| 335 |
+
"grad_norm": 2.578125,
|
| 336 |
+
"learning_rate": 1.999318766231816e-05,
|
| 337 |
+
"loss": 3.9241,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012,
|
| 342 |
+
"grad_norm": 1.9453125,
|
| 343 |
+
"learning_rate": 1.9992894726405894e-05,
|
| 344 |
+
"loss": 3.9166,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01225,
|
| 349 |
+
"grad_norm": 6.96875,
|
| 350 |
+
"learning_rate": 1.9992595626374083e-05,
|
| 351 |
+
"loss": 3.907,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.0125,
|
| 356 |
+
"grad_norm": 2.1875,
|
| 357 |
+
"learning_rate": 1.9992290362407232e-05,
|
| 358 |
+
"loss": 3.9276,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.01275,
|
| 363 |
+
"grad_norm": 2.125,
|
| 364 |
+
"learning_rate": 1.9991978934693638e-05,
|
| 365 |
+
"loss": 3.8798,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013,
|
| 370 |
+
"grad_norm": 2.953125,
|
| 371 |
+
"learning_rate": 1.9991661343425402e-05,
|
| 372 |
+
"loss": 3.904,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.01325,
|
| 377 |
+
"grad_norm": 2.078125,
|
| 378 |
+
"learning_rate": 1.9991337588798437e-05,
|
| 379 |
+
"loss": 3.8807,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.0135,
|
| 384 |
+
"grad_norm": 2.390625,
|
| 385 |
+
"learning_rate": 1.999100767101245e-05,
|
| 386 |
+
"loss": 3.9105,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.01375,
|
| 391 |
+
"grad_norm": 2.15625,
|
| 392 |
+
"learning_rate": 1.999067159027095e-05,
|
| 393 |
+
"loss": 3.8477,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014,
|
| 398 |
+
"grad_norm": 1.8125,
|
| 399 |
+
"learning_rate": 1.999032934678125e-05,
|
| 400 |
+
"loss": 3.8481,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.01425,
|
| 405 |
+
"grad_norm": 1.921875,
|
| 406 |
+
"learning_rate": 1.9989980940754458e-05,
|
| 407 |
+
"loss": 3.8395,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.0145,
|
| 412 |
+
"grad_norm": 2.421875,
|
| 413 |
+
"learning_rate": 1.9989626372405493e-05,
|
| 414 |
+
"loss": 3.8503,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01475,
|
| 419 |
+
"grad_norm": 1.8046875,
|
| 420 |
+
"learning_rate": 1.998926564195307e-05,
|
| 421 |
+
"loss": 3.8672,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.015,
|
| 426 |
+
"grad_norm": 2.078125,
|
| 427 |
+
"learning_rate": 1.9988898749619702e-05,
|
| 428 |
+
"loss": 3.8374,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.01525,
|
| 433 |
+
"grad_norm": 1.7421875,
|
| 434 |
+
"learning_rate": 1.998852569563171e-05,
|
| 435 |
+
"loss": 3.815,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.0155,
|
| 440 |
+
"grad_norm": 1.8125,
|
| 441 |
+
"learning_rate": 1.9988146480219212e-05,
|
| 442 |
+
"loss": 3.7989,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01575,
|
| 447 |
+
"grad_norm": 1.7734375,
|
| 448 |
+
"learning_rate": 1.998776110361613e-05,
|
| 449 |
+
"loss": 3.7988,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016,
|
| 454 |
+
"grad_norm": 1.7109375,
|
| 455 |
+
"learning_rate": 1.998736956606018e-05,
|
| 456 |
+
"loss": 3.8268,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.01625,
|
| 461 |
+
"grad_norm": 1.6953125,
|
| 462 |
+
"learning_rate": 1.998697186779288e-05,
|
| 463 |
+
"loss": 3.7969,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0165,
|
| 468 |
+
"grad_norm": 1.8515625,
|
| 469 |
+
"learning_rate": 1.998656800905955e-05,
|
| 470 |
+
"loss": 3.7883,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.01675,
|
| 475 |
+
"grad_norm": 1.921875,
|
| 476 |
+
"learning_rate": 1.998615799010932e-05,
|
| 477 |
+
"loss": 3.7614,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017,
|
| 482 |
+
"grad_norm": 1.6015625,
|
| 483 |
+
"learning_rate": 1.9985741811195098e-05,
|
| 484 |
+
"loss": 3.7673,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01725,
|
| 489 |
+
"grad_norm": 1.8125,
|
| 490 |
+
"learning_rate": 1.9985319472573615e-05,
|
| 491 |
+
"loss": 3.7686,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.0175,
|
| 496 |
+
"grad_norm": 1.6796875,
|
| 497 |
+
"learning_rate": 1.9984890974505383e-05,
|
| 498 |
+
"loss": 3.7445,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01775,
|
| 503 |
+
"grad_norm": 1.59375,
|
| 504 |
+
"learning_rate": 1.998445631725472e-05,
|
| 505 |
+
"loss": 3.7478,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.018,
|
| 510 |
+
"grad_norm": 1.9296875,
|
| 511 |
+
"learning_rate": 1.998401550108975e-05,
|
| 512 |
+
"loss": 3.749,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.01825,
|
| 517 |
+
"grad_norm": 2.015625,
|
| 518 |
+
"learning_rate": 1.9983568526282392e-05,
|
| 519 |
+
"loss": 3.7279,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0185,
|
| 524 |
+
"grad_norm": 1.5234375,
|
| 525 |
+
"learning_rate": 1.9983115393108353e-05,
|
| 526 |
+
"loss": 3.7297,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.01875,
|
| 531 |
+
"grad_norm": 1.7109375,
|
| 532 |
+
"learning_rate": 1.998265610184716e-05,
|
| 533 |
+
"loss": 3.7416,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019,
|
| 538 |
+
"grad_norm": 1.7265625,
|
| 539 |
+
"learning_rate": 1.9982190652782122e-05,
|
| 540 |
+
"loss": 3.7717,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.01925,
|
| 545 |
+
"grad_norm": 1.828125,
|
| 546 |
+
"learning_rate": 1.9981719046200346e-05,
|
| 547 |
+
"loss": 3.7422,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.0195,
|
| 552 |
+
"grad_norm": 1.6171875,
|
| 553 |
+
"learning_rate": 1.9981241282392748e-05,
|
| 554 |
+
"loss": 3.6887,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.01975,
|
| 559 |
+
"grad_norm": 1.6875,
|
| 560 |
+
"learning_rate": 1.9980757361654035e-05,
|
| 561 |
+
"loss": 3.7175,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.02,
|
| 566 |
+
"grad_norm": 1.953125,
|
| 567 |
+
"learning_rate": 1.9980267284282718e-05,
|
| 568 |
+
"loss": 3.7141,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.02025,
|
| 573 |
+
"grad_norm": 1.578125,
|
| 574 |
+
"learning_rate": 1.9979771050581096e-05,
|
| 575 |
+
"loss": 3.6943,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.0205,
|
| 580 |
+
"grad_norm": 1.59375,
|
| 581 |
+
"learning_rate": 1.997926866085527e-05,
|
| 582 |
+
"loss": 3.6833,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02075,
|
| 587 |
+
"grad_norm": 1.625,
|
| 588 |
+
"learning_rate": 1.9978760115415147e-05,
|
| 589 |
+
"loss": 3.7323,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.021,
|
| 594 |
+
"grad_norm": 1.5703125,
|
| 595 |
+
"learning_rate": 1.997824541457442e-05,
|
| 596 |
+
"loss": 3.7224,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02125,
|
| 601 |
+
"grad_norm": 1.4921875,
|
| 602 |
+
"learning_rate": 1.9977724558650574e-05,
|
| 603 |
+
"loss": 3.6503,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.0215,
|
| 608 |
+
"grad_norm": 1.359375,
|
| 609 |
+
"learning_rate": 1.997719754796491e-05,
|
| 610 |
+
"loss": 3.677,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.02175,
|
| 615 |
+
"grad_norm": 1.6328125,
|
| 616 |
+
"learning_rate": 1.9976664382842507e-05,
|
| 617 |
+
"loss": 3.6799,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.022,
|
| 622 |
+
"grad_norm": 1.4296875,
|
| 623 |
+
"learning_rate": 1.9976125063612254e-05,
|
| 624 |
+
"loss": 3.6711,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.02225,
|
| 629 |
+
"grad_norm": 1.6640625,
|
| 630 |
+
"learning_rate": 1.9975579590606826e-05,
|
| 631 |
+
"loss": 3.6514,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.0225,
|
| 636 |
+
"grad_norm": 1.46875,
|
| 637 |
+
"learning_rate": 1.9975027964162704e-05,
|
| 638 |
+
"loss": 3.6703,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.02275,
|
| 643 |
+
"grad_norm": 1.390625,
|
| 644 |
+
"learning_rate": 1.997447018462015e-05,
|
| 645 |
+
"loss": 3.6814,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023,
|
| 650 |
+
"grad_norm": 1.7265625,
|
| 651 |
+
"learning_rate": 1.997390625232324e-05,
|
| 652 |
+
"loss": 3.6675,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.02325,
|
| 657 |
+
"grad_norm": 1.53125,
|
| 658 |
+
"learning_rate": 1.9973336167619827e-05,
|
| 659 |
+
"loss": 3.6449,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.0235,
|
| 664 |
+
"grad_norm": 1.40625,
|
| 665 |
+
"learning_rate": 1.9972759930861573e-05,
|
| 666 |
+
"loss": 3.677,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02375,
|
| 671 |
+
"grad_norm": 1.4765625,
|
| 672 |
+
"learning_rate": 1.997217754240393e-05,
|
| 673 |
+
"loss": 3.6312,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024,
|
| 678 |
+
"grad_norm": 1.328125,
|
| 679 |
+
"learning_rate": 1.997158900260614e-05,
|
| 680 |
+
"loss": 3.647,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.02425,
|
| 685 |
+
"grad_norm": 1.296875,
|
| 686 |
+
"learning_rate": 1.997099431183125e-05,
|
| 687 |
+
"loss": 3.6581,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.0245,
|
| 692 |
+
"grad_norm": 1.28125,
|
| 693 |
+
"learning_rate": 1.9970393470446092e-05,
|
| 694 |
+
"loss": 3.6188,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.02475,
|
| 699 |
+
"grad_norm": 1.5859375,
|
| 700 |
+
"learning_rate": 1.9969786478821293e-05,
|
| 701 |
+
"loss": 3.6374,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.025,
|
| 706 |
+
"grad_norm": 1.6015625,
|
| 707 |
+
"learning_rate": 1.9969173337331283e-05,
|
| 708 |
+
"loss": 3.666,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.02525,
|
| 713 |
+
"grad_norm": 1.5078125,
|
| 714 |
+
"learning_rate": 1.996855404635427e-05,
|
| 715 |
+
"loss": 3.6358,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.0255,
|
| 720 |
+
"grad_norm": 1.703125,
|
| 721 |
+
"learning_rate": 1.9967928606272267e-05,
|
| 722 |
+
"loss": 3.7041,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.02575,
|
| 727 |
+
"grad_norm": 1.375,
|
| 728 |
+
"learning_rate": 1.9967297017471077e-05,
|
| 729 |
+
"loss": 3.6157,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.026,
|
| 734 |
+
"grad_norm": 1.4296875,
|
| 735 |
+
"learning_rate": 1.99666592803403e-05,
|
| 736 |
+
"loss": 3.6091,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.02625,
|
| 741 |
+
"grad_norm": 1.484375,
|
| 742 |
+
"learning_rate": 1.9966015395273318e-05,
|
| 743 |
+
"loss": 3.5903,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.0265,
|
| 748 |
+
"grad_norm": 1.6015625,
|
| 749 |
+
"learning_rate": 1.9965365362667315e-05,
|
| 750 |
+
"loss": 3.5895,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.02675,
|
| 755 |
+
"grad_norm": 1.3359375,
|
| 756 |
+
"learning_rate": 1.9964709182923263e-05,
|
| 757 |
+
"loss": 3.5795,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.027,
|
| 762 |
+
"grad_norm": 1.3359375,
|
| 763 |
+
"learning_rate": 1.9964046856445926e-05,
|
| 764 |
+
"loss": 3.6039,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02725,
|
| 769 |
+
"grad_norm": 1.234375,
|
| 770 |
+
"learning_rate": 1.996337838364386e-05,
|
| 771 |
+
"loss": 3.6208,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.0275,
|
| 776 |
+
"grad_norm": 1.2578125,
|
| 777 |
+
"learning_rate": 1.9962703764929413e-05,
|
| 778 |
+
"loss": 3.6238,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.02775,
|
| 783 |
+
"grad_norm": 1.3203125,
|
| 784 |
+
"learning_rate": 1.9962023000718727e-05,
|
| 785 |
+
"loss": 3.5832,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.028,
|
| 790 |
+
"grad_norm": 1.5390625,
|
| 791 |
+
"learning_rate": 1.9961336091431728e-05,
|
| 792 |
+
"loss": 3.6152,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.02825,
|
| 797 |
+
"grad_norm": 1.5625,
|
| 798 |
+
"learning_rate": 1.9960643037492132e-05,
|
| 799 |
+
"loss": 3.6012,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.0285,
|
| 804 |
+
"grad_norm": 1.4453125,
|
| 805 |
+
"learning_rate": 1.995994383932746e-05,
|
| 806 |
+
"loss": 3.5685,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.02875,
|
| 811 |
+
"grad_norm": 1.21875,
|
| 812 |
+
"learning_rate": 1.9959238497369006e-05,
|
| 813 |
+
"loss": 3.5879,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.029,
|
| 818 |
+
"grad_norm": 1.3359375,
|
| 819 |
+
"learning_rate": 1.995852701205186e-05,
|
| 820 |
+
"loss": 3.6383,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.02925,
|
| 825 |
+
"grad_norm": 1.3515625,
|
| 826 |
+
"learning_rate": 1.9957809383814903e-05,
|
| 827 |
+
"loss": 3.6029,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.0295,
|
| 832 |
+
"grad_norm": 1.5078125,
|
| 833 |
+
"learning_rate": 1.9957085613100806e-05,
|
| 834 |
+
"loss": 3.5941,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.02975,
|
| 839 |
+
"grad_norm": 1.1875,
|
| 840 |
+
"learning_rate": 1.995635570035602e-05,
|
| 841 |
+
"loss": 3.5772,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.03,
|
| 846 |
+
"grad_norm": 1.2109375,
|
| 847 |
+
"learning_rate": 1.99556196460308e-05,
|
| 848 |
+
"loss": 3.5685,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03025,
|
| 853 |
+
"grad_norm": 1.5234375,
|
| 854 |
+
"learning_rate": 1.995487745057918e-05,
|
| 855 |
+
"loss": 3.5991,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.0305,
|
| 860 |
+
"grad_norm": 1.1953125,
|
| 861 |
+
"learning_rate": 1.9954129114458985e-05,
|
| 862 |
+
"loss": 3.5844,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.03075,
|
| 867 |
+
"grad_norm": 1.203125,
|
| 868 |
+
"learning_rate": 1.995337463813182e-05,
|
| 869 |
+
"loss": 3.5727,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.031,
|
| 874 |
+
"grad_norm": 1.4296875,
|
| 875 |
+
"learning_rate": 1.9952614022063085e-05,
|
| 876 |
+
"loss": 3.565,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.03125,
|
| 881 |
+
"grad_norm": 1.21875,
|
| 882 |
+
"learning_rate": 1.995184726672197e-05,
|
| 883 |
+
"loss": 3.6115,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.0315,
|
| 888 |
+
"grad_norm": 1.6171875,
|
| 889 |
+
"learning_rate": 1.995107437258145e-05,
|
| 890 |
+
"loss": 3.5756,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.03175,
|
| 895 |
+
"grad_norm": 1.390625,
|
| 896 |
+
"learning_rate": 1.9950295340118274e-05,
|
| 897 |
+
"loss": 3.5647,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.032,
|
| 902 |
+
"grad_norm": 1.59375,
|
| 903 |
+
"learning_rate": 1.9949510169813006e-05,
|
| 904 |
+
"loss": 3.5523,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03225,
|
| 909 |
+
"grad_norm": 1.375,
|
| 910 |
+
"learning_rate": 1.994871886214996e-05,
|
| 911 |
+
"loss": 3.573,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.0325,
|
| 916 |
+
"grad_norm": 1.28125,
|
| 917 |
+
"learning_rate": 1.9947921417617265e-05,
|
| 918 |
+
"loss": 3.5667,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.03275,
|
| 923 |
+
"grad_norm": 1.2109375,
|
| 924 |
+
"learning_rate": 1.9947117836706823e-05,
|
| 925 |
+
"loss": 3.5334,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.033,
|
| 930 |
+
"grad_norm": 1.6796875,
|
| 931 |
+
"learning_rate": 1.9946308119914323e-05,
|
| 932 |
+
"loss": 3.5572,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03325,
|
| 937 |
+
"grad_norm": 1.40625,
|
| 938 |
+
"learning_rate": 1.9945492267739243e-05,
|
| 939 |
+
"loss": 3.5342,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.0335,
|
| 944 |
+
"grad_norm": 1.3203125,
|
| 945 |
+
"learning_rate": 1.994467028068483e-05,
|
| 946 |
+
"loss": 3.5825,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03375,
|
| 951 |
+
"grad_norm": 1.3203125,
|
| 952 |
+
"learning_rate": 1.994384215925814e-05,
|
| 953 |
+
"loss": 3.5594,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.034,
|
| 958 |
+
"grad_norm": 1.40625,
|
| 959 |
+
"learning_rate": 1.994300790396999e-05,
|
| 960 |
+
"loss": 3.5237,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.03425,
|
| 965 |
+
"grad_norm": 1.2578125,
|
| 966 |
+
"learning_rate": 1.9942167515334998e-05,
|
| 967 |
+
"loss": 3.565,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.0345,
|
| 972 |
+
"grad_norm": 1.15625,
|
| 973 |
+
"learning_rate": 1.994132099387155e-05,
|
| 974 |
+
"loss": 3.5404,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.03475,
|
| 979 |
+
"grad_norm": 1.3515625,
|
| 980 |
+
"learning_rate": 1.9940468340101834e-05,
|
| 981 |
+
"loss": 3.5461,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.035,
|
| 986 |
+
"grad_norm": 1.453125,
|
| 987 |
+
"learning_rate": 1.99396095545518e-05,
|
| 988 |
+
"loss": 3.5384,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.03525,
|
| 993 |
+
"grad_norm": 1.40625,
|
| 994 |
+
"learning_rate": 1.9938744637751194e-05,
|
| 995 |
+
"loss": 3.5355,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.0355,
|
| 1000 |
+
"grad_norm": 1.390625,
|
| 1001 |
+
"learning_rate": 1.9937873590233537e-05,
|
| 1002 |
+
"loss": 3.54,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.03575,
|
| 1007 |
+
"grad_norm": 1.3125,
|
| 1008 |
+
"learning_rate": 1.993699641253614e-05,
|
| 1009 |
+
"loss": 3.4974,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.036,
|
| 1014 |
+
"grad_norm": 1.4765625,
|
| 1015 |
+
"learning_rate": 1.9936113105200085e-05,
|
| 1016 |
+
"loss": 3.5405,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03625,
|
| 1021 |
+
"grad_norm": 1.34375,
|
| 1022 |
+
"learning_rate": 1.9935223668770244e-05,
|
| 1023 |
+
"loss": 3.5328,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.0365,
|
| 1028 |
+
"grad_norm": 1.1484375,
|
| 1029 |
+
"learning_rate": 1.9934328103795265e-05,
|
| 1030 |
+
"loss": 3.5091,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03675,
|
| 1035 |
+
"grad_norm": 1.3515625,
|
| 1036 |
+
"learning_rate": 1.993342641082758e-05,
|
| 1037 |
+
"loss": 3.5274,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.037,
|
| 1042 |
+
"grad_norm": 1.359375,
|
| 1043 |
+
"learning_rate": 1.9932518590423396e-05,
|
| 1044 |
+
"loss": 3.5198,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03725,
|
| 1049 |
+
"grad_norm": 1.2890625,
|
| 1050 |
+
"learning_rate": 1.9931604643142703e-05,
|
| 1051 |
+
"loss": 3.5387,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.0375,
|
| 1056 |
+
"grad_norm": 1.328125,
|
| 1057 |
+
"learning_rate": 1.9930684569549265e-05,
|
| 1058 |
+
"loss": 3.5332,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.03775,
|
| 1063 |
+
"grad_norm": 1.1796875,
|
| 1064 |
+
"learning_rate": 1.9929758370210636e-05,
|
| 1065 |
+
"loss": 3.5618,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.038,
|
| 1070 |
+
"grad_norm": 1.1015625,
|
| 1071 |
+
"learning_rate": 1.9928826045698138e-05,
|
| 1072 |
+
"loss": 3.5114,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.03825,
|
| 1077 |
+
"grad_norm": 1.1953125,
|
| 1078 |
+
"learning_rate": 1.9927887596586878e-05,
|
| 1079 |
+
"loss": 3.5164,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.0385,
|
| 1084 |
+
"grad_norm": 1.546875,
|
| 1085 |
+
"learning_rate": 1.992694302345574e-05,
|
| 1086 |
+
"loss": 3.5316,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.03875,
|
| 1091 |
+
"grad_norm": 1.28125,
|
| 1092 |
+
"learning_rate": 1.992599232688738e-05,
|
| 1093 |
+
"loss": 3.5218,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.039,
|
| 1098 |
+
"grad_norm": 1.21875,
|
| 1099 |
+
"learning_rate": 1.992503550746824e-05,
|
| 1100 |
+
"loss": 3.4989,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.03925,
|
| 1105 |
+
"grad_norm": 1.453125,
|
| 1106 |
+
"learning_rate": 1.992407256578853e-05,
|
| 1107 |
+
"loss": 3.5343,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.0395,
|
| 1112 |
+
"grad_norm": 1.296875,
|
| 1113 |
+
"learning_rate": 1.9923103502442242e-05,
|
| 1114 |
+
"loss": 3.5207,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.03975,
|
| 1119 |
+
"grad_norm": 1.2734375,
|
| 1120 |
+
"learning_rate": 1.9922128318027146e-05,
|
| 1121 |
+
"loss": 3.4942,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.04,
|
| 1126 |
+
"grad_norm": 1.171875,
|
| 1127 |
+
"learning_rate": 1.9921147013144782e-05,
|
| 1128 |
+
"loss": 3.4835,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.04025,
|
| 1133 |
+
"grad_norm": 1.078125,
|
| 1134 |
+
"learning_rate": 1.9920159588400463e-05,
|
| 1135 |
+
"loss": 3.513,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.0405,
|
| 1140 |
+
"grad_norm": 1.296875,
|
| 1141 |
+
"learning_rate": 1.9919166044403294e-05,
|
| 1142 |
+
"loss": 3.5164,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.04075,
|
| 1147 |
+
"grad_norm": 1.4453125,
|
| 1148 |
+
"learning_rate": 1.9918166381766134e-05,
|
| 1149 |
+
"loss": 3.4879,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.041,
|
| 1154 |
+
"grad_norm": 1.078125,
|
| 1155 |
+
"learning_rate": 1.9917160601105632e-05,
|
| 1156 |
+
"loss": 3.5012,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.04125,
|
| 1161 |
+
"grad_norm": 1.3046875,
|
| 1162 |
+
"learning_rate": 1.9916148703042193e-05,
|
| 1163 |
+
"loss": 3.555,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0415,
|
| 1168 |
+
"grad_norm": 1.25,
|
| 1169 |
+
"learning_rate": 1.9915130688200016e-05,
|
| 1170 |
+
"loss": 3.4971,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04175,
|
| 1175 |
+
"grad_norm": 1.25,
|
| 1176 |
+
"learning_rate": 1.9914106557207064e-05,
|
| 1177 |
+
"loss": 3.5221,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.042,
|
| 1182 |
+
"grad_norm": 1.3203125,
|
| 1183 |
+
"learning_rate": 1.9913076310695068e-05,
|
| 1184 |
+
"loss": 3.489,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.04225,
|
| 1189 |
+
"grad_norm": 1.2265625,
|
| 1190 |
+
"learning_rate": 1.9912039949299536e-05,
|
| 1191 |
+
"loss": 3.5137,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.0425,
|
| 1196 |
+
"grad_norm": 1.1796875,
|
| 1197 |
+
"learning_rate": 1.991099747365975e-05,
|
| 1198 |
+
"loss": 3.4931,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.04275,
|
| 1203 |
+
"grad_norm": 1.1328125,
|
| 1204 |
+
"learning_rate": 1.990994888441876e-05,
|
| 1205 |
+
"loss": 3.4985,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.043,
|
| 1210 |
+
"grad_norm": 1.25,
|
| 1211 |
+
"learning_rate": 1.990889418222339e-05,
|
| 1212 |
+
"loss": 3.4867,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.04325,
|
| 1217 |
+
"grad_norm": 1.640625,
|
| 1218 |
+
"learning_rate": 1.990783336772423e-05,
|
| 1219 |
+
"loss": 3.4829,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.0435,
|
| 1224 |
+
"grad_norm": 1.140625,
|
| 1225 |
+
"learning_rate": 1.9906766441575647e-05,
|
| 1226 |
+
"loss": 3.4714,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.04375,
|
| 1231 |
+
"grad_norm": 1.2109375,
|
| 1232 |
+
"learning_rate": 1.990569340443577e-05,
|
| 1233 |
+
"loss": 3.4518,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.044,
|
| 1238 |
+
"grad_norm": 1.125,
|
| 1239 |
+
"learning_rate": 1.9904614256966514e-05,
|
| 1240 |
+
"loss": 3.5356,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.04425,
|
| 1245 |
+
"grad_norm": 1.15625,
|
| 1246 |
+
"learning_rate": 1.990352899983354e-05,
|
| 1247 |
+
"loss": 3.4852,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.0445,
|
| 1252 |
+
"grad_norm": 1.15625,
|
| 1253 |
+
"learning_rate": 1.9902437633706292e-05,
|
| 1254 |
+
"loss": 3.494,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.04475,
|
| 1259 |
+
"grad_norm": 1.2734375,
|
| 1260 |
+
"learning_rate": 1.9901340159257977e-05,
|
| 1261 |
+
"loss": 3.521,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.045,
|
| 1266 |
+
"grad_norm": 1.4140625,
|
| 1267 |
+
"learning_rate": 1.990023657716558e-05,
|
| 1268 |
+
"loss": 3.5071,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.04525,
|
| 1273 |
+
"grad_norm": 1.3203125,
|
| 1274 |
+
"learning_rate": 1.9899126888109836e-05,
|
| 1275 |
+
"loss": 3.4657,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.0455,
|
| 1280 |
+
"grad_norm": 1.203125,
|
| 1281 |
+
"learning_rate": 1.9898011092775263e-05,
|
| 1282 |
+
"loss": 3.4848,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.04575,
|
| 1287 |
+
"grad_norm": 1.09375,
|
| 1288 |
+
"learning_rate": 1.9896889191850143e-05,
|
| 1289 |
+
"loss": 3.4962,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.046,
|
| 1294 |
+
"grad_norm": 1.0703125,
|
| 1295 |
+
"learning_rate": 1.989576118602651e-05,
|
| 1296 |
+
"loss": 3.4828,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.04625,
|
| 1301 |
+
"grad_norm": 1.4296875,
|
| 1302 |
+
"learning_rate": 1.9894627076000185e-05,
|
| 1303 |
+
"loss": 3.5066,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.0465,
|
| 1308 |
+
"grad_norm": 1.09375,
|
| 1309 |
+
"learning_rate": 1.989348686247074e-05,
|
| 1310 |
+
"loss": 3.5393,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.04675,
|
| 1315 |
+
"grad_norm": 1.2265625,
|
| 1316 |
+
"learning_rate": 1.9892340546141517e-05,
|
| 1317 |
+
"loss": 3.4682,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.047,
|
| 1322 |
+
"grad_norm": 1.125,
|
| 1323 |
+
"learning_rate": 1.989118812771962e-05,
|
| 1324 |
+
"loss": 3.4739,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.04725,
|
| 1329 |
+
"grad_norm": 1.0390625,
|
| 1330 |
+
"learning_rate": 1.989002960791592e-05,
|
| 1331 |
+
"loss": 3.4578,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.0475,
|
| 1336 |
+
"grad_norm": 1.171875,
|
| 1337 |
+
"learning_rate": 1.988886498744505e-05,
|
| 1338 |
+
"loss": 3.5077,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.04775,
|
| 1343 |
+
"grad_norm": 1.5078125,
|
| 1344 |
+
"learning_rate": 1.98876942670254e-05,
|
| 1345 |
+
"loss": 3.5499,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.048,
|
| 1350 |
+
"grad_norm": 1.2578125,
|
| 1351 |
+
"learning_rate": 1.988651744737914e-05,
|
| 1352 |
+
"loss": 3.5372,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.04825,
|
| 1357 |
+
"grad_norm": 1.15625,
|
| 1358 |
+
"learning_rate": 1.9885334529232186e-05,
|
| 1359 |
+
"loss": 3.4857,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.0485,
|
| 1364 |
+
"grad_norm": 1.2109375,
|
| 1365 |
+
"learning_rate": 1.9884145513314226e-05,
|
| 1366 |
+
"loss": 3.4781,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.04875,
|
| 1371 |
+
"grad_norm": 1.140625,
|
| 1372 |
+
"learning_rate": 1.9882950400358694e-05,
|
| 1373 |
+
"loss": 3.5086,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.049,
|
| 1378 |
+
"grad_norm": 1.25,
|
| 1379 |
+
"learning_rate": 1.9881749191102807e-05,
|
| 1380 |
+
"loss": 3.4468,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.04925,
|
| 1385 |
+
"grad_norm": 1.03125,
|
| 1386 |
+
"learning_rate": 1.9880541886287523e-05,
|
| 1387 |
+
"loss": 3.4255,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.0495,
|
| 1392 |
+
"grad_norm": 0.98828125,
|
| 1393 |
+
"learning_rate": 1.9879328486657577e-05,
|
| 1394 |
+
"loss": 3.4894,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.04975,
|
| 1399 |
+
"grad_norm": 1.1015625,
|
| 1400 |
+
"learning_rate": 1.9878108992961444e-05,
|
| 1401 |
+
"loss": 3.4429,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.05,
|
| 1406 |
+
"grad_norm": 1.125,
|
| 1407 |
+
"learning_rate": 1.9876883405951378e-05,
|
| 1408 |
+
"loss": 3.4698,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.05025,
|
| 1413 |
+
"grad_norm": 1.140625,
|
| 1414 |
+
"learning_rate": 1.987565172638338e-05,
|
| 1415 |
+
"loss": 3.4745,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.0505,
|
| 1420 |
+
"grad_norm": 1.2421875,
|
| 1421 |
+
"learning_rate": 1.987441395501721e-05,
|
| 1422 |
+
"loss": 3.474,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.05075,
|
| 1427 |
+
"grad_norm": 0.921875,
|
| 1428 |
+
"learning_rate": 1.9873170092616388e-05,
|
| 1429 |
+
"loss": 3.4558,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.051,
|
| 1434 |
+
"grad_norm": 1.171875,
|
| 1435 |
+
"learning_rate": 1.9871920139948193e-05,
|
| 1436 |
+
"loss": 3.4349,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.05125,
|
| 1441 |
+
"grad_norm": 1.28125,
|
| 1442 |
+
"learning_rate": 1.9870664097783656e-05,
|
| 1443 |
+
"loss": 3.477,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.0515,
|
| 1448 |
+
"grad_norm": 1.0546875,
|
| 1449 |
+
"learning_rate": 1.986940196689757e-05,
|
| 1450 |
+
"loss": 3.4598,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.05175,
|
| 1455 |
+
"grad_norm": 1.1875,
|
| 1456 |
+
"learning_rate": 1.9868133748068478e-05,
|
| 1457 |
+
"loss": 3.4637,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.052,
|
| 1462 |
+
"grad_norm": 1.171875,
|
| 1463 |
+
"learning_rate": 1.986685944207868e-05,
|
| 1464 |
+
"loss": 3.4514,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.05225,
|
| 1469 |
+
"grad_norm": 0.99609375,
|
| 1470 |
+
"learning_rate": 1.9865579049714238e-05,
|
| 1471 |
+
"loss": 3.4598,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.0525,
|
| 1476 |
+
"grad_norm": 1.1328125,
|
| 1477 |
+
"learning_rate": 1.9864292571764956e-05,
|
| 1478 |
+
"loss": 3.4518,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.05275,
|
| 1483 |
+
"grad_norm": 1.5625,
|
| 1484 |
+
"learning_rate": 1.98630000090244e-05,
|
| 1485 |
+
"loss": 3.4595,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.053,
|
| 1490 |
+
"grad_norm": 1.359375,
|
| 1491 |
+
"learning_rate": 1.9861701362289892e-05,
|
| 1492 |
+
"loss": 3.5267,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.05325,
|
| 1497 |
+
"grad_norm": 1.1171875,
|
| 1498 |
+
"learning_rate": 1.9860396632362495e-05,
|
| 1499 |
+
"loss": 3.4835,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.0535,
|
| 1504 |
+
"grad_norm": 1.0234375,
|
| 1505 |
+
"learning_rate": 1.9859085820047037e-05,
|
| 1506 |
+
"loss": 3.4736,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.05375,
|
| 1511 |
+
"grad_norm": 1.1875,
|
| 1512 |
+
"learning_rate": 1.985776892615209e-05,
|
| 1513 |
+
"loss": 3.4986,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.054,
|
| 1518 |
+
"grad_norm": 1.0546875,
|
| 1519 |
+
"learning_rate": 1.9856445951489984e-05,
|
| 1520 |
+
"loss": 3.4574,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.05425,
|
| 1525 |
+
"grad_norm": 1.1796875,
|
| 1526 |
+
"learning_rate": 1.985511689687679e-05,
|
| 1527 |
+
"loss": 3.4661,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.0545,
|
| 1532 |
+
"grad_norm": 1.15625,
|
| 1533 |
+
"learning_rate": 1.9853781763132343e-05,
|
| 1534 |
+
"loss": 3.494,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.05475,
|
| 1539 |
+
"grad_norm": 1.15625,
|
| 1540 |
+
"learning_rate": 1.9852440551080218e-05,
|
| 1541 |
+
"loss": 3.4418,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.055,
|
| 1546 |
+
"grad_norm": 1.1796875,
|
| 1547 |
+
"learning_rate": 1.985109326154774e-05,
|
| 1548 |
+
"loss": 3.5191,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.05525,
|
| 1553 |
+
"grad_norm": 0.9609375,
|
| 1554 |
+
"learning_rate": 1.9849739895365986e-05,
|
| 1555 |
+
"loss": 3.4303,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.0555,
|
| 1560 |
+
"grad_norm": 1.03125,
|
| 1561 |
+
"learning_rate": 1.9848380453369784e-05,
|
| 1562 |
+
"loss": 3.4678,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.05575,
|
| 1567 |
+
"grad_norm": 0.9921875,
|
| 1568 |
+
"learning_rate": 1.9847014936397698e-05,
|
| 1569 |
+
"loss": 3.4671,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.056,
|
| 1574 |
+
"grad_norm": 1.3125,
|
| 1575 |
+
"learning_rate": 1.9845643345292055e-05,
|
| 1576 |
+
"loss": 3.4354,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.05625,
|
| 1581 |
+
"grad_norm": 1.078125,
|
| 1582 |
+
"learning_rate": 1.9844265680898917e-05,
|
| 1583 |
+
"loss": 3.4307,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.0565,
|
| 1588 |
+
"grad_norm": 1.09375,
|
| 1589 |
+
"learning_rate": 1.98428819440681e-05,
|
| 1590 |
+
"loss": 3.462,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.05675,
|
| 1595 |
+
"grad_norm": 1.0234375,
|
| 1596 |
+
"learning_rate": 1.9841492135653158e-05,
|
| 1597 |
+
"loss": 3.4431,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.057,
|
| 1602 |
+
"grad_norm": 1.046875,
|
| 1603 |
+
"learning_rate": 1.9840096256511398e-05,
|
| 1604 |
+
"loss": 3.4699,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.05725,
|
| 1609 |
+
"grad_norm": 1.078125,
|
| 1610 |
+
"learning_rate": 1.983869430750387e-05,
|
| 1611 |
+
"loss": 3.4167,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.0575,
|
| 1616 |
+
"grad_norm": 1.125,
|
| 1617 |
+
"learning_rate": 1.9837286289495362e-05,
|
| 1618 |
+
"loss": 3.4563,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.05775,
|
| 1623 |
+
"grad_norm": 1.5859375,
|
| 1624 |
+
"learning_rate": 1.983587220335441e-05,
|
| 1625 |
+
"loss": 3.4369,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.058,
|
| 1630 |
+
"grad_norm": 1.375,
|
| 1631 |
+
"learning_rate": 1.98344520499533e-05,
|
| 1632 |
+
"loss": 3.4486,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.05825,
|
| 1637 |
+
"grad_norm": 1.09375,
|
| 1638 |
+
"learning_rate": 1.9833025830168043e-05,
|
| 1639 |
+
"loss": 3.4351,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.0585,
|
| 1644 |
+
"grad_norm": 1.0546875,
|
| 1645 |
+
"learning_rate": 1.9831593544878415e-05,
|
| 1646 |
+
"loss": 3.4519,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.05875,
|
| 1651 |
+
"grad_norm": 1.0703125,
|
| 1652 |
+
"learning_rate": 1.9830155194967918e-05,
|
| 1653 |
+
"loss": 3.4373,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.059,
|
| 1658 |
+
"grad_norm": 0.953125,
|
| 1659 |
+
"learning_rate": 1.9828710781323793e-05,
|
| 1660 |
+
"loss": 3.4507,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.05925,
|
| 1665 |
+
"grad_norm": 1.015625,
|
| 1666 |
+
"learning_rate": 1.9827260304837034e-05,
|
| 1667 |
+
"loss": 3.4329,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.0595,
|
| 1672 |
+
"grad_norm": 1.0859375,
|
| 1673 |
+
"learning_rate": 1.982580376640236e-05,
|
| 1674 |
+
"loss": 3.4942,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.05975,
|
| 1679 |
+
"grad_norm": 1.0859375,
|
| 1680 |
+
"learning_rate": 1.9824341166918245e-05,
|
| 1681 |
+
"loss": 3.4241,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.06,
|
| 1686 |
+
"grad_norm": 1.1015625,
|
| 1687 |
+
"learning_rate": 1.982287250728689e-05,
|
| 1688 |
+
"loss": 3.4555,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.06025,
|
| 1693 |
+
"grad_norm": 1.0078125,
|
| 1694 |
+
"learning_rate": 1.9821397788414237e-05,
|
| 1695 |
+
"loss": 3.4217,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.0605,
|
| 1700 |
+
"grad_norm": 1.046875,
|
| 1701 |
+
"learning_rate": 1.981991701120997e-05,
|
| 1702 |
+
"loss": 3.4166,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.06075,
|
| 1707 |
+
"grad_norm": 0.828125,
|
| 1708 |
+
"learning_rate": 1.9818430176587503e-05,
|
| 1709 |
+
"loss": 3.4367,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.061,
|
| 1714 |
+
"grad_norm": 1.0,
|
| 1715 |
+
"learning_rate": 1.9816937285463992e-05,
|
| 1716 |
+
"loss": 3.435,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.06125,
|
| 1721 |
+
"grad_norm": 1.078125,
|
| 1722 |
+
"learning_rate": 1.9815438338760328e-05,
|
| 1723 |
+
"loss": 3.433,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.0615,
|
| 1728 |
+
"grad_norm": 1.078125,
|
| 1729 |
+
"learning_rate": 1.9813933337401135e-05,
|
| 1730 |
+
"loss": 3.4239,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.06175,
|
| 1735 |
+
"grad_norm": 1.1640625,
|
| 1736 |
+
"learning_rate": 1.9812422282314774e-05,
|
| 1737 |
+
"loss": 3.4243,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.062,
|
| 1742 |
+
"grad_norm": 1.15625,
|
| 1743 |
+
"learning_rate": 1.981090517443334e-05,
|
| 1744 |
+
"loss": 3.4106,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.06225,
|
| 1749 |
+
"grad_norm": 1.1015625,
|
| 1750 |
+
"learning_rate": 1.9809382014692665e-05,
|
| 1751 |
+
"loss": 3.4095,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.0625,
|
| 1756 |
+
"grad_norm": 1.1171875,
|
| 1757 |
+
"learning_rate": 1.9807852804032306e-05,
|
| 1758 |
+
"loss": 3.4593,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.06275,
|
| 1763 |
+
"grad_norm": 1.0078125,
|
| 1764 |
+
"learning_rate": 1.9806317543395556e-05,
|
| 1765 |
+
"loss": 3.4737,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.063,
|
| 1770 |
+
"grad_norm": 1.0546875,
|
| 1771 |
+
"learning_rate": 1.9804776233729446e-05,
|
| 1772 |
+
"loss": 3.3898,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.06325,
|
| 1777 |
+
"grad_norm": 1.828125,
|
| 1778 |
+
"learning_rate": 1.9803228875984727e-05,
|
| 1779 |
+
"loss": 3.458,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.0635,
|
| 1784 |
+
"grad_norm": 0.96484375,
|
| 1785 |
+
"learning_rate": 1.9801675471115892e-05,
|
| 1786 |
+
"loss": 3.4422,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.06375,
|
| 1791 |
+
"grad_norm": 1.1015625,
|
| 1792 |
+
"learning_rate": 1.9800116020081156e-05,
|
| 1793 |
+
"loss": 3.4094,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.064,
|
| 1798 |
+
"grad_norm": 0.890625,
|
| 1799 |
+
"learning_rate": 1.979855052384247e-05,
|
| 1800 |
+
"loss": 3.4318,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.06425,
|
| 1805 |
+
"grad_norm": 1.0546875,
|
| 1806 |
+
"learning_rate": 1.979697898336551e-05,
|
| 1807 |
+
"loss": 3.4373,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.0645,
|
| 1812 |
+
"grad_norm": 0.99609375,
|
| 1813 |
+
"learning_rate": 1.9795401399619675e-05,
|
| 1814 |
+
"loss": 3.4386,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.06475,
|
| 1819 |
+
"grad_norm": 1.1171875,
|
| 1820 |
+
"learning_rate": 1.9793817773578104e-05,
|
| 1821 |
+
"loss": 3.4602,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.065,
|
| 1826 |
+
"grad_norm": 1.1640625,
|
| 1827 |
+
"learning_rate": 1.979222810621766e-05,
|
| 1828 |
+
"loss": 3.402,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.06525,
|
| 1833 |
+
"grad_norm": 1.2265625,
|
| 1834 |
+
"learning_rate": 1.9790632398518923e-05,
|
| 1835 |
+
"loss": 3.4369,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.0655,
|
| 1840 |
+
"grad_norm": 1.046875,
|
| 1841 |
+
"learning_rate": 1.9789030651466208e-05,
|
| 1842 |
+
"loss": 3.4059,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.06575,
|
| 1847 |
+
"grad_norm": 0.9140625,
|
| 1848 |
+
"learning_rate": 1.9787422866047553e-05,
|
| 1849 |
+
"loss": 3.4187,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.066,
|
| 1854 |
+
"grad_norm": 1.09375,
|
| 1855 |
+
"learning_rate": 1.978580904325472e-05,
|
| 1856 |
+
"loss": 3.42,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.06625,
|
| 1861 |
+
"grad_norm": 1.0078125,
|
| 1862 |
+
"learning_rate": 1.9784189184083203e-05,
|
| 1863 |
+
"loss": 3.3908,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.0665,
|
| 1868 |
+
"grad_norm": 0.92578125,
|
| 1869 |
+
"learning_rate": 1.97825632895322e-05,
|
| 1870 |
+
"loss": 3.4123,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.06675,
|
| 1875 |
+
"grad_norm": 0.96484375,
|
| 1876 |
+
"learning_rate": 1.9780931360604657e-05,
|
| 1877 |
+
"loss": 3.4122,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.067,
|
| 1882 |
+
"grad_norm": 1.1015625,
|
| 1883 |
+
"learning_rate": 1.977929339830722e-05,
|
| 1884 |
+
"loss": 3.449,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.06725,
|
| 1889 |
+
"grad_norm": 1.046875,
|
| 1890 |
+
"learning_rate": 1.977764940365027e-05,
|
| 1891 |
+
"loss": 3.4364,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.0675,
|
| 1896 |
+
"grad_norm": 0.86328125,
|
| 1897 |
+
"learning_rate": 1.977599937764791e-05,
|
| 1898 |
+
"loss": 3.4164,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.06775,
|
| 1903 |
+
"grad_norm": 0.875,
|
| 1904 |
+
"learning_rate": 1.977434332131795e-05,
|
| 1905 |
+
"loss": 3.4022,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.068,
|
| 1910 |
+
"grad_norm": 0.89453125,
|
| 1911 |
+
"learning_rate": 1.9772681235681936e-05,
|
| 1912 |
+
"loss": 3.3919,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.06825,
|
| 1917 |
+
"grad_norm": 1.0703125,
|
| 1918 |
+
"learning_rate": 1.9771013121765123e-05,
|
| 1919 |
+
"loss": 3.4108,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.0685,
|
| 1924 |
+
"grad_norm": 0.9609375,
|
| 1925 |
+
"learning_rate": 1.976933898059649e-05,
|
| 1926 |
+
"loss": 3.3949,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.06875,
|
| 1931 |
+
"grad_norm": 0.98046875,
|
| 1932 |
+
"learning_rate": 1.9767658813208725e-05,
|
| 1933 |
+
"loss": 3.399,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.069,
|
| 1938 |
+
"grad_norm": 0.95703125,
|
| 1939 |
+
"learning_rate": 1.976597262063825e-05,
|
| 1940 |
+
"loss": 3.4011,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.06925,
|
| 1945 |
+
"grad_norm": 1.09375,
|
| 1946 |
+
"learning_rate": 1.9764280403925183e-05,
|
| 1947 |
+
"loss": 3.3895,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.0695,
|
| 1952 |
+
"grad_norm": 1.078125,
|
| 1953 |
+
"learning_rate": 1.9762582164113372e-05,
|
| 1954 |
+
"loss": 3.4223,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.06975,
|
| 1959 |
+
"grad_norm": 1.109375,
|
| 1960 |
+
"learning_rate": 1.9760877902250378e-05,
|
| 1961 |
+
"loss": 3.3864,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.07,
|
| 1966 |
+
"grad_norm": 1.25,
|
| 1967 |
+
"learning_rate": 1.9759167619387474e-05,
|
| 1968 |
+
"loss": 3.4049,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.07025,
|
| 1973 |
+
"grad_norm": 1.421875,
|
| 1974 |
+
"learning_rate": 1.9757451316579653e-05,
|
| 1975 |
+
"loss": 3.4297,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.0705,
|
| 1980 |
+
"grad_norm": 0.92578125,
|
| 1981 |
+
"learning_rate": 1.975572899488561e-05,
|
| 1982 |
+
"loss": 3.3905,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.07075,
|
| 1987 |
+
"grad_norm": 0.96875,
|
| 1988 |
+
"learning_rate": 1.9754000655367763e-05,
|
| 1989 |
+
"loss": 3.3799,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.071,
|
| 1994 |
+
"grad_norm": 1.0,
|
| 1995 |
+
"learning_rate": 1.9752266299092234e-05,
|
| 1996 |
+
"loss": 3.4095,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.07125,
|
| 2001 |
+
"grad_norm": 1.0703125,
|
| 2002 |
+
"learning_rate": 1.9750525927128872e-05,
|
| 2003 |
+
"loss": 3.427,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.0715,
|
| 2008 |
+
"grad_norm": 1.125,
|
| 2009 |
+
"learning_rate": 1.9748779540551215e-05,
|
| 2010 |
+
"loss": 3.3989,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.07175,
|
| 2015 |
+
"grad_norm": 1.46875,
|
| 2016 |
+
"learning_rate": 1.9747027140436524e-05,
|
| 2017 |
+
"loss": 3.4027,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.072,
|
| 2022 |
+
"grad_norm": 1.0,
|
| 2023 |
+
"learning_rate": 1.9745268727865774e-05,
|
| 2024 |
+
"loss": 3.4169,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.07225,
|
| 2029 |
+
"grad_norm": 1.1484375,
|
| 2030 |
+
"learning_rate": 1.9743504303923634e-05,
|
| 2031 |
+
"loss": 3.4185,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.0725,
|
| 2036 |
+
"grad_norm": 1.0546875,
|
| 2037 |
+
"learning_rate": 1.9741733869698497e-05,
|
| 2038 |
+
"loss": 3.3739,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.07275,
|
| 2043 |
+
"grad_norm": 1.0390625,
|
| 2044 |
+
"learning_rate": 1.973995742628245e-05,
|
| 2045 |
+
"loss": 3.3852,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.073,
|
| 2050 |
+
"grad_norm": 1.0859375,
|
| 2051 |
+
"learning_rate": 1.9738174974771288e-05,
|
| 2052 |
+
"loss": 3.4313,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.07325,
|
| 2057 |
+
"grad_norm": 0.93359375,
|
| 2058 |
+
"learning_rate": 1.9736386516264533e-05,
|
| 2059 |
+
"loss": 3.4573,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.0735,
|
| 2064 |
+
"grad_norm": 1.1328125,
|
| 2065 |
+
"learning_rate": 1.9734592051865376e-05,
|
| 2066 |
+
"loss": 3.4102,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.07375,
|
| 2071 |
+
"grad_norm": 0.859375,
|
| 2072 |
+
"learning_rate": 1.973279158268075e-05,
|
| 2073 |
+
"loss": 3.4349,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.074,
|
| 2078 |
+
"grad_norm": 0.87109375,
|
| 2079 |
+
"learning_rate": 1.9730985109821268e-05,
|
| 2080 |
+
"loss": 3.4361,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.07425,
|
| 2085 |
+
"grad_norm": 0.87109375,
|
| 2086 |
+
"learning_rate": 1.972917263440125e-05,
|
| 2087 |
+
"loss": 3.4305,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.0745,
|
| 2092 |
+
"grad_norm": 1.078125,
|
| 2093 |
+
"learning_rate": 1.9727354157538724e-05,
|
| 2094 |
+
"loss": 3.3749,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.07475,
|
| 2099 |
+
"grad_norm": 0.80859375,
|
| 2100 |
+
"learning_rate": 1.9725529680355422e-05,
|
| 2101 |
+
"loss": 3.3979,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.075,
|
| 2106 |
+
"grad_norm": 0.9453125,
|
| 2107 |
+
"learning_rate": 1.9723699203976768e-05,
|
| 2108 |
+
"loss": 3.4267,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.07525,
|
| 2113 |
+
"grad_norm": 0.91796875,
|
| 2114 |
+
"learning_rate": 1.9721862729531894e-05,
|
| 2115 |
+
"loss": 3.3561,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.0755,
|
| 2120 |
+
"grad_norm": 0.90234375,
|
| 2121 |
+
"learning_rate": 1.972002025815363e-05,
|
| 2122 |
+
"loss": 3.4276,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.07575,
|
| 2127 |
+
"grad_norm": 0.94921875,
|
| 2128 |
+
"learning_rate": 1.9718171790978503e-05,
|
| 2129 |
+
"loss": 3.4302,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.076,
|
| 2134 |
+
"grad_norm": 0.96875,
|
| 2135 |
+
"learning_rate": 1.971631732914674e-05,
|
| 2136 |
+
"loss": 3.3828,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.07625,
|
| 2141 |
+
"grad_norm": 0.87890625,
|
| 2142 |
+
"learning_rate": 1.9714456873802274e-05,
|
| 2143 |
+
"loss": 3.3954,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.0765,
|
| 2148 |
+
"grad_norm": 0.86328125,
|
| 2149 |
+
"learning_rate": 1.9712590426092715e-05,
|
| 2150 |
+
"loss": 3.4076,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.07675,
|
| 2155 |
+
"grad_norm": 1.0234375,
|
| 2156 |
+
"learning_rate": 1.971071798716939e-05,
|
| 2157 |
+
"loss": 3.4176,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.077,
|
| 2162 |
+
"grad_norm": 0.9453125,
|
| 2163 |
+
"learning_rate": 1.9708839558187313e-05,
|
| 2164 |
+
"loss": 3.3667,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.07725,
|
| 2169 |
+
"grad_norm": 0.953125,
|
| 2170 |
+
"learning_rate": 1.970695514030519e-05,
|
| 2171 |
+
"loss": 3.3722,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.0775,
|
| 2176 |
+
"grad_norm": 0.984375,
|
| 2177 |
+
"learning_rate": 1.9705064734685425e-05,
|
| 2178 |
+
"loss": 3.3985,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.07775,
|
| 2183 |
+
"grad_norm": 1.015625,
|
| 2184 |
+
"learning_rate": 1.970316834249412e-05,
|
| 2185 |
+
"loss": 3.3936,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.078,
|
| 2190 |
+
"grad_norm": 0.890625,
|
| 2191 |
+
"learning_rate": 1.970126596490106e-05,
|
| 2192 |
+
"loss": 3.4097,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.07825,
|
| 2197 |
+
"grad_norm": 1.03125,
|
| 2198 |
+
"learning_rate": 1.969935760307973e-05,
|
| 2199 |
+
"loss": 3.356,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.0785,
|
| 2204 |
+
"grad_norm": 1.0078125,
|
| 2205 |
+
"learning_rate": 1.96974432582073e-05,
|
| 2206 |
+
"loss": 3.3871,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.07875,
|
| 2211 |
+
"grad_norm": 1.1015625,
|
| 2212 |
+
"learning_rate": 1.9695522931464637e-05,
|
| 2213 |
+
"loss": 3.3538,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.079,
|
| 2218 |
+
"grad_norm": 1.03125,
|
| 2219 |
+
"learning_rate": 1.9693596624036294e-05,
|
| 2220 |
+
"loss": 3.3427,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.07925,
|
| 2225 |
+
"grad_norm": 0.91015625,
|
| 2226 |
+
"learning_rate": 1.9691664337110515e-05,
|
| 2227 |
+
"loss": 3.3597,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.0795,
|
| 2232 |
+
"grad_norm": 0.921875,
|
| 2233 |
+
"learning_rate": 1.9689726071879233e-05,
|
| 2234 |
+
"loss": 3.3522,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.07975,
|
| 2239 |
+
"grad_norm": 0.984375,
|
| 2240 |
+
"learning_rate": 1.968778182953806e-05,
|
| 2241 |
+
"loss": 3.3797,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.08,
|
| 2246 |
+
"grad_norm": 1.203125,
|
| 2247 |
+
"learning_rate": 1.9685831611286312e-05,
|
| 2248 |
+
"loss": 3.366,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.08025,
|
| 2253 |
+
"grad_norm": 0.94921875,
|
| 2254 |
+
"learning_rate": 1.968387541832698e-05,
|
| 2255 |
+
"loss": 3.3661,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.0805,
|
| 2260 |
+
"grad_norm": 0.9453125,
|
| 2261 |
+
"learning_rate": 1.9681913251866732e-05,
|
| 2262 |
+
"loss": 3.3408,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.08075,
|
| 2267 |
+
"grad_norm": 0.92578125,
|
| 2268 |
+
"learning_rate": 1.9679945113115945e-05,
|
| 2269 |
+
"loss": 3.3602,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.081,
|
| 2274 |
+
"grad_norm": 0.88671875,
|
| 2275 |
+
"learning_rate": 1.9677971003288657e-05,
|
| 2276 |
+
"loss": 3.3802,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.08125,
|
| 2281 |
+
"grad_norm": 1.0625,
|
| 2282 |
+
"learning_rate": 1.96759909236026e-05,
|
| 2283 |
+
"loss": 3.3624,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.0815,
|
| 2288 |
+
"grad_norm": 0.9375,
|
| 2289 |
+
"learning_rate": 1.9674004875279188e-05,
|
| 2290 |
+
"loss": 3.3521,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.08175,
|
| 2295 |
+
"grad_norm": 0.90625,
|
| 2296 |
+
"learning_rate": 1.9672012859543512e-05,
|
| 2297 |
+
"loss": 3.3327,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.082,
|
| 2302 |
+
"grad_norm": 0.8984375,
|
| 2303 |
+
"learning_rate": 1.9670014877624353e-05,
|
| 2304 |
+
"loss": 3.3077,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.08225,
|
| 2309 |
+
"grad_norm": 1.09375,
|
| 2310 |
+
"learning_rate": 1.966801093075416e-05,
|
| 2311 |
+
"loss": 3.3407,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.0825,
|
| 2316 |
+
"grad_norm": 0.97265625,
|
| 2317 |
+
"learning_rate": 1.9666001020169075e-05,
|
| 2318 |
+
"loss": 3.3702,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.08275,
|
| 2323 |
+
"grad_norm": 1.015625,
|
| 2324 |
+
"learning_rate": 1.9663985147108907e-05,
|
| 2325 |
+
"loss": 3.348,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.083,
|
| 2330 |
+
"grad_norm": 0.91796875,
|
| 2331 |
+
"learning_rate": 1.966196331281715e-05,
|
| 2332 |
+
"loss": 3.3575,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.08325,
|
| 2337 |
+
"grad_norm": 1.140625,
|
| 2338 |
+
"learning_rate": 1.965993551854097e-05,
|
| 2339 |
+
"loss": 3.3811,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.0835,
|
| 2344 |
+
"grad_norm": 1.140625,
|
| 2345 |
+
"learning_rate": 1.9657901765531217e-05,
|
| 2346 |
+
"loss": 3.3567,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.08375,
|
| 2351 |
+
"grad_norm": 0.93359375,
|
| 2352 |
+
"learning_rate": 1.965586205504241e-05,
|
| 2353 |
+
"loss": 3.3877,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.084,
|
| 2358 |
+
"grad_norm": 1.03125,
|
| 2359 |
+
"learning_rate": 1.965381638833274e-05,
|
| 2360 |
+
"loss": 3.3359,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.08425,
|
| 2365 |
+
"grad_norm": 0.7890625,
|
| 2366 |
+
"learning_rate": 1.9651764766664085e-05,
|
| 2367 |
+
"loss": 3.3646,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.0845,
|
| 2372 |
+
"grad_norm": 0.8828125,
|
| 2373 |
+
"learning_rate": 1.9649707191301983e-05,
|
| 2374 |
+
"loss": 3.3608,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.08475,
|
| 2379 |
+
"grad_norm": 0.953125,
|
| 2380 |
+
"learning_rate": 1.9647643663515655e-05,
|
| 2381 |
+
"loss": 3.3463,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.085,
|
| 2386 |
+
"grad_norm": 0.98046875,
|
| 2387 |
+
"learning_rate": 1.9645574184577982e-05,
|
| 2388 |
+
"loss": 3.3526,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.08525,
|
| 2393 |
+
"grad_norm": 1.1015625,
|
| 2394 |
+
"learning_rate": 1.9643498755765527e-05,
|
| 2395 |
+
"loss": 3.331,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.0855,
|
| 2400 |
+
"grad_norm": 1.0703125,
|
| 2401 |
+
"learning_rate": 1.964141737835852e-05,
|
| 2402 |
+
"loss": 3.3612,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.08575,
|
| 2407 |
+
"grad_norm": 0.94140625,
|
| 2408 |
+
"learning_rate": 1.9639330053640854e-05,
|
| 2409 |
+
"loss": 3.3526,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.086,
|
| 2414 |
+
"grad_norm": 1.0546875,
|
| 2415 |
+
"learning_rate": 1.96372367829001e-05,
|
| 2416 |
+
"loss": 3.3393,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.08625,
|
| 2421 |
+
"grad_norm": 0.9921875,
|
| 2422 |
+
"learning_rate": 1.963513756742749e-05,
|
| 2423 |
+
"loss": 3.3212,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.0865,
|
| 2428 |
+
"grad_norm": 0.921875,
|
| 2429 |
+
"learning_rate": 1.9633032408517926e-05,
|
| 2430 |
+
"loss": 3.325,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.08675,
|
| 2435 |
+
"grad_norm": 1.015625,
|
| 2436 |
+
"learning_rate": 1.9630921307469978e-05,
|
| 2437 |
+
"loss": 3.3853,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.087,
|
| 2442 |
+
"grad_norm": 0.96484375,
|
| 2443 |
+
"learning_rate": 1.9628804265585878e-05,
|
| 2444 |
+
"loss": 3.3476,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.08725,
|
| 2449 |
+
"grad_norm": 1.203125,
|
| 2450 |
+
"learning_rate": 1.962668128417152e-05,
|
| 2451 |
+
"loss": 3.3518,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.0875,
|
| 2456 |
+
"grad_norm": 0.9375,
|
| 2457 |
+
"learning_rate": 1.9624552364536472e-05,
|
| 2458 |
+
"loss": 3.3856,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.08775,
|
| 2463 |
+
"grad_norm": 0.96484375,
|
| 2464 |
+
"learning_rate": 1.962241750799396e-05,
|
| 2465 |
+
"loss": 3.3312,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.088,
|
| 2470 |
+
"grad_norm": 0.890625,
|
| 2471 |
+
"learning_rate": 1.962027671586086e-05,
|
| 2472 |
+
"loss": 3.3453,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.08825,
|
| 2477 |
+
"grad_norm": 0.890625,
|
| 2478 |
+
"learning_rate": 1.961812998945773e-05,
|
| 2479 |
+
"loss": 3.3488,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.0885,
|
| 2484 |
+
"grad_norm": 0.94140625,
|
| 2485 |
+
"learning_rate": 1.9615977330108774e-05,
|
| 2486 |
+
"loss": 3.3669,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.08875,
|
| 2491 |
+
"grad_norm": 1.015625,
|
| 2492 |
+
"learning_rate": 1.9613818739141862e-05,
|
| 2493 |
+
"loss": 3.3359,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.089,
|
| 2498 |
+
"grad_norm": 0.92578125,
|
| 2499 |
+
"learning_rate": 1.961165421788852e-05,
|
| 2500 |
+
"loss": 3.3411,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.08925,
|
| 2505 |
+
"grad_norm": 1.046875,
|
| 2506 |
+
"learning_rate": 1.9609483767683937e-05,
|
| 2507 |
+
"loss": 3.3427,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.0895,
|
| 2512 |
+
"grad_norm": 0.92578125,
|
| 2513 |
+
"learning_rate": 1.960730738986695e-05,
|
| 2514 |
+
"loss": 3.3524,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.08975,
|
| 2519 |
+
"grad_norm": 0.9453125,
|
| 2520 |
+
"learning_rate": 1.9605125085780065e-05,
|
| 2521 |
+
"loss": 3.3711,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.09,
|
| 2526 |
+
"grad_norm": 1.1015625,
|
| 2527 |
+
"learning_rate": 1.9602936856769432e-05,
|
| 2528 |
+
"loss": 3.3501,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.09025,
|
| 2533 |
+
"grad_norm": 1.1015625,
|
| 2534 |
+
"learning_rate": 1.960074270418486e-05,
|
| 2535 |
+
"loss": 3.4039,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.0905,
|
| 2540 |
+
"grad_norm": 0.92578125,
|
| 2541 |
+
"learning_rate": 1.959854262937982e-05,
|
| 2542 |
+
"loss": 3.3296,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.09075,
|
| 2547 |
+
"grad_norm": 1.078125,
|
| 2548 |
+
"learning_rate": 1.959633663371142e-05,
|
| 2549 |
+
"loss": 3.3325,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.091,
|
| 2554 |
+
"grad_norm": 0.8203125,
|
| 2555 |
+
"learning_rate": 1.959412471854043e-05,
|
| 2556 |
+
"loss": 3.3177,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.09125,
|
| 2561 |
+
"grad_norm": 0.8125,
|
| 2562 |
+
"learning_rate": 1.9591906885231275e-05,
|
| 2563 |
+
"loss": 3.3416,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.0915,
|
| 2568 |
+
"grad_norm": 1.015625,
|
| 2569 |
+
"learning_rate": 1.958968313515202e-05,
|
| 2570 |
+
"loss": 3.3404,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.09175,
|
| 2575 |
+
"grad_norm": 0.83984375,
|
| 2576 |
+
"learning_rate": 1.9587453469674392e-05,
|
| 2577 |
+
"loss": 3.3442,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.092,
|
| 2582 |
+
"grad_norm": 0.91796875,
|
| 2583 |
+
"learning_rate": 1.958521789017376e-05,
|
| 2584 |
+
"loss": 3.4015,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.09225,
|
| 2589 |
+
"grad_norm": 0.90625,
|
| 2590 |
+
"learning_rate": 1.958297639802914e-05,
|
| 2591 |
+
"loss": 3.3414,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.0925,
|
| 2596 |
+
"grad_norm": 1.125,
|
| 2597 |
+
"learning_rate": 1.9580728994623194e-05,
|
| 2598 |
+
"loss": 3.3545,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.09275,
|
| 2603 |
+
"grad_norm": 0.94140625,
|
| 2604 |
+
"learning_rate": 1.9578475681342234e-05,
|
| 2605 |
+
"loss": 3.3611,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.093,
|
| 2610 |
+
"grad_norm": 0.85546875,
|
| 2611 |
+
"learning_rate": 1.9576216459576222e-05,
|
| 2612 |
+
"loss": 3.365,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.09325,
|
| 2617 |
+
"grad_norm": 1.0390625,
|
| 2618 |
+
"learning_rate": 1.9573951330718758e-05,
|
| 2619 |
+
"loss": 3.3885,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.0935,
|
| 2624 |
+
"grad_norm": 0.99609375,
|
| 2625 |
+
"learning_rate": 1.9571680296167086e-05,
|
| 2626 |
+
"loss": 3.3267,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.09375,
|
| 2631 |
+
"grad_norm": 0.85546875,
|
| 2632 |
+
"learning_rate": 1.956940335732209e-05,
|
| 2633 |
+
"loss": 3.3356,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.094,
|
| 2638 |
+
"grad_norm": 0.96484375,
|
| 2639 |
+
"learning_rate": 1.9567120515588307e-05,
|
| 2640 |
+
"loss": 3.3612,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.09425,
|
| 2645 |
+
"grad_norm": 0.890625,
|
| 2646 |
+
"learning_rate": 1.9564831772373906e-05,
|
| 2647 |
+
"loss": 3.3394,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.0945,
|
| 2652 |
+
"grad_norm": 0.90234375,
|
| 2653 |
+
"learning_rate": 1.9562537129090697e-05,
|
| 2654 |
+
"loss": 3.4066,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.09475,
|
| 2659 |
+
"grad_norm": 1.109375,
|
| 2660 |
+
"learning_rate": 1.956023658715413e-05,
|
| 2661 |
+
"loss": 3.3439,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.095,
|
| 2666 |
+
"grad_norm": 0.98046875,
|
| 2667 |
+
"learning_rate": 1.9557930147983303e-05,
|
| 2668 |
+
"loss": 3.3728,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.09525,
|
| 2673 |
+
"grad_norm": 0.984375,
|
| 2674 |
+
"learning_rate": 1.9555617813000935e-05,
|
| 2675 |
+
"loss": 3.3732,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.0955,
|
| 2680 |
+
"grad_norm": 0.8671875,
|
| 2681 |
+
"learning_rate": 1.9553299583633397e-05,
|
| 2682 |
+
"loss": 3.3491,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.09575,
|
| 2687 |
+
"grad_norm": 1.1015625,
|
| 2688 |
+
"learning_rate": 1.9550975461310685e-05,
|
| 2689 |
+
"loss": 3.3632,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.096,
|
| 2694 |
+
"grad_norm": 0.74609375,
|
| 2695 |
+
"learning_rate": 1.9548645447466433e-05,
|
| 2696 |
+
"loss": 3.3189,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.09625,
|
| 2701 |
+
"grad_norm": 0.92578125,
|
| 2702 |
+
"learning_rate": 1.9546309543537912e-05,
|
| 2703 |
+
"loss": 3.3851,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.0965,
|
| 2708 |
+
"grad_norm": 1.109375,
|
| 2709 |
+
"learning_rate": 1.9543967750966026e-05,
|
| 2710 |
+
"loss": 3.3458,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.09675,
|
| 2715 |
+
"grad_norm": 0.91015625,
|
| 2716 |
+
"learning_rate": 1.9541620071195316e-05,
|
| 2717 |
+
"loss": 3.3614,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.097,
|
| 2722 |
+
"grad_norm": 0.91015625,
|
| 2723 |
+
"learning_rate": 1.9539266505673938e-05,
|
| 2724 |
+
"loss": 3.3422,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.09725,
|
| 2729 |
+
"grad_norm": 0.9609375,
|
| 2730 |
+
"learning_rate": 1.9536907055853693e-05,
|
| 2731 |
+
"loss": 3.3395,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.0975,
|
| 2736 |
+
"grad_norm": 1.0,
|
| 2737 |
+
"learning_rate": 1.953454172319001e-05,
|
| 2738 |
+
"loss": 3.3522,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.09775,
|
| 2743 |
+
"grad_norm": 0.90234375,
|
| 2744 |
+
"learning_rate": 1.9532170509141954e-05,
|
| 2745 |
+
"loss": 3.3623,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.098,
|
| 2750 |
+
"grad_norm": 1.0390625,
|
| 2751 |
+
"learning_rate": 1.952979341517219e-05,
|
| 2752 |
+
"loss": 3.3469,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.09825,
|
| 2757 |
+
"grad_norm": 0.87890625,
|
| 2758 |
+
"learning_rate": 1.952741044274704e-05,
|
| 2759 |
+
"loss": 3.3344,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.0985,
|
| 2764 |
+
"grad_norm": 0.90625,
|
| 2765 |
+
"learning_rate": 1.9525021593336443e-05,
|
| 2766 |
+
"loss": 3.3391,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.09875,
|
| 2771 |
+
"grad_norm": 0.9921875,
|
| 2772 |
+
"learning_rate": 1.9522626868413956e-05,
|
| 2773 |
+
"loss": 3.3477,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.099,
|
| 2778 |
+
"grad_norm": 0.91015625,
|
| 2779 |
+
"learning_rate": 1.9520226269456767e-05,
|
| 2780 |
+
"loss": 3.3436,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.09925,
|
| 2785 |
+
"grad_norm": 0.921875,
|
| 2786 |
+
"learning_rate": 1.9517819797945687e-05,
|
| 2787 |
+
"loss": 3.3332,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.0995,
|
| 2792 |
+
"grad_norm": 0.87890625,
|
| 2793 |
+
"learning_rate": 1.9515407455365148e-05,
|
| 2794 |
+
"loss": 3.3458,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.09975,
|
| 2799 |
+
"grad_norm": 0.83203125,
|
| 2800 |
+
"learning_rate": 1.9512989243203208e-05,
|
| 2801 |
+
"loss": 3.3624,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.1,
|
| 2806 |
+
"grad_norm": 1.1484375,
|
| 2807 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 2808 |
+
"loss": 3.3656,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
}
|
| 2811 |
+
],
|
| 2812 |
+
"logging_steps": 10,
|
| 2813 |
+
"max_steps": 40000,
|
| 2814 |
+
"num_input_tokens_seen": 0,
|
| 2815 |
+
"num_train_epochs": 9223372036854775807,
|
| 2816 |
+
"save_steps": 2000,
|
| 2817 |
+
"stateful_callbacks": {
|
| 2818 |
+
"TrainerControl": {
|
| 2819 |
+
"args": {
|
| 2820 |
+
"should_epoch_stop": false,
|
| 2821 |
+
"should_evaluate": false,
|
| 2822 |
+
"should_log": false,
|
| 2823 |
+
"should_save": true,
|
| 2824 |
+
"should_training_stop": false
|
| 2825 |
+
},
|
| 2826 |
+
"attributes": {}
|
| 2827 |
+
}
|
| 2828 |
+
},
|
| 2829 |
+
"total_flos": 6.124876767166464e+18,
|
| 2830 |
+
"train_batch_size": 8,
|
| 2831 |
+
"trial_name": null,
|
| 2832 |
+
"trial_params": null
|
| 2833 |
+
}
|
llama1b_fw10b_0401/checkpoint-4000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86ceaf013c49cbbda58a254af4cb2d85b2cc15711504d191e26c24167d7c09da
|
| 3 |
+
size 5368
|